CN103268072A - Miniature vehicle, miniature vehicle control system and control method based on machine vision - Google Patents
Miniature vehicle, miniature vehicle control system and control method based on machine vision Download PDFInfo
- Publication number
- CN103268072A CN103268072A CN2013102011985A CN201310201198A CN103268072A CN 103268072 A CN103268072 A CN 103268072A CN 2013102011985 A CN2013102011985 A CN 2013102011985A CN 201310201198 A CN201310201198 A CN 201310201198A CN 103268072 A CN103268072 A CN 103268072A
- Authority
- CN
- China
- Prior art keywords
- module
- miniature
- miniature car
- control
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention provides a miniature vehicle, a miniature vehicle control system and control method based on machine vision. The miniature vehicle comprises a chassis, a vision sensor and a control plate. A motor and a steering engine are arranged on the chassis. A main board operates and controls a program according to information transmitted by the vision sensor. The control plate controls operation of the motor and the steering engine. The miniature vehicle is simple in structure and low in manufacturing cost, and a multi-vehicle testing environment can be easily established. A test field and the environment can be easily adjusted, and tests under a plurality of different environments can be carried out conveniently. According to the miniature vehicle control system, acquired information is connected into a server network through technical measures such as wireless communication, then analysis is carried out, a strategy is obtained, and accordingly control on miniature vehicle behavior is achieved, and the purpose that vehicles and a road, one vehicle and another vehicle, the vehicles and a city network are connected is achieved. According to the miniature vehicle control method, dynamic and static state target environment sensing under a complex road environment is achieved, and through remote management, the purpose that a vehicle operation state is monitored in real time is achieved.
Description
Technical field
The present invention relates to the intelligent transport technology field, be specifically related to a kind of miniature car based on machine vision, miniature vehicle control and control method.
Background technology
At present, China's traffic problems are serious day by day, because the automobile growth is too fast, and the road relative deficiency, traffic problems such as traffic congestion, traffic hazard, environmental pollution have become the bottleneck of economic development.The research of the miniature car control loop of intelligence will realize effectively alleviating driver's burden, reduce the phenomenon of driver tired driving, be conducive to improve traffic safety, simultaneously, cooperate urban traffic control system, and the reasonable distribution traffic flow realizes smooth traffic etc.
From the sixties in last century, the progress of electronic technology has just become the maximum power of automobile industry development, proposes the intelligent transportation system concept abroad the nineties in last century, and intelligent miniature car then is the important component part of intelligent transportation system.The miniature car of intelligence is a system ensemble that integrates functions such as environment sensing, programmed decision-making, many grades driver assistance.The miniature driving skills art of intelligence has comprised computing machine, mobile communication, control etc. makes miniature car have more the multinomial technology of comfortableness, recreational, security, convenience automatically, and is to realize basis and the necessary condition of intelligent miniature driving skills art based on the automobile informationization of PC platform.
Now, external many developed countries have all dropped into a large amount of funds and manpower and have carried out function path and the intelligentized research of miniature car for the transport solution problem.Developed the VaMP instruction carriage as the federal National Defence University of Munich, Germany and Mercedes's cooperation research and development, it is to be converted by a luxury benz 500SEL, and vision system mainly comprises Road Detection and follows the tracks of RDT and detection of obstacles and two modules of tracking ODT.1997, the U.S. has implemented one " driving highway system (AHS-Automated HighwaySystem) site test and demonstration project automatically " in the California, on existing road skeleton basis, utilize advanced technology to improve security, smoothness and travelling quality.The correlation technique of American I TS has produced significant benefit now, and as E-payment system (ETC), it need not stop and just can realize the function of charging, and has improved the service efficiency of road greatly.Meanwhile, some domestic colleges and universities and research institution are also in the research of actively developing aspect the intelligent automobile, as Inst. of Artificial Intelligence and Robot, Xi'an Jiaotong Univ. and automobile dynamic similation National Key Laboratory of Jilin University since calendar year 2001, launch the joint study of automobile assistant driving, finished the design effort of the design of route deviation warning system hardware frame, Road Detection and recognizer, system software structure.
From domestic and international intelligent driving research situation, present research is confined to some ins and outs mostly, the experimental situation of autonomous driving is also simple relatively, does not have the report that success is tested in many cars of real roads environment, and experimentizing in the real roads traffic environment faces certain difficulty.It at first is the problem that faces the social safety aspect.Though can guarantee miniature car and personnel's safety by a large amount of safeguard procedures, for the system of the such complexity of autonomous driving, can not get rid of wherein latent fault and danger fully.Especially in the early stage in the experimentation, may be faced with higher security risk.Secondly, in present traffic law intelligent vehicle is not had relevant regulation, if because the mistake of autonomous driving program causes traffic hazard, correlative study mechanism may face jural risk.Owing to need a large amount of precision equipments, the overall cost of intelligent vehicle is usually than higher in addition, and the cost of great number and maintenance cost are that most studies mechanism is difficult to bear, therefore the carrying out of having limited sweeping experiment.
Summary of the invention
In order to overcome the defective that exists in the above-mentioned prior art, the purpose of this invention is to provide a kind of miniature car based on machine vision, miniature vehicle control and control method, the size of this miniature car is less than the miniature car of actual vehicle, can be implemented on the real roads many cars and drive experiment jointly automatically when saving cost.
In order to realize above-mentioned purpose of the present invention, according to an aspect of the present invention, the invention provides a kind of miniature car based on machine vision, comprising: the chassis, described chassis is provided with motor and steering wheel; Vision sensor, described vision sensor is used for obtaining the road surface picture; Mainboard, described mainboard links to each other with described vision sensor, and described mainboard is according to described vision sensor information transmitted operation control program; Control panel, described control panel links to each other with described mainboard, and described control panel receives the operation that control command that described mainboard assigns is controlled described motor and steering wheel.
The road surface pictorial information that obtains according to vision sensor by mainboard and control panel based on the miniature car of machine vision of the present invention is controlled the operation of motor and steering wheel, this miniature car is with respect to the archeus vehicle, miniature intelligent vehicle simple in structure, cheap, many cars test environment makes up easily.And experiment place and environment are adjusted easily, can carry out the experiment under the multiple varying environment easily.
In a kind of preferred implementation of the present invention, this miniature car also comprises for the electronic compass of judging traffic direction and climb and fall angle with for the infrared distance sensor of judging front-and-rear vehicle distance and the miniature spacing of adjacent lane, described electronic compass links to each other with described control panel respectively with infrared distance sensor, and described control panel is controlled the operation of described motor and steering wheel according to described electronic compass and infrared distance sensor information transmitted.
The present invention is by utilizing electronic compass and infrared distance sensor, realized accurate control that miniature vehicle is travelled having improved the security of travelling greatly.
In a kind of preferred implementation of the present invention, mainboard comprises initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, surface mark detection module; Described initialization module links to each other with described vision sensor, described motor and described steering wheel respectively, is used for described vision sensor, described motor and described steering wheel are carried out initialization; Described hunting module links to each other with described vision sensor, is used for the road surface picture inspection vehicle diatom that obtains according to described vision sensor; Described detection of obstacles module links to each other with described vision sensor, is used for detecting according to the road surface picture that described vision sensor obtains the barrier in miniature car the place ahead; Described traffic lights detection module links to each other with described vision sensor, and the road surface picture that is used for obtaining according to described vision sensor detects the working condition of traffic lights; Described traffic sign detection module links to each other with described vision sensor, is used for traffic sign to be identified and judging according to the road surface picture that described vision sensor obtains; Described surface mark detection module links to each other with described vision sensor, for the surface mark in the miniature car of the road surface picture recognition track of living in that obtains according to described vision sensor.
The present invention carries out initialization by the initialization module of mainboard to vision sensor, motor and steering wheel, improved the accuracy of travelling, in addition, the hunting module that this mainboard can have, detection of obstacles module, traffic lights detection module, traffic sign detection module, surface mark detection module, realized that automated lane line following, site of road detect, move certainly, many cars are interactive and analyzed the ability of vehicle target direction, improved the security of travelling.
In another kind of preferred implementation of the present invention, mainboard also comprises rate control module and direction control module, and described rate control module links to each other with described initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module and surface mark detection module respectively with described direction control module; Described rate control module receives the information of described initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, the detection of surface mark detection module and produces the speed control information, described rate control module is transferred to described control panel with the speed control information, and described control panel is controlled the travelling speed of described motor; Described direction control module receives the information of described initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, the detection of surface mark detection module, and generation direction control information, described direction control module is transferred to described control panel with the direction control information, and described control panel is controlled the direction of described steering wheel.。
Mainboard of the present invention is by rate control module and the travelling speed of direction control module control motor and the direction of steering wheel, realize the behaviour decision making that miniature car should be taked after to the perception of surrounding environment, comprise the hunting walking, obstacle, observe traffic rules and regulations etc., improved the security of travelling.
In order to realize above-mentioned purpose of the present invention, according to two aspects of the present invention, the invention provides a kind of miniature vehicle control based on machine vision, comprising: at least one miniature car, described miniature car are the miniature car based on machine vision of the present invention; Server, described server links to each other with the mainboard of described miniature car, and described server and described mainboard carry out two-way information interaction; The management end computer, described management end computer links to each other with described server, and described management end computer receives described server information transmitted and by described server monitoring management is carried out in the operation of described miniature car.
The building of miniature vehicle control based on machine vision of the present invention is based on realizes on the PC platform base, by miniature car remote control administrative system environment sensing and the intelligent behavior decision-making capability of miniature car is tested.Miniature car is the information of obtaining to be connected in the network of server by technological means such as radio communications, reaches car and road, car and car, car and urban network and realizes interconnecting, and is analyzed then, draws strategy, thus the control that realization to miniature garage is.
On this miniature vehicle control, because the experimental situation relative closure of miniature car, and there is not the problem of secure context substantially in miniature car, so the autonomous driving experiment can not be subjected to the constraint of non-technical elements such as laws and regulations.In addition with respect to the archeus vehicle, miniature car simple in structure, cheap, many cars test environment makes up easily.And experiment place and environment are adjusted easily, can carry out the experiment under the multiple varying environment easily.The research of miniature car is accompanied by increasing the weight of day by day of urban traffic blocking and intelligent transportation solution continuous advancement in technology occurs, also be that municipal intelligent traffic is one of important embodiment of changing of the management mode of object based on the hot spot region, with the car, promoted advancing of China's intelligent transportation.
In a preferred embodiment of the present invention, have miniature car remote control administrative system in the described management end computer, described miniature car remote control administrative system comprises intelligent vehicle termination management module and remote monitoring function module; Described intelligent vehicle termination management module comprises system-based attribute configuration module, termination management module, status information primary attribute configuration module, status information customized management module, steering order release module and collection pictures management module, miniature car by server respectively with described system-based attribute configuration module, termination management module, status information primary attribute configuration module, status information customized management module, the steering order release module links to each other with collection pictures management module, described system-based attribute configuration module is used for arranging the underlying parameter of miniature truck system, comprises that the camera position coordinate is demarcated on the miniature car, per second reads camera picture frame number, communication interface, miniature car network numbering; Described status information primary attribute configuration module is used for the multidate information that the miniature garage of management crosses journey, comprises travel speed, acceleration-deceleration, the identification of climb and fall angle, traveling-position coordinate etc.; Described status information customized management module is used for the message customization of managerial demand and remote management terminal, is used for the telemanagement parameter that encapsulation also sends to miniature car in real time; Described steering order release module is used for all receptions of configuration and sends form and the concrete parameter of instruction; It is the road information of gathering in real time at driving process that described collection pictures management module is used for the management vision sensor, picture is carried out correlation analysis handle, and the result is fed back to status information primary attribute configuration module; Described remote monitoring function module comprises user's connection status monitoring module and automatic return state or lastest imformation module; Described user's connection status monitoring module links to each other with miniature car owner's plate, for realizing the be connected monitoring of every miniature vehicle control with the remote management terminal computer, the situation that is connected that shows every miniature car and management end computer shows parameters such as speed that every miniature car is current and running status; Described automatic return state or lastest imformation module link to each other with miniature car owner's plate, be used for obtaining in real time parameters such as miniature car running status, at first send reading command, miniature car sends to remote control terminal with relevant information after receiving reading command, remote control terminal upgrades data after receiving up-to-date motion state parameters, shows by user's connection status monitoring module again.
The present invention monitors the running status of miniature car in real time by miniature car remote control administrative system, miniature car terminal keeps being connected with server, be implemented on the information network platform according to different functional requirements to miniature car attribute information and quiet, multidate information extracts and effectively utilize, and effectively supervises and provide integrated service according to different functional requirements to the running status of miniature car.
In order to realize above-mentioned purpose of the present invention, according to three aspects of the present invention, the invention provides a kind of miniature car control method based on machine vision, comprise the steps:
S1: build the miniature vehicle control based on machine vision of the present invention;
S2: the initialization module of mainboard carries out initialization to vision sensor, motor and steering wheel;
S3: vision sensor obtains the road surface picture and described road surface picture is transferred to mainboard;
S4: described mainboard carries out hunting, detection of obstacles, traffic lights detection, traffic sign detection and surface mark according to described road surface picture and detects;
S5: described mainboard is assigned control command to control panel, controls the operation of described motor and steering wheel;
S6: described mainboard is transferred to the operation information of described miniature car server and is transferred to the management end computer by described server, and described management end computer expert crosses miniature car remote control administrative system monitoring management is carried out in the operation of described miniature car.
Miniature car control method based on machine vision of the present invention realizes under the complicated road environment moving, the static object environment sensing, realize the behaviour decision making that miniature car should be taked after to the perception of surrounding environment, comprise the hunting walking, obstacle, observe traffic rules and regulations etc., by telemanagement, realize the running status of real-time monitoring vehicle, miniature car terminal keeps being connected with server, server and management end computer according to different functional requirements to miniature car attribute information and quiet, multidate information extracts and effectively utilizes, and effectively supervises and provide integrated service according to different functional requirements to the running status of miniature car.
In a kind of preferred implementation of the present invention, described line-hunting method comprises the steps:
S81: described hunting module is carried out gradation conversion and binary conversion treatment to described picture after receiving the picture that described vision sensor obtains;
S82: described hunting module is carried out rim detection to described binary image;
S83: described hunting module looks for line to handle, and according to distance and the slope threshold value of lane line lane line is screened.
Line-hunting method of the present invention can find lane line rapidly and accurately, has improved traveling security.
In another kind of preferred implementation of the present invention, described traffic lights detection method comprises the steps:
S91: when miniature car travels to the crossroad pattern, at first judge whether to exist stop line, if existence, then execution in step S92;
S92: the height threshold according to vision sensor and traffic lights, obtain area-of-interest;
S93: read the tristimulus values of the pixel in the described area-of-interest and compare with the traffic lights tristimulus values of setting, when satisfying error requirements, described area-of-interest is the target area;
S94: conditional filtering is carried out in described target area, and the project of described conditional filtering comprises the number of screening pixel, and the ratio that tristimulus values is shared when all conditions all satisfies, is then judged red light or green light.
Traffic lights detection method of the present invention is by selected area-of-interest, and in area-of-interest the select target zone, improved the rapidity that traffic lights detect, conditional filtering is carried out in the target area, improved the accuracy that traffic lights detect.
In another preferred implementation of the present invention, method for traffic sign detection comprises the steps:
S101: described traffic sign detection module detect in the picture that obtains certain pixel and on every side connected domain whether have the red pixel point, if exist, then be set to the target area and enter step S102;
S102: in described target area, search for black pixel point, and obtain the rectangle of the connected region that comprises described black picture element, adjust the size of described rectangle by the adjusted size function;
S103: extract the characteristic information in the described rectangle, mate with template, if the match is successful, then draw the type of traffic sign, make miniature car will carry out corresponding operation.
Method for traffic sign detection of the present invention is by selected target zone and adjust the size of rectangle in the target area, has improved the rapidity that traffic sign detects, and characteristic information and template are mated, and has improved the accuracy of traffic sign detection.
Additional aspect of the present invention and advantage part in the following description provide, and part will become obviously from the following description, or recognize by practice of the present invention.
Description of drawings
Above-mentioned and/or additional aspect of the present invention and advantage are from obviously and easily understanding becoming the description of embodiment in conjunction with following accompanying drawing, wherein:
Fig. 1 is the structural representation that the present invention is based on the miniature car of machine vision;
Fig. 2 is the miniature car owner's plate structure of the present invention synoptic diagram;
Fig. 3 is the structural representation that the present invention is based on the miniature vehicle control of machine vision;
Fig. 4 is the structural representation of remote control administrative system of the present invention.
Fig. 5 is the process flow diagram that the present invention is based on the miniature car control method of machine vision;
Fig. 6 is based on the process flow diagram of the miniature car control method of machine vision in a kind of preferred implementation of the present invention.
Embodiment
Describe embodiments of the invention below in detail, the example of described embodiment is shown in the drawings, and wherein identical or similar label is represented identical or similar elements or the element with identical or similar functions from start to finish.Be exemplary below by the embodiment that is described with reference to the drawings, only be used for explaining the present invention, and can not be interpreted as limitation of the present invention.
In description of the invention, unless otherwise prescribed and limit, need to prove that term " installation ", " linking to each other ", " connection " should be done broad understanding, for example, can be mechanical connection or electrical connection, also can be the connection of two element internals, can be directly to link to each other, and also can link to each other indirectly by intermediary, for the ordinary skill in the art, can understand the concrete implication of above-mentioned term as the case may be.
The invention provides a kind of miniature car based on machine vision, as shown in Figure 1, it comprises the chassis, and this chassis is provided with motor and steering wheel.This miniature car also comprises vision sensor, mainboard and control panel, and vision sensor is used for obtaining the road surface picture, information such as identification lane line, road markings and barrier; Mainboard links to each other with vision sensor, and mainboard is according to vision sensor information transmitted operation control program and assign control command, and control panel links to each other with mainboard, the control command control motor that control panel reception mainboard is assigned and the operation of steering wheel.
In the present embodiment, this miniature chassis is selected the HPIcupracer chassis for use, and this chassis has motor and steering wheel, is used for mechanical motion.Control panel adopts the Arduino control panel of DFR0003 model.Mainboard adopts embedded x86 mainboard.Vision sensor can be 1, also can be for a plurality of, when vision sensor when being a plurality of, each vision sensor all links to each other with mainboard, in a preferred enforcement side of the present invention, vision sensor is two, is more preferably in the enforcement side at one of the present invention, and vision sensor is sieve skill camera.
The road surface pictorial information that obtains according to vision sensor by mainboard and control panel based on the miniature car of machine vision of the present invention is controlled the operation of motor and steering wheel, this miniature car is with respect to the archeus vehicle, miniature intelligent vehicle simple in structure, cheap, many cars test environment makes up easily.And experiment place and environment are adjusted easily, can carry out the experiment under the multiple varying environment easily.
In a kind of preferred implementation of the present invention, this miniature car also comprises for the electronic compass of judging traffic direction and climb and fall angle with for the infrared distance sensor of judging front-and-rear vehicle distance and the miniature spacing of adjacent lane, electronic compass links to each other with control panel respectively with infrared distance sensor, and control panel is according to the operation of electronic compass and infrared distance sensor information transmitted control motor and steering wheel.
In a preferred embodiment of the present invention, infrared distance sensor is two-way, and one the tunnel is used for judging front-and-rear vehicle distance, and another road is used for the distance of the miniature car of this miniature car of judgement and adjacent lane.
The present invention is by utilizing electronic compass and infrared distance sensor, realized accurate control that miniature vehicle is travelled having improved the security of travelling greatly.
In the present embodiment, this miniature car also comprises power supply, in a kind of preferred implementation of the present invention, adopts the 12V lithium battery to give main board power supply; Adopt the 8V lithium battery to power to motor; Vision sensor and control panel are by main board power supply.
In the present embodiment, miniature car also comprises the car shell, for the ease of realizing the research to miniature car, need to consider the arrangement situation of each accessory, comprise weight, size factor, because X86 mainboard and motor power consumption height, if select for use high power battery can increase miniature car weight amount, therefore need preferred dimension little, the battery that power is suitable, selecting for use of car shell also needs to consider size factor simultaneously.In a kind of preferred implementation of the present invention, follow following principle during configuration design:
1, mainboard battery and motor battery can install easily, dismantle, with convenient charging;
2, the control panel battery need not frequent dismounting, but must reserve charge port;
3, the car shell must be for convenience detach, and battery changes the outfit.Can consider the unified design of battery and car shell according to the big or small customized vehicle shell of vehicle body, be convenient for changing battery.
In the present embodiment, as shown in Figure 2, mainboard comprises initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, surface mark detection module.Initialization module links to each other with vision sensor, motor and steering wheel respectively, is used for vision sensor, motor and steering wheel are carried out initialization.The hunting module links to each other with vision sensor, is used for the road surface picture inspection vehicle diatom that obtains according to vision sensor.The detection of obstacles module links to each other with vision sensor, is used for detecting according to the road surface picture that vision sensor obtains the barrier in miniature car the place ahead.The traffic lights detection module links to each other with vision sensor, and the road surface picture that is used for obtaining according to vision sensor detects the working condition of traffic lights.The traffic sign detection module links to each other with vision sensor, is used for traffic sign to be identified and judging according to the road surface picture that vision sensor obtains.The surface mark detection module links to each other with vision sensor, for the surface mark in the miniature car of the road surface picture recognition track of living in that obtains according to vision sensor.The present invention carries out initialization by the initialization module of mainboard to vision sensor, motor and steering wheel, improved the accuracy of travelling, in addition, the hunting module that this mainboard can have, detection of obstacles module, traffic lights detection module, traffic sign detection module, surface mark detection module, realized that automated lane line following, site of road detect, move certainly, many cars are interactive and analyzed the ability of vehicle target direction, improved the security of travelling.
In another kind of preferred implementation of the present invention, mainboard also comprises rate control module and direction control module, and rate control module links to each other with initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module and surface mark detection module respectively with described direction control module.Rate control module receives the information of described initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, the detection of surface mark detection module and produces the speed control information, described rate control module is transferred to described control panel with the speed control information, and described control panel is controlled the travelling speed of described motor.The direction control module receives the information of described initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, the detection of surface mark detection module, and generation direction control information, described direction control module is transferred to described control panel with the direction control information, the direction of described control panel control steering wheel.Mainboard of the present invention is by rate control module and the travelling speed of direction control module control motor and the direction of steering wheel, realize the behaviour decision making that miniature car should be taked after to the perception of surrounding environment, comprise the hunting walking, obstacle, observe traffic rules and regulations etc., improved the security of travelling.
In a kind of preferred implementation of the present invention, mainboard adopts embedded x86 mainboard, has the ability that automated lane line following, site of road detect, move certainly, many cars are interactive and analyze the vehicle target direction based on the miniature car of this mainboard.In the present embodiment, mainboard has USB interface, and the hardware that its quantity can connect is as required adjusted, and can be limited is not limited to 4 the tunnel, and wherein, 2 tunnel USB interface connect camera, and 1 tunnel USB interface connects wireless network card; 1 tunnel USB interface connects control panel.Multi-path digital I/O mouth is arranged on the control panel, be used for connecting infrared distance sensor, electronic compass, equipment such as motor and steering wheel.
Each module of mainboard of the present invention can realize the related algorithm of dynamic and static targeted environment perception under the complicated road environment, comprises hunting algorithm, detection of obstacles algorithm, traffic lights detection algorithm, traffic sign detection algorithm, surface mark detection algorithm; Realize the behaviour decision making that miniature car should be taked after to the perception of surrounding environment, comprise the hunting walking, obstacle is observed traffic rules and regulations etc.
The present invention also provides a kind of miniature vehicle control based on machine vision, and as shown in Figure 3, it comprises at least one miniature car, server and management end computer, and server links to each other with the mainboard of miniature car, and server and mainboard carry out two-way information interaction; The management end computer links to each other with server, and management end computer reception server information transmitted is also carried out monitoring management by server to the operation of described miniature car.
In the present embodiment, miniature car is connected by TCP with server, also can miniature car terminal and server be coupled together by wireless network, and server is transferred to the management end computer with information, the management end computer is the running status of the miniature car of monitoring in real time, realizes the monitoring management to miniature car.
The building of miniature vehicle control based on machine vision of the present invention is based on realizes on the PC platform base, environment sensing and the intelligent behavior decision-making capability of miniature car is tested on the miniature car test platform of high emulation of simulation by vision sensor.Miniature car is the information of obtaining to be connected in the network of server by technological means such as radio communications, analyzed then, draw strategy, thereby realize the control that is to miniature garage, interconnect with road, car and car, car and urban network realization thereby reach car.On this miniature vehicle control, because the experimental situation relative closure of miniature car, and there is not the problem of secure context substantially in miniature car, so the autonomous driving experiment can not be subjected to the constraint of non-technical elements such as laws and regulations.In addition with respect to the archeus vehicle, miniature car simple in structure, cheap, many cars test environment makes up easily.And experiment place and environment are adjusted easily, can carry out the experiment under the multiple varying environment easily.The research of miniature car is accompanied by increasing the weight of day by day of urban traffic blocking and intelligent transportation solution continuous advancement in technology occurs, also be that municipal intelligent traffic is one of important embodiment of changing of the management mode of object based on the hot spot region, with the car, promoted advancing of China's intelligent transportation.
In a preferred embodiment of the present invention, as shown in Figure 4, has miniature car remote control administrative system in the management end computer, this miniature car remote control administrative system comprises intelligent vehicle termination management module and remote monitoring function module, wherein, the intelligent vehicle termination management module comprises system-based attribute configuration module, termination management module, status information primary attribute configuration module, status information customized management module, steering order release module and collection pictures management module, miniature car by server respectively with system-based attribute configuration module, termination management module, status information primary attribute configuration module, status information customized management module, the steering order release module links to each other with collection pictures management module, system-based attribute configuration module is used for arranging the underlying parameter of miniature truck system, includes but not limited to that specifically the camera position coordinate is demarcated on the miniature car, per second reads camera picture frame number, communication interface, information such as miniature car network numbering.Status information primary attribute configuration module links to each other with the mainboard of miniature car, is used for the multidate information that the miniature garage of management crosses journey, comprises information such as travel speed, acceleration-deceleration, the identification of climb and fall angle, traveling-position coordinate.Status information customized management module links to each other with miniature car owner's plate, is used for the message customization of managerial demand and remote management terminal, is used for the telemanagement parameter that encapsulation also sends to miniature car in real time.The steering order release module is used for all receptions of configuration and sends form and the concrete parameter of instruction.Gathering the pictures management module is the road information of gathering in real time for the management vision sensor at driving process, picture is carried out correlation analysis handle, and the result is fed back to status information primary attribute configuration module.The remote monitoring function module comprises user's connection status monitoring module and automatic return state or lastest imformation module, wherein, user's connection status monitoring module links to each other with miniature car owner's plate, for realizing the be connected monitoring of every miniature vehicle control with the remote management terminal computer, the situation that is connected that shows every miniature car and management end computer, show parameters such as speed that every miniature car is current and running status, automatically return state or lastest imformation module link to each other with miniature car owner's plate, be used for obtaining in real time parameters such as miniature car running status, at first send reading command, miniature car sends to remote control terminal with relevant information after receiving reading command, remote control terminal upgrades data after receiving up-to-date motion state parameters, shows by user's connection status monitoring module again.
The present invention monitors the running status of miniature car in real time by miniature car remote control administrative system, miniature car terminal keeps being connected with server, be implemented on the information network platform according to different functional requirements to miniature car attribute information and quiet, multidate information extracts and effectively utilize, and effectively supervises and provide integrated service according to different functional requirements to the running status of miniature car.
The present invention also provides a kind of miniature car control method based on machine vision, as shown in Figure 5, comprises the steps:
S1: build the miniature vehicle control based on machine vision of the present invention;
S2: the initialization module of mainboard carries out initialization to vision sensor, motor and steering wheel;
S3: vision sensor obtains the road surface picture and described road surface picture is transferred to mainboard;
S4: described mainboard carries out hunting, detection of obstacles, traffic lights detection, traffic sign detection and surface mark according to described road surface picture and detects;
S5: described mainboard is assigned control command to control panel, controls the operation of described motor and steering wheel;
S6: described mainboard is transferred to the operation information of described miniature car server and is transferred to the management end computer by described server, and described management end computer expert crosses miniature car remote control administrative system monitoring management is carried out in the operation of described miniature car.
Miniature car control method based on machine vision of the present invention realizes under the complicated road environment moving, the static object environment sensing, realize the behaviour decision making that miniature car should be taked after to the perception of surrounding environment, comprise the hunting walking, obstacle, observe traffic rules and regulations etc., by telemanagement, realize the running status of real-time monitoring vehicle, miniature car terminal keeps being connected with server, server and management end computer according to different functional requirements to miniature car attribute information and quiet, multidate information extracts and effectively utilizes, and effectively supervise and provide integrated service according to different functional requirements to the running status of miniature car, realized the collaborative innovation with early warning technology of bus or train route.
In a kind of preferred implementation of the present invention, this miniature car control method specifically comprises the steps:
The first step: build the miniature vehicle control based on machine vision of the present invention.Have this miniature car automated lane line following, site of road detect, move certainly, many cars are interactive and analyze the ability of vehicle target direction.This miniature vehicle control has the ability that remote vehicle tracking, inter-vehicle communication and long-range transport condition are analyzed based on the local area wireless network Long-distance Control.
Integrated use of the present invention machine vision; artificial intelligence; pattern-recognition; the advanced technology of multidisciplinary intersection such as wireless sense network and Meter Reliability; at the urban transportation characteristics; utilize emulation technology; in the real traffic circulation situation of 3 D stereo traffic sand table simulation test platform reproduction; or fictionalize the situation of future transportation operation; make it possible to low cost; low jeopardously manifesting taken place or nonevent traffic events; its feature and rule are studied; technical scheme of the present invention is transplanted on the true car; the intelligent automobile that can help enterprise's exploitation to have complete independent intellectual property right; the driving supplementary means of control vehicle and prevention dangerous situation is provided for the driver; promote the vehicle control ability of human pilot, prevention traffic hazard and protection pedestrains safety.
Intelligent vehicle of the present invention is driven main research integral body and is finished the vehicle drive task automatically or as DAS (Driver Assistant System).These tasks comprise the tracking road, keep vehicle to travel on correct road, keep a safe distance between the vehicle, the speed of regulating vehicle according to current traffic and roadway characteristic is overtaken other vehicles and is kept away the purpose of barrier and find the shortest path that reaches the destination and travel easily in the urban district and stop to reach across the track.Thereby the miniature intelligent vehicle based on machine vision reaches unpiloted purpose in the identification that realizes barrier, friendship traffic lights, traffic sign etc., all will realize by machine vision.Machine vision replaces human eye to do measurement and judgement with machine exactly.
In the present embodiment, vision sensor will be ingested target and convert picture signal to, send mainboard to, and this mainboard also comprises analog-digital commutator, analog-digital commutator is transformed into digitized signal according to pixel distribution and the information such as brightness, color of picture signal with picture signal; The hunting module of mainboard, the detection of obstacles module, the traffic lights detection module, the traffic sign detection module, the surface mark detection module carries out the equipment action that computing is extracted target signature separately and controlled the scene according to discrimination result to these digital signals.In the present embodiment, preferably adopt the function in the OpenCV image processing software that image is handled.In the present embodiment, the function that adopts includes but not limited to picture format transfer function cvCvtColor (), interesting image regions function cvSetImageROI () is set, binary conversion treatment function cvThreshold (), seek profile function cvFindContours (), profile bounding box return function cvBoundingRect () etc.
Second step: the initialization module of mainboard carries out initialization to vision sensor, motor and steering wheel.
The attainable function of this module of initialization is: to the initialization of parameter in all modules, include but not limited to visual attribute sensor, projection matrix, motor speed, the direction of steering wheel is carried out initialization, in a preferred embodiment of the present invention, initialized value can be set according to experiment or this area frequently-used data.On specific algorithm is realized, mainly call the function of opencv and handle.The function that the visual attribute sensor parameter call for example is set comprises:
CvCreateCameraCapture (); This function is that camera obtains function, can obtain the miniature intelligent vehicle property value of two cameras up and down by this function.
cvSetCaptureProperty(pCapture,CV_CAP_PROP_FRAME_WIDTH,320);
cvSetCaptureProperty(pCapture,CV_CAP_PROP_FRAME_HEIGHT,240);
These two functions are that the size of picture that camera is obtained is set, and the dimension of picture of setting in the function is the size of 320 pixel *, 240 pixels.
The 3rd step: vision sensor obtains the road surface picture and the road surface picture is transferred to mainboard.
The 4th step: mainboard carries out hunting, detection of obstacles, traffic lights detection, traffic sign detection and surface mark according to the road surface picture and detects.Specifically be that hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, the surface mark detection module of mainboard receives vision sensor respectively and obtain the road surface picture, and deal with the work accordingly respectively, specific as follows:
In a kind of preferred implementation of the present invention, line-hunting method comprises the steps:
S11: the road pavement picture carries out gradation conversion and binary conversion treatment behind the road surface picture that hunting module reception vision sensor obtains.
S12: the hunting module is carried out rim detection to binary image, specifically can but be not limited to adopt Canny function binary image to carry out rim detection.
S13: the hunting module looks for line to handle, and according to distance and the slope threshold value of lane line lane line is screened.In the present embodiment, the hunting module utilizes image transforming function transformation function hLines2 () to look for line, image transforming function transformation function cvHoughLines2 () has found the many lines in the image, some is wanted, some is undesired, in order to obtain lane line, just must carry out conditional filtering, actual conditions can include but not limited to distance, the slope threshold value to lane line, the distance of lane line and slope threshold value can be chosen according to the distance of the lane line on the real road in the concrete reality and the slope of lane line, also can reduce in proportion or amplify and choose.
Find after the lane line, miniature car changes for convenience, can determine which track residing specifically be according to the condition that whether has the greenery patches about lane line, the concrete condition of changing is, if there is the greenery patches on the right side, track, illustrate that then the track is the track on the right side, can only change trains left; If there is the greenery patches in track left side, illustrate that then the track is the greenery patches of doing the left side, can only change trains to the right, if the left and right sides does not all have the greenery patches, the track of explanation in the middle of being then, then to the left or change trains can on the right side.Line-hunting method of the present invention can find lane line rapidly and accurately, has improved traveling security.
In a kind of preferred implementation of the present invention, corresponding processing is identified and made to the detection of obstacles module to the barrier that the place ahead occurs, and obstacle detection method comprises the steps:
S21: the road pavement picture carries out format conversion behind the road surface picture that detection of obstacles module reception vision sensor obtains.After the detection of obstacles module is obtained picture from vision sensor, in order to avoid the light influence, in the processing procedure of picture, need to select suitable color space, in the present embodiment, rgb format is converted to the HSV form to be handled, the format conversion function that adopts is: and cvCvtColor (image, imgHSV, CV_RGB2HSV).
S22: the detection of obstacles module is carried out gradation conversion, binary conversion treatment, searching profile and conditional filtering.In the present embodiment, call that built-in function road pavement picture carries out gradation conversion, binary conversion treatment, searching profile, conditional filtering among the opencv.The concrete opencv function that mainly calls is:
Binary conversion treatment function cvThreshold ();
Seek profile function cvFindContours ().
After searching out profile, barrier is carried out conditional filtering, specifically screen apart from features such as the color of the distance of miniature car, barrier, size, areas according to barrier.Just can realize the identification to barrier, thereby command the action of miniature car, comprise stopping or changing.In the present embodiment, the condition of screening can be set according to actual tests.
In another kind of preferred implementation of the present invention, the traffic lights detection method comprises the steps:
S31: when miniature car travelled to the crossroad pattern, the traffic lights detection module judged at first whether the road picture exists stop line, if existence, then execution in step S32.
S32: the height threshold according to vision sensor and traffic lights, obtain area-of-interest.In the testing process of traffic lights, because the height of camera and traffic lights is all fixed, in order to improve processing speed, reduce factors such as environmental interference, therefore adopt area-of-interest is set.In the present embodiment, the height threshold of vision sensor and traffic lights can arrange according to the height of the vision sensor in concrete test or the real road and traffic lights, the certain formed scope of degree of height plus-minus that the concrete height threshold that arranges is traffic lights.
S33: read R, G, the B tristimulus values of the pixel in the area-of-interest and compare with R, G, the B tristimulus values of the traffic lights of setting, when satisfying error requirements, area-of-interest is the target area.Concrete error range can specifically be set according to concrete experiment.
S34: conditional filtering is carried out in the target area, and the project of described conditional filtering comprises the number of screening pixel, and R, G, the shared ratio of B tristimulus values difference when all conditions all satisfies, are then judged red light or green light.
Traffic lights detection method of the present invention is by selected area-of-interest, and in area-of-interest the select target zone, improved the rapidity that traffic lights detect, conditional filtering is carried out in the target area, improved the accuracy that traffic lights detect.
In a kind of preferred implementation of the present invention, the traffic sign type comprises craspedodrome, forbids keeping straight on, and turns right, and no right turn turns left, six types of no left turns, and miniature intelligent vehicle is by identification and the judgement of this module realization to above traffic sign.Method for traffic sign detection comprises the steps:
S41: described traffic sign detection module detect in the picture that obtains certain pixel and on every side connected domain whether have the red pixel point, if exist, then be set to the target area and enter step S42, the size in concrete UNICOM territory can be set according to the size of traffic sign in the test, specifically can but be not limited to less than, more than or equal to the size of traffic sign.
S42: in the target area, search for black pixel point, and obtain the rectangle of the connected region that comprises black picture element, adjust the size of described rectangle by the adjusted size function, in the present embodiment, by adjusted size function cvResize () rectangle size is adjusted into the rectangle of 5 pixel sizes of 7 pixel *.
S43: extract the characteristic information in the described rectangle, mate with template, if the match is successful, then draw the type of traffic sign, make miniature car will carry out corresponding operation.
Method for traffic sign detection of the present invention is by selected target zone and adjust the size of rectangle in the target area, has improved the rapidity that traffic sign detects, and characteristic information and template are mated, and has improved the accuracy of traffic sign detection.
In a kind of preferred implementation of the present invention, realize miniature car to identification and the reflex action of track of living in surface mark, as the sign of directly walking to turn right, the surface mark detection method comprises the steps:
S51: the road pavement picture carries out gradation conversion and binary conversion treatment behind the road surface picture that surface mark detection module reception vision sensor obtains.
S52: the surface mark detection module carries out rim detection to binary image, specifically can but be not limited to adopt Canny function binary image to carry out rim detection.
S53: the surface mark detection module looks for line to handle, and screens according to the size of lines.
S54: extract the characteristic information of described lines, mate with template, if the match is successful, then draw the type of surface mark, make miniature car will carry out corresponding operation.
In a preferred embodiment of the present invention, as shown in Figure 6, the operational process of the control program of mainboard is: at first, the initialization module of mainboard carries out initialization to vision sensor, motor and steering wheel.After the initialization, vision sensor detects the road surface picture and the road surface picture is transferred to hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module and surface mark detection module.The hunting module is sought lane line, and miniature car is normally advanced.In the process of advancing, the detection of obstacles module judges whether the track is clean, and whether the traffic lights detection module detects uses stop line.The detection of obstacles module judges that the track is clean, then miniature car continuation hunting is advanced, if the detection of obstacles module judges that the track is unclean, the detection of obstacles module detects and has judged whether barrier through conditional filtering, if barrier is arranged then stop, detects again whether barrier is arranged after the parking, stop if still have barrier then continue, if do not have barrier then continue hunting and advance, the situation of having avoided the error-detecting barrier to cause stopping takes place, and has improved accuracy; If judging, the detection of obstacles module do not have not need to stop behind barrier or the process conditional filtering, judge then whether change condition meets, if the condition of changing meets, then change, constantly detect to change in the process of changing and whether finish, if finish, then continue hunting and advance, do not finish if, continue to change, if the condition of changing does not satisfy, then continue to travel in former track.
The traffic lights detection module detects whether use stop line, if there is not stop line, then miniature car continuation hunting is advanced, if stop line is arranged, has then judged whether red light; If red light is arranged, then stop, after red light goes out, enter the crossroad traveling mode, the hunting module is sought lane line, search out lane line after, miniature car is normally advanced, if do not search out lane line, the hunting module continues hunting; If there is not red light, the traffic sign detection module detects whether traffic sign is arranged, if having, then according to traffic sign walking, the hunting module is sought lane line, search out lane line after, miniature car is normally advanced, if do not search out lane line, the hunting module continues hunting.If there is not traffic sign, then enter the crossroad traveling mode, the hunting module is sought lane line, search out lane line after, miniature car is normally advanced, if do not search out lane line, the hunting module continues hunting.
The 5th step: mainboard is assigned control command to control panel, the operation of control motor and steering wheel.The rate control module that specifically is mainboard receives the information of initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, the detection of surface mark detection module and produces the speed control information, described rate control module is transferred to described control panel with the speed control information, and described control panel is controlled the travelling speed of described motor.Described direction control module receives the information of described initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, the detection of surface mark detection module, and generation direction control information, described direction control module is transferred to described control panel with the direction control information, and described control panel is controlled the direction of described steering wheel.
The 6th step: mainboard is transferred to the operation information of miniature car server and is transferred to the management end computer by server, and the management end computer expert crosses miniature car remote control administrative system and realizes monitoring management is carried out in the operation of miniature car.
In the description of this instructions, concrete feature, structure, material or characteristics that the description of reference term " embodiment ", " some embodiment ", " example ", " concrete example " or " some examples " etc. means in conjunction with this embodiment or example description are contained at least one embodiment of the present invention or the example.In this manual, the schematic statement to above-mentioned term not necessarily refers to identical embodiment or example.And concrete feature, structure, material or the characteristics of description can be with the suitable manner combination in any one or more embodiment or example.
Although illustrated and described embodiments of the invention, those having ordinary skill in the art will appreciate that: can carry out multiple variation, modification, replacement and modification to these embodiment under the situation that does not break away from principle of the present invention and aim, scope of the present invention is limited by claim and equivalent thereof.
Claims (10)
1. the miniature car based on machine vision is characterized in that, comprising:
The chassis, described chassis is provided with motor and steering wheel;
Vision sensor, described vision sensor is used for obtaining the road surface picture;
Mainboard, described mainboard links to each other with described vision sensor, and described mainboard is according to described vision sensor information transmitted operation control program and send control command;
Control panel, described control panel links to each other with the chassis with described mainboard respectively, and described control panel receives the operation that control command that described mainboard assigns is controlled described motor and steering wheel.
2. the miniature car based on machine vision as claimed in claim 1, it is characterized in that: also comprise for the electronic compass of judging traffic direction and climb and fall angle with for the infrared distance sensor of judging front-and-rear vehicle distance and the miniature spacing of adjacent lane, described electronic compass links to each other with described control panel respectively with infrared distance sensor, and described control panel is controlled the operation of described motor and steering wheel according to described electronic compass and infrared distance sensor information transmitted.
3. the miniature car based on machine vision as claimed in claim 1, it is characterized in that: described mainboard comprises initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, surface mark detection module;
Described initialization module links to each other with described vision sensor, described motor and described steering wheel respectively, is used for described vision sensor, described motor and described steering wheel are carried out initialization;
Described hunting module links to each other with described vision sensor, is used for the road surface picture inspection vehicle diatom that obtains according to described vision sensor;
Described detection of obstacles module links to each other with described vision sensor, is used for detecting according to the road surface picture that described vision sensor obtains the barrier in miniature car the place ahead;
Described traffic lights detection module links to each other with described vision sensor, and the road surface picture that is used for obtaining according to described vision sensor detects the working condition of traffic lights;
Described traffic sign detection module links to each other with described vision sensor, is used for traffic sign to be identified and judging according to the road surface picture that described vision sensor obtains;
Described surface mark detection module links to each other with described vision sensor, for the surface mark in the miniature car of the road surface picture recognition track of living in that obtains according to described vision sensor.
4. the miniature car based on machine vision as claimed in claim 3, it is characterized in that: described mainboard also comprises rate control module and direction control module, and described rate control module links to each other with described initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module and surface mark detection module respectively with described direction control module;
Described rate control module receives the information of described initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, the detection of surface mark detection module and produces the speed control information, described rate control module is transferred to described control panel with the speed control information, and described control panel is controlled the travelling speed of described motor;
Described direction control module receives the information of described initialization module, hunting module, detection of obstacles module, traffic lights detection module, traffic sign detection module, the detection of surface mark detection module, and generation direction control information, described direction control module is transferred to described control panel with the direction control information, and described control panel is controlled the direction of described steering wheel.
5. the miniature vehicle control based on machine vision is characterized in that, comprising:
At least one miniature car, described miniature car are the described miniature car based on machine vision of one of claim 1-4;
Server, described server links to each other with the mainboard of described miniature car, and described server and described mainboard carry out two-way information interaction;
The management end computer, described management end computer links to each other with described server, and described management end computer receives described server information transmitted and by described server monitoring management is carried out in the operation of described miniature car.
6. the miniature vehicle control based on machine vision as claimed in claim 5, it is characterized in that: have miniature car remote control administrative system in the described management end computer, described miniature car remote control administrative system comprises intelligent vehicle termination management module and remote monitoring function module;
Described intelligent vehicle termination management module comprises system-based attribute configuration module, termination management module, status information primary attribute configuration module, status information customized management module, steering order release module and collection pictures management module,
Miniature car links to each other with described system-based attribute configuration module, termination management module, status information primary attribute configuration module, status information customized management module, steering order release module and collection pictures management module respectively by server,
Described system-based attribute configuration module is used for arranging the underlying parameter of miniature truck system, comprises that the demarcation of camera position coordinate, per second read camera picture frame number, communication interface, miniature car network numbering on the miniature car;
Described status information primary attribute configuration module is used for the multidate information that the miniature garage of management crosses journey, comprises travel speed, acceleration-deceleration, the identification of climb and fall angle, traveling-position coordinate etc.;
Described status information customized management module is used for the message customization of managerial demand and remote management terminal, is used for the telemanagement parameter that encapsulation also sends to miniature car in real time;
Described steering order release module is used for all receptions of configuration and sends form and the concrete parameter of instruction;
It is the road information of gathering in real time at driving process that described collection pictures management module is used for the management vision sensor, picture is carried out correlation analysis handle, and the result is fed back to status information primary attribute configuration module;
Described remote monitoring function module comprises user's connection status monitoring module and automatic return state or lastest imformation module;
Described user's connection status monitoring module links to each other with miniature car owner's plate, for realizing the be connected monitoring of every miniature vehicle control with the remote management terminal computer, the situation that is connected that shows every miniature car and management end computer shows parameters such as speed that every miniature car is current and running status;
Described automatic return state or lastest imformation module link to each other with miniature car owner's plate, be used for obtaining in real time parameters such as miniature car running status, at first send reading command, miniature car sends to remote control terminal with relevant information after receiving reading command, remote control terminal upgrades data after receiving up-to-date motion state parameters, shows by user's connection status monitoring module again.
7. the miniature car control method based on machine vision is characterized in that, comprises the steps:
S1: build the described miniature vehicle control based on machine vision as one of claim 5-6;
S2: the initialization module of mainboard carries out initialization to vision sensor, motor and steering wheel;
S3: vision sensor obtains the road surface picture and described road surface picture is transferred to mainboard;
S4: described mainboard carries out hunting, detection of obstacles, traffic lights detection, traffic sign detection and surface mark according to described road surface picture and detects;
S5: described mainboard is assigned control command to control panel, controls the operation of described motor and steering wheel;
S6: described mainboard is transferred to the operation information of described miniature car server and is transferred to the management end computer by described server, and described management end computer expert crosses miniature car remote control administrative system monitoring management is carried out in the operation of described miniature car.
8. the miniature car control method based on machine vision as claimed in claim 7 is characterized in that described line-hunting method comprises the steps:
S81: described hunting module is carried out gradation conversion and binary conversion treatment to described picture after receiving the picture that described vision sensor obtains;
S82: described hunting module is carried out rim detection to described binary image;
S83: described hunting module looks for line to handle, and according to distance and the slope threshold value of lane line lane line is screened.
9. the miniature car control method based on machine vision as claimed in claim 7 is characterized in that described traffic lights detection method comprises the steps:
S91: when miniature car travels to the crossroad, start the crossroad pattern, program at first judges whether to exist stop line under this pattern, if existence, then execution in step S92;
S92: the height threshold according to vision sensor and traffic lights, obtain area-of-interest;
S93: read the tristimulus values of the pixel in the described area-of-interest and compare with the traffic lights tristimulus values of setting, when satisfying error requirements, described area-of-interest is the target area;
D94: conditional filtering is carried out in described target area, and the project of described conditional filtering comprises the number of screening pixel, and the ratio that tristimulus values is shared when all conditions all satisfies, is then judged red light or green light.
10. the miniature car control method based on machine vision as claimed in claim 7 is characterized in that described method for traffic sign detection comprises the steps:
S101: described traffic sign detection module detect in the picture that obtains certain pixel and on every side connected domain whether have the red pixel point, if exist, then be set to the target area and enter step S102;
S102: in described target area, search for black pixel point, and obtain the rectangle of the connected region that comprises described black picture element, adjust the size of described rectangle by the adjusted size function;
S103: extract the characteristic information in the described rectangle, mate with template, if the match is successful, then draw the type of traffic sign, make miniature car will carry out corresponding operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013102011985A CN103268072A (en) | 2013-05-27 | 2013-05-27 | Miniature vehicle, miniature vehicle control system and control method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013102011985A CN103268072A (en) | 2013-05-27 | 2013-05-27 | Miniature vehicle, miniature vehicle control system and control method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103268072A true CN103268072A (en) | 2013-08-28 |
Family
ID=49011708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013102011985A Pending CN103268072A (en) | 2013-05-27 | 2013-05-27 | Miniature vehicle, miniature vehicle control system and control method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103268072A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102800236A (en) * | 2012-06-18 | 2012-11-28 | 中国人民解放军军事交通学院 | Electric and mechanical integration platform of automobile model micro-car |
| CN104407612A (en) * | 2014-10-16 | 2015-03-11 | 重庆市合川区何茗机械加工厂 | Miniature intelligent vehicle and test method applying miniature intelligent vehicle |
| CN104732835A (en) * | 2015-02-02 | 2015-06-24 | 上海交通大学 | Stadium intelligent microscopic vehicle teaching device |
| CN105109550A (en) * | 2015-08-21 | 2015-12-02 | 苏州斯卡柏通讯技术有限公司 | Control device for miniature intelligent automobile |
| CN105653257A (en) * | 2015-08-13 | 2016-06-08 | 哈尔滨安天科技股份有限公司 | Sand table system with customized strategy |
| CN106354028A (en) * | 2016-09-14 | 2017-01-25 | 华北水利水电大学 | Intelligent traffic simulation system |
| CN107089458A (en) * | 2017-07-03 | 2017-08-25 | 成都大学 | A kind of new intelligent environment protection rubbish automatic recovery system |
| CN107291074A (en) * | 2016-09-29 | 2017-10-24 | 中国科学院自动化研究所 | A kind of miniature intelligent vehicle system |
| CN107392710A (en) * | 2017-07-20 | 2017-11-24 | 宁波大学 | A kind of long-distance intelligent customization processing method of personalized product |
| CN107886034A (en) * | 2016-09-30 | 2018-04-06 | 比亚迪股份有限公司 | Driving based reminding method, device and vehicle |
| CN107891808A (en) * | 2016-09-30 | 2018-04-10 | 比亚迪股份有限公司 | Driving based reminding method, device and vehicle |
| CN108597315A (en) * | 2018-04-11 | 2018-09-28 | 广州维脉电子科技有限公司 | A kind of sand table model of mind controller of vehicle and method |
| CN112255630A (en) * | 2020-11-06 | 2021-01-22 | 上海电子信息职业技术学院 | Multifunctional model car |
| CN116168370A (en) * | 2023-04-24 | 2023-05-26 | 北京数字政通科技股份有限公司 | Automatic driving data identification method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1992008215A1 (en) * | 1990-10-25 | 1992-05-14 | Mestech Creation Corporation | Traffic surveillance system |
| US5761326A (en) * | 1993-12-08 | 1998-06-02 | Minnesota Mining And Manufacturing Company | Method and apparatus for machine vision classification and tracking |
| CN1464487A (en) * | 2002-06-03 | 2003-12-31 | 昆明利普机器视觉工程有限公司 | A traffic flow detection system based on visual vehicle optical characteristic recognition and matching |
| CN1804928A (en) * | 2005-11-24 | 2006-07-19 | 上海交通大学 | Machine vision based estimation method for local geometry of driveway and vehicle location |
| CN1897015A (en) * | 2006-05-18 | 2007-01-17 | 王海燕 | Method and system for inspecting and tracting vehicle based on machine vision |
| CN102136150A (en) * | 2011-03-22 | 2011-07-27 | 宁波大学 | Method for detecting speed limit sign based on image processing technology |
| CN202084185U (en) * | 2011-06-16 | 2011-12-21 | 长安大学 | Automatic traffic sign identification device |
-
2013
- 2013-05-27 CN CN2013102011985A patent/CN103268072A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1992008215A1 (en) * | 1990-10-25 | 1992-05-14 | Mestech Creation Corporation | Traffic surveillance system |
| US5761326A (en) * | 1993-12-08 | 1998-06-02 | Minnesota Mining And Manufacturing Company | Method and apparatus for machine vision classification and tracking |
| CN1464487A (en) * | 2002-06-03 | 2003-12-31 | 昆明利普机器视觉工程有限公司 | A traffic flow detection system based on visual vehicle optical characteristic recognition and matching |
| CN1804928A (en) * | 2005-11-24 | 2006-07-19 | 上海交通大学 | Machine vision based estimation method for local geometry of driveway and vehicle location |
| CN1897015A (en) * | 2006-05-18 | 2007-01-17 | 王海燕 | Method and system for inspecting and tracting vehicle based on machine vision |
| CN102136150A (en) * | 2011-03-22 | 2011-07-27 | 宁波大学 | Method for detecting speed limit sign based on image processing technology |
| CN202084185U (en) * | 2011-06-16 | 2011-12-21 | 长安大学 | Automatic traffic sign identification device |
Non-Patent Citations (2)
| Title |
|---|
| 毕建权等: "缩微智能车软件系统设计与实现", 《计算机工程与应用》, no. 1, 15 January 2013 (2013-01-15), pages 234 - 238 * |
| 邵桂珠: "道路交通标志识别算法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 10, 15 October 2008 (2008-10-15), pages 18 - 30 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102800236A (en) * | 2012-06-18 | 2012-11-28 | 中国人民解放军军事交通学院 | Electric and mechanical integration platform of automobile model micro-car |
| CN104407612A (en) * | 2014-10-16 | 2015-03-11 | 重庆市合川区何茗机械加工厂 | Miniature intelligent vehicle and test method applying miniature intelligent vehicle |
| CN104732835A (en) * | 2015-02-02 | 2015-06-24 | 上海交通大学 | Stadium intelligent microscopic vehicle teaching device |
| CN104732835B (en) * | 2015-02-02 | 2017-08-01 | 上海交通大学 | A kind of intelligent miniature vehicle instructional device in stadium |
| CN105653257A (en) * | 2015-08-13 | 2016-06-08 | 哈尔滨安天科技股份有限公司 | Sand table system with customized strategy |
| CN105653257B (en) * | 2015-08-13 | 2023-04-07 | 安天科技集团股份有限公司 | Sand table system capable of customizing strategy |
| CN105109550A (en) * | 2015-08-21 | 2015-12-02 | 苏州斯卡柏通讯技术有限公司 | Control device for miniature intelligent automobile |
| CN106354028A (en) * | 2016-09-14 | 2017-01-25 | 华北水利水电大学 | Intelligent traffic simulation system |
| CN107291074A (en) * | 2016-09-29 | 2017-10-24 | 中国科学院自动化研究所 | A kind of miniature intelligent vehicle system |
| CN107886034A (en) * | 2016-09-30 | 2018-04-06 | 比亚迪股份有限公司 | Driving based reminding method, device and vehicle |
| CN107891808A (en) * | 2016-09-30 | 2018-04-10 | 比亚迪股份有限公司 | Driving based reminding method, device and vehicle |
| CN107891808B (en) * | 2016-09-30 | 2020-06-19 | 比亚迪股份有限公司 | Driving reminding method and device and vehicle |
| CN107886034B (en) * | 2016-09-30 | 2020-10-20 | 比亚迪股份有限公司 | Driving reminding method and device and vehicle |
| CN107089458B (en) * | 2017-07-03 | 2023-03-31 | 成都大学 | Novel automatic recovery system of intelligence environmental protection rubbish |
| CN107089458A (en) * | 2017-07-03 | 2017-08-25 | 成都大学 | A kind of new intelligent environment protection rubbish automatic recovery system |
| CN107392710A (en) * | 2017-07-20 | 2017-11-24 | 宁波大学 | A kind of long-distance intelligent customization processing method of personalized product |
| CN107392710B (en) * | 2017-07-20 | 2021-01-19 | 宁波大学 | Remote intelligent customized processing method for personalized products |
| CN108597315A (en) * | 2018-04-11 | 2018-09-28 | 广州维脉电子科技有限公司 | A kind of sand table model of mind controller of vehicle and method |
| CN112255630A (en) * | 2020-11-06 | 2021-01-22 | 上海电子信息职业技术学院 | Multifunctional model car |
| CN116168370A (en) * | 2023-04-24 | 2023-05-26 | 北京数字政通科技股份有限公司 | Automatic driving data identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103268072A (en) | Miniature vehicle, miniature vehicle control system and control method based on machine vision | |
| CN103386975B (en) | A kind of vehicle obstacle-avoidance method and system based on machine vision | |
| CN103389733A (en) | Vehicle line walking method and system based on machine vision | |
| CN111524357B (en) | Method for fusing multiple data required for safe driving of vehicle | |
| CN109213126B (en) | Automatic driving automobile test system and method | |
| CN107782564B (en) | Automatic driving vehicle evaluation system and method | |
| CN111473980B (en) | Intelligent automobile automatic driving capability test system | |
| DE112020004133T5 (en) | SYSTEMS AND PROCEDURES FOR IDENTIFICATION OF POSSIBLE COMMUNICATION BARRIERS | |
| CN103778786B (en) | A kind of break in traffic rules and regulations detection method based on remarkable vehicle part model | |
| DE112020000821T5 (en) | VEHICLE NAVIGATION SYSTEMS AND PROCEDURES | |
| WO2022206942A1 (en) | Laser radar point cloud dynamic segmentation and fusion method based on driving safety risk field | |
| CN113378947A (en) | Vehicle road cloud fusion sensing system and method for unmanned transportation in open-pit mining area | |
| CN107272683A (en) | Parallel intelligent vehicle control based on ACP methods | |
| JP7207670B2 (en) | Highway system for connected autonomous vehicles and methods using it | |
| CN101944176A (en) | Exist the more excellent clear path of means of transportation sign to detect | |
| CN105976606A (en) | Intelligent urban traffic management platform | |
| CN205665896U (en) | Intersection signal lamp state recognition device | |
| CN201142163Y (en) | Road traffic flow model simulation device | |
| CN103413449B (en) | Expressway ramp intelligent way directing system and way directing method thereof | |
| CN108010324B (en) | Traffic warning system for expressway and emergency lane | |
| CN202025435U (en) | Camera control device, camera and crossing shooting system | |
| CN111429734A (en) | Real-time monitoring system and method for inside and outside port container trucks | |
| KR101510745B1 (en) | Autonomous vehicle system | |
| CN104407612A (en) | Miniature intelligent vehicle and test method applying miniature intelligent vehicle | |
| KR102562757B1 (en) | Prediction and recognition method of road marking information and road maintenance method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130828 |