A method, system, device, and medium for identifying tracked vehicles.

Abstract

This invention discloses a method, system, device, and medium for identifying tracked vehicles, relating to the field of computer vision technology. The method includes: determining a first short-term driving behavior semantic sequence corresponding to suspected tracked vehicles within a specified surrounding area of ​​a target vehicle, and determining a second short-term driving behavior semantic sequence of the target vehicle; calculating the similarity between the first and second short-term driving behavior semantic sequences; and identifying the suspected tracked vehicle as a tracked vehicle when the similarity exceeds a threshold. This invention identifies tracked vehicles by calculating the similarity between the short-term driving behavior semantic sequences of vehicles surrounding the vehicle owner (suspected tracked vehicles) and the short-term driving behavior semantic sequence of the vehicle owner (target vehicle), significantly improving the accuracy and timeliness of tracked vehicle identification.

Description

Technical Field

[0001] This invention relates to the field of computer vision technology, and in particular to a method, system, device and medium for identifying tracked vehicles. Background Technology

[0002] In daily work and life, cars have gradually become an important means of transportation. However, while cars bring great convenience to people, some criminals have also taken advantage of this situation. Specifically, they use their vehicles to maliciously follow other people who are also driving, thereby infringing on the privacy of these individuals and even threatening their personal safety.

[0003] Therefore, being able to promptly detect vehicles following or tailing a driver is crucial for protecting the driver's privacy and enhancing their personal safety.

[0004] Traditional methods mainly rely on video information to track and determine whether the driving path of vehicles behind the driver overlaps with that of the driver. However, this presents a difficult problem: the vehicle being tracked may not be behind the driver, and there may be more than one vehicle tracking the driver, which makes tracking and recognition very difficult. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to address the shortcomings of the prior art, and specifically provides a method, system, device and medium for identifying tracked vehicles, as detailed below:

[0006] 1) In a first aspect, the present invention provides a method for identifying tracked vehicles, the specific technical solution of which is as follows:

[0007] Determine a first short-term driving behavior semantic sequence corresponding to a suspected tracking vehicle within a specified surrounding area of ​​the target vehicle, and determine a second short-term driving behavior semantic sequence of the target vehicle. The first short-term driving behavior semantic sequence characterizes the driving behavior characteristics of the suspected tracking vehicle within a preset period, and the second short-term driving behavior semantic sequence characterizes the driving behavior characteristics of the target vehicle within a preset period.

[0008] Calculate the similarity between the first short-term driving behavior semantic sequence and the second short-term driving behavior semantic sequence. When the similarity exceeds a threshold, the suspected tracking vehicle is identified as the tracking vehicle.

[0009] The beneficial effects of the vehicle tracking identification method provided by this invention are as follows:

[0010] By calculating the similarity between the short-term driving behavior semantic sequences of vehicles around the vehicle owner (suspected tracking vehicles) and the short-term driving behavior semantic sequences of the vehicle owner (target vehicle), tracking vehicles can be identified, significantly improving the accuracy and timeliness of tracking vehicle identification.

[0011] Based on the above solution, the present invention can be further improved as follows.

[0012] Furthermore, the process for determining the similarity is as follows:

[0013] The first driving behavior type difference of the corresponding short-term driving behavior semantic sequence is determined based on the first short-term driving behavior semantic sequence. The first driving behavior type difference represents the duration ratio of different driving behavior types in the first short-term driving behavior semantic sequence.

[0014] The second driving behavior type difference of the corresponding short-term driving behavior semantic sequence is determined based on the second short-term driving behavior semantic sequence. The second driving behavior type difference represents the duration ratio of different driving behavior types in the second short-term driving behavior semantic sequence.

[0015] The similarity is determined based on the first driving behavior type difference and the second driving behavior type difference.

[0016] Furthermore, the method for determining the ratio of the first driving behavior type difference to the second driving behavior type difference is as follows:

[0017] Determine the first identical driving behavior type difference and the first different driving behavior type difference of the first short-term driving behavior semantic sequence, and average the first identical driving behavior type difference and the first different driving behavior type difference to obtain the first driving behavior type difference;

[0018] Alternatively, determine the second identical driving behavior type difference and the second different driving behavior type difference of the second short-term driving behavior semantic sequence, and perform averaging on the second identical driving behavior type difference and the second different driving behavior type difference to obtain the second driving behavior type difference.

[0019] Furthermore, the method for determining the first difference in the same driving behavior type or the second difference in the same driving behavior type is as follows:

[0020] The first short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. The first driving behavior and its corresponding duration in any equal window are determined. Based on the first correspondence between the semantic label, the first driving behavior, the duration corresponding to the first driving behavior, and the behavior type difference, the first same driving behavior type difference is determined.

[0021] Alternatively, the second short-term driving behavior semantic sequence can be divided into multiple equal windows, and the semantic label corresponding to each equal window can be determined. The first driving behavior and its corresponding duration in any equal window can be determined. Based on the first correspondence between the semantic label, the first driving behavior, the duration corresponding to the first driving behavior, and the behavior type difference, the second identical driving behavior type difference can be determined.

[0022] Furthermore, the method for determining the difference between the first and second different driving behavior types is as follows:

[0023] The first short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. At least one equal window that does not contain the specified type is selected from all semantic labels. Based on the number of equal windows that do not contain the specified type, the total duration of all equal windows that do not contain the specified type, and the second correspondence between the behavior types, the first difference between different driving behavior types is determined.

[0024] Alternatively, the second short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. At least one equal window that does not contain the specified type is selected from all semantic labels, and the second difference between different driving behavior types is determined based on the number of equal windows that do not contain the specified type, the total duration of all equal windows that do not contain the specified type, and the second correspondence between the behavior types.

[0025] 2) Secondly, the present invention also provides a vehicle tracking identification system, the specific technical solution of which is as follows:

[0026] The determination module is used to: determine a first short-term driving behavior semantic sequence corresponding to a suspected tracking vehicle in a specified surrounding area of ​​the target vehicle and determine a second short-term driving behavior semantic sequence of the target vehicle. The first short-term driving behavior semantic sequence characterizes the driving behavior characteristics of the suspected tracking vehicle within a preset period, and the second short-term driving behavior semantic sequence characterizes the driving behavior characteristics of the target vehicle within a preset period.

[0027] The calculation module is used to: calculate the similarity between the first short-term driving behavior semantic sequence and the second short-term driving behavior semantic sequence, and when the similarity exceeds a threshold, identify the suspected tracking vehicle as a tracking vehicle.

[0028] Based on the above solution, the present invention can be further improved as follows.

[0029] Furthermore, the process for determining the similarity is as follows:

[0030] The first driving behavior type difference of the corresponding short-term driving behavior semantic sequence is determined based on the first short-term driving behavior semantic sequence. The first driving behavior type difference represents the duration ratio of different driving behavior types in the first short-term driving behavior semantic sequence.

[0031] The second driving behavior type difference of the corresponding short-term driving behavior semantic sequence is determined based on the second short-term driving behavior semantic sequence. The second driving behavior type difference represents the duration ratio of different driving behavior types in the second short-term driving behavior semantic sequence.

[0032] The similarity is determined based on the first driving behavior type difference and the second driving behavior type difference.

[0033] Furthermore, the method for determining the ratio of the first driving behavior type difference to the second driving behavior type difference is as follows:

[0034] Determine the first identical driving behavior type difference and the first different driving behavior type difference of the first short-term driving behavior semantic sequence, and average the first identical driving behavior type difference and the first different driving behavior type difference to obtain the first driving behavior type difference;

[0035] Alternatively, determine the second identical driving behavior type difference and the second different driving behavior type difference of the second short-term driving behavior semantic sequence, and perform averaging on the second identical driving behavior type difference and the second different driving behavior type difference to obtain the second driving behavior type difference.

[0036] Furthermore, the method for determining the first difference in the same driving behavior type or the second difference in the same driving behavior type is as follows:

[0037] The first short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. The first driving behavior and its corresponding duration in any equal window are determined. Based on the first correspondence between the semantic label, the first driving behavior, the duration corresponding to the first driving behavior, and the behavior type difference, the first same driving behavior type difference is determined.

[0038] Alternatively, the second short-term driving behavior semantic sequence can be divided into multiple equal windows, and the semantic label corresponding to each equal window can be determined. The first driving behavior and its corresponding duration in any equal window can be determined. Based on the first correspondence between the semantic label, the first driving behavior, the duration corresponding to the first driving behavior, and the behavior type difference, the second identical driving behavior type difference can be determined.

[0039] Furthermore, the method for determining the difference between the first and second different driving behavior types is as follows:

[0040] The first short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. At least one equal window that does not contain the specified type is selected from all semantic labels. Based on the number of equal windows that do not contain the specified type, the total duration of all equal windows that do not contain the specified type, and the second correspondence between the behavior types, the first difference between different driving behavior types is determined.

[0041] Alternatively, the second short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. At least one equal window that does not contain the specified type is selected from all semantic labels, and the second difference between different driving behavior types is determined based on the number of equal windows that do not contain the specified type, the total duration of all equal windows that do not contain the specified type, and the second correspondence between the behavior types.

[0042] 3) In a third aspect, the present invention also provides an electronic device, the electronic device including a processor coupled to a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor to enable the electronic device to perform any of the above methods.

[0043] 4) In a fourth aspect, the present invention also provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to enable a computer to implement any of the above methods.

[0044] It should be noted that the beneficial effects of the technical solutions of the second to fourth aspects of the present invention and their corresponding possible implementations can be found in the above description of the technical effects of the first aspect and its corresponding possible implementations, and will not be repeated here. Attached Figure Description

[0045] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0046] Figure 1 This is a flowchart illustrating a method for identifying a tracked vehicle according to an embodiment of the present invention.

[0047] Figure 2 This is a structural framework diagram of an electronic device according to the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0049] like Figure 1 As shown, an embodiment of the present invention provides a method for identifying tracked vehicles, comprising the following steps:

[0050] S1, determine the first short-term driving behavior semantic sequence corresponding to the suspected tracking vehicle in the designated surrounding area of ​​the target vehicle and determine the second short-term driving behavior semantic sequence of the target vehicle. The first short-term driving behavior semantic sequence characterizes the driving behavior characteristics of the suspected tracking vehicle within a preset period, and the second short-term driving behavior semantic sequence characterizes the driving behavior characteristics of the target vehicle within a preset period.

[0051] S2, calculate the similarity between the first short-term driving behavior semantic sequence and the second short-term driving behavior semantic sequence. When the similarity exceeds a threshold, the suspected tracking vehicle is identified as the tracking vehicle.

[0052] The beneficial effects of the vehicle tracking identification method provided by this invention are as follows:

[0053] By calculating the similarity between the short-term driving behavior semantic sequences of vehicles around the vehicle owner (suspected tracking vehicles) and the short-term driving behavior semantic sequences of the vehicle owner (target vehicle), tracking vehicles can be identified, significantly improving the accuracy and timeliness of tracking vehicle identification.

[0054] S1, determine a first short-term driving behavior semantic sequence corresponding to suspected tracking vehicles within a specified surrounding area of ​​the target vehicle, and determine a second short-term driving behavior semantic sequence of the target vehicle. The first short-term driving behavior semantic sequence characterizes the driving behavior characteristics of the suspected tracking vehicles within a preset period, and the second short-term driving behavior semantic sequence characterizes the driving behavior characteristics of the target vehicle within the preset period. Wherein:

[0055] The target vehicle refers to any motor vehicle for which a determination is to be made as to whether a tracking vehicle exists.

[0056] The designated surrounding area refers to any region within a radius of a preset distance centered on the target vehicle. It's important to note that there may be more than one designated surrounding area; the number of designated surrounding areas can be determined based on the processing capacity of the processing chip and the amount of data computation required.

[0057] Suspected tracked vehicles refer to motor vehicles or non-motor vehicles that appear in a designated surrounding area for a period of time exceeding a preset period.

[0058] The first short-term driving behavior semantic sequence refers to the driving behavior of the suspected tracked vehicle over a continuous period of time. Driving behavior refers to driving behavior characteristics, including but not limited to: speed, acceleration, etc.

[0059] The process of determining the semantic sequence of the first short-term driving behavior can include the following methods:

[0060] Based on video data collected by traffic cameras, semantic sequences of suspected tracked vehicle driving behavior are identified within the camera's capture area. These sequences are then processed by time-segmentation to obtain multiple equal-length window sequences, each representing the first short-term driving behavior semantic sequence. It is important to note that driving behavior recognition is performed on each window sequence to obtain a corresponding semantic label.

[0061] For example: TD(j) = {SP1, SP2, ..., SP} y}

[0062] Where TD(j) represents the semantic sequence of the first short-term driving behavior, SP i Let be the semantic label for the driving behavior of the i-th window (each window can correspond to multiple semantic labels), i = 1...y, where y is the number of windows processed in frames, j is used to identify the sequence number of vehicles around the driver, and SP i ={SC i SD i ST i SU i SE i};SC i Indicates the type of driving behavior (e.g., forward, backward, etc.), SD i This represents the driving semantic tag with the highest distribution rate among this driving behavior type. Driving behavior semantic tags are categorized according to driving behavior type, such as going straight, turning, accelerating, decelerating, stopping, and making a U-turn. ST i This indicates the duration segment with the highest proportion of duration distribution among the activity types of this driving behavior, SU i SE represents the duration segment with the highest distribution rate in this type of driving behavior. i This indicates the number of driving behavior segments with the highest distribution ratio.

[0063] The driving semantic tag, which has the highest distribution ratio among driving behavior types, can be determined in the following ways:

[0064] In the video data corresponding to the i-th window, determine the driving behavior type corresponding to the i-th window, such as forward. Determine all driving semantic labels corresponding to the i-th window, such as straight and acceleration. Determine the duration corresponding to each driving semantic label, such as straight for 3 seconds and acceleration for 1 second. At this time, the driving semantic label with the highest distribution ratio among the driving behavior types is straight.

[0065] The duration segment with the highest distribution ratio among driving behavior types refers to: the driving behavior type with the highest distribution ratio is straight driving. Assuming that straight driving is continuous for 1-3 seconds and acceleration is in the 4th second, then the duration segment with the highest distribution ratio among driving behavior types is 1-3 seconds.

[0066] The duration segment with the highest proportion of duration distribution among the various types of driving activities is 3 seconds.

[0067] The segment with the highest distribution rate of driving behavior refers to: 1.

[0068] The process of determining the second short-term driving behavior semantic sequence is the same as that of determining the first short-term driving behavior semantic sequence.

[0069] S2, calculate the similarity between the first short-term driving behavior semantic sequence and the second short-term driving behavior semantic sequence. When the similarity exceeds a threshold, the suspected tracking vehicle is identified as the tracking vehicle.

[0070] The process of calculating the similarity between the first short-term driving behavior semantic sequence and the second short-term driving behavior semantic sequence is as follows:

[0071] S21, calculate the difference in the same driving behavior type among short-term driving behavior semantic sequences, and then... i and TD k Given any two first short-term driving behavior semantic sequences, the difference in the same driving behavior type between the second and third short-term driving behavior semantic sequences is calculated in the same way as the difference in the same driving behavior type between the first and third short-term driving behavior semantic sequences. The following explanation uses the difference in the same driving behavior type between the first and third short-term driving behavior semantic sequences as an example:

[0072] S211, calculate the difference of a single identical driving behavior type. The difference of a single identical driving behavior type is calculated as the ratio of the time length difference corresponding to its (driving behavior semantic label) to the total window duration, expressed as:

[0073]

[0074] TD i and TD k These are the i-th short-term driving behavior semantic sequence and the k-th short-term driving behavior semantic sequence, respectively. i,j SC represents the type label of the j-th driving behavior in the i-th short-term driving behavior semantic sequence (i.e., the driving behavior type label; the behavior semantic sequence contains multiple driving behavior types). k,l |TD represents the type label of the l-th driving behavior in the semantic sequence of the k-th short-term driving behavior. i | indicates TD i The window length of the time window, Lthsim (SC i,j =s) represents TD i Or TD k The driving behavior type is s, and the driving behavior type difference (the difference between different driving behavior types can be expressed in various ways, such as Euclidean distance) is ST. i,j ST represents the duration segment with the highest proportion of duration distribution in the j-th driving behavior within the semantic sequence of the i-th short-term driving behavior type. k,l This represents the duration segment with the highest proportion of duration distribution in the l-th driving behavior within the semantic sequence of the k-th short-term driving behavior type; it should be noted that when calculating TD... i When the difference corresponds to the first identical driving behavior type, the denominator of the above formula is TD. i When calculating TD k When the difference corresponds to the second identical driving behavior type, the denominator of the above formula is TD. k The formulas for both are the same.

[0075] S212, If there are multiple identical driving behavior types in a short-term driving behavior semantic sequence, then the differences between each driving behavior type are summed. The differences between identical driving behavior types in a short-term driving behavior semantic sequence are expressed as:

[0076]

[0077] Dtype sim (TD i ,TD k ) represents a short-term driving behavior semantic sequence TD i and TD k The difference in the same driving behavior type, n is TD i and TD k The number of instances of the same driving behavior type s.

[0078] Step S22: Calculate the difference between different driving behavior types in the short-term driving behavior semantic sequence. Specifically, step S22 includes:

[0079] S221, calculate the difference between individual driving behavior types. The difference between individual driving behavior types is calculated as the ratio of the time length difference corresponding to its (driving behavior semantic label) to the total window duration, expressed as:

[0080]

[0081] Lth dif (SC i,j =s) represents TD i It contains but TD kThe ratio of the duration of driving behavior of type s to the total duration of the window;

[0082] S222, sum the differences between individual different driving behavior types to obtain the difference value between different driving behavior types. The difference between different driving behavior types in a short-time driving behavior semantic sequence is expressed as:

[0083]

[0084] Dtype dif (TD i ,TD k ) represents a short-term driving behavior semantic sequence TD i and TD k The difference between different driving behavior types, where n is TD i and TD k The number of different driving behavior types s.

[0085] Step S23: Calculate the driving behavior type difference of the short-term driving behavior semantic sequence. The driving behavior type difference of the short-term driving behavior semantic sequence is obtained by averaging the driving behavior type difference of the same driving behavior in the short-term driving behavior semantic sequence and the driving behavior type difference of different driving behavior in the short-term driving behavior semantic sequence, expressed as:

[0086]

[0087] DIS type (TD i ,TD k )∈[0,1], the smaller the value, the more representative the semantic sequence TD of driving behavior type. i and TD k The higher the similarity, the better. It should be further noted that TD... i and TD k Given the sequence of two vehicles, both vehicles were determined using the same semantic sequence method, which will not be elaborated here. The result obtained through the above similarity calculation can characterize the similarity between the two vehicles in terms of driving direction and synchronization. The higher the similarity, the higher the probability that the suspected tracking vehicle is indeed a tracking vehicle.

[0088] Furthermore, the process for determining the similarity is as follows:

[0089] The first driving behavior type difference of the corresponding short-term driving behavior semantic sequence is determined based on the first short-term driving behavior semantic sequence. The first driving behavior type difference represents the duration ratio of different driving behavior types in the first short-term driving behavior semantic sequence.

[0090] The second driving behavior type difference of the corresponding short-term driving behavior semantic sequence is determined based on the second short-term driving behavior semantic sequence. The second driving behavior type difference represents the duration ratio of different driving behavior types in the second short-term driving behavior semantic sequence.

[0091] The similarity is determined based on the first driving behavior type difference and the second driving behavior type difference.

[0092] Furthermore, the method for determining the ratio of the first driving behavior type difference to the second driving behavior type difference is as follows:

[0093] Determine the first identical driving behavior type difference and the first different driving behavior type difference of the first short-term driving behavior semantic sequence, and average the first identical driving behavior type difference and the first different driving behavior type difference to obtain the first driving behavior type difference;

[0094] Alternatively, determine the second identical driving behavior type difference and the second different driving behavior type difference of the second short-term driving behavior semantic sequence, and perform averaging on the second identical driving behavior type difference and the second different driving behavior type difference to obtain the second driving behavior type difference.

[0095] Furthermore, the method for determining the first difference in the same driving behavior type or the second difference in the same driving behavior type is as follows:

[0096] The first short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. The first driving behavior and its corresponding duration in any equal window are determined. Based on the first correspondence between the semantic label, the first driving behavior, the duration corresponding to the first driving behavior, and the behavior type difference, the first same driving behavior type difference is determined.

[0097] Alternatively, the second short-term driving behavior semantic sequence can be divided into multiple equal windows, and the semantic label corresponding to each equal window can be determined. The first driving behavior and its corresponding duration in any equal window can be determined. Based on the first correspondence between the semantic label, the first driving behavior, the duration corresponding to the first driving behavior, and the behavior type difference, the second identical driving behavior type difference can be determined.

[0098] Furthermore, the method for determining the difference between the first and second different driving behavior types is as follows:

[0099] The first short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. At least one equal window that does not contain the specified type is selected from all semantic labels. Based on the number of equal windows that do not contain the specified type, the total duration of all equal windows that do not contain the specified type, and the second correspondence between the behavior types, the first difference between different driving behavior types is determined.

[0100] Alternatively, the second short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. At least one equal window that does not contain the specified type is selected from all semantic labels, and the second difference between different driving behavior types is determined based on the number of equal windows that do not contain the specified type, the total duration of all equal windows that do not contain the specified type, and the second correspondence between the behavior types.

[0101] The specified type is a specific type selected by the user.

[0102] In the above embodiments, although the steps are numbered S1, S2, etc., they are only specific embodiments given by the present invention. Those skilled in the art can adjust the execution order of S1, S2, etc. according to the actual situation, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0103] The present invention also provides a vehicle tracking identification system, the specific technical solution of which is as follows:

[0104] The determination module is used to: determine a first short-term driving behavior semantic sequence corresponding to a suspected tracking vehicle in a specified surrounding area of ​​the target vehicle and determine a second short-term driving behavior semantic sequence of the target vehicle. The first short-term driving behavior semantic sequence characterizes the driving behavior characteristics of the suspected tracking vehicle within a preset period, and the second short-term driving behavior semantic sequence characterizes the driving behavior characteristics of the target vehicle within a preset period.

[0105] The calculation module is used to: calculate the similarity between the first short-term driving behavior semantic sequence and the second short-term driving behavior semantic sequence, and when the similarity exceeds a threshold, identify the suspected tracking vehicle as a tracking vehicle.

[0106] Based on the above solution, the present invention can be further improved as follows.

[0107] Furthermore, the process for determining the similarity is as follows:

[0108] The first driving behavior type difference of the corresponding short-term driving behavior semantic sequence is determined based on the first short-term driving behavior semantic sequence. The first driving behavior type difference represents the duration ratio of different driving behavior types in the first short-term driving behavior semantic sequence.

[0109] The second driving behavior type difference of the corresponding short-term driving behavior semantic sequence is determined based on the second short-term driving behavior semantic sequence. The second driving behavior type difference represents the duration ratio of different driving behavior types in the second short-term driving behavior semantic sequence.

[0110] The similarity is determined based on the first driving behavior type difference and the second driving behavior type difference.

[0111] Furthermore, the method for determining the ratio of the first driving behavior type difference to the second driving behavior type difference is as follows:

[0112] Determine the first identical driving behavior type difference and the first different driving behavior type difference of the first short-term driving behavior semantic sequence, and average the first identical driving behavior type difference and the first different driving behavior type difference to obtain the first driving behavior type difference;

[0113] Alternatively, determine the second identical driving behavior type difference and the second different driving behavior type difference of the second short-term driving behavior semantic sequence, and perform averaging on the second identical driving behavior type difference and the second different driving behavior type difference to obtain the second driving behavior type difference.

[0114] Furthermore, the method for determining the first difference in the same driving behavior type or the second difference in the same driving behavior type is as follows:

[0115] The first short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. The first driving behavior and its corresponding duration in any equal window are determined. Based on the first correspondence between the semantic label, the first driving behavior, the duration corresponding to the first driving behavior, and the behavior type difference, the first same driving behavior type difference is determined.

[0116] Alternatively, the second short-term driving behavior semantic sequence can be divided into multiple equal windows, and the semantic label corresponding to each equal window can be determined. The first driving behavior and its corresponding duration in any equal window can be determined. Based on the first correspondence between the semantic label, the first driving behavior, the duration corresponding to the first driving behavior, and the behavior type difference, the second identical driving behavior type difference can be determined.

[0117] Furthermore, the method for determining the difference between the first and second different driving behavior types is as follows:

[0118] The first short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. At least one equal window that does not contain the specified type is selected from all semantic labels. Based on the number of equal windows that do not contain the specified type, the total duration of all equal windows that do not contain the specified type, and the second correspondence between the behavior types, the first difference between different driving behavior types is determined.

[0119] Alternatively, the second short-term driving behavior semantic sequence is divided into multiple equal windows, and the semantic label corresponding to each equal window is determined. At least one equal window that does not contain the specified type is selected from all semantic labels, and the second difference between different driving behavior types is determined based on the number of equal windows that do not contain the specified type, the total duration of all equal windows that do not contain the specified type, and the second correspondence between the behavior types.

[0120] It should be noted that the beneficial effects of the vehicle tracking identification system provided in the above embodiments are the same as those of the vehicle tracking identification method described above, and will not be repeated here. Furthermore, the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, and will not be repeated here.

[0121] like Figure 2 As shown, an electronic device 300 according to an embodiment of the present invention includes a processor 320 coupled to a memory 310. The memory 310 stores at least one computer program 330, which is loaded and executed by the processor 320 to enable the electronic device 300 to implement any of the above-mentioned methods. Specifically:

[0122] The electronic device 300 can vary considerably due to differences in configuration or performance. It may include one or more processors 320 (Central Processing Units, CPUs) and one or more memories 310. The one or more memories 310 store at least one computer program 330, which is loaded and executed by the one or more processors 320 to enable the electronic device 300 to implement the vehicle tracking identification method provided in the above embodiments. Of course, the electronic device 300 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The electronic device 300 may also include other components for implementing device functions, which will not be elaborated upon here.

[0123] An embodiment of the present invention provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to enable a computer to implement any of the above-described methods.

[0124] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0125] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform any of the methods described above.

[0126] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0127] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product in one or more computer-readable media containing computer-readable program code.

[0128] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0129] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method of identifying a vehicle for tracking, characterized by, The method comprises the following steps: determining a first short-time driving behavior semantic sequence corresponding to a suspected tracking vehicle in a specified surrounding area of a target vehicle, the first short-time driving behavior semantic sequence representing driving behavior characteristics of the suspected tracking vehicle in a preset period; the determination process of the first short-time driving behavior semantic sequence comprises the following steps: determining a driving behavior semantic sequence of the suspected tracking vehicle in the collection area of the traffic camera according to the video data collected by the traffic camera, and obtaining a plurality of equal-length window sequences after time frame processing, each window being a first short-time driving behavior semantic sequence; calculating the similarity of the first short-time driving behavior semantic sequence and the second short-time driving behavior semantic sequence, and determining the suspected tracking vehicle as a tracking vehicle when the similarity exceeds a threshold value; the determination process of the similarity comprises the following steps: determining a first driving behavior type difference of the corresponding short-time driving behavior semantic sequence according to the first short-time driving behavior semantic sequence, the first driving behavior type difference representing the time length proportion of different driving behavior types in the first short-time driving behavior semantic sequence; determining a second driving behavior type difference of the corresponding short-time driving behavior semantic sequence according to the second short-time driving behavior semantic sequence, the second driving behavior type difference representing the time length proportion of different driving behavior types in the second short-time driving behavior semantic sequence; determining the similarity according to the first driving behavior type difference and the second driving behavior type difference; the determination method of the first driving behavior type difference / second driving behavior type difference comprises the following steps: determining a first same driving behavior type difference and a first different driving behavior type difference of the first short-time driving behavior semantic sequence, and performing average processing on the first same driving behavior type difference and the first different driving behavior type difference to obtain the first driving behavior type difference; alternatively, determining a second same driving behavior type difference and a second different driving behavior type difference of the second short-time driving behavior semantic sequence, and performing average processing on the second same driving behavior type difference and the second different driving behavior type difference to obtain the second driving behavior type difference; the determination method of the first same driving behavior type difference or the second same driving behavior type difference comprises the following steps: dividing the first short-time driving behavior semantic sequence into a plurality of equal division windows, determining a semantic label corresponding to each equal division window, determining a first driving behavior and a corresponding duration in any equal division window, and determining the first same driving behavior type difference based on a first correspondence relationship between the semantic label, the first driving behavior, the duration corresponding to the first driving behavior, and the behavior type difference. Or, the second short-time driving behavior semantic sequence is divided into multiple equal windows, and a semantic label corresponding to each equal window is determined, a first driving behavior in any equal window and a corresponding duration are determined, a first driving behavior type difference of the corresponding short-time driving behavior semantic sequence is determined according to the semantic label, the first driving behavior, the duration corresponding to the first driving behavior, and a first corresponding relationship between the behavior types, and a second driving behavior type difference of the corresponding short-time driving behavior semantic sequence is determined according to the second driving behavior type difference. The determination manner of the first driving behavior type difference or the second driving behavior type difference is that: The first short-time driving behavior semantic sequence is divided into multiple equal windows, and a semantic label corresponding to each equal window is determined, at least one equal window without a specified type is selected from all semantic labels, and a first driving behavior type difference is determined according to the number of equal windows without the specified type, a total duration corresponding to all equal windows without the specified type, and a second corresponding relationship between the behavior types. Or, the second short-time driving behavior semantic sequence is divided into multiple equal windows, and a semantic label corresponding to each equal window is determined, at least one equal window without a specified type is selected from all semantic labels, and a second driving behavior type difference is determined according to the number of equal windows without the specified type, a total duration corresponding to all equal windows without the specified type, and a second corresponding relationship between the behavior types.

2. An identification system for tracking vehicles, employing an identification method for tracking vehicles as claimed in claim 1, characterized in that The system comprises: The determination module is configured to determine a first short-time driving behavior semantic sequence corresponding to a suspected tracking vehicle in a specified surrounding area of a target vehicle and determine a second short-time driving behavior semantic sequence of the target vehicle, the first short-time driving behavior semantic sequence representing driving behavior characteristics of the suspected tracking vehicle in a preset period, and the second short-time driving behavior semantic sequence representing driving behavior characteristics of the target vehicle in the preset period; The calculation module is configured to calculate a similarity between the first short-time driving behavior semantic sequence and the second short-time driving behavior semantic sequence, and determine the suspected tracking vehicle as a tracking vehicle when the similarity exceeds a threshold value. The determination process of the similarity is that: A first driving behavior type difference of the corresponding short-time driving behavior semantic sequence is determined according to the first short-time driving behavior semantic sequence, and the first driving behavior type difference represents a time length proportion of different driving behavior types in the first short-time driving behavior semantic sequence; A second driving behavior type difference of the corresponding short-time driving behavior semantic sequence is determined according to the second short-time driving behavior semantic sequence, and the second driving behavior type difference represents a time length proportion of different driving behavior types in the second short-time driving behavior semantic sequence; The similarity is determined according to the first driving behavior type difference and the second driving behavior type difference. The determination manner of the first driving behavior type difference / second driving behavior type difference is that: determining a first same driving behavior type difference and a first different driving behavior type difference of the first short-time driving behavior semantic sequence, and performing an averaging process on the first same driving behavior type difference and the first different driving behavior type difference to obtain the first driving behavior type difference; or, determining a second same driving behavior type difference and a second different driving behavior type difference of a second short-time driving behavior semantic sequence, and performing an averaging process on the second same driving behavior type difference and the second different driving behavior type difference to obtain the second driving behavior type difference.

3. An electronic device, comprising: The electronic device includes a processor coupled with a memory, and the memory stores at least one computer program, which is loaded and executed by the processor to enable the electronic device to implement the method of claim 1.

4. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one computer program, which is loaded and executed by the processor to enable the computer to implement the method of claim 1.

Images