Search Images Maps Play YouTube News Gmail Drive More »
Sign in
Screen reader users: click this link for accessible mode. Accessible mode has the same essential features but works better with your reader.

Patents

  1. Advanced Patent Search
Publication numberCN104021670 A
Publication typeApplication
Application numberCN 201410118280
Publication date3 Sep 2014
Filing date27 Mar 2014
Priority date27 Mar 2014
Also published asCN104021670B
Publication number201410118280.6, CN 104021670 A, CN 104021670A, CN 201410118280, CN-A-104021670, CN104021670 A, CN104021670A, CN201410118280, CN201410118280.6
Inventors谷正气, 张勇, 李程, 李健
Applicant湖南工业大学
Export CitationBiBTeX, EndNote, RefMan
External Links: SIPO, Espacenet
Method for extracting vehicle queue state information in urban road network based on high-resolution remote-sensing image
CN 104021670 A
Abstract
Vehicle queue state information is one of basic parameters for urban road traffic analysis. The invention provides a method for extracting vehicle queue state information in an urban road network based on a high-resolution remote-sensing image. The extraction method in the invention comprises the following steps: 1) obtaining planar road and planar vehicle information data in the high-resolution remote-sensing image; 2) extracting center line and edge lines of a planar road and carrying out cutting according to a certain length threshold to form road searching blocks; 3) calculating road vehicle occupation ratio of each road searching block; 4) taking a certain vehicle occupation ratio as a threshold value under the condition of a congestion queue, and screening out the road searching blocks, of which the road vehicle occupation ratio is larger or equal to the threshold value, at this moment, the total length of the plurality of road searching blocks being the length of the congestion vehicle queue in this road section. Specific position is determined by matching the central position of the road searching blocks with an electronic map or combining GPS data.
Claims(4)  translated from Chinese
1.一种利用高分遥感影像提取城市路网拥堵车辆队列信息的方法,其特征在于:选取高分辨率遥感影像中提取的面状道路和面状车辆矢量数据为输入参数,进而计算出车辆队列长度,结合电子地图或GPS数据,可获得车辆队列所在位置,至少包含以下步骤: 步骤一:从高分分辨率遥感影像中提取城市路网中面状道路和面状车辆信息数据; 步骤二:提取面状道路中心线和边线,并按设定的长度阈值进行截断,形成道路搜索块; 步骤三:计算所述道路搜索块的道路车辆占有率; 步骤四:以拥堵条件下的道路车辆占有率作为阈值,将步骤三中计算出的道路车辆占有率与所述阀值作比较,筛选出大于或等于该阈值的道路搜索块,则此时若干道路搜索块的总长度,即为是该路段上拥堵车辆队列的长度; 步骤五:将道路搜索块的中心位置与电子地图匹配或结合GPS数据相结合,获得城市路网中拥堵车辆队列位置信息。 A high use of remote sensing image of urban road network congestion method for a vehicle queue information, wherein: Select resolution remote sensing image extracted planar and planar vehicle road vector data as input parameters, and then calculate the vehicle queue length, combined with electronic map or GPS data, where available vehicle queues, including at least the following steps: Step 1: Extract the urban road network in the planar surface of roads and vehicle information like data from high-resolution remote sensing images; step two : extract planar road centerline and edges, according to a set length threshold truncated form a road block search; Step three: calculate road vehicles share the road search block; Step Four: The road vehicle under congested conditions share as the threshold value, calculated in step three vehicles share the road compared with the threshold screening of greater than or equal to the threshold of the way the search block, this time the total number of road length search block, namely the the length of the vehicle on the road congestion queue; Step 5: With its central location and path search block matching or a combination of GPS electronic map data combined with access to urban road network congestion vehicle queue position information.
2.如权利要求1所述的一种利用高分遥感影像提取城市路网拥堵车辆队列信息的方法,其特征在于:从城市路网中提取面状道路的中心线和边线,获取步骤二中所述道路搜索块,至少包含以下步骤: 步骤一:获取面状道路的首尾点:首先获得构成面状道路边界的点集P= (P1, P2,……Pm, Pm+1,……,Pm+n},共包含m+n (η≥m≥2)个点,将点集按顺时针方向两两组合成向量 2. A high claim 1, wherein the use of remote sensing vehicle congestion queue information extraction method of the urban road network, characterized by: extracting the planar center line and sideline road from the city road network, access to step two The path search block, including at least the following steps: Step 1: Get first and last points of the planar path: first obtaining a planar point set constituting road boundary P = (P1, P2, ...... Pm, Pm + 1, ......, Pm + n}, contains a total of m + n (η≥m≥2) points, the set of points in a clockwise direction pairwise combination vector
Figure CN104021670AC00021
共m+n个向量,依次计算其余弦值;其中最小的余弦值所对应的点,即为道路首尾点; 步骤二:获取道路中心线:假设道路首尾点为点PdPPm,将面状道路在首尾点处打断形成两个道路边线点集,A= {P1; P2,……PJ和B={pm+1,Pm+2,……,Pm+n};在点P1处采用顺时针方向组合点集A,即依次连接PpP2、……Pm形成道路边线X ;点Pm+1处采用逆时针组合点集B,即Pm+n、Pnrtri'……、Pm+1、Pm形成道路边线Y ;取组成道路边线点集中包含点个数较少的点集中的初始点,假设为点P1,分别计算点P1和点Pm+n,点P1和点Pnrtri中点坐标,依次类推,计算两道路边线点集的中点形成点集C= IC1,C2,……,Clri,CJ,共包含η个点,将点集C中各点依次连接成线,即为道路中线; 步骤三:获取道路搜索块:将点集C形成的道路中线按一定长度L打断,L的选取,根据实际常见城市道路拥堵时队列最小长度选取,形成中线定长点集D={D1; D2,……,Di+ DJ,共i个点,最后不足L的部分不再分类;定义道路边线长度与道路中线长度的比值为比例因子Φ,将两条边线道路边线分别按LX Φ进行打断,分别形成两条边线点集X={X1;X2,……,Xh,XJ, Y= (Y1, Y2,……,Yh,YJ,此时对点集D、X、Y中的相邻两点进行连接,形成以中线为分界线的左右两边道路搜索块; 步骤四:重复步骤一至三,对城市路网中所有面状道路进行道路搜索块划分。 A total of m + n vectors, followed by calculating the cosine; cosine of the smallest corresponding point, is the beginning and end point of the road; Step Two: Get road centerline: Suppose road and last point is the point PdPPm, the planar roads beginning and end points of the formation of two road edges break point set, A = {P1; P2, ...... PJ and B = {pm + 1, Pm + 2, ......, Pm + n}; adoption at point P1 clockwise direction combination point set A, that is in turn connected PpP2, ...... Pm road edges form X; point Pm + 1 at the use of counter-clockwise combination point set B, which Pm + n, Pnrtri '......, Pm + 1, Pm road edges form Y; take the road edges point set composition contains less number of points a point on the initial point, is assumed to point P1, respectively calculate the points P1 and Pm + n, the points P1 and Pnrtri midpoint coordinates, and so on, to calculate two mid way point set of edges forming point set C = IC1, C2, ......, Clri, CJ, contains η points, set the point C at various points in turn is connected to a line, that is the road center line; Step three: Get Search Road Blocks: Road to the midline point set C formed interrupted by a certain length L, L selection, according to the actual common urban road congestion queue minimum length selected to form a neutral point fixed length set D = {D1; D2, ...... , Di + DJ, a total of i points, the last part of the L is no longer inadequate classification; road edge length ratio defined road centerline length scale factor Φ, the two edges of the road edges respectively LX Φ be interrupted, formed two Article sideline point set X = {X1; X2, ......, Xh, XJ, Y = (Y1, Y2, ......, Yh, YJ, this time on the set of points D, X, Y connecting the adjacent points , the formation of the center line as the boundary of the search block on both sides of the road; Step four: Repeat steps one to three of the urban road network in all planar road roads search block division.
3.如权利要求1所述的一种利用高分遥感影像提取城市路网拥堵车辆队列信息的方法,其特征在于:计算所述道路车辆面积占有率采用的数学模式为: According to claim 1, wherein a high extraction method using GIS road network congestion vehicle queue information, which is characterized by: a mathematical model to calculate the area of road vehicle occupancy used are:
Figure CN104021670AC00022
其中,Z代表道路搜索块中的道路车辆面积占用率,S车代表道路搜索块中的单个车辆的面积 An area where, Z for road search block road vehicle area occupancy rate, S road car represents search blocks of a single vehicle
Figure CN104021670AC00031
则代表在道路搜索块中车辆面积的总和,S路代表道路搜索块的面积。 It represents the sum of the vehicle search area at the road block, S Road, the road on behalf of the search area block.
4.如权利要求1所述的一种利用高分遥感影像提取城市路网拥堵车辆队列信息的方法,其特征在于:设定拥堵状态下的道路面积占用率为阈值z,所述道路搜索块的道路面积占用率大于或等于阈值z的,判定为包含拥堵车辆队列的道路搜索块,则此时若干拥堵道路搜索块的总长度,即为是该路段上拥堵车辆队列的长度。 4. A high claim 1, wherein the use of remote sensing image extraction method of urban road network congestion queue information vehicle, characterized in that: the road area occupancy rate of the threshold value z set congestion state, the path search block The road area occupancy rate z is greater than or equal to the threshold, it is determined to contain the congestion queue road vehicle search block, at this time the total length of the road congestion several search block, i.e. the length of the vehicle on the road congestion queue.
Description  translated from Chinese

一种高分遥感影像提取城市路网车辆队列状态信息方法 One kind of scores of remote sensing image of urban road network of the vehicle queue status information method

技术领域 Technical Field

[0001] 本发明属于宏观交通状态判别技术领域,具体涉及交通遥感应用与智能交通技术。 [0001] The present invention belongs to the field of macro-traffic state identification technology, remote sensing applications in particular to transport and intelligent transportation technology.

背景技术 Background

[0002] 近年来,我国城市化进程加快,交通拥堵问题日益严重。 [0002] In recent years, China's urbanization process accelerated, the growing problem of traffic congestion. 如何全面、快速掌握整个城市路网交通拥堵和交通瓶颈分布节点、了解交通拥堵状态、乃至于预测拥堵扩散范围,为交通管理部门进行交通疏导和路网科学建设提供科学性数据依据。 How comprehensive, quickly grasp the entire city road network traffic congestion and traffic bottlenecks in distribution points, to understand the state of traffic congestion, and even predict congestion diffusion range, perform traffic control and road network construction as the traffic management department of science provide scientific data basis. 车辆队列(信息包括位置和长度)是城市拥堵的重要表现形式,是进行城市道路交通分析的基本参数之一。 Vehicles queue (information including the location and length) is an important form of urban congestion, is one of the basic parameters of urban road traffic analysis. 然而,当前地面交通信息数据获取手段(视频、线圈、微波、雷达)多为点源微观交通信息,数据获取中间传输环节过多,存储物理空间大,数据保存和处理困难,宏观可视化程度低,数据覆盖面有限,设备运营维护成本昂贵,无法满足城市乃至城市群路网大范围交通状态分析和宏观规划的智能交通数据需求。 However, the current ground traffic information data acquisition means (video, coils, microwave, radar) more microscopic traffic information as a point source, data acquisition intermediate transmission links too large physical storage space, data storage and processing difficulties, low macro level visualization, limited data coverage, equipment operation and maintenance costs of expensive, unable to meet the city and the urban agglomeration Road Network Traffic Analysis and a wide range of macro planning of intelligent transportation data requirements. 随着卫星技术和遥感影像成像质量的不断提升,2012年国家高分卫星“资源3号”上天,高分辨率遥感影像已进入“平民化时代”。 With satellite technology and remote sensing image and improve image quality, in 2012 the national high satellite "Resource No. 3" heaven, high-resolution remote sensing has entered a "civilian era." 将高分遥感数据应用于智能交通领域进行交通拥堵下的道路车辆队列判别成为一个重要而热门的研究课题。 The score of remote sensing data used in intelligent transportation field for road vehicle traffic congestion at queue discrimination has become an important and popular research topic.

[0003] 专利对比文献I (201010220935.2),公布了一种十字路口摄像头视频图像进行车俩长度的检测,该发明只能获取一个路口有限长度车辆队列情况,无法从宏观上获得整个路网的车辆队列信息。 [0003] Patent comparative literature I (201010220935.2), discloses a crossroads video camera to detect both the length of the vehicle, the invention can only get a finite length of the vehicle crossing the queue situation, we can not get the whole road network of the vehicle from the macro queue information.

[0004] 专利对比文献2(200910092506.9),公布了一种浮动车数据提取车辆排队长度,但由于浮动车数量的限制,也无法全面准确获取整个城市路网中的车辆队列信息。 [0004] Patent Document 2 Comparison (200910092506.9), discloses a floating car data extraction vehicle queue length, but due to the number of floating cars, can not fully and accurately obtain the entire city road network in the vehicle queue information.

[0005] 专利对比文献3 (201210044347.7),公布了一种环形线圈检测器的数据进行车辆队列的提取,属于点源监测,其检测器的安装与维护都对道路有一定损毁,且受成本因素限制,无法获取整个城市路网中车辆队列信息的获取。 [0005] Patent Document 3 Comparison (201210044347.7), discloses a toroidal coil detector data extraction queue of vehicles belonging to the point source monitoring, installation and maintenance of its detectors are on the road has some damage, and the cost factors restrictions, can not get the entire city road network of the vehicle queue to information.

[0006] 以上方法均属于地面交通信息获取手段,存在不足,且与本发明方法不属于同一信息来源。 Above [0006] The method belongs to ground transportation information acquisition means, there is a shortage, and with the methods of the present invention does not belong to the same sources of information.

[0007]科技论文对比文献 I (Jens Leitloff, Stefan Hinz&UweStilla, etal.Detectionof Vehicle Queues in QuickBird Imagery of City [J] Areas PhotogrammetrieFernerkundungGeoinformation, 4/2006, 315-325),提出了一种通过构建高分遥感影像中车辆队列特征知识库,应用形态学、灰度等信息,直接从遥感影像中提取车辆队列信息的方法,也不同于本发明所述的方法。 [0007] Comparative Literature Scientific Paper I (Jens Leitloff, Stefan Hinz & UweStilla, etal.Detectionof Vehicle Queues in QuickBird Imagery of City [J] Areas PhotogrammetrieFernerkundungGeoinformation, 4/2006, 315-325), proposes a remote sensing image by building a high score Knowledge vehicle queue features, morphological, gray and other information, the vehicle queue information extraction from remote sensing images directly, but also from the method of the present invention.

发明内容 DISCLOSURE

[0008] 本发明目的在于克服现有技术中车辆队列判别方法的不足,提出了基于高分辨率遥感影像的滑块阈值搜索法,提取车辆队列信息。 [0008] The present invention aims to overcome the shortage of vehicles queue identification method of the prior art, the proposed queue information is based on high-resolution remote sensing image slider threshold search method to extract the vehicle.

[0009] 本发明方法包括以下步骤: [0009] The present invention comprises the steps of:

(I)、应用图像处理相关算法,基于遥感影像提取面状道路和面状车辆矢量信息;(2)、提取面状道路中心线和边线,形成搜索块路; (I), the application of image processing related algorithms, based on remote sensing image and planar planar road vehicle vector information; (2) to extract planar road centerline and edges to form a search block road;

a、获取面状道路,找到面状道路的首尾点:如附图1所示,首先获得构成面状道路边界的点集P = (P1, P2,……Pm, Pm+1,……,PnrtJ,共包含m+n (η≥m≥2)个点,将点集按顺时针方向两两组合成向量P = (P1, P2,……Pm,Pm+1,……,?m+n},共包含m+n(n≥m≥2)个 a, get a planar road, find first and last points of the planar road: as shown in Figure 1, the first set of points obtained constitute a planar road boundary P = (P1, P2, ...... Pm, Pm + 1, ......, PnrtJ, contains a total of m + n (η≥m≥2) points, the set of points in a clockwise direction pairwise combination vector P = (P1, P2, ...... Pm, Pm + 1, ......,? m + n}, contains a total of m + n (n≥m≥2) a

点,将点集按顺时针方向两两组合成向量 Point, the point set clockwise pairwise combination vector

Figure CN104021670AD00051

共m+n个 A total of m + n

向量。 Vector. 依次计算其余弦值,如点q: In order to calculate the cosine value, such as point q:

当q = I时,计算巧巧与H两向量的余弦值; When q = I, the calculation Qiaoqiao and cosine of two vectors H;

当l〈q〈m+n时,计算以点q为起点的向量和点q后一点即点q_l为终点的向量的余弦值,即计算 When l <q <m + n when computing point after starting the vector q q point and the point that is the end point q_l vector cosine of that calculation

Figure CN104021670AD00052

其中Θ为向量弋匕,和向量.的夹 Where Θ is the vector Yi dagger, and vectors. Folders

角; Angle;

当q = m+n时,计算愚+„&+„ ^P1P2的余弦。 When q = m + n, the calculation stupid + "& +" ^ P1P2 cosine.

[0010] 其中最小的余弦值所对应的点,即为道路首尾点(因为在图像中面状路的出入口处两端的线段近似平行)。 [0010] where the cosine value corresponding to the minimum point and last point is the road (as in the image of the line across the entrance to approximately parallel to the surface shape of the road).

[0011] b、道路中心线:如图2所示,假设道路首尾点为APdPPm。 [0011] b, road centerline: 2, first and last point of the path is assumed APdPPm. 将面状道路在首尾点处打断形成两个道路边线点集,A= {P1; P2,……PJ和B={Pm+1,Pm+2,……,Pm+n}。 The planar road at beginning and end points of the formation of two road edges break point set, A = {P1; P2, ...... PJ and B = {Pm + 1, Pm + 2, ......, Pm + n}. 在点P1处采用顺时针方向组合点集A,即依次连接PpP2、……Pm形成道路边线X ;点Pm+1处采用逆时针组合点集B,即Pnrt^Pnrtr1、……、Pm+1、Pm形成道路边线Y。 Adoption at point P1 clockwise combined point set A, that is in turn connected PpP2, ...... Pm road edges form X; point Pm + 1 at the use of counter-clockwise combination point set B, which Pnrt ^ Pnrtr1, ......, Pm + 1 , Pm road edges forming Y. 取组成道路边线点集中包含点个数较少的点集中的初始点,假设为点P1,分别计算点P1和点Pm+n,点P1和点Pnrtri中点坐标,依次类推,计算两道路边线点集的中点形成点集C= IC1, C2,……,Cn_1; CJ,共包含η个点,将点集C依次连接成线即为道路中线; Take the composition of road edges point set contains less number of points a point on the initial point, is assumed to point P1, the points P1 and Pm + n, the points P1 and Pnrtri midpoint coordinates are calculated, and so on, to calculate two road edges forming a midpoint point set point set C = IC1, C2, ......, Cn_1; CJ, contains η points, the point set C is in turn connected to line the road center line;

C、划分道路搜索块:将点集C形成的道路中线按一定长度L打断,L的选取,根据实际常见城市道路拥堵时队列最小长度选取。 C, divided road search block: the point set path C formed midline interrupted by a certain length L, L selection, based on the actual common urban road congestion queue minimum length selection. 形成中线定长点集D= {D1; D2,……,Di+Dj,共i个点,最后不足L的部分不再分类;定义道路边线长度与道路中线长度的比值为比例因子Φ,将两条边线道路边线分别按ίΧΦ进行打断,分别形成两条边线点集X={X1; X2,……,Xh,XJ, Y= (Y1, Y2,……,Yh,YJ,此时对点集D、X、Y中的相邻两点进行连接,形成以中线为分界线的左右两边道路搜索块; Forming a neutral point set length D = {D1; D2, ......, Di + Dj, i total points, the last part of the L is no longer inadequate classification; road edge length ratio defined road centerline length scale factor Φ, will two edges of the road edges respectively ίΧΦ be interrupted, the two edges are formed set of points X = {X1; X2, ......, Xh, XJ, Y = (Y1, Y2, ......, Yh, YJ, at this time point set D, X, Y adjacent points are connected, form a center line on both sides of the road as the boundary of the search block;

d、重复a、b、C,对城市路网中所有面状道路进行道路搜索块划分。 d, repeating a, b, C, of the urban road network in all planar road roads search block division.

[0012] ( 3 )、计算各道路搜索块中车辆占有率。 [0012] (3), calculate the share of road vehicles in the search block.

[0013] 道路车辆面积占有率的定义为:在道路中的车辆面积总和占某搜索块路段面积的百分数。 [0013] The definition of road vehicles area occupancy is: the sum of the vehicle in the road area percentage of a search block section area.

[0014] 如用字母Z表示,则可按(I)式的数学模式计算: [0014] As represented by the letter Z, you can press the (I) formula mathematical model calculations:

Figure CN104021670AD00053

式中,Z代表某搜索块路中的道路车辆面积占用率,Sdf表该搜索路块中的单个车辆面积,Σ 则代表在该搜索块路中车辆面积的总和,Sk代表某搜索块路的面积。 Formula, Z is representative of a path search block area occupancy rate of the vehicle on the road, Sdf path table for this search block is a single area of the vehicle, Σ represents the sum of the vehicle in the area of the search block path, Sk representative of a path search block area. [0015] (4)阈值法检测道路队列信息;设定拥堵状态下的道路面积占用率为阈值z,若所述道路搜索块的道路面积占用率大于或等于阈值z的,判定为包含拥堵车辆队列的道路搜索块,则此时若干拥堵道路搜索块的总长度,即为是该路段上拥堵车辆队列的长度。 [0015] (4) The threshold queue information detected by the road; the set state road congestion area occupancy rate threshold z, road area occupancy rate of the road if the search block is greater than or equal to a threshold value of z, determined to contain the vehicle congestion search queue road block, the total length of the search block at this time a number of congested roads, namely the length of the vehicle on the road congestion queue. 拥堵车辆队列搜索块的中心即认为是该路段上某个车辆队列所在的位置,结合电子地图或GPS,即可获得该队列所在的区域道路名称。 Congestion vehicle cohort search block that is considered to be the location of a vehicle on the road where the queue, combined with electronic map or GPS, you can get the name of the queue area where the road.

[0016] 本发明采用高分遥感影像实现车辆队列的检测,具有宏观性好、可视化程度高、检测区域面积大。 [0016] The present invention uses remote sensing to achieve high detection vehicle queues, having macro, high degree of visibility, a large area of detection. 检测结果可为交通管理和规划部门科学决策提供准确的数据支撑。 The test results can provide accurate data support for traffic management and planning department of scientific decision-making. 应用本发明的方法,同比与对比文献中的车辆拥堵队列提取方法,具有计算精度的优点。 Methods of the present invention and comparative literature up traffic congestion queue extraction method has the advantage of calculation accuracy. 同时,由于本发明,采用迭代搜索法,构建迭代公式即可实现循环计算,在计算机硬件不断升级和CPU计算次数不断提升下,计算速度越来越短的优势越来越明显。 Also, since the present invention, an iterative search method to construct iterative loop calculation formula can be realized in the computer hardware upgrades and CPU constantly rising number of calculations, the advantage of the computing speed is getting shorter and more obvious.

附图说明 Brief Description

[0017] 图1是依据遥感图像提取的面状道路边线示意图,其中集合P={P1; P2,……Pm,Pm+1,……,pm+n}是获得构成面状道路边线的点集; [0017] FIG. 1 is a schematic view of a planar road edges extracted based on remote sensing image, wherein the set P = {P1; P2, ...... Pm, Pm + 1, ......, pm + n} is to get constitution planar point road edges set;

图2是面状道路提取道路中线的示意图,其中集合C=IC1, C2,……,Cn_1; CJ是构成道路中线的点集; Figure 2 is a schematic view of a planar road road centerline extraction, wherein the set C = IC1, C2, ......, Cn_1; CJ is a set of points constituting the road centerline;

图3是形成道路搜索块示意图,集合X= (X1,X2,……,Xi^XihY=H……,Yi+YJ, D= {D1; D2,……,Dh,DJ为两边道路搜索块边线点集; Figure 3 is a block schematic diagram of the search path is formed, the set of X = (X1, X2, ......, Xi ^ XihY = H ......, Yi + YJ, D = {D1; D2, ......, Dh, DJ for the search block both sides of the road Side Lines Set;

图4是基于高分遥感影像判别车辆队列的方法流程图。 Figure 4 is a high remote sensing discrimination flowchart of a method based on vehicle queues.

具体实施方式 DETAILED DESCRIPTION

[0018] 为了更清楚地说明本发明实施例的技术方案,结合附图对本发明作进一步说明: 本发明突出的方法步骤如图4所示: [0018] In order to more clearly illustrate the technical aspect of an embodiment of the present invention, with reference to the present invention will be further explained: projecting step of the present invention, a method shown in Figure 4:

(1)、应用图像处理相关算法,基于遥感影像提取面状道路和面状车辆矢量信息; (1), the application of image processing related algorithms, based on remote sensing image and planar planar road vehicle vector information;

(2)、提取面状道路中心线和边线,形成搜索块路; (2), to extract planar road centerline and edges to form a search block road;

a、获取面状道路,找到面状道路的首尾点:如附图1所示,首先获得构成面状道路边界的点集P = (P1, P2,……Pm, Pm+1,……,PnrtJ,共包含m+n (η≥m≥2)个点,将点集按顺时 a, get a planar road, find first and last points of the planar road: as shown in Figure 1, the first set of points obtained constitute a planar road boundary P = (P1, P2, ...... Pm, Pm + 1, ......, PnrtJ, contains a total of m + n (η≥m≥2) points when the point set by cis

针方向两两组合成向量 Clockwise pairwise combination vector

Figure CN104021670AD00061

写共m+n个向量。 Write a co m + n vectors. 依次计算其 In order to calculate the

余弦值,如点q: Cosine, such as point q:

当q = I时,计算P1P2与U議两向量的余弦值; When q = I, the calculation of the cosine P1P2 and U proposed two vectors;

当l〈q〈m+n时,计算以点q为起点的向量丨,,,和点q后一点即点q_l为终点的向量 Later when l <q <m + n, the calculation starting point of the vector q 丨 ,,, and point q point that is a vector end point q_l

___P.PP ___ P.PP

7UfU 的余弦值,即计算 7UfU cosine, that calculation

Figure CN104021670AD00062

,其中Θ 为向量ξξ;和向量/^ξ—;的夹 Where Θ is the vector ξξ; and vector / ^ ξ-; folder

角; Angle;

当q = m+n时,计算H与PlPz的余弦。 When q = m + n, the calculation H and PlPz cosine.

其中最小的余弦值所对应的点,即为道路首尾点(因为在图像中面状路的出入口处两端的线段近似平行); The smallest cosine corresponding point, and last point is the road (because the image of the entrance road surface shape at both ends of the line nearly parallel);

b、道路中心线:如图2所示,假设道路首尾点为点P1和Pm。 b, road centerline: 2, first and last point of the path is assumed to point P1 and Pm. 将面状道路在首尾点处打断形成两个道路边线点集,A = (P1, P2,……PJ和B= {Pm+1,Pm+2,……,Pm+n}。在点P1*采用顺时针方向组合点集A,即PpP2、……Pm为依次连接成线段形成道路边线X ;点Pm+1处采用逆时针组合点集B,即……、Pm+1、Pm形成道路边线Y。取组成道路边线点集中包含点个数较少的点集中的初始点,假设为点P1,分别计算点P1和点Pm+n,点P1和点Pnrtri The planar road at beginning and end points of the formation of two road edges break point set, A = (P1, P2, ...... PJ and B = {Pm + 1, Pm + 2, ......, Pm + n}. In point P1 * clockwise direction using a combination of point set A, namely PpP2, ...... Pm is in turn connected to a line forming road sideline X; point Pm + 1 at the use of counter-clockwise combination point set B, which ......, Pm + 1, Pm form Take the road edges Y. composition containing point road edges point set number of points less concentrated initial point is assumed to point P1, respectively calculate the points P1 and Pm + n, the points P1 and Pnrtri

中点坐标,依次类推,计算两道路边线点集的中点形成点集C = (C1, C2,......, cn_1; cn},共 Midpoint coordinates, and so on, to calculate the midpoint of two road edges forming point set point set C = (C1, C2, ......, cn_1; cn}, Total

包含η个点,将点集C依次连接成线即为道路中线; Contains η points, the point set C is in turn connected to line the road center line;

C、划分道路搜索块:将点集C形成的道路中线按距离L = 20米(根据经验和实际调查,选取最短队列长度L = 20米,因中国轿车一般车长为5米,大巴和公交一般在10米,取最常见的3辆轿车拥堵或两辆大巴排队的长度)打断,形成中线定长点集D= {D1; D2,……,Di+ DJ,共i个点,如图3中五角星标志,最后道路中线中长度不足d的部分不再分类。 C, divided road search block: the road centerline point set C formed by distance L = 20 m (based on experience and practical research, choose the shortest queue length L = 20 meters because of Chinese cars in general is five meters long car, bus and bus generally 10 meters, take the most common three car congestion or two buses queue length) interrupted, forming the center line length point set D = {D1; D2, ......, Di + DJ, a total of i points, as 3 Pentastar, some final road centerline insufficient length d is no longer classified. 定义道路边线长度与道路中线长度的比值为比例因子Φ,由于X、Y长度不同,故对应的两条边线比例因子也不同,具体大小,以计算结果为准。 Defined as the ratio of road edge length of the road centerline length scale factor Φ, due to the different X, Y length, so the two edges corresponding to the scale factor is different, specific size to calculate the results shall prevail. 将两条边线道路边线分别按LX Φ进行打断,分别形成两条边线点集X = {X1; X2,……,X^ijXJjY = (Y1, Y2,……U},此时对点集D、X、Y中的相邻两点进行连接,形成以中线为分界线的左右两边道路搜索块;如图3中三角形标志,都包含i个点。将形成的点集依次连接成线段,即分别在点集D、X、Y中依次取两点组合,共生成21-2段搜索块路; The two edges of the road edges respectively LX Φ be interrupted, the two edges are formed set of points X = {X1; X2, ......, X ^ ijXJjY = (Y1, Y2, ...... U}, at this time point set D, X, Y adjacent points are connected, form a center line on both sides of the road as the boundary of the search block; as shown in the triangle mark 3, contains the i-th point point set to be formed in order to connect to a line segment. namely the set of points D, X, Y sequentially taken two combined 21-2 segment generated total search block road;

d、重复a、b、c,直到所有面状道路都形成搜索块道路; d, repeating a, b, c, until all roads are planar path search block is formed;

(3)、计算各道路搜索块中车辆占有率。 (3), calculate the share of road vehicles in the search block.

[0019] 道路车辆占有率的定义为:在道路中的车辆面积总和占某搜索块路段面积的百分数。 Definitions [0019] share of road vehicles: the sum of the vehicle in the road area percentage of a search block section area. 如用字母Z表示,则可按(I)式的数学模式计算: As expressed by the letter Z, you can press the (I) formula mathematical model calculations:

Figure CN104021670AD00071

式中,Z代表某搜索块路中的道路车辆面积占用率,Sdf表该搜索路块中的单个车辆面积,Σ 则代表在该搜索块路中车辆面积的总和,Sk代表某搜索块路的面积。 Formula, Z is representative of a path search block area occupancy rate of the vehicle on the road, Sdf path table for this search block is a single area of the vehicle, Σ represents the sum of the vehicle in the area of the search block path, Sk representative of a path search block area.

[0020] (4)、阈值法检测道路队列信息;设定某队列状态下的道路面积占用率为阈值z为70% (考虑到车辆间距,一条道路不可能全部被车首尾无间隙占满),大于阈值z的,即判定为该程度下的拥堵车辆队列搜索块,则此时若干拥堵道路搜索块的总长度,即为是该路段上拥堵车辆队列的长度。 [0020] (4), the threshold assay queue road information; road area occupancy rate of the threshold value z set a queue state is 70% (taking into account the distance between vehicles, road vehicles can not all be filled from beginning to end without gaps) , greater than the threshold value of z, it is determined that the vehicle congestion queue for the degree under the search block, at this time the total length of the search block several congested roads, namely the length of the vehicle on the road congestion queue. 拥堵车辆队列搜索块的中心即认为是该路段上某个车辆队列所在的位置,结合电子地图或GPS,即可获得该队列所在的区域道路名称。 Congestion vehicle cohort search block that is considered to be the location of a vehicle on the road where the queue, combined with electronic map or GPS, you can get the name of the queue area where the road.

Patent Citations
Cited PatentFiling datePublication dateApplicantTitle
CN101980317A *3 Sep 201023 Feb 2011浙江大学Method for predicting traffic flow extracted by improved C-V model-based remote sensing image road network
CN102567963A *10 Nov 201111 Jul 2012西安电子科技大学Quantum multi-target clustering-based remote sensing image segmentation method
CN102609706A *25 Jan 201125 Jul 2012龚建华System for extracting road information from high-resolution remote-sensing image
US5862244 *13 Jul 199519 Jan 1999Motorola, Inc.Satellite traffic reporting system and methods
US20140074566 *11 Sep 201313 Mar 2014James K. McCoyRemote Sensing of Vehicle Occupancy
Non-Patent Citations
Reference
1 *张勇 等: "高分遥感影像在交通限行决策中的应用", 《公路与汽运》, no. 157, 31 July 2013 (2013-07-31), pages 69 - 71
2 *张素兰: "基于卫星遥感影像的交通状态判别研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 10, 15 October 2010 (2010-10-15), pages 15 - 53
Referenced by
Citing PatentFiling datePublication dateApplicantTitle
CN105157710B *6 Jun 20157 Sep 2016烟台惠通网络技术有限公司基于遥感通信的路段拥堵程度检测系统
Classifications
International ClassificationG08G1/123, G08G1/01
Legal Events
DateCodeEventDescription
3 Sep 2014C06Publication
29 Oct 2014C10Entry into substantive examination
15 Jun 2016C14Grant of patent or utility model