Vehicle identification method, vehicle identification device and computer storage medium

Abstract

The invention provides a vehicle identification method, a vehicle identification device and a computer storage medium. The vehicle identification method comprises the following steps: acquiring a to-be-identified vehicle track; extracting motion quantization characteristics of the vehicle track to be identified; obtaining a confidence score of the motion quantization feature; based on the confidence score and a preset vehicle identification model, obtaining a probability score of the to-be-identified vehicle trajectory; and determining a vehicle type corresponding to the to-be-identified vehicle track according to the probability score. According to the vehicle identification method, the vehicle identification model is designed, the type of the vehicle is judged according to the preset probability threshold value, the type of the vehicle can be rapidly determined through the real-time trajectory data, and the accuracy of vehicle identification is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle management technology, and in particular to a vehicle identification method, a vehicle identification device, and a computer storage medium. Background Art

[0002] Vehicle type recognition is an important part of intelligent traffic management systems and has a wide range of applications, such as traffic flow statistics, intelligent parking, and vehicle type detection. Therefore, robust vehicle type recognition methods are of great significance to intelligent transportation systems. Existing methods generally use technologies such as ultrasound and magnetic induction coils. However, with the development of imaging technology and the widespread use of traffic management cameras, image-based vehicle type recognition methods have become the main trend.

[0003] However, current vehicle type recognition methods all use artificially designed general visual features, which are not specialized for vehicle type recognition in intelligent traffic scenarios and cannot guarantee sufficient discrimination, so they may fail in complex scenarios. Summary of the invention

[0004] In order to solve the above technical problems, the present application proposes a vehicle identification method, a vehicle identification device and a computer storage medium.

[0005] In order to solve the above technical problems, the present application proposes a vehicle identification method, which includes: Obtain the trajectory of the vehicle to be identified; Extracting the motion quantification features of the to-be-identified vehicle trajectory; Obtaining a confidence score of the motion quantization feature; Based on the confidence score and a preset vehicle recognition model, obtaining a probability score of the to-be-recognized vehicle trajectory; The vehicle type corresponding to the to-be-identified vehicle trajectory is determined according to the probability score.

[0006] Wherein, after extracting the motion quantization feature of the to-be-identified vehicle trajectory, the vehicle identification method further comprises: Get a decay function that decays as the time distance from the current time increases; The motion quantization feature is attenuated using the attenuation function.

[0007] Wherein, obtaining the confidence score of the motion quantization feature includes: Obtaining a logarithmic function value of the motion quantization feature; The logarithmic function value is normalized by arctangent to obtain the confidence score.

[0008] Wherein, obtaining the trajectory of the vehicle to be identified includes: Acquire collected images of several collection points; Identify the vehicle image to be identified with the same license plate number in all collected images; Obtain a sequence of vehicles to be identified consisting of all images of vehicles to be identified; The to-be-identified vehicle trajectory is generated by using the to-be-identified vehicle sequence.

[0009] Wherein, the step of generating the trajectory of the vehicle to be identified by using the sequence of vehicles to be identified includes: Traversing adjacent vehicle trajectory points in the sequence of vehicles to be identified; One of the adjacent vehicle trajectory points whose acquisition time difference is within a preset time length and whose acquisition position difference is less than a preset distance threshold is eliminated to generate the vehicle trajectory to be identified.

[0010] Wherein, the step of generating the trajectory of the vehicle to be identified by using the sequence of vehicles to be identified includes: Acquire a target sequence to be identified, wherein the target sequence to be identified and the vehicle sequence to be identified have the same license plate number information; Determining a first fusion weight based on a first acquisition quality score of the target sequence to be identified; Determine a second fusion weight based on the second acquisition quality score of the vehicle sequence to be identified The to-be-identified target sequence and the to-be-identified vehicle sequence are fused by using the first fusion weight and the second fusion weight to generate the to-be-identified vehicle trajectory.

[0011] Wherein, the vehicle identification method further includes: Acquire the target sequence to be identified, and / or adjacent trajectory points in the target sequence to be identified; One of the adjacent trajectory points whose speed change is greater than a preset speed change threshold is removed.

[0012] The step of removing one of the adjacent trajectory points whose speed change is greater than a preset speed change threshold comprises: One of the adjacent track points whose speed change is greater than a preset speed change threshold and whose position angle change is greater than a preset angle change threshold is removed.

[0013] In order to solve the above technical problems, the present application also proposes a vehicle identification device, which includes a memory and a processor coupled to the memory; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the vehicle identification method as described above.

[0014] In order to solve the above technical problems, the present application also proposes a computer storage medium, which is used to store program data. When the program data is executed by a computer, it is used to implement the above vehicle identification method.

[0015] Compared with the prior art, the beneficial effects of the present application are: the vehicle identification device obtains the trajectory of the vehicle to be identified; extracts the motion quantification feature of the vehicle trajectory to be identified; obtains the confidence score of the motion quantification feature; obtains the probability score of the vehicle trajectory to be identified based on the confidence score and the preset vehicle identification model; and determines the vehicle type corresponding to the vehicle trajectory to be identified according to the probability score. Through the above vehicle identification method, a vehicle identification model is designed, and the type of vehicle is determined according to a preset probability threshold. The vehicle type can be quickly determined through real-time trajectory data, and the accuracy of vehicle identification is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 It is a flow chart of an embodiment of a vehicle identification method provided by the present application; Figure 2 It is a schematic diagram of the overall process of the vehicle identification method provided by this application; Figure 3 This is a flowchart of an embodiment of obtaining the trajectory of a vehicle to be identified provided by the present application; Figure 4 yes Figure 1 The specific flow chart of step S11 of the vehicle identification method shown; Figure 5 This is a flowchart of another embodiment of obtaining the trajectory of a vehicle to be identified provided by the present application; Figure 6 It is a schematic diagram of an embodiment of vehicle trajectory fusion and completion provided by the present application; Figure 7 It is a flowchart of an embodiment of an identification method of an online car-hailing identification model provided by the present application; Figure 8 It is a schematic diagram of the user interaction interface of the vehicle identification system; Fig. 9 It is a structural schematic diagram of an embodiment of a vehicle identification device provided by the present application; Fig.10 It is a structural diagram of an embodiment of a computer storage medium provided by the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] In order to solve the problem of how to quickly identify the type of vehicles and manage and dispatch them accurately and efficiently, the present application provides a vehicle identification system and method based on trajectory fusion.

[0020] It should be noted that the vehicle type determined by the vehicle identification method of the present application can be any vehicle type, including but not limited to: online-hailing vehicles, ambulances, fire trucks, etc. In the subsequent implementation examples, online-hailing vehicles will be used as an example.

[0021] The technologies involved in the vehicle identification method of this application include but are not limited to: Online car-hailing: Taxi booking via the Internet is a new mode of transportation that provides travel services by booking taxis or private cars on the Internet platform.

[0022] Collection: Technology that uses cameras installed at specific locations to automatically capture and record image or video data at a specific time point or time period.

[0023] Trajectory: The path or route that a vehicle moves along during a specific period of time, including a number and a sequence of GPS (Global Positioning System) coordinates.

[0024] RFM model: a commonly used analysis method for refined user operations. R (Recency) represents the time interval between the last consumption, F (Frequency) represents the consumption frequency, and M (Monetary) represents the consumption amount.

[0025] Long tail effect: The imbalance of data categories causes a small number of classes to account for the majority of samples, while the majority of classes have only a small number of samples, showing a long tail phenomenon in the quantity distribution diagram.

[0026] Please refer to Figure 1 and Figure 2 , Figure 1 is a flow chart of an embodiment of a vehicle identification method provided by the present application, Figure 2 It is a schematic diagram of the overall process of the vehicle identification method provided by this application.

[0027] The vehicle identification method of the present application is applied to a vehicle identification device, wherein the vehicle identification device of the present application can be a server, a terminal device, or a system in which a server and a terminal device cooperate with each other. Accordingly, the various parts included in the vehicle identification device, such as various units, subunits, modules, and submodules, can all be set in the server, can all be set in the terminal device, or can be set in the server and the terminal device respectively.

[0028] Furthermore, the above-mentioned server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules used to provide distributed servers, or it can be implemented as a single software or software module, which is not specifically limited here.

[0029] like Figure 1 As shown, the specific steps are as follows: Step S11: Obtain the trajectory of the vehicle to be identified.

[0030] In an embodiment of the present application, the vehicle identification device obtains real-time collected images from cameras at various collection points, and uses image recognition technology to extract vehicle targets in the collected images, as well as other identification targets that can assist in analyzing vehicle trajectories.

[0031] Among them, the vehicle identification device can use the collected image containing the target vehicle to generate the trajectory of the vehicle to be identified, which is used to determine the vehicle type of the target vehicle.

[0032] Specifically, the vehicle identification device obtains a vehicle trajectory data set, that is, obtains vehicle and vehicle target trajectory data collected at multiple collection points to construct a local vehicle data set. The vehicle target is other information on the vehicle, including but not limited to the marking style, unique identification, and temporary identification on the vehicle. The temporary identification can be an object in the vehicle identified through the window, such as a doll.

[0033] For details on the technical solution for obtaining the trajectory of the vehicle to be identified in this application, please refer to Figure 3 , Figure 3 It is a flowchart of an embodiment of obtaining the trajectory of a vehicle to be identified provided by the present application.

[0034] like Figure 3 As shown, first, the vehicle identification device generates a vehicle trajectory set and a vehicle target trajectory set. Due to the different types of collection points at different locations and sections, the vehicle data is mainly divided into the following two parts: the vehicle's driving trajectory is generated based on the license plate information collected at the collection point, and the vehicle trajectory set attributes should at least include but are not limited to the license plate number, collection point number, collection point coordinates, collection time, etc.; the vehicle target trajectory is generated based on the vehicle target data collected at the collection point, and the target attributes are identified with the help of target recognition technology, and the corresponding vehicle information is completed. The final vehicle target trajectory attributes should at least include but are not limited to the target number, license plate number, collection point number, collection point coordinates, collection time, etc. The trajectory data set can be updated in real time based on the newly added vehicle trajectory.

[0035] It should be noted that the captured images in the vehicle target trajectory set do not necessarily need to identify the license plate number, and may only identify the target number, that is, the vehicle target trajectory set is mainly created with the vehicle target as the trajectory core.

[0036] Furthermore, before performing vehicle identification, in order to improve the efficiency of vehicle identification, the vehicle identification device may first remove hotspot data from the above vehicle trajectory set and / or vehicle target trajectory set.

[0037] Specifically, in some popular areas or vehicle operation congestion areas, there may be a large number of collections of the same vehicle or the same vehicle target, resulting in data redundancy. Therefore, the continuous collection within a short period of time needs to be removed from the vehicle trajectory set and / or the vehicle target trajectory set. Specifically, the collection of the same vehicle or the same vehicle target can be sorted in descending order of time, and the time difference and distance change between the collections are calculated. For the trajectory sequence data of the same set, only the trajectory sequence data in which the position change of the collection point is greater than the preset distance threshold within the adjacent preset time is retained. For example, the vehicle identification device can only retain the collection data within the adjacent 5 minutes and the GPS change is greater than 100m.

[0038] The vehicle identification device can simultaneously extract a vehicle trajectory set and a vehicle target trajectory set. Given that the collection points at the current intersection have the function of collecting vehicles and vehicle targets, and can form a set based on vehicle targets to obtain real-name information, the vehicle identification device can choose to fuse the vehicle trajectory and the vehicle target trajectory to make up for the possible loss of vehicle trajectories, thereby making the vehicle trajectory more continuous and the feature information richer.

[0039] Please refer to Figure 4 and Figure 5 , Figure 4 yes Figure 1 The specific flow chart of step S11 of the vehicle identification method is shown in FIG. Figure 5 It is a flowchart of another embodiment of obtaining the trajectory of a vehicle to be identified provided by the present application.

[0040] like Figure 4 As shown, the specific steps are as follows: Step S111: obtaining a sequence of targets to be identified, wherein the sequence of targets to be identified and the sequence of vehicles to be identified have the same license plate number information.

[0041] In an embodiment of the present application, the vehicle identification device obtains a target sequence to be identified based on a vehicle target trajectory set, and obtains a vehicle sequence to be identified based on a vehicle trajectory set, and the above two sequences are associated through the same license plate number.

[0042] Furthermore, if Figure 5 As shown, before fusing and completing the vehicle trajectory, the vehicle identification device may further remove abnormal trajectory data in the target sequence to be identified and / or the vehicle sequence to be identified in order to improve the accuracy of the vehicle trajectory.

[0043] Due to the influence of collection angle, light and other reasons, there may be abnormal data in the vehicle and vehicle target trajectories, which will affect the subsequent model analysis. Therefore, it is necessary to clean the obtained vehicle trajectory data set and remove the abnormal trajectory data.

[0044] Taking the sequence of vehicles to be identified as an example, the vehicle identification device sorts the trajectory data of the sequence of vehicles to be identified according to the time sequence, and calculates the speed change and angle change between adjacent trajectory points. If the speed change and angle change exceed the preset threshold within a certain time interval, the adjacent trajectory points have trajectory abnormalities, and the data of the adjacent trajectory points are discarded.

[0045] Specifically, the speed anomaly calculation formula is as follows:

[0046] in, is the velocity change of adjacent trajectory points, is the speed change threshold.

[0047] Specifically, the angle anomaly calculation formula is as follows:

[0048] in, is the angle change of adjacent trajectory points, is the angle change threshold.

[0049] In summary, the vehicle identification device may choose to remove the abnormal speed trajectory points and / or abnormal angle trajectory points calculated above to update the sequence of vehicles to be identified.

[0050] Step S112: determining a first fusion weight based on the first acquisition quality score of the target sequence to be identified.

[0051] Step S113: Determine a second fusion weight based on the second acquisition quality score of the vehicle sequence to be identified.

[0052] In the embodiment of the present application, the vehicle identification device uses the target sequence to be identified to complete the vehicle trajectory fusion of the vehicle sequence to be identified. Specifically, due to the actual situation that the collection points are not fully covered, it is easy for the trajectory data to be blank for a long time or the trajectory to jump, resulting in the problem of low subsequent model recognition rate. Therefore, it is necessary to combine the vehicle collection data with the vehicle target collection data to fuse and complete the overall trajectory.

[0053] Specific as Figure 6 As shown, Figure 6 FIG. 1 is a schematic diagram of an embodiment of vehicle trajectory fusion and completion provided by the present application. Figure 6 As shown, the vehicle identification device identifies abnormal trajectory points in the vehicle trajectory through step S111, then removes the abnormal trajectory points first, and then fuses the vehicle trajectory and the vehicle target trajectory to obtain the final fused trajectory, that is, the vehicle trajectory to be identified shown in step S11.

[0054] Specifically, the vehicle recognition device obtains the vehicle trajectory and vehicle target trajectory under the same license plate. If the two trajectories use different coordinate systems, the coordinates need to be spatially transformed. The vehicle recognition device calculates the quality score for each image to evaluate the quality of the current acquisition, and calculates the average quality score of all acquired images in the two types of trajectories. and And normalized as the calculation weight for subsequent trajectory fusion.

[0055] Among them, the quality score of the collected images of the vehicle trajectory and the vehicle target trajectory can be evaluated by the image clarity and the integrity of the vehicle or vehicle target.

[0056] Therefore, the vehicle trajectory and vehicle target trajectory Respectively expressed as:

[0057] Step S114: using the first fusion weight and the second fusion weight, the target sequence to be identified and the vehicle sequence to be identified are fused to generate a trajectory of the vehicle to be identified.

[0058] Furthermore, the vehicle identification device obtains the overall trajectory time range, that is, the start time and end time of the vehicle trajectory to be identified:

[0059] The vehicle identification device interpolates and fuses the trajectories according to the calculated weights:

[0060] After the above processing, two or more trajectories corresponding to the license plate can be effectively merged into one trajectory to obtain complete vehicle operation trajectory information.

[0061] In this regard, the vehicle identification device can obtain a trajectory data sequence of each vehicle for multiple days by repeatedly performing the above processing flow on the vehicle trajectory data of different dates.

[0062] Step S12: extracting the motion quantitative features of the vehicle trajectory to be identified.

[0063] In the embodiments of this application, please continue to refer to Figure 5 The vehicle identification device constructs hotspot data, boarding and alighting points and other motion quantitative features based on the fused and completed trajectory of the vehicle to be identified. Among them, the motion quantitative features refer to the characteristics of the vehicle movement rules and vehicle movement points measured and evaluated by specific values ​​and indicators during the vehicle movement process, which are used to characterize the vehicle movement information.

[0064] Specifically, since online-hailing vehicles have a fixed driving pattern, which is characterized by frequent travel back and forth between hot spots and the boarding and alighting points are often concentrated in hot spots, the vehicle identification device can obtain the hot spots of vehicle travel through trajectory data based on this feature.

[0065] First, the vehicle identification device identifies parking spots by a time window-based method and obtains all parking spot data of the vehicle in one day. Specifically, the vehicle identification device sets a time window, and if the vehicle stays at a certain location for more than a threshold, the location is considered to be a parking spot.

[0066] Then, the vehicle identification device uses a clustering algorithm to identify hot spots in the trajectory and count the number of times the vehicle stops in the hot spots, such as the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm.

[0067] Finally, the vehicle identification device counts the driving frequency and total driving distance of the vehicle in different time periods (including morning and evening peak hours) to infer the number of trips of the vehicle. Specifically, the vehicle identification device can divide a day into 48 time intervals with an interval of 30 minutes, and count the number of times the same vehicle is collected in each time interval as the driving frequency of the vehicle.

[0068] Please continue reading Figure 7 , Figure 7 It is a flow chart of an embodiment of the identification method of the online car-hailing identification model provided in this application.

[0069] like Figure 7 As shown, the vehicle identification device quantifies the vehicle trajectory data, obtains the online car-hailing identification model, and identifies the vehicle according to the confidence level. Specifically, the vehicle identification device quantifies the vehicle trajectory data, and through RFM model analysis, the following three dimensional features can be obtained: Rencency feature, Frequency feature, and Monetary feature.

[0070] Specifically, the Rencency feature indicates the number of parking spots in the hotspot area in the most recent date of the vehicle trajectory set. The larger the number, the more active it is. The Frequency feature indicates the number of days in which the trajectory collection occurs within a certain period of the vehicle trajectory set. The higher the number, the more active it is. The Monetary feature indicates the driving frequency and total mileage of the vehicle trajectory set within a certain period. The higher the driving frequency and total mileage, the more active it is.

[0071] The features of each dimension above represent the accumulated behaviors in the past period of time. In order to make the behaviors more recent have a greater impact on the activity score, the vehicle identification device can also multiply the data of each day by a weight and then sum them up. This weight is a function that decays as the time increases. The specific decay formula is as follows:

[0072] in, represents the decay function, Represents the characteristics of any of the above dimensions.

[0073] Step S13: Obtain the confidence score of the motion quantization feature.

[0074] In the embodiment of the present application, in order to increase the discrimination of the data and avoid the long-tail effect of the data, the vehicle identification device processes the features extracted in step S12 through a function. Subsequently, the vehicle identification device performs arctangent normalization processing on the feature data to unify the data of different dimensions into the same dimension, which is convenient for the subsequent calculation of the trajectory judgment confidence score.

[0075] The specific calculation formula is as follows:

[0076] in, is the confidence score of each dimension feature.

[0077] Furthermore, since the present application can evaluate the motion quantitative features of different dimensions of the vehicle trajectory to be identified, the vehicle identification device needs to calculate the confidence score in a weighted manner, assign a weight to the score of each dimensional feature, and sum up to obtain the final confidence score that the target vehicle is an online car-hailing vehicle:

[0078] in, is the weight, which can be obtained through labeled data training or given manually.

[0079] Step S14: Based on the confidence score and the preset vehicle recognition model, the probability score of the to-be-recognized vehicle trajectory is obtained.

[0080] In the embodiment of the present application, the vehicle identification device can judge the vehicle trajectory through a binary classification / or multi-classification analysis model based on the vehicle confidence score obtained in step S13.

[0081] Specifically, the vehicle identification device can generate a vehicle judgment model through a logistic regression analysis method, map the output of the linear combination to between 0 and 1, and determine whether the vehicle is an online-hailing vehicle:

[0082] in, Represents the weight of the category on the input feature, which can be learned through training data; Represents the bias term, which can be regarded as a constant term of the model, used to adjust the baseline probability of each category; Represents the confidence score, which contains all the features of the vehicle trajectory to be identified. Each feature affects the model result through the above weights; Represents the total number of categories, which is 2 in the binary classification problem; Represents the probability that the vehicle is an online-hailing car.

[0083] Step S15: Determine the vehicle type corresponding to the to-be-identified vehicle trajectory according to the probability score.

[0084] In an embodiment of the present application, the vehicle identification device determines whether the vehicle is an online-hailing vehicle based on a probability threshold set for the online-hailing vehicle.

[0085] In other embodiments, the vehicle identification device may also set corresponding probability thresholds for other vehicle types, and the determination process thereof is as described in the above steps S11 to S15 and will not be described in detail here.

[0086] Furthermore, this application also provides a user interaction interface, please refer to Figure 8 , Figure 8 This is a schematic diagram of the user interface of the vehicle identification system. Figure 8 As shown, the user selects any vehicle in the vehicle details through the interactive interface, and the interactive interface displays the trajectory status in a graphical manner, as well as specific trajectory details, including the captured image of each trajectory point.

[0087] In the present application, the vehicle identification device obtains the trajectory of the vehicle to be identified; extracts the motion quantification feature of the trajectory of the vehicle to be identified; obtains the confidence score of the motion quantification feature; obtains the probability score of the trajectory of the vehicle to be identified based on the confidence score and a preset vehicle identification model; and determines the vehicle type corresponding to the trajectory of the vehicle to be identified according to the probability score. Through the above vehicle identification method, a vehicle identification model is designed, and the type of vehicle is determined according to a preset probability threshold. The vehicle type can be quickly determined through real-time trajectory data, and the accuracy of vehicle identification is improved.

[0088] The vehicle identification method of the present application fills in the gaps in trajectory data by combining multiple trajectories, making data utilization more efficient and identification more accurate.

[0089] The vehicle identification method of the present application utilizes real-time acquisition equipment such as video acquisition points that are laid out over a large area to achieve comprehensive regional coverage, avoid vehicle trajectories, and achieve real-time and accurate entity management.

[0090] The vehicle identification method of the present application designs an online car-hailing identification model to determine whether a vehicle is an online car-hailing vehicle based on a set probability threshold; it deeply integrates trajectory data, data mining technology and transportation services to effectively identify online car-hailing vehicles and improve traffic management efficiency.

[0091] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0092] In order to implement the above vehicle identification method, this application also proposes a vehicle identification device, please refer to Fig. 9 , Fig. 9 It is a structural schematic diagram of an embodiment of a vehicle identification device provided in the present application.

[0093] The vehicle identification device 400 of this embodiment includes a processor 41 , a memory 42 , an input / output device 43 , and a bus 44 .

[0094] The processor 41 , the memory 42 , and the input / output device 43 are respectively connected to the bus 44 . The memory 42 stores program data, and the processor 41 is used to execute the program data to implement the vehicle identification method described in the above embodiment.

[0095] In the embodiment of the present application, the processor 41 may also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip having the ability to process signals. The processor 41 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or the processor 41 may also be any conventional processor, etc.

[0096] This application also provides a computer storage medium, please continue to refer to Fig.10 , Fig.10 It is a schematic diagram of the structure of an embodiment of a computer storage medium provided in the present application. The computer storage medium 600 stores a computer program 61. When the computer program 61 is executed by a processor, it is used to implement the vehicle identification method of the above embodiment.

[0097] When the embodiments of the present application are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0098] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle identification method, characterized in that: The vehicle identification method comprises: Obtain the trajectory of the vehicle to be identified; Extracting the motion quantification features of the to-be-identified vehicle trajectory; Obtaining a confidence score of the motion quantization feature; Based on the confidence score and a preset vehicle recognition model, obtaining a probability score of the to-be-recognized vehicle trajectory; The vehicle type corresponding to the to-be-identified vehicle trajectory is determined according to the probability score.

2. The vehicle identification method according to claim 1, characterized in that: After extracting the motion quantization feature of the to-be-identified vehicle trajectory, the vehicle identification method further includes: Get a decay function that decays as the time distance from the current time increases; The motion quantization feature is attenuated using the attenuation function.

3. The vehicle identification method according to claim 1 or 2, characterized in that: The obtaining of the confidence score of the motion quantization feature comprises: Obtaining a logarithmic function value of the motion quantization feature; The logarithmic function value is normalized by arctangent to obtain the confidence score.

4. The vehicle identification method according to claim 1, characterized in that: The step of obtaining the trajectory of the vehicle to be identified comprises: Acquire collected images of several collection points; Identify the vehicle image to be identified with the same license plate number in all collected images; Obtain a sequence of vehicles to be identified consisting of all images of vehicles to be identified; The to-be-identified vehicle trajectory is generated by using the to-be-identified vehicle sequence.

5. The vehicle identification method according to claim 4, characterized in that: The step of generating the to-be-identified vehicle trajectory by using the to-be-identified vehicle sequence comprises: Traversing adjacent vehicle trajectory points in the sequence of vehicles to be identified; One of the adjacent vehicle trajectory points whose acquisition time difference is within a preset time length and whose acquisition position difference is less than a preset distance threshold is eliminated to generate the vehicle trajectory to be identified.

6. The vehicle identification method according to claim 4, characterized in that: The step of generating the to-be-identified vehicle trajectory by using the to-be-identified vehicle sequence comprises: Acquire a target sequence to be identified, wherein the target sequence to be identified and the vehicle sequence to be identified have the same license plate number information; Determining a first fusion weight based on a first acquisition quality score of the target sequence to be identified; Determine a second fusion weight based on the second acquisition quality score of the vehicle sequence to be identified The first fusion weight and the second fusion weight are used to fuse the to-be-identified target sequence and the to-be-identified vehicle sequence to generate the to-be-identified vehicle trajectory.

7. The vehicle identification method according to claim 6, characterized in that: The vehicle identification method further includes: Acquire the target sequence to be identified, and / or adjacent trajectory points in the target sequence to be identified; One of the adjacent trajectory points whose speed change is greater than a preset speed change threshold is removed.

8. The vehicle identification method according to claim 7, characterized in that: The step of removing one of the adjacent trajectory points whose speed change is greater than a preset speed change threshold comprises: One of the adjacent track points whose speed change is greater than a preset speed change threshold and whose position angle change is greater than a preset angle change threshold is removed.

9. A vehicle identification device, characterized in that: The vehicle identification device includes a memory and a processor coupled to the memory; The memory is used to store program data, and the processor is used to execute the program data to implement the vehicle identification method as described in any one of claims 1 to 8.

10. A computer storage medium, characterized in that: The computer storage medium is used to store program data, and when the program data is executed by a computer, it is used to implement the vehicle identification method according to any one of claims 1 to 8.

Images