An abnormal vehicle determination method and device, vehicle, and storage medium

Abstract

The application discloses a kind of determination method, device, vehicle and storage medium of abnormal vehicle.The method comprises: obtaining the first space-time trajectory feature of target section in the vehicle to be measured;Utilize template trajectory feature and the first space-time trajectory feature, determine the first group of internal relationship coefficient, wherein the template trajectory feature is determined according to the second space-time trajectory feature of sample vehicle in the target section, and the first group of internal relationship coefficient is used to represent the correlation degree of the template trajectory feature and the first space-time trajectory feature;According to the first group of internal relationship coefficient, determine whether the vehicle to be measured is abnormal vehicle.The technical scheme of the embodiment of the application comprehensively considers the space-time trajectory feature of vehicle in target section, compared with the traditional way of judging abnormal vehicle by relying on the speed of vehicle, consider more comprehensive and detection accuracy is higher, more manpower is saved.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and in particular to a method, apparatus, device, and storage medium for identifying abnormal vehicles. Background Technology

[0002] With the continuous development of information technology, intelligent transportation systems are an inevitable trend in future road management systems. Abnormal vehicle behavior detection at intersections is a crucial component of intelligent transportation systems, playing a vital role in improving transportation efficiency and ensuring road safety.

[0003] However, existing detection methods have significant drawbacks. One type of traditional abnormal vehicle detection method typically determines whether a vehicle is abnormal based on its speed relative to the speeds of other vehicles on the road. For example, if a vehicle's speed exceeds a set threshold, it is considered abnormal. However, vehicle speeds vary at different locations on the road, meaning that setting the threshold too strictly or too slack will lead to serious missed detections and false positives. Another type of traditional abnormal vehicle detection method fails to consider the differences in vehicle speed characteristics on the same road segment at different times. In other words, vehicle speed characteristics differ on the same road segment at different times. Manually setting speed thresholds for different time periods to detect abnormal vehicles would undoubtedly waste a lot of manpower, and the accuracy of the detection is difficult to guarantee. Summary of the Invention

[0004] This invention provides a method, apparatus, vehicle, and storage medium for identifying abnormal vehicles, in order to solve the problem of poor detection results for abnormal vehicles.

[0005] In a first aspect, the present invention provides a method for determining abnormal vehicles, comprising:

[0006] Obtain the first spatiotemporal trajectory features of the vehicle to be tested in the target road segment;

[0007] Using template trajectory features and the first spatiotemporal trajectory features, a first group of intra-group relation coefficients are determined, wherein the template trajectory features are determined based on the second spatiotemporal trajectory features of sample vehicles in the target road segment, and the first group of intra-group relation coefficients are used to characterize the correlation between the template trajectory features and the first spatiotemporal trajectory features;

[0008] The test vehicle is determined as an abnormal vehicle based on the relationship coefficient within the first group.

[0009] Secondly, the present invention provides a device for determining abnormal vehicles, comprising:

[0010] The feature acquisition module is used to acquire the first spatiotemporal trajectory features of the vehicle to be tested in the target road segment;

[0011] The relation coefficient determination module is used to determine the relation coefficient within a first group using the template trajectory features and the first spatiotemporal trajectory features, wherein the template trajectory features are determined based on the second spatiotemporal trajectory features of sample vehicles in the target road segment, and the relation coefficient within the first group is used to characterize the correlation between the template trajectory features and the first spatiotemporal trajectory features;

[0012] The abnormal vehicle determination module is used to determine whether the vehicle under test is an abnormal vehicle based on the relationship coefficient within the first group.

[0013] Thirdly, the present invention provides an electronic device comprising:

[0014] At least one processor;

[0015] and memory that is communicatively connected to at least one processor;

[0016] The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to perform the method for determining the abnormal vehicle described in the first aspect.

[0017] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a processor to execute the method for determining abnormal vehicles described in the first aspect.

[0018] The present invention provides a scheme for identifying abnormal vehicles. It acquires the first spatiotemporal trajectory features of a vehicle to be tested in a target road segment. Using template trajectory features and the first spatiotemporal trajectory features, a first intra-group correlation coefficient is determined. The template trajectory features are determined based on the second spatiotemporal trajectory features of sample vehicles in the target road segment. The first intra-group correlation coefficient characterizes the correlation between the template trajectory features and the first spatiotemporal trajectory features. Based on the first intra-group correlation coefficient, it is determined whether the vehicle to be tested is an abnormal vehicle. By adopting the above technical solution, template trajectory features that characterize the features of normal vehicles are determined using the spatiotemporal trajectory features of sample vehicles in the target road segment. These template trajectory features are then compared with the spatiotemporal trajectory features of subsequent vehicles to be tested in the same road segment to obtain an intra-group correlation coefficient characterizing the correlation between the trajectory features of the vehicle to be tested and the template trajectory features. This coefficient is used to identify abnormal vehicles. This scheme comprehensively considers the spatiotemporal features of vehicles, and compared with the traditional method of judging abnormal vehicles based on vehicle speed, it is more comprehensive, has higher detection accuracy, and saves manpower.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a method for determining abnormal vehicles according to Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart of a method for determining abnormal vehicles according to Embodiment 2 of the present invention;

[0023] Figure 3 This is a schematic diagram of an abnormal vehicle detection scenario provided in Embodiment 2 of the present invention;

[0024] Figure 4 This is a schematic diagram of the structure of an abnormal vehicle determination device according to Embodiment 3 of the present invention;

[0025] Figure 5 This is a structural schematic diagram of a vehicle provided according to Embodiment 4 of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. In the description of this invention, unless otherwise stated, "a plurality of" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist; for example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0028] Example 1

[0029] Figure 1 The flowchart of an embodiment of the present invention provides a method for determining abnormal vehicles. This embodiment is applicable to the detection of abnormal vehicles in traffic flow. The method can be executed by an abnormal vehicle determination device, which can be implemented in hardware and / or software. The abnormal vehicle determination device can be configured in an electronic device, which can be composed of two or more physical entities.

[0030] like Figure 1 As shown, the method for determining abnormal vehicles provided in Embodiment 1 of the present invention specifically includes the following steps:

[0031] S101. Obtain the first spatiotemporal trajectory features of the vehicle to be tested in the target road segment.

[0032] In this embodiment, the target road segment can be understood as a road segment equipped with a device capable of acquiring first spatiotemporal trajectory features, such as a smart camera or LiDAR. The first spatiotemporal trajectory features may include the distance between the position of the vehicle under test at each moment and its first position after entering the target road segment, as well as the corresponding time.

[0033] S102. Using the template trajectory features and the first spatiotemporal trajectory features, determine the first group intra-relation coefficient, wherein the template trajectory features are determined based on the second spatiotemporal trajectory features of the sample vehicles in the target road segment, and the first group intra-relation coefficient is used to characterize the correlation between the template trajectory features and the first spatiotemporal trajectory features.

[0034] In this embodiment, the template trajectory features can be spatiotemporal trajectory features pre-determined using the second spatiotemporal trajectory features of multiple sample vehicles in the target road segment. The second spatiotemporal trajectory features can include features of multiple trajectories, each of which may include the distance between the sample vehicle's position at each moment and its first position after entering the target road segment, as well as the corresponding moment. The average distance at each moment in the second spatiotemporal trajectory features can be calculated, and the correspondence between this average distance and the moment is determined as the template trajectory features. These template trajectory features can be understood as the trajectory features of a normal vehicle. A (first) intra-group correlation coefficient can be calculated between the template trajectory features and the first spatiotemporal trajectory features. This coefficient characterizes the correlation between the template trajectory features and the first spatiotemporal trajectory features. The larger the coefficient, the closer the spatiotemporal trajectory features of the vehicle under test are to the template trajectory features, and the greater the probability that the vehicle under test is normal.

[0035] S103. Determine whether the vehicle under test is an abnormal vehicle based on the relationship coefficient within the first group.

[0036] In this embodiment, if the correlation coefficient within the first group is greater than a set value, the vehicle under test can be identified as an abnormal vehicle; otherwise, the vehicle under test can be identified as a normal vehicle.

[0037] The method for determining abnormal vehicles provided in this invention is proprietary. The technical solution of this invention utilizes the spatiotemporal trajectory features of sample vehicles in a target road segment to determine template trajectory features that can characterize normal vehicles. These template trajectory features are then compared with the spatiotemporal trajectory features of subsequent vehicles to be tested in the same road segment to obtain an intra-group correlation coefficient characterizing the correlation between the trajectory features of the vehicles to be tested and the template trajectory features. This coefficient is used to determine abnormal vehicles. This solution comprehensively considers the spatiotemporal characteristics of vehicles, and compared with the traditional method of relying on vehicle speed to determine abnormal vehicles, it is more comprehensive, has higher detection accuracy, and saves manpower.

[0038] Optionally, the method for determining the template trajectory features includes: acquiring second spatiotemporal trajectory features of sample vehicles in the target road segment, wherein the second spatiotemporal trajectory features include the correspondence between the distances of multiple sample vehicles at different times and their initial positions, the initial position being the first position of the sample vehicle after entering the target road segment; for each time moment, determining a first cumulative value of the distances, and determining the quotient of the first cumulative value and the total number of trajectories, wherein the second spatiotemporal trajectory features contain spatiotemporal features of multiple sample trajectories, and the total number of trajectories is the total number of sample trajectories; and determining the correspondence between time and the quotient as the template trajectory features. The advantage of this setup is that, by utilizing the above method, template trajectory features that can characterize the trajectory features of normal vehicles are accurately determined.

[0039] For example, the second spatiotemporal trajectory features include the spatiotemporal features of multiple sample trajectories, and the spatiotemporal features of the sample trajectory of each sample vehicle can be represented as:

[0040] Tr={(l 1, t1),(l 2, t2),…,(l n, t n )}

[0041] Where t1, ..., t n Let l1, ..., l be the n time points after the sample vehicle enters the target road segment. n This represents the distance between the sample vehicle's position at the corresponding time (i.e., the position of the trajectory point) and its initial position. For example, l1 represents the distance between the sample vehicle's position at time t1 and its initial position. Template trajectory features It can be represented as:

[0042]

[0043]

[0044] in, Let be the average distance between the position of the sample vehicle at time j and its initial position, i.e., the quotient of the first cumulative value and the total number of trajectories, j = 1, ..., n. is the distance between the j-th trajectory point in the i-th trajectory and the initial position, and m is the number of sample trajectories included in the second spatiotemporal trajectory feature.

[0045] Example 2

[0046] Figure 2 This is a flowchart of a method for determining abnormal vehicles provided in Embodiment 2 of the present invention. The technical solution of the present invention is further optimized based on the above optional technical solutions, and provides a specific method for detecting abnormal vehicles.

[0047] Optionally, determining the intra-group correlation coefficient using the template trajectory features and the first spatiotemporal trajectory features includes: generating a trajectory matrix based on the template trajectory features and the first spatiotemporal trajectory features, and using the trajectory matrix to determine the target deviation from the mean square and the degrees of freedom, wherein the target deviation from the mean square includes the intra-group deviation and the inter-group deviation; using the target deviation from the mean square and the degrees of freedom to determine the target mean square, and using the target mean square to determine the intra-group correlation coefficient, wherein the target mean square includes the intra-group mean square and the inter-group mean square. The advantage of this configuration is that it accurately and quickly calculates the correlation between the template trajectory features and the first spatiotemporal trajectory features.

[0048] Optionally, determining whether the vehicle under test is an abnormal vehicle based on the first group's intra-group relationship coefficient includes: if the first group's intra-group relationship coefficient is less than a first preset threshold, then identifying the vehicle under test as a suspected abnormal vehicle; and filtering the suspected abnormal vehicles to obtain abnormal vehicles. The advantage of this setup is that by using a preset threshold to filter the first group's intra-group relationship coefficient, suspicious vehicles, i.e., suspected abnormal vehicles, can be quickly identified; and by further filtering the suspected abnormal vehicles, abnormal vehicles can be accurately identified.

[0049] Optionally, the above method further includes: updating the template trajectory features at preset update intervals using the third spatiotemporal trajectory features of new sample vehicles entering the target road segment. The advantage of this setting is that updating the template trajectory features using new spatiotemporal trajectory features allows for continuous adaptation of the template trajectory features to changing traffic conditions, ensuring the accuracy of identifying abnormal vehicles.

[0050] like Figure 2 As shown in Embodiment 2 of the present invention, a method for determining abnormal vehicles specifically includes the following steps:

[0051] S201. Obtain the first spatiotemporal trajectory features of the vehicle to be tested in the target road segment.

[0052] S202. Generate a trajectory matrix based on the template trajectory features and the first spatiotemporal trajectory features, and use the trajectory matrix to determine the target deviation and degrees of freedom.

[0053] The target deviation from the mean square includes the within-group deviation from the mean square and the between-group deviation from the mean square.

[0054] For example, if the template trajectory features are [(10,1),(10,2),(10,3),(10,4),(10,5),(9,6),(10,7)], and the first spatiotemporal trajectory features are [(10,1),(9,2),(10,3)], the first three feature data of the template trajectory features can be taken together with the first spatiotemporal trajectory features to generate a trajectory matrix. That is, the template trajectory features are truncated according to the dimension of the first spatiotemporal trajectory features, and then the trajectory matrix is...

[0055]

[0056] Then, using this trajectory matrix, the (target) deviation from the mean square and the degrees of freedom of these two sets of features can be calculated. The deviation from the mean square and the degrees of freedom can be calculated using industry-known methods, such as performing a first preset operation on the elements of the trajectory matrix. This first preset operation can include addition and multiplication, etc.

[0057] Optionally, determining the target deviation from the mean square and degrees of freedom using the trajectory matrix includes: determining the first square root of the cumulative sum of elements in each row of the trajectory matrix, and using the first square root to determine the within-group deviation from the mean square in the target deviation from the mean square, wherein the elements in the first row of the trajectory matrix are the template trajectory features, and the elements in the second row are the first spatiotemporal trajectory features; determining the second square root of the cumulative sum of elements in each column of the trajectory matrix, and using the second square root to determine the intermediate deviation from the mean square; using the within-group deviation from the mean square and the intermediate deviation from the mean square, determining the between-group deviation from the target deviation from the mean square, and determining the within-group degrees of freedom and between-group degrees of freedom according to the number of rows and columns of the trajectory matrix. The advantage of this configuration is that, by using the above method, the target deviation from the mean square and degrees of freedom can be accurately determined.

[0058] For example, the degrees of freedom within a group, v 组内 and the degrees of freedom between groups v 组间 The determination method can be:

[0059] v 组内 =b-1

[0060] v 组间 =(k-1)(b-1)

[0061] Where b is the number of within groups, i.e., the number of columns in the trajectory matrix, k is the number of intermediate groups, i.e., the number of rows in the trajectory matrix, and SS is the within-group deviation from the mean square. 组内 The determination method can be:

[0062]

[0063] Where, x p,q The feature data is located in the p-th row and q-th column of the trajectory matrix. Let be the cumulative sum of the elements in the p-th row of the trajectory matrix, K be the number of rows in the trajectory matrix, B be the number of columns in the trajectory matrix, ∑ be the cumulative sum sign, and C be the correction coefficient. The intermediate deviation from the mean square can be determined as follows:

[0064]

[0065] in, The sum of the elements in the q-th column of the trajectory matrix, and the inter-group deviation SS. 组间 The determination method can be:

[0066]

[0067] The correction coefficient C can be determined as follows:

[0068]

[0069] Where N is the number of elements in the trajectory matrix.

[0070] S203. Using the target deviation from the mean square and the degrees of freedom, determine the target mean square, and use the target mean square to determine the coefficients of the first group of relationships.

[0071] The target mean squared error includes the within-group mean squared error and the between-group mean squared error.

[0072] For example, the mean squared error within groups (MS) 组内 and the mean squared variance between groups (MS) 组间 The determination method can be:

[0073]

[0074]

[0075] The method for determining the intra-group relation coefficient (ICC) can be as follows:

[0076]

[0077] S204. If the correlation coefficient within the first group is less than the first preset threshold, the vehicle to be tested is identified as a suspected abnormal vehicle.

[0078] Specifically, (first) the intragroup relationship coefficient is generally greater than or equal to zero and less than or equal to 1. Generally, the confidence level of the intragroup relationship coefficient is greater than 0.75, and the confidence level of the intragroup relationship coefficient is less than 0.4. The first preset threshold can be 0.4.

[0079] S205. Screen suspected abnormal vehicles to identify abnormal vehicles.

[0080] For example, suspected abnormal vehicles can be further screened. For instance, if the correlation coefficient within the first group remains less than a third preset threshold for a certain period of time, vehicles with a correlation coefficient less than 0.2 are identified as abnormal vehicles. The third preset threshold can be less than or equal to the first preset threshold. Figure 3 This is a schematic diagram of an abnormal vehicle detection scenario. Figure 3 The detection equipment mentioned is the device that can acquire spatiotemporal trajectory features. Figure 3 The road segment in the text is the target road segment, and vehicles marked with BV are detected abnormal vehicles.

[0081] Optionally, the step of screening the suspected abnormal vehicles to obtain abnormal vehicles includes: determining multiple second-group intra-coefficients for the suspected abnormal vehicles within a preset time period, and performing curve fitting on the multiple second-group intra-coefficients to obtain curve fitting results, wherein the start time of the preset time period is later than or equal to the end time corresponding to the first spatiotemporal trajectory feature; and identifying vehicles among the suspected abnormal vehicles whose slope corresponding to the curve fitting results is less than a second preset threshold as abnormal vehicles. The advantage of this setting is that by determining the slope of the curve corresponding to the second-group intra-coefficients and using the second preset threshold to filter based on that slope, abnormal vehicles that consistently deviate from the group state can be identified.

[0082] Specifically, the criterion for identifying an abnormal vehicle can be whether its intra-group correlation coefficient drops rapidly over a subsequent period. A rapid drop indicates that the vehicle exhibits uncorrected abnormal behavior during operation. The method for determining whether the intra-group correlation coefficient drops rapidly is as follows: within a preset time period, fit the second intra-group correlation coefficient of the suspected abnormal vehicle. If the slope of the fitted curve is consistently less than a second preset threshold (e.g., consistently less than zero), it indicates that the suspected abnormal vehicle's driving state consistently deviates from the group state, and it can be marked as an abnormal vehicle. Otherwise, it is not marked.

[0083] Optionally, if the correlation coefficient within the first group is less than a fourth preset threshold, the vehicle under test is identified as an abnormal vehicle, wherein the fourth preset threshold may be less than the first preset threshold and the third preset threshold.

[0084] S206. At each preset update interval, the template trajectory features are updated using the third spatiotemporal trajectory features of new sample vehicles entering the target road segment.

[0085] Specifically, the characteristics of traffic flow on roads are not static; they constantly change with traffic flow characteristics, time, and seasons. Therefore, it is possible to adaptively learn the traffic flow characteristics within lanes. Since the traffic flow state is not abrupt, and the spatiotemporal trajectory characteristics of newly arriving vehicles can characterize the latest traffic flow state, the template trajectory characteristics can be updated using the third spatiotemporal trajectory characteristics of new sample vehicles.

[0086] For example, the template trajectory features can be updated in the following ways:

[0087]

[0088] in, For the updated template trajectory features, Tr old For the spatiotemporal trajectory features of the template trajectory features before the update, Tr new For the newly added spatiotemporal trajectory features, i.e., the third spatiotemporal trajectory features of the new sample vehicles, M is the number of sample trajectories in the template trajectory features before the update, E is the number of sample trajectories corresponding to the third spatiotemporal trajectory features, ∑Tr old This means that for each time point, Tr is determined separately. old The sum of multiple distances in ∑Tr new This means that for each time point, Tr is determined separately. new The sum of multiple distances in the equation.

[0089] The method for determining abnormal vehicles provided in this invention accurately and quickly calculates the correlation between template trajectory features and first spatiotemporal trajectory features. Then, by using a preset threshold to filter the correlation coefficients within the first group, suspicious vehicles, i.e. suspected abnormal vehicles, can be quickly identified. By further filtering suspected abnormal vehicles, abnormal vehicles can be accurately identified. Finally, the template trajectory features are updated using new spatiotemporal trajectory features, which can continuously adapt the template trajectory features to the ever-changing traffic flow, ensuring the accuracy of identifying abnormal vehicles.

[0090] Example 3

[0091] Figure 4 This is a schematic diagram of the structure of a device for determining abnormal vehicles provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: a feature acquisition module 301, a relationship coefficient determination module 302, and an abnormal vehicle determination module 303, wherein:

[0092] The feature acquisition module is used to acquire the first spatiotemporal trajectory features of the vehicle to be tested in the target road segment;

[0093] The relation coefficient determination module is used to determine the relation coefficient within a first group using the template trajectory features and the first spatiotemporal trajectory features, wherein the template trajectory features are determined based on the second spatiotemporal trajectory features of sample vehicles in the target road segment, and the relation coefficient within the first group is used to characterize the correlation between the template trajectory features and the first spatiotemporal trajectory features;

[0094] The abnormal vehicle determination module is used to determine whether the vehicle under test is an abnormal vehicle based on the relationship coefficient within the first group.

[0095] The device for identifying abnormal vehicles provided in this invention uses the spatiotemporal trajectory features of sample vehicles in a target road segment to determine template trajectory features that can characterize the characteristics of normal vehicles. It then compares these template trajectory features with the spatiotemporal trajectory features of subsequent vehicles to be tested in the same road segment to obtain an intra-group correlation coefficient that characterizes the correlation between the trajectory features of the vehicles to be tested and the template trajectory features. This coefficient is used to identify abnormal vehicles. This solution comprehensively considers the spatiotemporal characteristics of vehicles, and compared to the traditional method of relying on vehicle speed to determine abnormal vehicles, it is more comprehensive, has higher detection accuracy, and saves manpower.

[0096] Optionally, the method for determining the template trajectory features includes: acquiring second spatiotemporal trajectory features of sample vehicles in the target road segment, wherein the second spatiotemporal trajectory features include the correspondence between the distances of multiple sample vehicles at different times and their initial positions, the initial position being the first position of the sample vehicle after entering the target road segment; for each time moment, determining a first cumulative value of the distances, and determining the quotient of the first cumulative value and the total number of trajectories, wherein the second spatiotemporal trajectory features contain spatiotemporal features of multiple sample trajectories, the total number of trajectories being the total number of sample trajectories; and determining the correspondence between time and the quotient as the template trajectory features.

[0097] Optionally, the relationship coefficient determination module includes:

[0098] The deviation from the mean square and degree of freedom determination unit is used to generate a trajectory matrix based on the template trajectory features and the first spatiotemporal trajectory features, and to determine the target deviation from the mean square and degree of freedom using the trajectory matrix, wherein the target deviation from the mean square includes within-group deviation from the mean square and between-group deviation from the mean square;

[0099] The target mean square error determination unit is used to determine the target mean square error using the target deviation from the mean square error and the degrees of freedom, and to determine the first group within-group relation coefficient using the target mean square error, wherein the target mean square error includes the within-group mean square error and the between-group mean square error.

[0100] Furthermore, determining the target deviation from the mean square and degrees of freedom using the trajectory matrix includes: determining the first square root of the sum of the elements in each row of the trajectory matrix, and using the first square root to determine the within-group deviation from the mean square in the target deviation from the mean square, wherein the elements in the first row of the trajectory matrix are the template trajectory features, and the elements in the second row are the first spatiotemporal trajectory features; determining the second square root of the sum of the elements in each column of the trajectory matrix, and using the second square root to determine the intermediate deviation from the mean square; using the within-group deviation from the mean square and the intermediate deviation from the mean square, determining the between-group deviation from the target deviation from the mean square, and determining the within-group degrees of freedom and between-group degrees of freedom according to the number of rows and columns of the trajectory matrix.

[0101] Optionally, the abnormal vehicle determination module includes:

[0102] A suspected abnormal vehicle determination unit is used to determine the vehicle under test as a suspected abnormal vehicle if the relationship coefficient within the first group is less than a first preset threshold.

[0103] An abnormal vehicle identification unit is used to screen the suspected abnormal vehicles and identify the abnormal vehicles.

[0104] Furthermore, the step of screening the suspected abnormal vehicles to obtain abnormal vehicles includes: determining multiple second-group intra-coefficients of the suspected abnormal vehicles within a preset time period, and performing curve fitting on the multiple second-group intra-coefficients to obtain curve fitting results, wherein the start time of the preset time period is later than or equal to the end time corresponding to the first spatiotemporal trajectory feature; and identifying vehicles among the suspected abnormal vehicles whose slope corresponding to the curve fitting results is less than a second preset threshold as abnormal vehicles.

[0105] Optionally, the device may also include:

[0106] The update module is used to update the template trajectory features at preset update intervals using the third spatiotemporal trajectory features of new sample vehicles entering the target road segment.

[0107] The abnormal vehicle determination device provided in this embodiment of the invention can execute the abnormal vehicle determination method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0108] Example 4

[0109] Figure 5A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0110] like Figure 5 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 and a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded from storage unit 48 into the RAM 43. The RAM 43 can also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0111] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0112] Processor 41 may include various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as methods for identifying abnormal vehicles.

[0113] In some embodiments, the method for determining abnormal vehicles may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the method for determining abnormal vehicles described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the method for determining abnormal vehicles by any other suitable means (e.g., by means of firmware).

[0114] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0115] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0116] The computer equipment provided above can be used to execute the abnormal vehicle determination method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0117] Example 5

[0118] In the context of this invention, the computer-readable storage medium may be a tangible medium, and the computer-executable instructions, when executed by a computer processor, are used to perform a method for determining an abnormal vehicle, the method comprising:

[0119] Obtain the first spatiotemporal trajectory features of the vehicle to be tested in the target road segment;

[0120] Using template trajectory features and the first spatiotemporal trajectory features, a first group of intra-group relation coefficients are determined, wherein the template trajectory features are determined based on the second spatiotemporal trajectory features of sample vehicles in the target road segment, and the first group of intra-group relation coefficients are used to characterize the correlation between the template trajectory features and the first spatiotemporal trajectory features;

[0121] The test vehicle is determined as an abnormal vehicle based on the relationship coefficient within the first group.

[0122] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by, or in conjunction with, an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0123] The computer equipment provided above can be used to execute the abnormal vehicle determination method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0124] It is worth noting that in the embodiments of the above-mentioned abnormal vehicle determination device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0125] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for identifying abnormal vehicles, characterized in that, include: Obtain the first spatiotemporal trajectory features of the vehicle to be tested in the target road segment; Using template trajectory features and the first spatiotemporal trajectory features, a first group of intra-group relation coefficients are determined, wherein the template trajectory features are determined based on the second spatiotemporal trajectory features of sample vehicles in the target road segment, and the first group of intra-group relation coefficients are used to characterize the correlation between the template trajectory features and the first spatiotemporal trajectory features; Determine whether the vehicle under test is an abnormal vehicle based on the relationship coefficient within the first group; The step of determining the intra-group relation coefficients using template trajectory features and the first spatiotemporal trajectory features includes: A trajectory matrix is ​​generated based on the template trajectory features and the first spatiotemporal trajectory features, and the target deviation and degrees of freedom are determined using the trajectory matrix, wherein the target deviation includes within-group deviation and between-group deviation. Using the target deviation from the mean square and the degrees of freedom, the target mean square is determined, and the first group relationship coefficient is determined using the target mean square, wherein the target mean square includes the within-group mean square and the between-group mean square; The step of determining whether the vehicle under test is an abnormal vehicle based on the intra-group relation coefficient includes: If the correlation coefficient within the first group is less than the first preset threshold, the vehicle under test is identified as a suspected abnormal vehicle. The suspected abnormal vehicles were screened to identify the abnormal vehicles; The process of screening the suspected abnormal vehicles to identify abnormal vehicles includes: Determine multiple second-group intra-correlation coefficients of the suspected abnormal vehicle within a preset time period, and perform curve fitting on the multiple second-group intra-correlation coefficients to obtain curve fitting results, wherein the start time of the preset time period is later than or equal to the end time corresponding to the first spatiotemporal trajectory feature. Vehicles whose slope corresponding to the curve fitting result among the suspected abnormal vehicles is less than the second preset threshold are identified as abnormal vehicles.

2. The method according to claim 1, characterized in that, The method for determining the template trajectory features includes: The second spatiotemporal trajectory features of sample vehicles in the target road segment are obtained, wherein the second spatiotemporal trajectory features include the correspondence between the distance and time between the positions of multiple sample vehicles at different times and their initial positions, and the initial position is the first position of the sample vehicle after entering the target road segment; For each moment, a first cumulative value of the distance is determined, and the quotient of the first cumulative value and the total number of trajectories is determined, wherein the second spatiotemporal trajectory feature includes the spatiotemporal features of multiple sample trajectories, and the total number of trajectories is the total number of sample trajectories; The correspondence between time and the quotient is determined as the template trajectory feature.

3. The method according to claim 1, characterized in that, The step of determining the target's deviation from the mean square and degrees of freedom using the trajectory matrix includes: The first square root of the sum of the elements in each row of the trajectory matrix is ​​determined, and the first square root is used to determine the within-group deviation from the mean square in the target deviation from the mean square, wherein the first row of the trajectory matrix is ​​the template trajectory feature, and the second row of the trajectory matrix is ​​the first spatiotemporal trajectory feature. Determine the second square root of the cumulative sum of the elements in each column of the trajectory matrix, and use the second square root to determine the mean square deviation. Using the within-group deviation from the mean square and the intermediate deviation from the mean square, the between-group deviation from the target mean square is determined, and the within-group degrees of freedom and between-group degrees of freedom are determined according to the number of rows and columns of the trajectory matrix.

4. The method according to claim 1, characterized in that, Also includes: At preset update intervals, the template trajectory features are updated using the third spatiotemporal trajectory features of new sample vehicles entering the target road segment.

5. A device for identifying abnormal vehicles, characterized in that, include: The feature acquisition module is used to acquire the first spatiotemporal trajectory features of the vehicle to be tested in the target road segment; The relation coefficient determination module is used to determine the relation coefficient within a first group using the template trajectory features and the first spatiotemporal trajectory features, wherein the template trajectory features are determined based on the second spatiotemporal trajectory features of sample vehicles in the target road segment, and the relation coefficient within the first group is used to characterize the correlation between the template trajectory features and the first spatiotemporal trajectory features; An abnormal vehicle determination module is used to determine whether the vehicle under test is an abnormal vehicle based on the relationship coefficient within the first group. The module for determining relationship coefficients includes: The deviation from the mean square and degree of freedom determination unit is used to generate a trajectory matrix based on the template trajectory features and the first spatiotemporal trajectory features, and to determine the target deviation from the mean square and degree of freedom using the trajectory matrix, wherein the target deviation from the mean square includes within-group deviation from the mean square and between-group deviation from the mean square; The target mean square error determination unit is used to determine the target mean square error using the target deviation from the mean square error and the degrees of freedom, and to determine the first group within-group relation coefficient using the target mean square error, wherein the target mean square error includes the within-group mean square error and the between-group mean square error; The abnormal vehicle identification module includes: A suspected abnormal vehicle determination unit is used to determine the vehicle under test as a suspected abnormal vehicle if the relationship coefficient within the first group is less than a first preset threshold. An abnormal vehicle identification unit is used to screen the suspected abnormal vehicles and identify abnormal vehicles. The step of screening the suspected abnormal vehicles to obtain abnormal vehicles includes: determining multiple second-group intra-correlation coefficients of the suspected abnormal vehicles within a preset time period, and performing curve fitting on the multiple second-group intra-correlation coefficients to obtain curve fitting results, wherein the start time of the preset time period is later than or equal to the end time corresponding to the first spatiotemporal trajectory feature; and identifying vehicles among the suspected abnormal vehicles whose slope corresponding to the curve fitting results is less than a second preset threshold as abnormal vehicles.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining the abnormal vehicle according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining an abnormal vehicle as described in any one of claims 1-4.

Images