A vehicle re-identification method, device and equipment

Abstract

Embodiments of the present specification disclose a vehicle re-identification method, device and equipment. The method comprises: obtaining a first vehicle re-identification result between each of first vehicles corresponding to a first vehicle data set; generating a preset identifier for reflecting whether vehicle re-identification processing is continued between any two first vehicles according to the first vehicle re-identification result between each of the first vehicles, to obtain a preset identifier set; and performing vehicle re-identification processing between at least part of second vehicles corresponding to a second vehicle data set to be processed according to the preset identifier set, to obtain a second vehicle re-identification result. The scheme can reduce the amount of calculation in the vehicle re-identification processing, to save the computing resources of a vehicle re-identification server.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, and in particular to a vehicle re-identification method, device and equipment. BACKGROUND

[0002] The roadside perception device is mainly used for sensing the related vehicle data of the vehicle on the road. In order to ensure the continuity of the perception data, when deploying the roadside perception device, the perception areas of the adjacent roadside perception devices will have a part of the overlapping area. When any vehicle is located in the overlapping area, the vehicle will be sensed by two or more roadside perception devices at the same time. Or, if the vehicle tracked and sensed by the roadside perception device is also tracked and sensed by the vehicle-mounted perception device installed on the vehicle itself or other vehicles, the roadside perception device and / or the vehicle-mounted perception device will send the vehicle data collected in this data collection period to the server. Therefore, there will be repeated vehicle data in the vehicle data received by the server. Before the server analyzes and processes the received vehicle data, the vehicle data of the repeated vehicle needs to be identified and fused.

[0003] In the prior art, for the vehicle data of each vehicle received by the server in any batch, the server will perform a re-identification calculation between any two vehicles when performing vehicle re-identification, which results in a large amount of calculation in the vehicle re-identification process and causes a waste of the computing resources of the vehicle re-identification server.

[0004] Therefore, how to reduce the amount of calculation in the vehicle re-identification process to save the computing resources of the vehicle re-identification server has become a technical problem to be solved. SUMMARY

[0005] The vehicle re-identification method, device and equipment provided by the embodiments of the present application can solve the problem of large amount of calculation in the vehicle re-identification process and waste of the computing resources of the vehicle re-identification server.

[0006] To solve the above technical problem, the embodiments of the present application are implemented as follows:

[0007] A vehicle re-identification method, comprising,

[0008] Obtaining a first vehicle re-identification result between each first vehicle corresponding to a first vehicle data set, the first vehicle re-identification result reflecting the similarity between the vehicle data of each first vehicle.

[0009] According to the first vehicle re-identification result between each of the first vehicles, a preset identifier for reflecting whether vehicle re-identification processing is continued between any two of the first vehicles is generated, and a preset identifier set is obtained.

[0010] A second vehicle data set to be subjected to vehicle re-identification processing is acquired.

[0011] According to the preset identifier set, vehicle re-identification processing is performed between at least part of the second vehicles corresponding to the second vehicle data set, and a second vehicle re-identification result is obtained.

[0012] A vehicle re-identification device comprises,

[0013] A first acquisition module is configured to acquire a first vehicle re-identification result between each of first vehicles corresponding to a first vehicle data set, the first vehicle re-identification result being used to reflect a similarity between vehicle data of each of the first vehicles.

[0014] A generation module is configured to generate, according to the first vehicle re-identification result between each of the first vehicles, a preset identifier for reflecting whether vehicle re-identification processing is continued between any two of the first vehicles, and obtain a preset identifier set.

[0015] A second acquisition module is configured to acquire a second vehicle data set to be subjected to vehicle re-identification processing.

[0016] A processing module is configured to perform, according to the preset identifier set, vehicle re-identification processing between at least part of second vehicles corresponding to the second vehicle data set, and obtain a second vehicle re-identification result.

[0017] A vehicle re-identification device comprises,

[0018] at least one processor; and

[0019] a memory connected with the at least one processor in communication; wherein

[0020] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0021] acquire a first vehicle re-identification result between each of first vehicles corresponding to a first vehicle data set, the first vehicle re-identification result being used to reflect a similarity between vehicle data of each of the first vehicles.

[0022] generate, according to the first vehicle re-identification result between each of the first vehicles, a preset identifier for reflecting whether vehicle re-identification processing is continued between any two of the first vehicles, and obtain a preset identifier set.

[0023] Obtain a second vehicle data set to be processed for vehicle re-identification.

[0024] According to the preset identifier set, vehicle re-identification is performed between at least part of the second vehicles corresponding to the second vehicle data set, and a second vehicle re-identification result is obtained.

[0025] At least one embodiment provided in the specification can achieve the following beneficial effects:

[0026] In this scheme, first, according to each vehicle re-identification result obtained by the server performing vehicle re-identification calculation between each first vehicle corresponding to the first vehicle data set, a preset identifier set is generated. Then, according to the preset identifier set, vehicle re-identification is performed between at least part of the second vehicles corresponding to the second vehicle data set to be processed for vehicle re-identification. Without performing vehicle re-identification processing between each second vehicle corresponding to the second vehicle data set respectively, the vehicle re-identification calculation amount between each second vehicle corresponding to the second vehicle data set can be reduced, so as to save the calculation resources of the vehicle re-identification server. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the specification or the prior art, the drawings needed to be used in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0028] Figure 1 A flowchart of a vehicle re-identification method provided by an embodiment of the specification;

[0029] Figure 2 A two-dimensional array diagram provided by an embodiment of the specification;

[0030] Figure 3 An effect diagram of adding and deleting elements of a two-dimensional array provided by an embodiment of the specification;

[0031] Figure 4 A structural diagram of a vehicle re-identification device corresponding to Figure 1 provided by an embodiment of the specification;

[0032] Figure 5 A structural diagram of a vehicle re-identification device corresponding to Figure 1 provided by an embodiment of the specification. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of one or more embodiments of the present specification clearer, the technical solutions of one or more embodiments of the present specification will be described clearly and completely below in conjunction with specific embodiments of the present specification and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present specification, rather than all the embodiments. Based on the embodiments in the present specification, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of one or more embodiments of the present specification.

[0034] The technical solutions provided by the embodiments of the present application will be described in detail below in conjunction with the drawings.

[0035] Figure 1 A flowchart of a vehicle re-identification method provided by an embodiment of the present specification is shown. From the perspective of the program, the execution subject of the flowchart can be a device with a vehicle re-identification function, or an application program loaded on the device with the vehicle re-identification function. As shown in the figure, the flowchart can include the following steps: Figure 1

[0036] Step 102: Obtain a first vehicle re-identification result between each first vehicle corresponding to a first vehicle data set; the first vehicle re-identification result is used to reflect the similarity between the vehicle data of each first vehicle.

[0037] In an embodiment of the present specification, a server for vehicle re-identification can receive vehicle data uploaded by a perception device in a preset area at a preset time interval. The perception device can include a perception device in a roadside computing unit and / or a perception device in a vehicle-mounted computing unit. The perception device in the roadside computing unit can be a device installed on the roadside with the function of collecting relevant driving data of vehicles or pedestrians on the road; the perception device in the vehicle-mounted computing unit can be a device installed on the vehicle that can collect relevant driving data of the vehicle itself, other vehicles or pedestrians. The preset time interval can be 100 milliseconds, or other time intervals can also be selected according to the performance of the server. The preset area can be a service area set according to the processing performance of the server. The better the server processing performance, the larger the range of the preset area.

[0038] In an embodiment of the present specification, the first vehicle data set can be composed of any one batch of vehicle data received by the server from at least part of the perception devices in the preset area covered by the server. Any one vehicle data in the first vehicle data set can include at least one of vehicle identification, vehicle location, vehicle data collection time, vehicle heading angle, vehicle speed, etc. Each vehicle data can correspond to a first vehicle, and the first vehicle re-identification result between each first vehicle can be obtained for each first vehicle corresponding to the first vehicle data set.​

[0039] In the embodiments of the present specification, the first vehicle re-identification result between any two first vehicles can be obtained in two ways. The first way can be: if the server has generated a vehicle re-identification result for the any two first vehicles within the last batch, the corresponding first vehicle re-identification result can be directly obtained from the server; the second way can be: using a preset algorithm to calculate the first vehicle re-identification result. The preset algorithm can be any one of the algorithms for calculating the Mahalanobis distance, Euclidean distance, Manhattan distance, Chebyshev distance, and Minkowski distance between vehicles according to the vehicle data of each vehicle, and the first vehicle re-identification result obtained by the algorithm can represent the corresponding distance between the two first vehicles. The closer the distance between the two first vehicles, the greater the possibility that the two first vehicle data corresponding to the two first vehicles are repeated vehicle data. Therefore, any first vehicle re-identification result can be used to reflect the similarity between the corresponding two vehicle data.

[0040] It should be noted that the two first vehicles corresponding to any vehicle re-identification result do not belong to the same perception device tracked and perceived vehicle. That is, when the server performs vehicle re-identification, it does not perform vehicle re-identification processing between vehicles tracked and perceived by the same perception device.

[0041] Step 104: According to the first vehicle re-identification result between each of the first vehicles, generate a preset identifier for reflecting whether vehicle re-identification processing is continued between any two first vehicles, and obtain a preset identifier set.

[0042] In the embodiments of the present specification, the preset identifier can be an identifier for reflecting whether vehicle re-identification processing is continued between two first vehicles. The format of the preset identifier can be various, wherein the preset identifier can be an identifier in the format of any number, symbol or character, such as a combination of 0 and 1, a combination of + and -, a combination of any two English letters, or a combination of any two symbols. Taking the combination of 0 and 1 as an example, when the preset identifier is 1, it can indicate that vehicle re-identification processing is continued between the two first vehicles, and when the preset identifier is 0, it can indicate that vehicle re-identification processing is not continued between the two first vehicles. The preset identifier can also be an identifier in other formats, which will not be described one by one here.

[0043] Step 106: Obtain a second vehicle data set to be processed for vehicle re-identification.

[0044] In the embodiments of the present specification, the vehicle re-identification processing can be a kind of identification processing method for determining whether two vehicles are the same vehicle for a preset number of vehicles. The second vehicle data set can be any batch of vehicle data set received by the server for vehicle re-identification processing. The time when the server receives the second vehicle data set can be later than or earlier than the time when the first vehicle data set is received. The present application does not limit the receiving time of the server receiving the second vehicle data set, as long as the second vehicle data set is the vehicle data set set by the server for vehicle re-identification processing.

[0045] Step 108: According to the preset identification set, vehicle re-identification processing is performed between at least part of the second vehicles corresponding to the second vehicle data set, and a second vehicle re-identification result is obtained.

[0046] In the embodiments of the present specification, the preset identification set is iteratively queried, and according to the preset identification for continuing vehicle re-identification processing queried from the preset identification set, vehicle re-identification processing is performed between at least part of the second vehicles corresponding to the second vehicle data set, and a second vehicle re-identification result is obtained. If no preset identification for reflecting the need to continue vehicle re-identification processing is queried in the preset identification set, vehicle re-identification processing is not performed between any two second vehicles corresponding to the second vehicle data set; if no preset identification for reflecting the prohibition of continuing vehicle re-identification processing is queried in the preset identification set, vehicle re-identification processing is performed between any two second vehicles corresponding to the second vehicle data set; if part of the preset identification for reflecting the need to continue vehicle re-identification processing is queried in the preset identification set, the second vehicle corresponding to the part of the preset identification for reflecting the need to continue vehicle re-identification processing is determined from the second vehicle data set according to the part of the preset identification for reflecting the need to continue vehicle re-identification processing, and vehicle re-identification processing is only performed between the determined associated second vehicles, without the need to perform vehicle re-identification processing between each second vehicle corresponding to the second vehicle data set.

[0047] Figure 1 The method in the above embodiment can be used for vehicle re-identification processing. According to the preset identification set, vehicle re-identification processing is only performed between part of the second vehicles corresponding to the second vehicle data set, without the need to perform vehicle re-identification processing between each second vehicle corresponding to the second vehicle data set, so as to reduce the calculation amount in the vehicle re-identification processing process, thereby saving the calculation resources of the vehicle re-identification server.

[0048] Based on the above Figure 1The method in the first aspect of the present application, and some specific embodiments of the method are provided in the present specification, which are described below.

[0049] Since the first vehicle re-identification results of each of the first vehicles are different after the vehicle re-identification processing between the first vehicles, the preset identifiers generated according to the different first vehicle re-identification results are also different. Based on this, step 104: according to the first vehicle re-identification results between each of the first vehicles, a preset identifier for reflecting whether the vehicle re-identification processing continues between any two of the first vehicles is generated, and a preset identifier set is obtained, which can specifically include:

[0050] If the first vehicle re-identification result between any two of the first vehicles is greater than or equal to a preset threshold, a first preset identifier for reflecting that the vehicle re-identification processing is prohibited to continue between the two first vehicles is generated.

[0051] If the first vehicle re-identification result between any two of the first vehicles is less than a preset threshold, a second preset identifier for reflecting that the vehicle re-identification processing is instructed to continue between the two first vehicles is generated.

[0052] In the present specification, the first vehicle re-identification result can be used to represent the distance between two first vehicles. When the distance between two first vehicles is greater than or equal to a preset threshold, it can be considered that the two first vehicles are not the same vehicle, and for the two first vehicles that are not the same vehicle, a first preset identifier for reflecting that the vehicle re-identification processing is prohibited to continue between the two first vehicles can be generated. Similarly, when the distance between two first vehicles is less than a preset threshold, it can be considered that it cannot be determined whether the two first vehicles are the same vehicle, and for the two first vehicles that cannot be determined whether they are the same vehicle, a second preset identifier for reflecting that the vehicle re-identification processing is instructed to continue between the two first vehicles can be generated.

[0053] It should be noted that after each of the first vehicle re-identification results is obtained for each of the first vehicles corresponding to the first vehicle data set, the repeated first vehicles can be matched according to the weighted Hungarian algorithm. If two first vehicles are repeated first vehicles, a second preset identifier for reflecting that the vehicle re-identification processing is instructed to continue between the two repeated first vehicles will also be generated. This is because sometimes the vehicle data collected by the perception device can be incorrect vehicle data, so the result that the two first vehicles are repeated vehicles calculated using the incorrect vehicle data is an incorrect result. In order to avoid this incorrect result, the calculation for the two repeated first vehicles needs to continue in the next batch. Therefore, for the two repeated first vehicles, a second preset identifier for reflecting that the vehicle re-identification processing needs to continue will also be generated.

[0054] It should be further noted that when the server detects that two first vehicles are both tracked and perceived vehicles of the same perception device, the server can not generate a preset identifier for the two first vehicles, or the server can directly generate a first preset identifier reflecting that the vehicle re-identification processing is prohibited for the two first vehicles without vehicle re-identification processing for the two first vehicles.

[0055] In the embodiments of the present specification, when the first vehicle re-identification result between the two first vehicles is greater than or equal to a preset threshold, the vehicle re-identification processing is prohibited for the two first vehicles, and when the first vehicle re-identification result between the two first vehicles is less than the preset threshold, the vehicle re-identification processing is still needed for the two first vehicles. Thus, the accuracy of determining whether the vehicle re-identification processing is performed between two vehicles can be improved.

[0056] After generating each first preset identifier or each second preset identifier according to each first vehicle re-identification result, each first preset identifier or each second preset identifier is counted to obtain a preset identifier set. In order to facilitate subsequent query of the preset identifier between any two first vehicles, a two-dimensional array can be used to count each first preset identifier or each second preset identifier. Based on this, the preset identifier set is a first two-dimensional array, and any element in the first two-dimensional array is Aij, where i represents a first vehicle with a preset vehicle index i, j represents a first vehicle with a preset vehicle index j, and Aij represents a preset identifier of whether the vehicle re-identification processing is continued between the first vehicle with the preset vehicle index i and the first vehicle with the preset vehicle index j.

[0057] The vehicle re-identification processing is performed between at least part of the second vehicles corresponding to the second vehicle data set according to the preset identifier set, and a second vehicle re-identification result is obtained, specifically including:

[0058] The vehicle re-identification processing is performed between at least part of the second vehicles corresponding to the second vehicle data set according to the first two-dimensional array, and a second vehicle re-identification result is obtained.

[0059] In the embodiments of the present specification, a two-dimensional array is essentially a matrix with rows and columns. The position of each element in the two-dimensional array can be represented by a row number and a column number. Assuming that a two-dimensional array A[i][j] is defined, this two-dimensional array is an i-row j-column two-dimensional array. Any element Aij in it represents an element at the intersection of the ith row and the jth column.

[0060] In the embodiments of the present specification, according to the first vehicle data, a preset vehicle index is respectively set for each corresponding first vehicle. When the preset vehicle index is respectively set for each first vehicle corresponding to the first vehicle data set, the preset vehicle index can be sequentially set according to the order of the collection time of each first vehicle data, and each preset vehicle index can be each continuous natural number obtained by sequentially adding 1 from 0. Alternatively, each preset vehicle index can also be each continuous natural number obtained by sequentially adding 1 from any natural number. The preset vehicle index of any first vehicle is a preset vehicle index with uniqueness. It should be noted that when the preset vehicle index is respectively set for each first vehicle corresponding to the first vehicle data set, the preset vehicle index can also be sequentially set according to the order of the sending time or the receiving time of each first vehicle data.

[0061] As shown in Figure 2 , the two-dimensional array can be a two-dimensional array of 9 rows and 9 columns, 0., 1., 2., and 3. can represent the preset vehicle index, and the corresponding vehicles are: the vehicle with a preset vehicle index of 0., the vehicle with a preset vehicle index of 1., the vehicle with a preset vehicle index of 2., and the vehicle with a preset vehicle index of 3. It should be noted that in order to distinguish "0 and 1" in the preset vehicle index from "0 and 1" in the two-dimensional array elements, Figure 2 , the preset vehicle index 0., 1., 2., and 3. are used to represent the preset vehicle index 0, 1, 2, and 3. It should be noted that the two-dimensional array can also not display each preset vehicle index. When each preset vehicle index is not displayed in the two-dimensional array, the server needs to establish a correspondence between the preset vehicle index and the rows and columns in the two-dimensional array, such as the preset vehicle index n corresponds to the L row and the L column in the two-dimensional array, and the preset vehicle index m corresponds to the P row and the P column in the two-dimensional array. When the preset identification between the vehicle corresponding to the preset vehicle index n and the vehicle corresponding to the preset vehicle index m needs to be queried, the corresponding element at the intersection of the L row and the P column or the P row and the L column in the two-dimensional array can be queried. In the present specification, Figure 2 is a two-dimensional array that displays each preset vehicle index in the two-dimensional array.

[0062] In the embodiments of the present specification, when generating each element in the two-dimensional array, the server determines the corresponding two vehicles according to the two preset vehicle indexes corresponding to each element, and then determines the specific content of the element according to the vehicle re-identification processing result generated between the two vehicles. As shown in Figure 2As shown in the middle, any one element "1" in the two-dimensional array can represent a second preset identifier for reflecting that the vehicle re-identification processing is continued between the corresponding two vehicles; any one element "0" in the two-dimensional array can represent a first preset identifier for reflecting that the vehicle re-identification processing is prohibited between the corresponding two vehicles; any one element "n / a" in the two-dimensional array can represent an element a at the intersection position of the row and the column in which the preset vehicle index of the same vehicle is located, and the server will not perform the vehicle re-identification processing on the vehicle corresponding to the element a, regardless of whether the element a is "0" or "1".

[0063] In the embodiments of the present specification, for any one element Aij in the two-dimensional array, assuming that i represents a first vehicle with a preset vehicle index i and j represents a first vehicle with a preset vehicle index j, Aij represents a preset identifier of whether the vehicle re-identification processing is continued between the first vehicle with the preset vehicle index i and the first vehicle with the preset vehicle index j. It should be noted that if i is equal to j, any one element Aij in the two-dimensional array can be a preset identifier for the same vehicle, and at this time, the server does not perform the vehicle re-identification processing on the vehicle corresponding to Aij.

[0064] In the embodiments of the present specification, after obtaining the first two-dimensional array according to the vehicle re-identification processing results of each first vehicle, when determining whether the vehicle re-identification processing needs to be continued between any two second vehicles corresponding to the second vehicle data set, the corresponding element can be queried from the first two-dimensional array, and it is determined whether the vehicle re-identification processing needs to be continued between the any two second vehicles according to the queried element. If the queried element is the second preset identifier, the vehicle re-identification processing is continued between the any two second vehicles, and the second vehicle re-identification result is obtained. If the queried element is the first preset identifier, the vehicle re-identification processing is not continued between the any two second vehicles.

[0065] The preset identifier set is set as a two-dimensional array, and for any two vehicles, the corresponding element can be conveniently and quickly queried from the two-dimensional array, so that the convenience of determining whether the vehicle re-identification processing needs to be continued between any two vehicles can be improved.

[0066] Specifically, the vehicle re-identification processing is performed between at least part of the second vehicles corresponding to the second vehicle data set according to the first two-dimensional array, and the second vehicle re-identification result is obtained, which can include:

[0067] determining a difference vehicle set between a first vehicle set corresponding to the first vehicle data set and a second vehicle set corresponding to the second vehicle data set; the difference vehicle set contains first difference vehicles belonging to the second vehicle set but not belonging to the first vehicle set, and / or second difference vehicles belonging to the first vehicle set but not belonging to the second vehicle set.

[0068] adding each first element corresponding to each of the first difference vehicles in the first two-dimensional array to obtain a second two-dimensional array; one first element is used to reflect a preset identifier indicating whether vehicle re-identification processing is needed between any first vehicle and the first difference vehicle, or one first element is used to reflect a preset identifier indicating whether vehicle re-identification processing is needed between any other difference vehicle in the difference vehicle set and the first difference vehicle.

[0069] deleting each second element corresponding to each of the second difference vehicles in the second two-dimensional array to obtain a third two-dimensional array; one second element is used to reflect a preset identifier indicating whether vehicle re-identification processing is needed between any first vehicle and the second difference vehicle, or one second element is used to reflect a preset identifier indicating whether vehicle re-identification processing is needed between any first difference vehicle and the second difference vehicle.

[0070] performing vehicle re-identification processing between at least part of the second vehicles corresponding to the second vehicle data set according to the third two-dimensional array to obtain a second vehicle re-identification result.

[0071] In the embodiments of the present specification, each perception device can be provided with a certain perception area. In different data collection periods, the actual vehicles that can be perceived by the perception device in the perception area are usually not fixed, some vehicles can drive out of the perception area at a certain moment, so that the perception information of the perception device for these driving-out vehicles will disappear; at the same time, some vehicles can drive into the perception area at a certain moment, so that the perception information of the perception device will add the information of these driving-in vehicles. The first vehicle set can be a vehicle set composed of each first vehicle corresponding to the first vehicle data set, and the second vehicle set can be a vehicle set composed of each second vehicle corresponding to the second vehicle data set. Since the first vehicle data set and the second vehicle data set are different batches of vehicle data sets received by the server, the first vehicle set and the second vehicle set are usually not completely consistent. By comparing each first vehicle in the first vehicle set with each second vehicle in the second vehicle set respectively, the difference vehicle set between the first vehicle set and the second vehicle set is determined. The difference vehicle set can be composed of each first difference vehicle and each second difference vehicle, the first difference vehicle can be a vehicle that only exists in the second vehicle set and does not exist in the first vehicle set, and the second difference vehicle can be a vehicle that only exists in the first vehicle set and does not exist in the second vehicle set.

[0072] In the embodiments of the present specification, each element in the first two-dimensional array is a preset identifier generated between each first vehicle in the first vehicle set, so the first vehicle corresponding to each element in the first two-dimensional array does not include the first difference vehicle. Each first element corresponding to each first difference vehicle is added in the first two-dimensional array. Since each first difference vehicle is a newly added vehicle relative to the first vehicle set, i.e., vehicle re-identification processing has not been performed between any first difference vehicle and each first vehicle in the first vehicle set, vehicle re-identification processing needs to be performed between any first difference vehicle and any first vehicle. Therefore, the newly added first element can be used to reflect the preset identifier that vehicle re-identification processing needs to be performed between any first vehicle and any first difference vehicle.

[0073] In addition, vehicle re-identification processing has not been performed between each first difference vehicle, i.e., vehicle re-identification processing needs to be performed between each first difference vehicle. Therefore, the newly added first element can also be used to reflect the preset identifier that vehicle re-identification processing needs to be performed between any two first difference vehicles.

[0074] It should be noted that the newly added first element can also be used to reflect the preset identifier generated for the same first difference vehicle, whether the preset identifier generated for the same first difference vehicle indicates that vehicle re-identification processing needs to be continued or not, the server does not perform vehicle re-identification processing for the same first difference vehicle.

[0075] In the embodiments of the present specification, after adding each first element to the first two-dimensional array, a second two-dimensional array can be obtained. The second difference vehicle is a vehicle that does not exist in the second vehicle set, and therefore, when determining whether vehicle re-identification needs to be continued between each second vehicle in the second vehicle set, in order to avoid the interference of the element corresponding to the second difference vehicle, each second element corresponding to each second difference vehicle in the second two-dimensional array also needs to be deleted. The deleted second element can be used to reflect the preset identifier between any second difference vehicle and any first vehicle whether vehicle re-identification processing is needed, or can be used to reflect the preset identifier between any second difference vehicle and any first difference vehicle whether vehicle re-identification processing is needed, or can be used to reflect the preset identifier generated for the same second difference vehicle.

[0076] In the embodiments of the present specification, after deleting each second element from the second two-dimensional array, a third two-dimensional array can be obtained, and when determining whether vehicle re-identification needs to be continued between any two second vehicles corresponding to the second vehicle data set, the corresponding element can be queried from the third two-dimensional array, and whether vehicle re-identification needs to be continued between the any two second vehicles is determined according to the queried element. If the queried element is the second preset identifier, vehicle re-identification is continued between the any two second vehicles, and a second vehicle re-identification result is obtained. If the queried element is the first preset identifier, vehicle re-identification is not continued between the any two second vehicles.

[0077] Each element in the third two-dimensional array is a preset identifier generated for each second vehicle in the second vehicle set, and does not include a preset identifier generated for each second difference vehicle that does not exist in the second vehicle set, so that when determining whether vehicle re-identification needs to be continued between each second vehicle in the second vehicle set, the interference of the element corresponding to the second difference vehicle can be avoided, thereby improving the accuracy of the second vehicle re-identification result.

[0078] When querying the preset identifier corresponding to two vehicles in the two-dimensional array, the corresponding element of the two vehicles needs to be queried from the two-dimensional array according to the preset vehicle index, and the queried element is the preset identifier to be queried. Therefore, in order to improve the accuracy of the query result, the preset vehicle index set for each vehicle in the two-dimensional array needs to be a unique index. Based on this, before obtaining the first vehicle re-identification result between each first vehicle corresponding to the first vehicle data set, the method can further include:

[0079] Obtaining each first vehicle identifier carried by each first vehicle data in the first vehicle data set; wherein the first vehicle identifier corresponds to the first vehicle one by one.

[0080] generating a preset vehicle index for each of the first vehicles.

[0081] establishing an association between the first vehicle identifier of each of the first vehicles and the preset vehicle index generated for each of the first vehicles.

[0082] In the embodiments of the present specification, the first vehicle identifier can be an identifier determined for the first vehicle that is different from other first vehicles, and the first vehicle identifier and the first vehicle are in one-to-one correspondence. The first vehicle identifier can be a vehicle ID, and the first vehicle IDs carried in the first vehicle data perceived by different perception devices for the same first vehicle are different.

[0083] In the embodiments of the present specification, an association can be established between the first vehicle identifier of each of the first vehicles and the preset vehicle index of the first vehicle. According to the association, the preset vehicle index of the first vehicle can be obtained according to the first vehicle identifier of the first vehicle, and the first vehicle identifier of the first vehicle can be obtained according to the preset vehicle index of the first vehicle.

[0084] After obtaining the vehicle identifiers of each vehicle, the difference vehicle set between the first vehicle set and the second vehicle set can be determined according to the vehicle identifiers. Based on this, after obtaining the second vehicle data set to be processed for vehicle re-identification, the method can further include:

[0085] obtaining each second vehicle identifier carried in each second vehicle data in the second vehicle data set.

[0086] The method can further include:

[0087] matching each first vehicle identifier and each second vehicle identifier to obtain a difference vehicle set and a target vehicle set; the difference vehicle set includes vehicles to which the first vehicle identifier or the second vehicle identifier that fails to match successfully belongs; and the target vehicle set includes second vehicles to which the second vehicle identifier that matches successfully belongs.

[0088] After determining the difference vehicle set between the first vehicle set corresponding to the first vehicle data set and the second vehicle set corresponding to the second vehicle data set, the method can further include:

[0089] The preset vehicle index with the specified first vehicle identifier and the association relationship is determined as the preset vehicle index of the specified second vehicle in the target vehicle set; wherein the specified second vehicle is the second vehicle to which the specified second vehicle identifier matches successfully with the specified first vehicle identifier.

[0090] The first element corresponding to each first difference vehicle is added in the first two-dimensional array, and the first element corresponding to each first difference vehicle is added in the first two-dimensional array.

[0091] The preset vehicle index of the first difference vehicle is generated.

[0092] According to the preset vehicle index of the first difference vehicle, each first element corresponding to the first difference vehicle is added in the first two-dimensional array.

[0093] In the embodiment of the present specification, for the second vehicle data set to be processed by vehicle re-identification, each second vehicle identifier carried by each second vehicle data in the second vehicle data set is obtained. Any one second vehicle identifier is selected, and the selected second vehicle identifier is matched with each first vehicle identifier. If one first vehicle identifier matches the selected second vehicle identifier successfully, the second vehicle corresponding to the selected second vehicle identifier is determined as a vehicle in the target vehicle set. If any one first vehicle identifier does not match the selected second vehicle identifier, the second vehicle corresponding to the selected second vehicle identifier is determined as a vehicle in the difference vehicle set. For each second vehicle identifier, one second vehicle identifier is selected each time until each second vehicle identifier is selected once. Each first vehicle identifier in the first vehicle identifier that does not match any second vehicle identifier is determined, and each first vehicle corresponding to the first vehicle identifier that does not match any second vehicle identifier is determined as a vehicle in the difference vehicle set.

[0094] In the embodiment of the present specification, the second vehicle identifier of each second vehicle in the target vehicle set is a vehicle identifier that matches a first vehicle identifier of a certain first vehicle successfully. Since the vehicle identifier and the vehicle are one-to-one, the first vehicle and the second vehicle corresponding to the matched first vehicle identifier and the second vehicle identifier are the same vehicle. Since each vehicle needs to be provided with a unique preset vehicle index, in order to ensure the uniqueness of the preset vehicle index of any vehicle, for the first vehicle and the second vehicle belonging to the same vehicle, the preset vehicle index of the second vehicle is determined as the preset vehicle index of the first vehicle corresponding to the first vehicle identifier that matches the second vehicle identifier of the second vehicle successfully.

[0095] In the embodiments of the present specification, the first difference vehicle is a vehicle that belongs to the second vehicle set but does not belong to the first vehicle set, that is, the first difference vehicle is a vehicle newly entering the perception area when the perception device perceives the second vehicle data. Since the first difference vehicles are all vehicles newly entering the perception area, the server has not set the preset vehicle index for the first difference vehicles. The process of setting the preset vehicle index for each first difference vehicle can be: first, determine the maximum preset vehicle index in each preset vehicle index corresponding to each first vehicle, and then sequentially add 1 to the maximum preset vehicle index to obtain each value, and sequentially determine each array obtained as the preset vehicle index of each first difference vehicle. In order to facilitate understanding, the following example is given: assuming that the maximum preset vehicle index determined from each preset vehicle index corresponding to each first vehicle is 20, if the number of first difference vehicles is 5, then sequentially add 1 to 20 for 5 times, and the values obtained are 21, 22, 23, 24, and 25. Each value 21, 22, 23, 24, and 25 is sequentially determined as the preset vehicle index corresponding to the five first difference vehicles. It should be noted that how each value 21, 22, 23, 24, and 25 corresponds to the above five first difference vehicles can refer to the way of determining the preset vehicle index of each first vehicle, which will not be described one by one here.

[0096] Specifically, according to the preset vehicle index of the first difference vehicle, the first element corresponding to the first difference vehicle can be added in the first two-dimensional array. Since the first difference vehicle is a newly added vehicle, each first element added in the first two-dimensional array can be the second preset identifier.

[0097] For the same vehicle in the period that can be continuously perceived by the perception device, the preset vehicle index of the vehicle in the two-dimensional array remains unchanged, thereby improving the accuracy of querying the corresponding preset identifier in the two-dimensional array according to the preset vehicle index.

[0098] The third two-dimensional array is a two-dimensional array after deleting each second element, and therefore, there is usually a scenario of a blank area between two elements in the third two-dimensional array. When querying the preset identifier, the server usually also queries and traverses for this blank area between two elements, thereby causing waste of server query resources. Therefore, the blank area between two elements in the third two-dimensional array needs to be handled accordingly. Based on this, after deleting each second element corresponding to each second difference vehicle in the second two-dimensional data to obtain the third two-dimensional array, the method can further include:

[0099] determining the target number of the second difference vehicles;

[0100] arranging the preset vehicle indexes of the second vehicles in descending order, and modifying the preset vehicle indexes of the target number of the second vehicles to the preset vehicle indexes of the target number of the second difference vehicles in descending order.

[0101] In the embodiments of the present specification, the second difference vehicle is a vehicle that exists in the first vehicle set but does not exist in the second vehicle set. That is, the second difference vehicle is a vehicle that has driven out of the perception area when the perception device perceives the second vehicle data. After deleting the corresponding second element of the second difference vehicle in the two-dimensional array, the blank area after deleting the second element needs to be maintained in a corresponding manner. The maintenance manner can be: first, determine the target number of all second difference vehicles, then modify the preset vehicle indexes of the target number of second vehicles to the preset vehicle indexes of the target number of second difference vehicles in descending order of the preset vehicle indexes of each second vehicle in the third two-dimensional array, and when modifying, modify in a one-to-one correspondence manner of the preset vehicle indexes of the target number of second vehicles and the preset vehicle indexes of the target number of second difference vehicles.

[0102] Specifically, as shown in Figure 3 , assuming that the vehicle with a preset vehicle index of 7 belongs to the first difference vehicle, according to the preset vehicle index 7, the two-dimensional array after adding the corresponding first element for the vehicle with the preset vehicle index of 7 is a 9x9 array, as shown in the two-dimensional array (a) in Figure 3 . Assuming that the vehicle with a preset vehicle index of 2 and the vehicle with a preset vehicle index of 4 belong to the second difference vehicle, then all related elements of the vehicle with a preset vehicle index of 2 in the two-dimensional array (a) in Figure 3 are deleted, and all related elements of the vehicle with a preset vehicle index of 4 are deleted, to obtain the two-dimensional array (b) as shown in Figure 3 .

[0103] Specifically, for Figure 3The two-dimensional array (b) in the process of maintaining as follows: first, since the second difference vehicle is the vehicle with preset vehicle index 2. and the vehicle with preset vehicle index 4., i.e. the target number of the second difference vehicle is 2. Then from the two-dimensional array (b) in turn to select the largest preset vehicle index 7. and the preset vehicle index only less than 7. 6.;Again, modify the preset vehicle index "7." of the vehicle with preset vehicle index 7. or the preset vehicle index "6." of the vehicle with preset vehicle index 6. to the preset vehicle index "2.", if the preset vehicle index "7." of the vehicle with preset vehicle index 7. is modified to the preset vehicle index "2.", the preset vehicle index "6." of the vehicle with preset vehicle index 6. is modified to the preset vehicle index "4.", if the preset vehicle index "6." of the vehicle with preset vehicle index 6. is modified to the preset vehicle index "2.", the preset vehicle index "7." of the vehicle with preset vehicle index 7. is modified to the preset vehicle index "4.". It should be noted that the preset vehicle index "7." or the preset vehicle index "6." and the preset vehicle index "2." or the preset vehicle index "4." are one-to-one correspondence when modified. After modification, delete the preset vehicle index "7." and the preset vehicle index "6." in the two-dimensional array.

[0104] It should be noted that after the modification of the preset vehicle index is completed, as shown in Figure 3 , assuming that the preset vehicle index "6." of the vehicle with preset vehicle index 6. is modified to the preset vehicle index "2.", and the preset vehicle index "7." of the vehicle with preset vehicle index 7. is modified to the preset vehicle index "4.", the related elements of the original vehicle with preset vehicle index 6. in the two-dimensional array need to be moved to the position after the related elements of the original vehicle with preset vehicle index 2. are deleted, and the related elements of the original vehicle with preset vehicle index 7. in the two-dimensional array need to be moved to the position after the related elements of the original vehicle with preset vehicle index 4. are deleted. If the target number of the second difference vehicle is other values, the modification principle is the same as that of the target number 2, which will not be described one by one. Figure 3 The two-dimensional array (c) in the process of maintaining is an example of the third two-dimensional array after maintenance.

[0105] According to the difference between the first vehicle set and the second vehicle set, the two-dimensional array is maintained accordingly, so that the maintained two-dimensional array can be consistent with the vehicle set corresponding to the vehicle data set received by the server in real time, thereby improving the convenience and accuracy of querying the corresponding preset identifier in the maintained two-dimensional array.

[0106] The capacity of the two-dimensional array for recording the preset identifiers is initially preset. When the maximum preset vehicle index in the preset vehicle index configured for each vehicle in the two-dimensional array is equal to the maximum value of the capacity of the two-dimensional array, the two-dimensional array needs to be expanded. Specifically, the method of one or more embodiments described above can further include the following steps.

[0107] According to the maximum value of the preset vehicle index, it is determined whether the two-dimensional array for recording the preset identifiers needs to be expanded, and a determination result is obtained.

[0108] If the determination result indicates that the two-dimensional array for recording the preset identifiers needs to be expanded, an instruction for expanding the two-dimensional array for recording the preset identifiers is generated.

[0109] In the embodiments of the present specification, each preset vehicle index set for each vehicle in the two-dimensional array for recording the preset identifiers can be each natural number set in a continuous order. When the maximum preset vehicle index in each preset vehicle index is equal to the maximum value of the capacity of the two-dimensional array for recording the preset identifiers, the capacity of the two-dimensional array for recording the preset identifiers can be expanded; or the capacity of the two-dimensional array for recording the preset identifiers can also be expanded when the difference between the maximum value of the capacity of the two-dimensional array for recording the preset identifiers and the maximum preset vehicle index is equal to or less than a preset value. It should be noted that the preset value can be set to any natural number greater than or equal to 0 according to user demand. If it is determined that the capacity of the two-dimensional array for recording the preset identifiers needs to be expanded, an instruction for expanding the capacity of the two-dimensional array for recording the preset identifiers is generated, and the server expands the two-dimensional array for recording the preset identifiers by a preset size in response to the instruction.

[0110] Based on the same idea, the present specification also provides a device corresponding to the above method. Figure 4 The present specification provides a vehicle re-identification device corresponding to Figure 1 The structure diagram of the vehicle re-identification device is shown in FIG. 1. Figure 4 As shown in FIG. 1, the device can include:

[0111] The first acquisition module 402 is configured to acquire a first vehicle re-identification result between each first vehicle corresponding to a first vehicle data set; and the first vehicle re-identification result is used to reflect the similarity between the vehicle data of each first vehicle.

[0112] The generation module 404 is configured to generate, according to the first vehicle re-identification result between each first vehicle, a preset identifier for reflecting whether vehicle re-identification processing is continued between any two first vehicles, and obtain a preset identifier set.

[0113] The second acquisition module 406 is configured to acquire a second vehicle data set to be subjected to vehicle re-identification processing.

[0114] The processing module 408 is configured to perform vehicle re-identification processing between at least part of second vehicles corresponding to the second vehicle data set according to the preset identification set, to obtain a second vehicle re-identification result.

[0115] Optionally, the generation module 404 can specifically include:

[0116] The first generation unit is configured to generate a first preset identification reflecting that vehicle re-identification processing is prohibited between any two of the first vehicles if the first vehicle re-identification result between the any two of the first vehicles is greater than or equal to a preset threshold.

[0117] The first generation unit is configured to generate a second preset identification reflecting that vehicle re-identification processing is instructed to continue between any two of the first vehicles if the first vehicle re-identification result between the any two of the first vehicles is less than a preset threshold.

[0118] Optionally, the preset identification set is a first two-dimensional array, and any element in the first two-dimensional array is Aij, where i represents a first vehicle with a preset vehicle index i, j represents a first vehicle with a preset vehicle index j, and Aij represents a preset identification of whether vehicle re-identification processing is to be continued between the first vehicle with the preset vehicle index i and the first vehicle with the preset vehicle index j.

[0119] The processing module 408 can specifically include:

[0120] The processing unit is configured to perform vehicle re-identification processing between at least part of second vehicles corresponding to the second vehicle data set according to the first two-dimensional array, to obtain a second vehicle re-identification result.

[0121] Optionally, the processing unit can specifically include:

[0122] The first determination sub-unit is configured to determine a difference vehicle set between a first vehicle set corresponding to the first vehicle data set and a second vehicle set corresponding to the second vehicle data set, the difference vehicle set including a first difference vehicle belonging to the second vehicle set but not belonging to the first vehicle set, and / or a second difference vehicle belonging to the first vehicle set but not belonging to the second vehicle set.

[0123] An adding subunit is configured to add each first element corresponding to each first difference vehicle in the first two-dimensional array to obtain a second two-dimensional array. One first element is configured to reflect a preset identifier for vehicle re-identification processing between any first vehicle and the first difference vehicle, or one first element is configured to reflect a preset identifier for vehicle re-identification processing between any other difference vehicle in the difference vehicle set and the first difference vehicle.

[0124] A deleting subunit is configured to delete each second element corresponding to each second difference vehicle in the second two-dimensional array to obtain a third two-dimensional array. One second element is configured to reflect a preset identifier for vehicle re-identification processing between any first vehicle and the second difference vehicle, or one second element is configured to reflect a preset identifier for vehicle re-identification processing between any first difference vehicle and the second difference vehicle.

[0125] A processing subunit is configured to perform vehicle re-identification processing between at least part of second vehicles corresponding to the second vehicle data set according to the third two-dimensional array to obtain a second vehicle re-identification result.

[0126] Optionally, the first acquisition module 402 can further include:

[0127] A third acquisition module is configured to acquire each first vehicle identifier carried by each first vehicle data in the first vehicle data set. The first vehicle identifier corresponds to the first vehicle in a one-to-one manner.

[0128] A first generation module is configured to generate a preset vehicle index with uniqueness for any one first vehicle.

[0129] An establishing module is configured to establish an association between the first vehicle identifier of the any one first vehicle and the preset vehicle index generated for the any one first vehicle.

[0130] Optionally, the second acquisition module 406 can further include:

[0131] A fourth acquisition module is configured to acquire each second vehicle identifier carried by each second vehicle data in the second vehicle data set.

[0132] The first determination subunit can specifically include:

[0133] The first determining subunit is specifically configured to perform matching processing on each of the first vehicle identifier and each of the second vehicle identifier, to obtain a difference vehicle set and a target vehicle set; the difference vehicle set contains vehicles to which the first vehicle identifier or the second vehicle identifier that fails to be matched successfully belongs; and the target vehicle set contains second vehicles to which the second vehicle identifier that is successfully matched with the first vehicle identifier belongs.

[0134] The first determining subunit can further include:

[0135] A second determining subunit is configured to determine, as a preset vehicle index of a specified second vehicle in the target vehicle set, the preset vehicle index of the specified first vehicle identifier that has the association relationship; the specified second vehicle is the second vehicle to which the second vehicle identifier that is successfully matched with the specified first vehicle identifier belongs.

[0136] The adding subunit can specifically include:

[0137] The adding subunit is specifically configured to generate the preset vehicle index of the first difference vehicle.

[0138] The adding subunit is specifically configured to add, in the first two-dimensional array, each first element corresponding to the first difference vehicle according to the preset vehicle index of the first difference vehicle.

[0139] Optionally, the deleting subunit can further include:

[0140] A third determining subunit is configured to determine a target number of the second difference vehicle.

[0141] A modifying subunit is configured to, after arranging the preset vehicle index of each second vehicle in descending order, modify, in descending order, the preset vehicle index of the target number of second vehicles to the preset vehicle index of the target number of second difference vehicles.

[0142] Optionally, each preset vehicle index is a natural number arranged in a continuous order.

[0143] The device can further include:

[0144] A judging module is configured to judge, according to a maximum value of the preset vehicle index, whether expansion processing needs to be performed on a two-dimensional array for recording the preset identifier, to obtain a judgment result.

[0145] The second generating module is configured to generate an instruction for expanding the two-dimensional array for recording the preset identifiers if the judgment result indicates that the two-dimensional array for recording the preset identifiers needs to be expanded.

[0146] Based on the same idea, the present specification also provides a device corresponding to the above method.

[0147] Figure 5 The present specification provides a structure diagram of a vehicle re-identification device corresponding to Figure 1 The device 500 can include: Figure 5

[0148] at least one processor 510; and

[0149] a memory 530 in communication with the at least one processor; wherein

[0150] The memory 530 stores instructions 520 executable by the at least one processor 510, and the instructions are executed by the at least one processor 510 to enable the at least one processor 510 to:

[0151] obtain a first vehicle re-identification result between each first vehicle corresponding to a first vehicle data set, the first vehicle re-identification result reflecting the similarity between the vehicle data of each first vehicle.

[0152] According to the first vehicle re-identification result between each first vehicle, generate a preset identifier for reflecting whether vehicle re-identification processing is continued between any two first vehicles, and obtain a preset identifier set.

[0153] Obtain a second vehicle data set to be processed for vehicle re-identification.

[0154] According to the preset identifier set, perform vehicle re-identification processing between at least part of the second vehicles corresponding to the second vehicle data set, and obtain a second vehicle re-identification result.

[0155] It should be understood that in the method described in one or more embodiments of the present specification, the order of some steps can be adjusted according to actual needs, or some steps can be omitted.

[0156] Each embodiment in the present specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the device shown in Figure 5 , since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.​

[0157] The above embodiments are only used to illustrate the present application, but not to limit it. Various modifications and changes can be made by those skilled in the art. Any modification, equivalent replacement, improvement, and the like made within the spirit and principle of the present application shall fall into the scope of claims of the present application.

Claims

1. A vehicle re-identification method, characterized in that, include: Obtain the first vehicle re-identification result between each first vehicle corresponding to the first vehicle data set. The first vehicle re-identification result is used to reflect the similarity between the vehicle data of each first vehicle. Based on the first vehicle re-identification results between each of the first vehicles, a preset identifier is generated to reflect whether vehicle re-identification processing continues between any two first vehicles, thus obtaining a preset identifier set. Obtain the second set of vehicle data to be re-identified; Based on the preset identifier set, vehicle re-identification processing is performed on at least a portion of the second vehicles corresponding to the second vehicle data set to obtain the second vehicle re-identification result. The preset identifier set is a first two-dimensional array, and any element in the first two-dimensional array is Aij, where i represents the first vehicle with preset vehicle index i, j represents the first vehicle with preset vehicle index j, and Aij represents the preset identifier for whether vehicle re-identification processing should continue between the first vehicle with preset vehicle index i and the first vehicle with preset vehicle index j. The step of performing vehicle re-identification processing on at least a portion of the second vehicles corresponding to the second vehicle data set based on the preset identifier set to obtain the second vehicle re-identification result specifically includes: Based on the first two-dimensional array, vehicle re-identification processing is performed on at least a portion of the second vehicles corresponding to the second vehicle data set to obtain the second vehicle re-identification result. The step of performing vehicle re-identification processing on at least a portion of the second vehicles corresponding to the second vehicle data set based on the first two-dimensional array to obtain the second vehicle re-identification result specifically includes: Determine the set of vehicles that differ between the first vehicle set corresponding to the first vehicle data set and the second vehicle set corresponding to the second vehicle data set; the set of vehicles that differ includes first vehicles that belong to the second vehicle set but not to the first vehicle set, and / or second vehicles that belong to the first vehicle set but not to the second vehicle set; Add each first element corresponding to each of the first different vehicles to the first two-dimensional array to obtain a second two-dimensional array; one first element is used to reflect a preset identifier that needs to be re-identified between any first vehicle and the first different vehicle, or one first element is used to reflect a preset identifier that needs to be re-identified between any other different vehicle in the set of different vehicles and the first different vehicle. In the second two-dimensional array, each second element corresponding to each second difference vehicle is deleted to obtain a third two-dimensional array; a second element is used to reflect a preset identifier that indicates whether vehicle re-identification processing is required between any first vehicle and the second difference vehicle, or a second element is used to reflect a preset identifier that indicates whether vehicle re-identification processing is required between any first difference vehicle and the second difference vehicle. Based on the third two-dimensional array, vehicle re-identification processing is performed on at least a portion of the second vehicles corresponding to the second vehicle data set to obtain the second vehicle re-identification result.

2. The method as described in claim 1, characterized in that, Based on the first vehicle re-identification results between each of the first vehicles, preset identifiers are generated to reflect whether vehicle re-identification processing should continue between any two first vehicles, resulting in a preset identifier set, which specifically includes: If the first vehicle re-identification result between any two first vehicles is greater than or equal to a preset threshold, a first preset identifier is generated to reflect the prohibition of continuing vehicle re-identification processing between the two first vehicles. If the first vehicle re-identification result between any two first vehicles is less than a preset threshold, a second preset identifier is generated to indicate that vehicle re-identification processing should continue between the two first vehicles.

3. The method as described in claim 2, characterized in that, Before obtaining the first vehicle re-identification results among the various first vehicles corresponding to the first vehicle data set, the method further includes: Obtain each first vehicle identifier carried by each first vehicle data in the first vehicle data set; wherein, each first vehicle identifier corresponds one-to-one with a first vehicle; For any one of the first vehicles, a unique preset vehicle index is generated; Establish an association between the first vehicle identifier of any one of the first vehicles and the preset vehicle index generated for any one of the first vehicles.

4. The method as described in claim 3, characterized in that, After obtaining the second set of vehicle data to be re-identified, the process further includes: Obtain the identifier of each second vehicle carried by each second vehicle data in the second vehicle data set; The step of determining the difference set of vehicles between the first vehicle set corresponding to the first vehicle data set and the second vehicle set corresponding to the second vehicle data set specifically includes: Each first vehicle identifier is matched with each second vehicle identifier to obtain a set of differing vehicles and a set of target vehicles; the set of differing vehicles includes vehicles to which either the first vehicle identifier or the second vehicle identifier did not match successfully; the set of target vehicles includes second vehicles to which the second vehicle identifier that matched the first vehicle identifier successfully belongs. After determining the difference set of vehicles between the first vehicle set corresponding to the first vehicle data set and the second vehicle set corresponding to the second vehicle data set, the method further includes: The preset vehicle index that has the association relationship with the specified first vehicle identifier is determined as the preset vehicle index of the specified second vehicle in the target vehicle set; wherein, the specified second vehicle is the second vehicle to which the second vehicle identifier that successfully matches the specified first vehicle identifier belongs; The step of adding each first element corresponding to each of the first differentiated vehicles to the first two-dimensional array specifically includes: Generate the preset vehicle index for the first differentiated vehicle; Based on the preset vehicle index of the first differentiated vehicle, add each first element corresponding to the first differentiated vehicle to the first two-dimensional array.

5. The method as described in claim 4, characterized in that, After deleting each second element corresponding to each of the second-differentiated vehicles from the second two-dimensional array to obtain the third two-dimensional array, the method further includes: Determine the target number of the second differential vehicles; After arranging the preset vehicle indices of each second vehicle in descending order, the preset vehicle indices of the target number of second vehicles are sequentially modified to the preset vehicle indices of the target number of second differential vehicles in descending order.

6. The method according to any one of claims 1 to 5, characterized in that, Each of the preset vehicle indices is a natural number set in a consecutive order; the method further includes: Based on the maximum value of the preset vehicle index, determine whether it is necessary to expand the two-dimensional array used to record the preset identifier, and obtain the determination result; If the determination result indicates that the two-dimensional array used to record the preset identifier needs to be expanded, then an instruction to expand the two-dimensional array used to record the preset identifier is generated.

7. A vehicle re-identification device, characterized in that, include: The first acquisition module is used to acquire the first vehicle re-identification results between each first vehicle corresponding to the first vehicle data set. The first vehicle re-identification results are used to reflect the similarity between the vehicle data of each first vehicle. The generation module is used to generate preset identifiers based on the first vehicle re-identification results between each of the first vehicles, thereby obtaining a preset identifier set; The second acquisition module is used to acquire a second set of vehicle data to be re-identified; The processing module is used to perform vehicle re-identification processing on at least a portion of the second vehicles corresponding to the second vehicle data set according to the preset identifier set, and to obtain the second vehicle re-identification result. The preset identifier set is a first two-dimensional array, and any element in the first two-dimensional array is Aij, where i represents the first vehicle with preset vehicle index i, j represents the first vehicle with preset vehicle index j, and Aij represents the preset identifier for whether vehicle re-identification processing should continue between the first vehicle with preset vehicle index i and the first vehicle with preset vehicle index j. The processing module specifically includes: The processing unit is configured to perform vehicle re-identification processing on at least a portion of the second vehicles corresponding to the second vehicle data set based on the first two-dimensional array, and obtain the second vehicle re-identification result. The processing unit specifically includes: The first determining subunit is used to determine the difference vehicle set between the first vehicle set corresponding to the first vehicle data set and the second vehicle set corresponding to the second vehicle data set; the difference vehicle set includes a first difference vehicle that belongs to the second vehicle set but not to the first vehicle set, and / or a second difference vehicle that belongs to the first vehicle set but not to the second vehicle set. A new sub-unit is added to the first two-dimensional array to add each first element corresponding to each of the first different vehicles to obtain a second two-dimensional array; one first element is used to reflect a preset identifier that needs to be re-identified between any first vehicle and the first different vehicle, or one first element is used to reflect a preset identifier that needs to be re-identified between any other different vehicle in the set of different vehicles and the first different vehicle. The deletion sub-unit is used to delete each second element corresponding to each of the second different vehicles in the second two-dimensional array to obtain a third two-dimensional array; one second element is used to reflect a preset identifier that indicates whether vehicle re-identification processing is required between any first vehicle and the second different vehicle, or one second element is used to reflect a preset identifier that indicates whether vehicle re-identification processing is required between any first different vehicle and the second different vehicle. The processing subunit is used to perform vehicle re-identification processing on at least a portion of the second vehicles corresponding to the second vehicle data set based on the third two-dimensional array, so as to obtain the second vehicle re-identification result.

8. A vehicle re-identification device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: Obtain the first vehicle re-identification result between each first vehicle corresponding to the first vehicle data set. The first vehicle re-identification result is used to reflect the similarity between the vehicle data of each first vehicle. Based on the first vehicle re-identification results between each of the first vehicles, a preset identifier is generated to reflect whether vehicle re-identification processing continues between any two first vehicles, thus obtaining a preset identifier set. Obtain the second set of vehicle data to be re-identified; Based on the preset identifier set, vehicle re-identification processing is performed on at least a portion of the second vehicles corresponding to the second vehicle data set to obtain the second vehicle re-identification result. The preset identifier set is a first two-dimensional array, and any element in the first two-dimensional array is Aij, where i represents the first vehicle with preset vehicle index i, j represents the first vehicle with preset vehicle index j, and Aij represents the preset identifier for whether vehicle re-identification processing should continue between the first vehicle with preset vehicle index i and the first vehicle with preset vehicle index j. The step of performing vehicle re-identification processing on at least a portion of the second vehicles corresponding to the second vehicle data set based on the preset identifier set to obtain the second vehicle re-identification result specifically includes: Based on the first two-dimensional array, vehicle re-identification processing is performed on at least a portion of the second vehicles corresponding to the second vehicle data set to obtain the second vehicle re-identification result. The step of performing vehicle re-identification processing on at least a portion of the second vehicles corresponding to the second vehicle data set based on the first two-dimensional array to obtain the second vehicle re-identification result specifically includes: Determine the set of vehicles that differ between the first vehicle set corresponding to the first vehicle data set and the second vehicle set corresponding to the second vehicle data set; the set of vehicles that differ includes first vehicles that belong to the second vehicle set but not to the first vehicle set, and / or second vehicles that belong to the first vehicle set but not to the second vehicle set; Add each first element corresponding to each of the first different vehicles to the first two-dimensional array to obtain a second two-dimensional array; one first element is used to reflect a preset identifier that needs to be re-identified between any first vehicle and the first different vehicle, or one first element is used to reflect a preset identifier that needs to be re-identified between any other different vehicle in the set of different vehicles and the first different vehicle. In the second two-dimensional array, each second element corresponding to each second difference vehicle is deleted to obtain a third two-dimensional array; a second element is used to reflect a preset identifier that indicates whether vehicle re-identification processing is required between any first vehicle and the second difference vehicle, or a second element is used to reflect a preset identifier that indicates whether vehicle re-identification processing is required between any first difference vehicle and the second difference vehicle. Based on the third two-dimensional array, vehicle re-identification processing is performed on at least a portion of the second vehicles corresponding to the second vehicle data set to obtain the second vehicle re-identification result.

Images