CN104157160A - Vehicle drive control method and device as well as vehicle - Google Patents
Vehicle drive control method and device as well as vehicle Download PDFInfo
- Publication number
- CN104157160A CN104157160A CN201410390012.XA CN201410390012A CN104157160A CN 104157160 A CN104157160 A CN 104157160A CN 201410390012 A CN201410390012 A CN 201410390012A CN 104157160 A CN104157160 A CN 104157160A
- Authority
- CN
- China
- Prior art keywords
- lane line
- vehicle
- information
- particle
- lane
- 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.)
- Granted
Links
Abstract
The invention provides a vehicle drive control method and device as well as a vehicle. The method comprises steps as follows: a lane line image acquired and sent by a vehicle-mounted camera is received; the lane line image is subjected to lane line detection by adopting a lane line detecting algorithm to obtain a lane line detecting result which shows whether a front lane line disappears; if the lane line detecting result shows that a front lane line disappears, the vehicle is controlled to stop driving, and current location information of the vehicle is sent to a network side information center, so that the network side information center determines the drive control information of the vehicle according to the current location information of the vehicle; and the drive control information sent by the network side information center is received, and vehicle drive is controlled according to the drive control information. According to the provided vehicle drive control method, the vehicle drive can be continuously controlled when the lane line condition is poorer or the lane line disappears, and drive safety is guaranteed.
Description
Technical field
The present invention relates to intelligent transport technology, relate in particular to a kind of vehicle travel control method, device and vehicle.
Background technology
Intelligent transport technology is that the new and high technologies such as advanced satellite positioning navigation technology, computer technology, graph and image processing technology, data communication technology, sensor technology, infotech, electron controls technology are applied in transportation, control and the vehicle manufacture of traffic effectively, thereby makes vehicle lean on the intelligence of self safe on road, freely travel.
At present, intelligent vehicle is applied on the less highway of automobile more, utilize lane detection algorithm to determine the positional information of lane line, for navigation provides reference, if automotive run-off-road line, by the master controller of vehicle, according to vehicle, with respect to the position steering axle of both sides lane line, turn over certain angle, thereby control vehicle in predetermined lanes, can realize to a certain extent unmanned.
The deficiencies in the prior art part is, the direction of automatic driving vehicle is controlled the lane line position that places one's entire reliance upon and detect, when or lane line poor in a certain section lane line situation disappear, according to algorithm, may examine and not measure lane line, can cause vehicle cannot continue to travel.
Summary of the invention
The invention provides a kind of vehicle travel control method, device and vehicle, the problem that while disappearing in order to solve in prior art or lane line poor in lane line situation, vehicle cannot continue to travel.
First aspect of the present invention is to provide a kind of vehicle travel control method, comprising:
Receive the lane line image of vehicle-mounted camera collection transmission;
Adopt lane detection algorithm to carry out lane detection to described lane line image, obtain lane detection result, described lane detection result represents whether the place ahead lane line disappears;
If described lane detection result represents the place ahead lane line and disappears, controlling vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Receive the control information of travelling that network side information center sends, and control described Vehicle Driving Cycle according to the described control information of travelling.
Further, in above-mentioned vehicle travel control method, the current position of described vehicle information, comprises at least one in following information:
The road image information in the place ahead, the current position of described vehicle that described vehicle-mounted camera is taken;
The vehicle mounted guidance image information in the place ahead, the current position of described vehicle;
The latitude and longitude information of the current position of described vehicle.
Further, in above-mentioned vehicle travel control method, described employing lane detection algorithm carries out lane detection to described lane line image, obtains lane detection result, comprising:
From described lane line image, extract the boundary pixel point of lane line;
State value by particle in previous frame lane line image and dimensional Gaussian random noise are added, obtain the state value of particle in described lane line image, described state value is the transverse and longitudinal coordinate of particle in lane line image, described particle produces in the following way in the first two field picture: the straight line that obtains lane line place in the first frame lane line image according to the boundary pixel point of lane line, on described straight line, choose the point of interest of the first quantity, the particle of the second quantity evenly producing with normal distribution centered by each point of interest;
The state value in described lane line image according to the boundary pixel point of the lane line extracting and described particle, obtains the weight of described particle in described lane line image;
The particle that weight is greater than to the first predetermined threshold value is set as effective particle, and judges whether that the weight sum of effective particle of each point of interest is less than the second predetermined threshold value, if so, determines that current lane line disappears, and if not, determines that current lane line does not disappear.
Further, above-mentioned vehicle travel control method, the control information of travelling that described reception network side information center sends, and after controlling described Vehicle Driving Cycle according to the described control information of travelling, also comprise:
Receive the driving message recovery that network side information center sends, wherein, described driving message recovery is the transmission when definite lane line recovers of described network side information center;
Adopt lane detection algorithm to control described Vehicle Driving Cycle.
Further, above-mentioned vehicle travel control method, also comprises:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent indication vehicle front has barrier, controlling vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Receive the control information of travelling that network side information center sends, and control described Vehicle Driving Cycle according to the described control information of travelling.
Another aspect of the present invention is to provide a kind of controlling device for vehicle running, comprises,
Lane line receiver module, for receiving the lane line image of vehicle-mounted camera collection transmission;
Lane detection module, for adopting lane detection algorithm to carry out lane detection to described lane line image, obtains lane detection result, and described lane detection result represents whether the place ahead lane line disappears;
Information sending module, be used for when described lane detection result represents that the place ahead lane line disappears, control vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Information receiving module, the control information of travelling sending for receiving network side information center, and control described Vehicle Driving Cycle according to the described control information of travelling.
Further, in above-mentioned controlling device for vehicle running, the current position of described vehicle information, comprises at least one in following information:
The road image information in the place ahead, the current position of described vehicle that described vehicle-mounted camera is taken;
The vehicle mounted guidance image information in the place ahead, the current position of described vehicle;
The latitude and longitude information of the current position of described vehicle.
Further, in above-mentioned controlling device for vehicle running, described lane detection module, comprising:
Boundary Extraction unit, for extracting the boundary pixel point of lane line from described lane line image;
State value determining unit, for by particle, state value and the dimensional Gaussian random noise at previous frame lane line image is added, obtain the state value of particle in described lane line image, described state value is the transverse and longitudinal coordinate of particle in lane line image, described particle produces in the following way in the first two field picture: the straight line that obtains lane line place in the first frame lane line image according to the boundary pixel point of lane line, on described straight line, choose the point of interest of the first quantity, the particle of the second quantity evenly producing with normal distribution centered by each point of interest;
Weight determining unit, at the state value of described lane line image, obtains the weight of described particle in described lane line image for the boundary pixel point of the lane line that extracts and described particle;
Judging unit, is set as effective particle for weight being greater than to the particle of the first predetermined threshold value, and judges whether that the weight sum of effective particle of each point of interest is less than the second predetermined threshold value, if, determine that current lane line disappears, if not, determine that current lane line does not disappear.
Further, in above-mentioned controlling device for vehicle running, described information receiving module, also for:
The control information of travelling sending in described reception network side information center, and after controlling described Vehicle Driving Cycle according to the described control information of travelling, receive the driving message recovery that network side information center sends, wherein, described driving message recovery is the transmission when definite lane line recovers of described network side information center;
Adopt lane detection algorithm to control described Vehicle Driving Cycle.
Further, in above-mentioned controlling device for vehicle running, described information sending module, also for:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent indication vehicle front has barrier, controlling vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Receive the control information of travelling that network side information center sends, and control described Vehicle Driving Cycle according to the described control information of travelling.
Another aspect of the present invention is to provide a kind of vehicle, comprises vehicle-mounted camera and intelligent control platform, and wherein, described intelligent control platform comprises above-mentioned arbitrary controlling device for vehicle running.
Vehicle travel control method provided by the invention, device and vehicle, when lane line disappearance being detected, controlling vehicle stop travels, communicate with network side information center simultaneously, send the current position of vehicle information to information center, and Vehicle Driving Cycle is controlled in the control information of travelling of determining according to information center, can be in lane line situation poor or lane line while disappearing, continue to control Vehicle Driving Cycle, and guaranteed the security of travelling.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of vehicle travel control method embodiment of the present invention;
Fig. 2 is the process flow diagram of lane detection algorithm in vehicle travel control method embodiment of the present invention;
Fig. 3 is the structural representation of controlling device for vehicle running embodiment of the present invention;
Fig. 4 is the structural representation of lane detection module in controlling device for vehicle running embodiment of the present invention;
Fig. 5 is the structural representation of vehicle embodiment of the present invention.
Embodiment
For making object, technical scheme and the advantage of the embodiment of the present invention clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, rather than whole embodiment.Embodiment based in the present invention, those of ordinary skills, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
Fig. 1 is the process flow diagram of vehicle travel control method embodiment of the present invention, and as shown in Figure 1, the method for the present embodiment can comprise:
The lane line image of step 101, reception vehicle-mounted camera collection transmission;
Wherein, vehicle-mounted camera carries out video acquisition to lane line, video is comprised of picture frame, and vehicle-mounted camera sends to each frame lane line image in real time for carrying out the device of Vehicle Driving Cycle control, and camera should guarantee accurately to collect the information of vehicle dead ahead lane line when mounted.
Step 102, employing lane detection algorithm carry out lane detection to described lane line image, obtain lane detection result, and described lane detection result represents whether the place ahead lane line disappears;
Particularly, after receiving the lane line image of vehicle-mounted camera transmission, with the lane line that lane detection algorithm detects in this image, whether disappear, lane detection algorithm has a variety of, for example, can be Kalman filtering algorithm, dynamic bayesian network etc., the present embodiment does not limit this.
If the described lane detection result of step 103 represents the place ahead lane line and disappears, controlling vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Particularly, if testing result represents lane line, do not disappear, control vehicle and travel along the lane line detecting, if testing result represents the place ahead lane line, disappear, control vehicle stop and travel, and the current position of vehicle information is sent to information center.
Wherein, the current position of vehicle information can be at least one in following information:
The road image information in the place ahead, the current position of this vehicle that vehicle-mounted camera is taken;
The vehicle mounted guidance image information in the place ahead, the current position of vehicle;
The latitude and longitude information of the current position of vehicle.
The current position of above-mentioned vehicle information is connected and is sent to information center by GPRS data by vehicle-mounted high-capacity SIM card.
When Xiang information center sends the current position of vehicle information, can also send sound prompting to information center, with this vehicle of prompting message center, need information center to its control of travelling.When information center receives after sound prompting, display module by information center's staff's opening information center, the positional information of display module for showing that the vehicle-mounted camera that receives and/or onboard navigation system collect, information center can determine according to the position coordinates at the vehicle front traffic information comprising in positional information or vehicle place the control information of travelling of vehicle.For example, the image information that the staff of information center can photograph according to vehicle-mounted camera, as driver, vehicle is controlled in real time, wherein, travelling control information can be for vehicle steering angle or acceleration, deceleration, so that vehicle normally travels in the situation that lane line disappears according to this control information of travelling.
The control information of travelling that step 104, reception network side information center send, and control described Vehicle Driving Cycle according to the described control information of travelling.
The vehicle travel control method that the present embodiment provides, when lane line disappearance being detected, controlling vehicle stop travels, communicate with network side information center simultaneously, send the current position of vehicle information to information center, and Vehicle Driving Cycle is controlled in the control information of travelling of determining according to information center, can be in lane line situation poor or lane line while disappearing, continue to control Vehicle Driving Cycle, and guaranteed the security of travelling.
Fig. 2 is the process flow diagram of lane detection algorithm in vehicle travel control method embodiment of the present invention, and as shown in Figure 2, on the basis of the technical scheme providing at above-described embodiment, the embodiment of step 102 can comprise:
Step 1021, from described lane line image, extract the boundary pixel point of lane line;
In real road, road surface is divided into one or more tracks by lane line, and lane line has following characteristics substantially:
(1), on color, lane line is with white and yellow in the majority;
(2) gray scale of lane line is apparently higher than the gray scale of surrounding environment;
(3) lane line is in the majority with straight line and regular curve, and curved degree is little.
In lane detection algorithm, can make full use of these features.For the lane line of different situations, the method that extraction boundary pixel point adopts is also different.For example, to lane line, be white situation, the RGB image receiving from vehicle-mounted camera can be converted to gray image, then gray image is carried out to luminance transformation, extract the boundary pixel point of lane line; To lane line, it is yellow situation, can adopt the method for the colour edging detection of gradient to carry out Boundary Extraction, colour edging detection method is with respect to the method that is directly converted to gray image, can retain the brightness of coloured image, the boundary pixel point of yellow lane line is extracted, make the gray scale of the white lane line that obtains in its gray scale and preceding method close.
In order to guarantee the real-time of lane detection, the efficiency of lane detection algorithm can not be too low, so after extracting the boundary pixel point of lane line, can also intercept processing to lane line image, for example, 1/2 in the middle of global image can being intercepted on width and/or on height is converted into topography, then according to the relation between part and global image, carries out conversion process, wherein, the width of cut-away view picture must be greater than lane line interval.Image is intercepted to processing and not only greatly reduce calculated amount, can also avoid noise.
Step 1022, the state value by particle in previous frame lane line image and dimensional Gaussian random noise are added, obtain the state value of particle in described lane line image, described state value is the transverse and longitudinal coordinate of particle in lane line image, described particle produces in the following way in the first two field picture: the straight line that obtains lane line place in the first frame lane line image according to the boundary pixel point of lane line, on described straight line, choose the point of interest of the first quantity, the particle of the second quantity evenly producing with normal distribution centered by each point of interest;
After extracting the boundary pixel point of lane line, can adopt particle filter algorithm further to detect lane line.Particle filter algorithm is a kind of method of utilizing Monte Carlo simulation to realize Bayes's filtering, and it can reasonable solution nonlinear problem.Core concept is to utilize the weight of a series of samples of randomly drawing and sample to come the posterior probability of alternative state to distribute, and when the number of sample becomes enough large, by such arbitrary sampling method, just can obtain real posteriority good being similar to that distribute.
Particularly, for the first frame lane line image, adopt Hough transformation to process the lane line boundary pixel point extracting, can determine the straight line at lane line place.On the straight line at lane line place, choose the point of interest of the first quantity, the particle of the second quantity evenly producing with normal distribution centered by each point of interest.In the present embodiment, choose 20 points of interest, the point of interest of choosing at least will be with image boundary apart from 10-20 more than pixel, in case point of interest goes out image boundary in follow-up lane detection process.To each point of interest, near it, produce the particle of some, in order to guarantee precision, number of particles will be chosen abundantly, and the number of particles that the present embodiment is selected is 100.
Since the second frame lane line image, the state value of each particle in current lane line image is state value and the dimensional Gaussian random noise sum of particle in previous frame lane line image, that is, in the present embodiment, the state equation of particle filter is:
H
ij(t)＝H
ij(t-1)+M (1)
Wherein, H
ij(t) represent the state value of j particle of i point of interest in t two field picture, M is dimensional Gaussian random noise, and M obeys the normal distribution of N (0,5).In the present embodiment, i=1,2 ... 20, j=1,2 ... 100, horizontal ordinate and the ordinate (x (t) of particle for state value, y (t)) represent, the state value of particle in t frame lane line image, equals state value and the dimensional Gaussian random noise sum of this particle in t-1 frame lane line image.
Boundary pixel point and the state value of described particle in described lane line image of the lane line that step 1023, basis extract, obtain the weight of described particle in described lane line image;
First, the state value H in current lane line image by particle
ij(t) add observation noise E, obtain the observed reading Z of particle in current lane line image
ij(t), that is, in this enforcement, the observation equation of particle filter is:
Z
ij(t)＝H
ij(t)+E (2)
Wherein, observed reading Z
ij(t) also transverse and longitudinal coordinate, consist of, observation noise E obeys the normal distribution of N (0,3).
Then, the boundary pixel point of lane line is linked to be to a level and smooth line segment, asks the observed reading Z of particle
ij(t) arrive the nearest distance l of this line segment
ij; If lane line is thicker, the boundary pixel of lane line point can be linked to be two sections of line segments, and the center line of these two sections of line segments of can take is benchmark, asks the observed reading Z of particle
ij(t) arrive the nearest distance l of this center line
ij.
Finally, according to l
ijobtain the likelihood probability p of particle
ij, the likelihood probability computing formula of particle is:
p
ij＝exp(-a×l
ij) (3)
Wherein a is greater than 0 constant.
The likelihood probability of all particles of each point of interest is normalized, to guarantee that the probability sum of all particles is added, equals 1, the likelihood probability after normalization is the weight of each particle.
Step 1024, the particle that weight is greater than to the first predetermined threshold value are set as effective particle, the weight sum that judges whether effective particle of each point of interest is less than the second predetermined threshold value, if so, determines that current lane line disappears, if not, determine that current lane line does not disappear.
For example, for first point of interest, comprise 100 particles, after weight calculation, finding has the weight of 10 to be less than the first predetermined threshold value in these 100 particles, thinks that these 10 particles are invalid particles, and remaining 90 particles is effective particles, weight summation to 90 effective particles, and judge whether weight sum is less than the second predetermined threshold value.For remaining point of interest, also carry out aforesaid operations, if effective particle weight sum of all points of interest is all less than the second predetermined threshold value, think that current lane line disappears.
When lane line does not disappear, for each point of interest, by the state value H of its all particles
ijwith weight p
ijweighted sum, we think that the value obtaining is exactly the actual position of this point of interest in current lane line image, can obtain the estimated position of the lane line in present image, and control Vehicle Driving Cycle with this according to the actual position of whole points of interest.
When lane line disappears, control vehicle stop and travel, Bing Yu network side information center communicates, so that travel under the control of vehicle Neng information center.
In addition, after obtaining the actual position of point of interest in current lane line image, can also reject invalid particle, and carry out re-sampling operations according to remaining effective particle, object is to reduce the number of the particle that weight is less, and notice is concentrated on the particle with larger weight.The method resampling has a variety of, conventional, the larger effective particle of weight is split as two or more, to fill up the position of the invalid particle of rejecting, makes the number of particles after resampling still remain 100.
For example, for a certain point of interest, suppose after weight calculation, in t two field picture, there is the weight of 10 particles to be less than the first predetermined threshold value, these 10 invalid particles are rejected, now particle number reduces, and 90 remaining particles are re-started to normalized, obtain the new weight of each particle, make the weight sum that remains 90 particles equal 1.Suppose that normalized recoil is designated as (48, 52) weight of particle is 0.08, coordinate is (42, 50) weight of particle is 0.04, the weight of 88 particles of residue is 0.01, in order to keep particle number constant, the particle that is 0.08 by weight splits into 8, the particle that is 0.04 by weight splits into 4, all the other particles remain unchanged, again gather into 100 particles, that is to say, in 100 new particles, the coordinate that has 8 is (48, 52), the coordinate that has 4 is (42, 50), when t+1 frame lane line image is processed, take these 100 new particles is basic calculation state value.
In the vehicle travel control method that the present embodiment provides, adopt particle filter algorithm to carry out lane detection, wherein directly adopt the transverse and longitudinal coordinate of particle as the state value of particle, can reduce the complexity of algorithm, improve efficiency of algorithm.
Further, on the basis of the technical scheme providing at above-described embodiment, preferably, the control information of travelling that described reception network side information center sends, and after controlling described Vehicle Driving Cycle according to the described control information of travelling, also comprise:
Receive the driving message recovery that network side information center sends, wherein, described driving message recovery is the transmission when definite lane line recovers of described network side information center;
After receiving driving message recovery, adopt lane detection algorithm to control described Vehicle Driving Cycle.
Further, on the basis of the technical scheme providing at above-described embodiment, preferably, also comprise:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent indication vehicle front has barrier, controlling vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Receive the control information of travelling that network side information center sends, and control described Vehicle Driving Cycle according to the described control information of travelling.
Particularly, vehicle is also provided with the sensor for detection of barrier, for example, Vehicle radar sensor, when the place ahead being detected and have barrier, if automobile also continues to travel according to the lane line detecting, may cause danger, therefore,, even if now lane line does not disappear, carry out the device of Vehicle Driving Cycle control and also can communicate by letter with information center, the current position of vehicle information is sent to information center, information center can adjust vehicle heading according to the traffic information of the current position of vehicle, avoids the place ahead barrier.
In addition, if vehicle has arrived destination, the distance travelled number that is vehicle reaches default mileage number, can control vehicle stop travels, Bing Xiang information center sends prompting message, by information center, be that vehicle distributes next task of travelling, the starting point of next task of travelling is the current position of vehicle, and terminal is reset by information center.
Fig. 3 is the structural representation of controlling device for vehicle running embodiment of the present invention, and as shown in Figure 3, the device of the present embodiment can comprise:
Lane line receiver module 31, for receiving the lane line image of vehicle-mounted camera collection transmission;
Lane detection module 32, for adopting lane detection algorithm to carry out lane detection to described lane line image, obtains lane detection result, and described lane detection result represents whether the place ahead lane line disappears;
Information sending module 33, be used for when described lane detection result represents that the place ahead lane line disappears, control vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Information receiving module 34, the control information of travelling sending for receiving network side information center, and control described Vehicle Driving Cycle according to the described control information of travelling.
The device of the present embodiment, can be for the technical scheme of embodiment of the method shown in execution graph 1, and it realizes principle and technique effect is similar, repeats no more herein.
On the basis of the apparatus structure providing at above-described embodiment, further, the current position of described vehicle information, comprises at least one in following information:
The road image information in the place ahead, the current position of described vehicle that described vehicle-mounted camera is taken;
The vehicle mounted guidance image information in the place ahead, the current position of described vehicle;
The latitude and longitude information of the current position of described vehicle.
Fig. 4 is the structural representation of lane detection module in controlling device for vehicle running embodiment of the present invention, and as shown in Figure 4, the device of the present embodiment is on the basis of Fig. 3 shown device structure, and further, lane detection module 32 can comprise:
Boundary Extraction unit 321, for extracting the boundary pixel point of lane line from described lane line image;
State value determining unit 322, for by particle, state value and the dimensional Gaussian random noise at previous frame lane line image is added, obtain the state value of particle in described lane line image, described state value is the transverse and longitudinal coordinate of particle in lane line image, described particle produces in the following way in the first two field picture: the straight line that obtains lane line place in the first frame lane line image according to the boundary pixel point of lane line, on described straight line, choose the point of interest of the first quantity, the particle of the second quantity evenly producing with normal distribution centered by each point of interest,
Weight determining unit 323, the boundary pixel point of the lane line extracting for basis and described particle, at the state value of described lane line image, obtain the weight of described particle in described lane line image;
Judging unit 324, is set as effective particle for weight being greater than to the particle of the first predetermined threshold value, and judges whether that the weight sum of effective particle of each point of interest is less than the second predetermined threshold value, if, determine that current lane line disappears, if not, determine that current lane line does not disappear.
The device of the present embodiment, can be for the technical scheme of lane detection algorithm in embodiment of the method shown in execution graph 2, and it realizes principle and technique effect is similar, repeats no more herein.
On the basis of the apparatus structure providing at above-described embodiment, further, information receiving module 34, also for:
The control information of travelling sending in described reception network side information center, and after controlling described Vehicle Driving Cycle according to the described control information of travelling, receive the driving message recovery that network side information center sends, wherein, described driving message recovery is the transmission when definite lane line recovers of described network side information center;
Adopt lane detection algorithm to control described Vehicle Driving Cycle.
On the basis of the apparatus structure providing at above-described embodiment, further, information sending module 33, also for:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent indication vehicle front has barrier, controlling vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Receive the control information of travelling that network side information center sends, and control described Vehicle Driving Cycle according to the described control information of travelling.
Fig. 5 is the structural representation of vehicle embodiment of the present invention, and as shown in Figure 5, the vehicle of the present embodiment can comprise vehicle-mounted camera 51 and intelligent control platform 52, and wherein, intelligent control platform 55 comprises the controlling device for vehicle running described in above-mentioned arbitrary embodiment.
Vehicle provided by the invention, when lane line disappearance being detected, stop travelling, communicate with network side information center simultaneously, send current position information to information center, and the control information of travelling of determining according to information center is travelled, can be in lane line situation poor or lane line continue to travel while disappearing, and guaranteed the security of travelling.
One of ordinary skill in the art will appreciate that: all or part of step that realizes above-mentioned each embodiment of the method can complete by the relevant hardware of programmed instruction.Aforesaid program can be stored in a computer read/write memory medium.This program, when carrying out, is carried out the step that comprises above-mentioned each embodiment of the method; And aforesaid storage medium comprises: various media that can be program code stored such as ROM, RAM, magnetic disc or CDs.
Finally it should be noted that: each embodiment, only in order to technical scheme of the present invention to be described, is not intended to limit above; Although the present invention is had been described in detail with reference to aforementioned each embodiment, those of ordinary skill in the art is to be understood that: its technical scheme that still can record aforementioned each embodiment is modified, or some or all of technical characterictic is wherein equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme.
Claims (11)
1. a vehicle travel control method, is characterized in that, comprising:
Receive the lane line image of vehicle-mounted camera collection transmission;
Adopt lane detection algorithm to carry out lane detection to described lane line image, obtain lane detection result, described lane detection result represents whether the place ahead lane line disappears;
If described lane detection result represents the place ahead lane line and disappears, controlling vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Receive the control information of travelling that network side information center sends, and control described Vehicle Driving Cycle according to the described control information of travelling.
2. method according to claim 1, is characterized in that, the current position of described vehicle information, comprises at least one in following information:
The road image information in the place ahead, the current position of described vehicle that described vehicle-mounted camera is taken;
The vehicle mounted guidance image information in the place ahead, the current position of described vehicle;
The latitude and longitude information of the current position of described vehicle.
3. method according to claim 1 and 2, is characterized in that, described employing lane detection algorithm carries out lane detection to described lane line image, obtains lane detection result, comprising:
From described lane line image, extract the boundary pixel point of lane line;
State value by particle in previous frame lane line image and dimensional Gaussian random noise are added, obtain the state value of particle in described lane line image, described state value is the transverse and longitudinal coordinate of particle in lane line image, described particle produces in the following way in the first two field picture: the straight line that obtains lane line place in the first frame lane line image according to the boundary pixel point of lane line, on described straight line, choose the point of interest of the first quantity, the particle of the second quantity evenly producing with normal distribution centered by each point of interest;
The state value in described lane line image according to the boundary pixel point of the lane line extracting and described particle, obtains the weight of described particle in described lane line image;
The particle that weight is greater than to the first predetermined threshold value is set as effective particle, and judges whether that the weight sum of effective particle of each point of interest is less than the second predetermined threshold value, if so, determines that current lane line disappears, and if not, determines that current lane line does not disappear.
4. method according to claim 1 and 2, is characterized in that, the control information of travelling that described reception network side information center sends, and after controlling described Vehicle Driving Cycle according to the described control information of travelling, also comprise:
Receive the driving message recovery that network side information center sends, wherein, described driving message recovery is the transmission when definite lane line recovers of described network side information center;
Adopt lane detection algorithm to control described Vehicle Driving Cycle.
5. method according to claim 1 and 2, is characterized in that, also comprises:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent indication vehicle front has barrier, controlling vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Receive the control information of travelling that network side information center sends, and control described Vehicle Driving Cycle according to the described control information of travelling.
6. a controlling device for vehicle running, is characterized in that, comprise,
Lane line receiver module, for receiving the lane line image of vehicle-mounted camera collection transmission;
Lane detection module, for adopting lane detection algorithm to carry out lane detection to described lane line image, obtains lane detection result, and described lane detection result represents whether the place ahead lane line disappears;
Information sending module, be used for when described lane detection result represents that the place ahead lane line disappears, control vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Information receiving module, the control information of travelling sending for receiving network side information center, and control described Vehicle Driving Cycle according to the described control information of travelling.
7. device according to claim 6, is characterized in that, the current position of described vehicle information, comprises at least one in following information:
The road image information in the place ahead, the current position of described vehicle that described vehicle-mounted camera is taken;
The vehicle mounted guidance image information in the place ahead, the current position of described vehicle;
The latitude and longitude information of the current position of described vehicle.
8. according to the method described in claim 6 or 7, it is characterized in that, described lane detection module, comprising:
Boundary Extraction unit, for extracting the boundary pixel point of lane line from described lane line image;
State value determining unit, for by particle, state value and the dimensional Gaussian random noise at previous frame lane line image is added, obtain the state value of particle in described lane line image, described state value is the transverse and longitudinal coordinate of particle in lane line image, described particle produces in the following way in the first two field picture: the straight line that obtains lane line place in the first frame lane line image according to the boundary pixel point of lane line, on described straight line, choose the point of interest of the first quantity, the particle of the second quantity evenly producing with normal distribution centered by each point of interest;
Weight determining unit, the boundary pixel point of the lane line extracting for basis and described particle, at the state value of described lane line image, obtain the weight of described particle in described lane line image;
Judging unit, is set as effective particle for weight being greater than to the particle of the first predetermined threshold value, and judges whether that the weight sum of effective particle of each point of interest is less than the second predetermined threshold value, if, determine that current lane line disappears, if not, determine that current lane line does not disappear.
9. according to the device described in claim 6 or 7, it is characterized in that, described information receiving module, also for:
The control information of travelling sending in described reception network side information center, and after controlling described Vehicle Driving Cycle according to the described control information of travelling, receive the driving message recovery that network side information center sends, wherein, described driving message recovery is the transmission when definite lane line recovers of described network side information center;
Adopt lane detection algorithm to control described Vehicle Driving Cycle.
10. according to the device described in claim 6 or 7, it is characterized in that, described information sending module, also for:
Receive the barrier heat transfer agent that onboard sensor sends;
If described barrier heat transfer agent indication vehicle front has barrier, controlling vehicle stop travels, Bing Xiang network side information center sends the current position of described vehicle information, for described network side information center, determines the control information of travelling of described vehicle according to the current position of described vehicle information;
Receive the control information of travelling that network side information center sends, and control described Vehicle Driving Cycle according to the described control information of travelling.
11. 1 kinds of vehicles, is characterized in that, comprise vehicle-mounted camera and intelligent control platform, and wherein, described intelligent control platform comprises the controlling device for vehicle running described in claim 6-10 any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410390012.XA CN104157160B (en) | 2014-08-08 | 2014-08-08 | Vehicle travel control method, device and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410390012.XA CN104157160B (en) | 2014-08-08 | 2014-08-08 | Vehicle travel control method, device and vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104157160A true CN104157160A (en) | 2014-11-19 |
| CN104157160B CN104157160B (en) | 2016-08-17 |
Family
ID=51882646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410390012.XA Active CN104157160B (en) | 2014-08-08 | 2014-08-08 | Vehicle travel control method, device and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104157160B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105261224A (en) * | 2015-09-02 | 2016-01-20 | 奇瑞汽车股份有限公司 | Intelligent vehicle control method and apparatus |
| CN106203341A (en) * | 2016-07-11 | 2016-12-07 | 百度在线网络技术（北京）有限公司 | A kind of Lane detection method and device of unmanned vehicle |
| CN106681318A (en) * | 2016-12-09 | 2017-05-17 | 重庆长安汽车股份有限公司 | Vehicle safety control system and method for lane line detection temporary loss in automatic drive |
| CN106886217A (en) * | 2017-02-24 | 2017-06-23 | 安科智慧城市技术（中国）有限公司 | Automatic navigation control method and apparatus |
| CN108247630A (en) * | 2017-12-01 | 2018-07-06 | 西安电子科技大学 | Moving robot obstacle avoiding method based on Bayesian network model |
| CN110177722A (en) * | 2017-01-19 | 2019-08-27 | 本田技研工业株式会社 | Vehicle control system, control method for vehicle and vehicle control program |
| CN110580046A (en) * | 2019-09-12 | 2019-12-17 | 吉利汽车研究院（宁波）有限公司 | Control method and system for unmanned sightseeing vehicle |
| CN113447970A (en) * | 2021-06-28 | 2021-09-28 | 潍柴动力股份有限公司 | Navigation data continuous and reliable data filling method and device and navigation system |
| CN113954750A (en) * | 2020-07-20 | 2022-01-21 | 深圳市麦道微电子技术有限公司 | Electronic exterior mirror system and imaging method for commercial vehicle |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001074490A (en) * | 1999-09-03 | 2001-03-23 | Aisin Aw Co Ltd | Navigation apparatus and memory medium |
| US20100063649A1 (en) * | 2008-09-10 | 2010-03-11 | National Chiao Tung University | Intelligent driving assistant systems |
| CN102541061A (en) * | 2012-02-07 | 2012-07-04 | 清华大学 | Micro intelligent vehicle based on visual and auditory information |
| CN102819263A (en) * | 2012-07-30 | 2012-12-12 | 中国航天科工集团第三研究院第八三五七研究所 | Multi-camera visual perception system for UGV (Unmanned Ground Vehicle) |
| CN102862574A (en) * | 2012-09-21 | 2013-01-09 | 上海永畅信息科技有限公司 | Method for realizing active safety of vehicle on the basis of smart phone |
| CN103592903A (en) * | 2013-08-18 | 2014-02-19 | 北京联合大学 | Method and system for remote monitoring on intelligent automobile driving test data |
-
2014
- 2014-08-08 CN CN201410390012.XA patent/CN104157160B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001074490A (en) * | 1999-09-03 | 2001-03-23 | Aisin Aw Co Ltd | Navigation apparatus and memory medium |
| US20100063649A1 (en) * | 2008-09-10 | 2010-03-11 | National Chiao Tung University | Intelligent driving assistant systems |
| CN102541061A (en) * | 2012-02-07 | 2012-07-04 | 清华大学 | Micro intelligent vehicle based on visual and auditory information |
| CN102819263A (en) * | 2012-07-30 | 2012-12-12 | 中国航天科工集团第三研究院第八三五七研究所 | Multi-camera visual perception system for UGV (Unmanned Ground Vehicle) |
| CN102862574A (en) * | 2012-09-21 | 2013-01-09 | 上海永畅信息科技有限公司 | Method for realizing active safety of vehicle on the basis of smart phone |
| CN103592903A (en) * | 2013-08-18 | 2014-02-19 | 北京联合大学 | Method and system for remote monitoring on intelligent automobile driving test data |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105261224A (en) * | 2015-09-02 | 2016-01-20 | 奇瑞汽车股份有限公司 | Intelligent vehicle control method and apparatus |
| CN106203341A (en) * | 2016-07-11 | 2016-12-07 | 百度在线网络技术（北京）有限公司 | A kind of Lane detection method and device of unmanned vehicle |
| CN106203341B (en) * | 2016-07-11 | 2019-05-21 | 百度在线网络技术（北京）有限公司 | A kind of Lane detection method and device of unmanned vehicle |
| CN106681318A (en) * | 2016-12-09 | 2017-05-17 | 重庆长安汽车股份有限公司 | Vehicle safety control system and method for lane line detection temporary loss in automatic drive |
| US11292460B2 (en) | 2017-01-19 | 2022-04-05 | Honda Motor Co., Ltd. | Vehicle control system, vehicle control method, and vehicle control program |
| CN110177722B (en) * | 2017-01-19 | 2022-07-01 | 本田技研工业株式会社 | Vehicle control system, vehicle control method, and storage medium |
| CN110177722A (en) * | 2017-01-19 | 2019-08-27 | 本田技研工业株式会社 | Vehicle control system, control method for vehicle and vehicle control program |
| CN106886217A (en) * | 2017-02-24 | 2017-06-23 | 安科智慧城市技术（中国）有限公司 | Automatic navigation control method and apparatus |
| CN106886217B (en) * | 2017-02-24 | 2020-09-08 | 深圳中智卫安机器人技术有限公司 | Autonomous navigation control method and device |
| CN108247630A (en) * | 2017-12-01 | 2018-07-06 | 西安电子科技大学 | Moving robot obstacle avoiding method based on Bayesian network model |
| CN110580046A (en) * | 2019-09-12 | 2019-12-17 | 吉利汽车研究院（宁波）有限公司 | Control method and system for unmanned sightseeing vehicle |
| CN110580046B (en) * | 2019-09-12 | 2022-08-16 | 吉利汽车研究院（宁波）有限公司 | Control method and system for unmanned sightseeing vehicle |
| CN113954750A (en) * | 2020-07-20 | 2022-01-21 | 深圳市麦道微电子技术有限公司 | Electronic exterior mirror system and imaging method for commercial vehicle |
| CN113954750B (en) * | 2020-07-20 | 2023-12-29 | 深圳市麦道微电子技术有限公司 | Electronic outside mirror system of commercial vehicle and imaging method |
| CN113447970A (en) * | 2021-06-28 | 2021-09-28 | 潍柴动力股份有限公司 | Navigation data continuous and reliable data filling method and device and navigation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104157160B (en) | 2016-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104157160A (en) | Vehicle drive control method and device as well as vehicle | |
| US11084494B2 (en) | Method for detecting safety of driving behavior, apparatus, device and storage medium | |
| AU2021313775A1 (en) | Drivable surface identification techniques | |
| JP7040374B2 (en) | Object detection device, vehicle control system, object detection method and computer program for object detection | |
| CN110400478A (en) | A kind of road condition notification method and device | |
| CN106127107A (en) | The model recognizing method that multi-channel video information based on license board information and vehicle's contour merges | |
| CN105426864A (en) | Multiple lane line detecting method based on isometric peripheral point matching | |
| CN102222236A (en) | Image processing system and position measurement system | |
| CN110458050B (en) | Vehicle cut-in detection method and device based on vehicle-mounted video | |
| CN104616502A (en) | License plate identification and positioning system based on combined type vehicle-road video network | |
| CN106326866B (en) | Early warning method and device for vehicle collision | |
| CN103164958B (en) | Method and system for vehicle monitoring | |
| KR20210080459A (en) | Lane detection method, apparatus, electronic device and readable storage medium | |
| CN113421432A (en) | Traffic restriction information detection method and device, electronic equipment and storage medium | |
| CN108230667A (en) | A kind of vehicle peccancy behavioral value method | |
| Behrendt et al. | Deep learning lane marker segmentation from automatically generated labels | |
| CN106092123A (en) | A kind of video navigation method and device | |
| CN102252859A (en) | Road train straight-line running transverse stability automatic identification system | |
| CN111062971A (en) | Cross-camera mud head vehicle tracking method based on deep learning multi-mode | |
| CN110554409B (en) | Concave obstacle detection method and system | |
| Huang | Real-time multi-vehicle detection and sub-feature based tracking for traffic surveillance systems | |
| CN104268859A (en) | Image preprocessing method for night lane line detection | |
| SE1650608A1 (en) | Method and control unit for a vehicle | |
| CN111427063A (en) | Method, device, equipment, system and medium for controlling passing of mobile device | |
| CN109895694B (en) | Lane departure early warning method and device and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |