An intersection traffic state evaluation method and system based on video target tracking

Abstract

The application discloses a kind of intersection traffic state evaluation method and system based on video target tracking, it is related to intelligent road parking management field, including: according to intersection area video image acquisition intersection each vehicle corresponding stay duration, and according to different congestion state respectively corresponding preset average speed information of vehicle driving and the width information corresponding to the intersection determine that different congestion state respectively corresponding vehicle stay duration in intersection, then the stay time of vehicle in intersection and different congestion state respectively corresponding vehicle stay duration in intersection is compared in real time, determine the intersection traffic state, to realize the intersection traffic state evaluation based on video image vehicle target tracking, compared with by radar to carry out intersection vehicle speed measurement, and based on the intersection traffic state evaluation of vehicle speed monitored by radar, based on video image vehicle target tracking directly through each vehicle corresponding stay duration in intersection to carry out intersection traffic state evaluation, so as to improve the accuracy of intersection traffic state evaluation.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of urban intelligent parking management, in particular to a traffic state evaluation method and system based on video target tracking. BACKGROUND

[0002] In recent years, with the increasing number of cars, urban traffic congestion problem is becoming increasingly serious, accurate judgment of congestion state is the first step of precise congestion control. The congestion and intelligent management of urban intersections are the most important. At present, when judging the congestion state of the intersection, the radar speed measuring device is usually used to collect the driving speed of the passing vehicle, and then the current intersection congestion is judged by the vehicle passing speed. However, when the vehicle speed is low, the radar speed measuring device cannot accurately obtain the vehicle speed or the error of the collected vehicle speed is large. At this time, if the current intersection congestion is judged based on the vehicle passing speed, the accuracy of the judgment of the intersection traffic state will be low and the error will be large. SUMMARY

[0003] To solve the above technical problems, the present application provides a traffic state evaluation method and system based on video target tracking in intersection, which can solve the problem of low accuracy and large error in judging the current intersection traffic state.

[0004] To achieve the above purpose, on the one hand, the present application provides a traffic state evaluation method based on video target tracking in intersection, which comprises:

[0005] obtaining the stay duration of each vehicle in the intersection according to the video image of the intersection area;

[0006] obtaining the width information of the intersection according to the standard specification information of the urban intersection;

[0007] determining the stay duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the driving vehicle corresponding to different congestion states and the width information of the intersection;

[0008] determining the traffic state in the intersection according to the stay duration of the vehicle in the intersection and the stay duration of the vehicle in the intersection corresponding to different congestion states.

[0009] Further, the step of obtaining the width information of the intersection according to the intersection state information of the intersection comprises:

[0010] obtaining the width information of the intersection according to the width range standard of the entrance lane, the width range standard of the exit lane, the width range standard of the sidewalk and the number of lanes of the intersection.

[0011] Further, the step of determining the staying duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the vehicle in the intersection corresponding to different congestion states and the width information of the intersection comprises:

[0012] The quotient of the width information of the intersection and the preset average speed information of the vehicle in the intersection corresponding to different congestion states is taken as the staying duration of the vehicle in the intersection.

[0013] Further, the step of determining the staying duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the vehicle in the intersection corresponding to different congestion states and the width information of the intersection comprises:

[0014] The staying duration of the vehicle in the intersection corresponding to different congestion states is determined according to the preset average speed information of the vehicle in the intersection corresponding to different congestion states and the width information of the intersection under the green light state of the intersection.

[0015] Further, the step of determining the staying duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the vehicle in the intersection corresponding to different congestion states and the width information of the intersection comprises:

[0016] The congestion state information of the intersection is determined according to the position interval of the staying duration of the vehicle in the intersection corresponding to different congestion states.

[0017] On the other hand, the application provides a traffic state evaluation system in an intersection based on video target tracking, which comprises:

[0018] An acquisition unit is configured to acquire the staying duration of each vehicle in the intersection according to the video image of the intersection region;

[0019] The acquisition unit is further configured to acquire the width information of the intersection according to the standard specification information of the city intersection;

[0020] A determination unit is configured to determine the staying duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the vehicle in the intersection corresponding to different congestion states and the width information of the intersection;

[0021] The determination unit is further configured to determine the traffic state in the intersection according to the staying duration of the vehicle in the intersection corresponding to different congestion states and the staying duration of the vehicle in the intersection corresponding to different congestion states.

[0022] Further, the acquisition unit is specifically configured to acquire the width information corresponding to the intersection according to the width range standard of the entry lane, the width range standard of the exit lane, the width range standard of the sidewalk, and the number of lanes corresponding to the intersection.

[0023] Further, the determination unit is specifically configured to take the quotient of the width information corresponding to the intersection and the preset average speed information of the vehicle in the different congestion states as the duration of the vehicle staying in the intersection.

[0024] Further, the intersection traffic state evaluation system based on video target tracking has the characteristics that

[0025] The determination unit is further configured to determine the vehicle duration time in the different congestion states according to the preset average speed of the vehicle in the different congestion states and the width information corresponding to the intersection under the green light state of the intersection.

[0026] Further, the determination unit is specifically configured to determine the congestion state information of the intersection according to the position interval of the duration of the real-time vehicle staying in the intersection in the vehicle duration time in the different congestion states.

[0027] The intersection traffic state evaluation method and system based on video target tracking provided by the application acquire the duration of each vehicle staying in the intersection according to the video image of the intersection area, determine the duration of the vehicle staying in the intersection in the different congestion states according to the preset average speed information of the vehicle in the different congestion states and the width information corresponding to the intersection, compare the duration of the real-time vehicle staying in the intersection with the duration of the vehicle staying in the intersection in the different congestion states, and determine the traffic state in the intersection, so as to realize the evaluation of the traffic state in the intersection based on the video image vehicle target tracking. Compared with the radar-based intersection vehicle speed measurement and the evaluation of the traffic state in the intersection based on the vehicle speed monitored by the radar, the intersection traffic state evaluation based on the video image vehicle target tracking directly uses the duration of each vehicle staying in the intersection to evaluate the traffic state in the intersection, so as to improve the accuracy of the evaluation of the traffic state in the intersection. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 is a flowchart of the intersection traffic state evaluation method based on video target tracking provided by the application;

[0029] Figure 2 is a structural schematic diagram of the intersection traffic state evaluation system based on video target tracking provided by the application. DETAILED DESCRIPTION

[0030] The technical solutions of the present application are described in further detail below with reference to the accompanying drawings and examples.

[0031] As Figure 1 shown, the intersection traffic state evaluation method based on video target tracking provided by the embodiment of the present application comprises the following steps:

[0032] 101. Obtain the stay duration of each vehicle in the intersection area according to the video image of the intersection area.

[0033] Specifically, for example, identify the passing vehicles in the intersection based on the video target detection technology, assign a non-repeating ID to each vehicle, and continuously track. Count the number of vehicle IDs in the intersection, the stay duration of each vehicle ID in the intersection, and the driving speed in the intersection, and return the result every 1 second.

[0034] 102. Obtain the width information corresponding to the intersection according to the standard specification information of the city intersection.

[0035] For the embodiment of the present application, step 102 can specifically include: obtaining the width information corresponding to the intersection according to the width range standard of the entrance lane of the city plane intersection, the width range standard of the exit lane, the width range standard of the sidewalk, and the number of lanes corresponding to the intersection.

[0036] Specifically, for example, the width of the entrance lane of the city plane intersection should be 3.0-3.25m, the width of the exit lane should be 3.25-3.50m, and the minimum width of the sidewalk should not be less than 1.5m. In the embodiment of the present application, the lane width can be 3.25m, and the minimum width of the sidewalk can be 1.5m. Then the intersection width estimation formula is as follows:

[0037] W = 2*(3.25n + 1.5) = (6.5n + 3)

[0038] Where W is the intersection width, n is the number of lanes at the intersection, and the stay time of the vehicle in the intersection is:

[0039] T = (6.5n + 3) / V

[0040] Where V is the speed of the vehicle passing through the intersection.

[0041] 103. Determine the stay duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the vehicle corresponding to different congestion states and the width information corresponding to the intersection.

[0042] For the embodiment of the present application, step 103 can specifically include: taking the quotient of the width information corresponding to the intersection and the preset average vehicle running speed information corresponding to the different congestion states respectively as the staying duration of the vehicle in the intersection. The vehicle staying duration corresponding to the different congestion states respectively is determined according to the preset average vehicle running speed corresponding to the different congestion states respectively under the green light state of the intersection and the width information corresponding to the intersection.

[0043] Specifically, for example, the relationship between the vehicle passing speed in the intersection and the congestion state can be defined as follows: when the average vehicle speed during the green light period is less than 5 km / h, it is severe congestion; when the average vehicle speed during the green light period is 5 km / h inclusive-15 km / h, it is congestion; when the average vehicle speed during the green light period is 15 km / h-35 km / h, it is slow; and when the average vehicle speed during the green light period is greater than 35 km / h inclusive, it is smooth. Then the relationship between the staying time of the vehicle in the intersection and the congestion state is as follows: severe congestion: the average staying time T of the vehicle in the intersection is greater than congestion: the average staying time T of the vehicle in the intersection is slow: the average staying time T of the vehicle in the intersection is smooth: the average staying time T of the vehicle in the intersection is less than

[0044] 104. Determine the traffic state in the intersection according to the real-time obtained staying time of the vehicle in the intersection and the staying duration of the vehicle in the intersection corresponding to the different congestion states respectively.

[0045] For the embodiment of the present application, step 104 can specifically include: determining the congestion state information of the intersection according to the position interval of the real-time staying time of the vehicle in the intersection in the staying duration of the vehicle corresponding to the different congestion states respectively.

[0046] Specifically, for example, according to the determined severe congestion, congestion, slow, and smooth vehicle staying time critical value, the real-time congestion state in the intersection is obtained by comparing the real-time obtained average staying time of the vehicle in the intersection with the critical value.

[0047] For the embodiment of the present application, the specific application application scenario can be as follows, but is not limited thereto, including: for example, the intersection south-north direction is bidirectional two lanes, the average time T of the vehicle passing through the intersection is detected by video to be 10s, since it is bidirectional two lanes, so n=2, then the average time of the vehicle passing through the intersection is 10s, which is between 3.8s and 11.4s, so the congestion state in the intersection is congestion. For another example, the intersection is bidirectional four lanes, the average time T of the vehicle passing through the intersection is detected by video to be 6s, since it is bidirectional two lanes, so n=4, then The average time of the vehicle passing through the intersection is 6s, between 3s and 6.9s, so the congestion state in the intersection is slow.

[0048] The application provides an intersection traffic state evaluation method based on video target tracking, which obtains the corresponding residence duration of each vehicle in the intersection according to the intersection area video image, and determines the residence duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the running vehicle and the width information corresponding to the intersection corresponding to different congestion states, and then compares the residence time of the vehicle in the intersection obtained in real time with the residence duration of the vehicle in the intersection corresponding to different congestion states, to determine the intersection traffic state, so as to realize the intersection traffic state evaluation based on the video image vehicle target tracking, compared with the radar intersection vehicle speed measurement and the intersection traffic state evaluation based on the radar monitored vehicle speed, the intersection traffic state evaluation based on the video image vehicle target tracking directly through the residence duration of each vehicle in the intersection, so as to improve the accuracy of the intersection traffic state evaluation.

[0049] To realize the method provided by the embodiment of the application, the embodiment of the application provides an intersection traffic state evaluation system based on video target tracking, as shown in Figure 2 The system comprises an acquisition unit 21 and a determination unit 22.

[0050] The acquisition unit 21 is used for obtaining the corresponding residence duration of each vehicle in the intersection according to the intersection area video image.

[0051] The acquisition unit 21 is also used for obtaining the width information corresponding to the intersection according to the city intersection standard specification information.

[0052] The determination unit 22 is used for determining the residence duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the running vehicle and the width information corresponding to the intersection corresponding to different congestion states.

[0053] The determination unit 22 is also used for determining the intersection traffic state according to the residence time of the vehicle in the intersection obtained in real time and the residence duration of the vehicle in the intersection corresponding to different congestion states.

[0054] Further, the acquisition unit 21 is specifically used for obtaining the width information corresponding to the intersection according to the width range standard of the city plane intersection import lane, the width range standard of the export lane, the width range standard of the sidewalk, and the number of lanes corresponding to the intersection.

[0055] Further, the determining unit 22 is specifically configured to take the quotient of the width information corresponding to the intersection and the preset average driving vehicle speed information corresponding to the different congestion states respectively as the staying duration of the vehicle in the intersection.

[0056] Further, the intersection traffic state evaluation system based on video target tracking has the characteristics that,

[0057] The determining unit 22 is further configured to determine the vehicle staying duration corresponding to the different congestion states according to the preset average driving vehicle speed corresponding to the different congestion states under the green light state of the intersection and the width information corresponding to the intersection.

[0058] Further, the determining unit 22 is specifically configured to determine the congestion state information of the intersection according to the position interval of the real-time vehicle staying duration in the intersection in the vehicle staying duration corresponding to the different congestion states.

[0059] The intersection traffic state evaluation method and system based on video target tracking provided by the application obtain the staying duration of each vehicle in the intersection according to the intersection area video image, determine the vehicle staying duration in the intersection corresponding to the different congestion states according to the preset average driving vehicle speed information corresponding to the different congestion states and the width information corresponding to the intersection, then compare the real-time vehicle staying duration in the intersection with the vehicle staying duration in the intersection corresponding to the different congestion states, and determine the intersection traffic state, so as to realize the intersection traffic state evaluation based on the video image vehicle target tracking. Compared with the intersection vehicle speed measurement by radar and the intersection traffic state evaluation based on the radar monitored vehicle speed, the intersection traffic state evaluation based on the video image vehicle target tracking directly uses the staying duration of each vehicle in the intersection to evaluate the intersection traffic state, so as to improve the accuracy of the intersection traffic state evaluation.

[0060] It should be understood that the specific order or hierarchy of steps in the processes disclosed should not be taken as a limitation of the example methods. By way of example, the specific order or hierarchy of steps in the processes could be re-arranged, or omitted, or combined, or sub-divided, without departing from the scope of the disclosure. The accompanying method claims present elements of the various steps in exemplary order and are not intended to be limited to the specific order or hierarchy presented.

[0061] In the above detailed description, various features are grouped together in single embodiments for the purpose of streamlining the disclosure. This method of disclosure, however, is not to be interpreted as reflecting a necessity or desire to group the claimed embodiments together in such a way. In addition, each of the various embodiments described for a single embodiment can be used in combination with another embodiment, and the claimed subject matter contemplates such embodiments. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate preferred embodiment.

[0062] The disclosed embodiments are to be considered as illustrative of the principles of the application. Numerous modifications and adaptations will be readily apparent to those skilled in the art in view of this description. This application is therefore to be considered as including all such modifications and adaptations insofar as they come within the scope of the principles of the application.

[0063] The above description includes one or more examples. Of course, not all possible combinations of components or method steps are described, but one of ordinary skill in the art having the benefit of this disclosure will recognize that many more combinations and permutations of the described elements are possible. Accordingly, the described embodiments are intended to embrace all such alterations, modifications and variations which fall within the scope of the appended claims. Additionally, the term "comprising" as used in the specification and in the following claims is to be construed as meaning "including, but not limited to." Furthermore, where used in the specification and the claims, the term "or" is to be construed as "nonexclusive or", unless otherwise indicated.

[0064] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, and steps described in connection with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.

[0065] The various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. The various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality, without limitation. Depending upon the implementation, the various illustrative blocks, modules, circuits, and steps could be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of them. The software implemented as a computer program, software, or firmware in electronic form, which includes but is not limited to software

[0066] The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium can be integral to the processor. The processor and the storage medium can reside in an ASIC. The ASIC can reside in a user terminal. In the alternative, the processor and the storage medium can reside as distinct components in a user terminal. Exemplary components for a user terminal include, but are not limited to, mobile computing devices, netbooks, notebooks, ultrabooks, laptops, desktops, handheld devices, tablets, televisions, cameras, personal digital assistants, media players, game consoles, or any other computing device.

[0067] In one or more exemplary designs, the functions described can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions can be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. Storage media can be any available media that can be accessed by a computer. By way of example, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or other wire-based, fiber- optic based, or wireless based communications, then the coaxial cable, fiber optic cable, twisted pair, DSL, or other wire-based, fiber-optic based, or wireless based communications are included in the definition of medium. Disk and disc, as used herein, includes compact disc (CD), laser disc, optical disc, DVD, floppy disk, and Blu-ray® disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0068] The specific implementation described above is illustrative for purposes of teaching the present application. The application should not be limited, however, to these specific implementation. Any modifications, equivalents, or improvements, as long as they are within the spirit and scope of the present application are included in the scope of the present application.

Claims

1. A traffic state evaluation method in an intersection based on video target tracking, characterized by, The method comprises: According to the intersection area video image, the stay duration of each vehicle in the intersection is obtained; According to the standard specification information of the city intersection, the width information corresponding to the intersection is obtained; According to the preset average speed information of the vehicle in driving state corresponding to different congestion states and the width information corresponding to the intersection, the stay duration of the vehicle in the intersection corresponding to different congestion states is determined; According to the real-time stay duration of the vehicle in the intersection and the stay duration of the vehicle in the intersection corresponding to different congestion states, the traffic state in the intersection is determined; The step of obtaining the width information corresponding to the intersection according to the intersection state information corresponding to the intersection comprises: According to the width range standard of the entrance lane of the city intersection, the width range standard of the exit lane, the width range standard of the sidewalk, and the number of lanes corresponding to the intersection, the width information corresponding to the intersection is obtained; The step of determining the stay duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the vehicle in driving state corresponding to different congestion states and the width information corresponding to the intersection comprises: The quotient of the width information corresponding to the intersection and the preset average speed information of the vehicle in driving state corresponding to different congestion states is taken as the stay duration of the vehicle in the intersection corresponding to different congestion states; The step of determining the stay duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the vehicle in driving state corresponding to different congestion states and the width information corresponding to the intersection comprises: According to the preset average speed of the vehicle in driving state corresponding to different congestion states and the width information corresponding to the intersection under the green light state of the intersection, the stay duration of the vehicle corresponding to different congestion states is determined.

2. The intersection traffic state evaluation method based on video target tracking according to claim 1, characterized in that, The step of determining the traffic state in the intersection according to the real-time stay duration of the vehicle in the intersection and the stay duration of the vehicle in the intersection corresponding to different congestion states comprises: According to the position interval of the real-time stay duration of the vehicle in the intersection in the stay duration of the vehicle corresponding to different congestion states, the congestion state information of the intersection is determined.

3. A traffic state evaluation system in an intersection based on video target tracking, characterized by, The system comprises: An acquisition unit is configured to obtain the stay duration of each vehicle in the intersection according to the intersection area video image; The acquisition unit is further configured to obtain the width information corresponding to the intersection according to the standard specification information of the city intersection; A determination unit is configured to determine the stay duration of the vehicle in the intersection corresponding to different congestion states according to the preset average speed information of the vehicle in driving state corresponding to different congestion states and the width information corresponding to the intersection; The determination unit is further configured to determine the traffic state in the intersection according to the real-time stay duration of the vehicle in the intersection and the stay duration of the vehicle in the intersection corresponding to different congestion states; The acquisition unit is specifically configured to obtain the width information corresponding to the intersection according to the width range standard of the entrance lane of the city intersection, the width range standard of the exit lane, the width range standard of the sidewalk, and the number of lanes corresponding to the intersection. The determination unit is specifically configured to take the quotient of the width information corresponding to the intersection and the preset average vehicle driving speed information corresponding to the different congestion states respectively as the staying duration of the vehicle in the intersection; The determination unit is further configured to determine the vehicle continuous staying time corresponding to the different congestion states according to the preset average vehicle driving speed corresponding to the different congestion states under the green light state of the intersection and the width information corresponding to the intersection.

4. The intersection traffic state evaluation system based on video target tracking according to claim 3, characterized in that, The determination unit is specifically further configured to determine the congestion state information of the intersection according to the position interval of the staying time of the real-time vehicle in the intersection in the vehicle continuous staying time corresponding to the different congestion states respectively.

Images