Identity matching method and apparatus, electronic device, and computer-readable storage medium

Abstract

The application discloses an identity matching method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: obtaining target archive data of a target object, wherein the target archive data comprises a face image of the target object driving a vehicle and recognized license plate information; according to the license plate information in the target archive data, taking identity information associated with the license plate information in preset vehicle registration data as target identity information, wherein the preset vehicle registration data comprises identity information and license plate information; if the number of information of the target identity information associated with each license plate information in the target archive data is equal to one, matching the face image in the target archive data with identity images in the target identity information to obtain an identity matching result. The above scheme can improve the accuracy of identity matching.

Description

Technical Field

[0001] This application relates to the fields of security and image processing technology, and in particular to an identity matching method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] Currently, facial image-based identity recognition typically involves comparing the features of a captured facial image with images in a database. If the feature comparison results meet a certain threshold, the facial image is considered a match for the corresponding identity. However, the image capture scenario is affected by factors such as high vehicle speed or reflections from car windows causing blurry facial images, resulting in inconsistent image quality and thus reducing the accuracy of identity matching. Summary of the Invention

[0003] This application provides at least one identity matching method, apparatus, electronic device, and computer-readable storage medium.

[0004] The first aspect of this application provides an identity matching method, comprising: acquiring target profile data of a target object, the target profile data including a captured facial image of the target object driving a vehicle and identified license plate information; based on the license plate information in the target profile data, using identity information associated with the license plate information in preset vehicle registration data as target identity information, the preset vehicle registration data including associated identity information and license plate information; if the number of target identity information associated with each license plate information in the target profile data is equal to one, matching the facial image in the target profile data with the identity image in the target identity information to obtain an identity matching result.

[0005] In one embodiment, the method further includes: responding to a situation where the number of target identity information associated with each license plate information in the target file data is greater than one, acquiring facial images and other images captured when the target object drives the vehicle corresponding to each license plate information in the target file data, wherein the other images include images in the target file data whose image quality is ranked high within a preset range; determining the identity images in the target identity information corresponding to each license plate information in the target file data as target identity images based on the matching results between the other images and the identity images in the target identity information corresponding to each license plate information in the target file data; and matching the identity images in the target identity information corresponding to each license plate information in the target file data with the target identity images to obtain the identity matching result.

[0006] In one embodiment, the step of determining the identity image in the target identity information corresponding to each license plate information in the target file data as the target identity image based on the matching results between the other images and the identity images in the target identity information corresponding to each license plate information in the target file data includes: calculating the average value of the feature similarity between each other image and the identity image in the target identity information corresponding to the license plate information in the target file data to obtain the average value of multiple feature similarities; and determining the identity image corresponding to the maximum average value among the multiple feature similarities as the target identity image.

[0007] In one embodiment, the step of matching the face image in the target file data with the identity image in the target identity information to obtain an identity matching result includes: calculating the image feature similarity between the face image in the target file data and the identity image in the target identity information; if the image feature similarity is greater than a similarity threshold, then the identity matching result is a successful match.

[0008] In one embodiment, the step of obtaining target file data of the target object includes: obtaining initial file data of the target object; filtering the license plate information in the initial file data according to the number of license plate information in the initial file data to obtain filtered license plate information; and determining the filtered license plate information as the license plate information of the vehicle driven by the target object in the target file data.

[0009] In one embodiment, the step of filtering the license plate information in the initial file based on the number of license plate information in the initial file data to obtain filtered license plate information includes: if the number of license plate information in the initial file data is equal to one, then the license plate information in the initial file data is determined as the license plate information in the target file data; if the number of license plate information in the initial file data is greater than one, then the number of each license plate information in the initial file data is determined; the target license plate information and other license plate information in the initial file data are obtained, wherein the target license plate information is the license plate information with the largest number of information among all license plate information; other license plate information whose ratio between the number of information of other license plate information and the number of information of the target license plate information is greater than a ratio threshold, and the target license plate information are used as the filtered license plate information.

[0010] In one embodiment, the step of obtaining the initial archive data of the target object includes: obtaining the captured image data of each target object within a preset spatiotemporal range; and performing clustering processing based on the image features of the captured images in the captured image data to obtain the initial archive data of each target object.

[0011] In one embodiment, the step of determining the target identity information corresponding to the license plate information in preset vehicle registration data based on the license plate information in the target file data includes: selecting the license plate information in the preset vehicle registration data that is the same as the license plate information; and determining the identity information corresponding to the same license plate information in the preset vehicle registration data as the target identity information corresponding to the license plate information.

[0012] A second aspect of this application provides an identity matching device, comprising: an acquisition module for acquiring target profile data of a target object, the target profile data including a captured facial image of the target object driving a vehicle and identified license plate information; a determination module for determining, based on the license plate information in the target profile data, using identity information associated with the license plate information in preset vehicle registration data as target identity information, the preset vehicle registration data including associated identity information and license plate information; and a matching module for matching the facial image in the target profile data with the identity image in the target identity information if the number of target identity information associated with each license plate information in the target profile data is equal to one, to obtain an identity matching result.

[0013] A third aspect of this application provides an electronic device, including a memory and a processor, wherein the processor is configured to execute program instructions stored in the memory to implement the aforementioned identity matching method.

[0014] A fourth aspect of this application provides a computer-readable storage medium having program instructions stored thereon, which, when executed by a processor, implement the aforementioned identity matching method.

[0015] The above scheme, based on the license plate information in the target file data, identifies the identity information associated with the license plate information in the preset vehicle registration data as the target identity information for the corresponding license plate information. Responding to the condition that the number of target identity information associated with each license plate information in the target file data is equal to one, the facial image in the target file data is matched with the identity image in the target identity information to obtain the identity matching result. Therefore, based on establishing the association between identity information and vehicle information, further matching the images in the target file data according to the number of target identity information associated with each license plate information in the target file data can achieve accurate identity matching and avoid the problem of low accuracy caused by a single matching attempt.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the technical solutions of this application.

[0018] Figure 1 This is a flowchart illustrating an exemplary embodiment of the identity matching method of this application;

[0019] Figure 2 yes Figure 1 A flowchart illustrating an exemplary embodiment of the identity matching method after step 120 is shown.

[0020] Figure 3 yes Figure 1 A flowchart illustrating an exemplary embodiment of step 110 in the identity matching method is shown.

[0021] Figure 4 This is a block diagram illustrating an identity matching device according to an exemplary embodiment of this application;

[0022] Figure 5 This is a schematic diagram of the structure of an embodiment of the electronic device of this application;

[0023] Figure 6 This is a schematic diagram of the structure of an embodiment of the computer-readable storage medium of this application. Detailed Implementation

[0024] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0025] In the following description, specific details such as particular system architectures, interfaces, and technologies are presented for illustrative purposes rather than for limiting purposes, in order to provide a thorough understanding of this application.

[0026] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, "many" in this document means two or more. Moreover, the term "at least one" in this document means any combination of at least two of any one or more of a plurality of objects. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0027] First, it's important to note that with technological advancements and the growing need for convenience, various facial recognition applications have become widespread, including facial recognition for unlocking doors, opening doors, security checks, boarding flights, checking into hotels, and making payments for medical treatment. These applications are taking root across various industries, generating a vast amount of trajectory data. To ensure this trajectory data positively impacts social progress and stability, the most crucial step is to classify the trajectory images within this data into identity records. Currently, facial image-based identity recognition typically involves comparing the captured facial image with images in a database. If the feature comparison results meet a certain threshold, a match is determined between the facial image and the corresponding identity. However, image capture scenarios, especially at checkpoints, can be problematic. High vehicle speeds or glare from car windows can cause blurry images, resulting in inconsistent image quality and reduced accuracy in identity matching. It's worth noting that integrated vehicle-to-everything (V2X) facial recognition checkpoints can simultaneously capture license plates and facial images of people inside vehicles. Vehicle license plate information and facial images captured through this checkpoint can be associated with the same ID.

[0028] Therefore, to improve the accuracy of identity matching, this application proposes an identity matching method, apparatus, electronic device, and computer-readable storage medium. For details, please refer to... Figure 1 , Figure 1 This is a flowchart illustrating an exemplary embodiment of the identity matching method of this application. Specifically, the identity matching method of this embodiment includes the following steps:

[0029] Step S110: Obtain the target file data of the target object.

[0030] The target group includes drivers who are driving vehicles on the road.

[0031] The target profile data includes facial images of the target object while driving a vehicle and the identified license plate information. Target profile data can also be understood as the target object's movement trajectory within a preset spatiotemporal range. For example, the target profile data includes all driving images of target object A captured by a checkpoint in City B from February 10th to February 15th. The captured driving images are then segmented to obtain facial images, and license plate recognition is performed on the driving images to obtain the identified license plate information.

[0032] Step S120: Based on the license plate information in the target file data, the identity information associated with the license plate information in the preset vehicle registration data is used as the target identity information. The preset vehicle registration data includes the associated identity information and license plate information.

[0033] The preset vehicle registration data includes associated identity information and license plate information. It should be noted that the preset license plate registration data can be obtained from authorized sources such as vehicle management offices. Furthermore, considering the possibility of expired or duplicate invalid data in the preset vehicle registration data, to improve the accuracy of identity matching, this embodiment preprocesses the preset vehicle registration data before determining the target identity information. As an example, the identity matching device can obtain the license plate information associated with each identity information within a month, and determine the final associated license plate information based on the number of license plate information associated with that identity information, avoiding the problem of invalid data in the preset vehicle registration data due to the target person changing vehicles. As another example, the identity matching device can obtain the associated identity information within the past month based on the license plate number in the license plate information, and determine the final associated identity information for that license plate number based on the number of identity information associated with that license plate number, thereby updating the data in the preset vehicle registration data.

[0034] The identity matching device determines the identity information associated with the license plate information from the preset vehicle registration data based on the license plate information in the target file data, and uses the determined identity information as the target identity information for that license plate information. Specifically, the identity matching device selects license plate information in the preset vehicle registration data that is identical to the license plate information in the target file data, and determines the identity information corresponding to the identical license plate information in the preset vehicle registration data as the target identity information corresponding to that license plate information.

[0035] Step S130: If the number of target identity information associated with each license plate information in the target file data is equal to one, match the face image in the target file data with the identity image in the target identity information to obtain the identity matching result.

[0036] The number of information items refers to the number of target identity information items associated with each license plate information. For example, if the identity matching device matches a target identity item from the preset vehicle registration data based on license plate number one to license plate number three in the target file data, then the number of information items in this case is one.

[0037] The identity matching device determines whether the information data of the target identity information associated with each license plate information in the target file data is equal to one. If so, it matches the face image in the target file data with the identity image in the target identity information to obtain the identity matching result.

[0038] As can be seen, this embodiment of the application determines the identity information associated with the license plate information in the preset vehicle registration data as the target identity information corresponding to the license plate information based on the license plate information in the target file data. In response to the condition that the number of target identity information associated with each license plate information in the target file data is equal to one, the face image in the target file data is matched with the identity image in the target identity information to obtain the identity matching result. Therefore, based on establishing the association between identity information and vehicle information, further matching the images in the target file data according to the number of target identity information associated with each license plate information in the target file data can achieve accurate identity matching and avoid the problem of low accuracy in identity matching due to a single matching attempt.

[0039] Based on the above embodiments, the embodiments of this application adopt... Figure 2 The flowchart shown details the situation where the number of target identity information associated with each license plate in the target file data is not equal to one. Please refer to [link / reference]. Figure 2 , Figure 2 yes Figure 1 The illustrated flowchart shows an exemplary embodiment of the identity matching method after step 120. Specifically, the method of this embodiment includes the following steps:

[0040] Step S210: In response to the fact that the number of target identity information associated with each license plate information in the target file data is greater than one, the face image and other images captured when the target object drives the vehicle corresponding to each license plate information in the target file data are obtained.

[0041] Other images include those in the target archive data whose image quality ranks highly within a preset range. The preset ranking can be the top three. Specifically, the acquisition method for other images involves obtaining the sharpness, face angle, mask score, sunglasses score, number of people wearing hats, and face size of each image in the target archive data. The image quality of each image is determined by summing the products of its sharpness, face angle, mask score, sunglasses score, number of people wearing hats, and face size with their corresponding weights.

[0042] Specifically, the calculation method for image quality can be found in the following formula:

[0043]

[0044] in, The weighting coefficients representing the image sharpness. This represents the weighting coefficient corresponding to the angle of a face in the image. This represents the weighting coefficient corresponding to the mask scores in the image. This represents the weighting coefficient corresponding to the sunglasses score in the image. This represents the weighting coefficient corresponding to the hat score in the image. This represents the weighting coefficient corresponding to the size of the face in the image.

[0045] If the identity matching device determines that the number of target identity information associated with each license plate information in the target file data is greater than one, it will acquire the facial image and other images of the target object driving the vehicle corresponding to each license plate information in the file data.

[0046] Step S220: Based on the matching results between other images and the identity images in the target identity information corresponding to each license plate information in the target file data, the identity images in the target identity information corresponding to each license plate information in the target file data are determined as the target identity images.

[0047] The identity matching device compares the feature similarity of identity images corresponding to license plates in other images and target file data, and then determines the target identity image from the target identity information corresponding to license plates in the target file data. Specifically, it calculates the average feature similarity between the identity images corresponding to license plates in other images and target file data, obtains the average of multiple feature similarities, and selects the identity image corresponding to the maximum average of multiple feature similarities as the target identity image.

[0048] Step S230: Match the identity image in the target identity information corresponding to each license plate information in the target file data with the target identity image to obtain the identity matching result.

[0049] The identity matching device calculates the image feature similarity between a face image in the target file data and an identity image in the target identity information, and determines whether the image feature similarity is greater than a similarity threshold. If the image feature similarity is greater than the similarity threshold, the identity matching result is successful. For example, the identity matching device can set the similarity threshold to a first preset similarity threshold and a second preset similarity threshold, where the first preset similarity threshold is greater than the second preset similarity threshold. Then, it calculates the feature similarity between the identity image in the target identity information corresponding to each license plate information in the file data and the target identity image. If the feature similarity is greater than the first preset similarity threshold, it indicates that the identity matching is successful. It should be noted that if no identity image meets the first preset similarity threshold, it further determines whether there is an identity image whose feature similarity is greater than the second preset similarity threshold. If so, it indicates that the identity matching is successful.

[0050] As can be seen, in this embodiment of the application, in response to a situation where the number of target identity information associated with each license plate information in the target file data is greater than one, the application acquires facial images and other images captured when the target object drives the vehicle corresponding to each license plate information in the target file data. These other images include facial images in the target file data whose image quality ranks highly within a preset range. Based on the matching results between these other images and the identity images in the target identity information corresponding to each license plate information in the target file data, the application determines the target identity image from the target identity information corresponding to each license plate information in the target file data. The application then matches the identity images in the target identity information corresponding to each license plate information in the target file data with the target identity image to obtain the identity matching result. Therefore, by establishing the association between identity information and vehicle information, and further matching the images in the target file data according to the number of target identity information associated with each license plate information, accurate identity matching can be achieved, avoiding the problem of low accuracy in identity matching due to a single matching attempt.

[0051] Based on the above embodiments, the embodiments of this application adopt... Figure 3 The flowchart shown illustrates in detail how to determine the target file data of the target object. Please refer to [link / reference]. Figure 3 , Figure 3 yes Figure 1 The illustrated flowchart shows an exemplary embodiment of step 110 in the identity matching method. Specifically, the method of this embodiment includes the following steps:

[0052] Step S310: Obtain the initial file data of the target object.

[0053] The initial profile data may include all trajectory data of the target object within a preset spatiotemporal range. For example, the identity matching device can acquire image data of each target object within the preset spatiotemporal range and perform clustering processing based on the image features of the acquired images to obtain the initial profile data for each target object. Here, the acquired image data refers to all data collected by the checkpoint within the preset spatiotemporal range.

[0054] It should be noted that the clustering method can be to compare the features of the captured images in the image collection with the features of existing archives according to the activity time sequence. Images with a similarity greater than a threshold are assigned to the corresponding archive; if the similarity is less than the threshold, a new archive is created, and the images to be compared are assigned to the new archive. For example, the trajectory of person A's activity in a certain area during a certain period is {A1, A2, A3, A4, A5}, where each trajectory includes the capture time, capture area, and captured image features. Additionally, if it is a face image captured by a vehicle checkpoint, it also includes the captured vehicle license plate information. Specifically, the features of the images in each trajectory of person A are compared with the features of existing archives; if the similarity is less than the threshold, the images are assigned to the corresponding archives. If the feature similarity between the trajectory and file B meets the threshold, then the trajectory will be... If the data is assigned to file B, and none of the existing files meet the threshold, then file C is created and the trajectory is recorded. It is then placed into file C. After that, the other trajectories of person A are processed in the same way.

[0055] It should also be noted that K-means clustering can also be used for clustering operations, but this application does not limit the implementation of this method.

[0056] Step S320: Filter the license plate information in the initial file according to the number of license plate information entries in the initial file data to obtain the filtered license plate information.

[0057] Filtering includes filtering license plate information and facial images in the initial archive data.

[0058] It should be noted that when filtering facial images, considering vehicle driving type, facial images are divided into driver's image and passenger's image. The driver's image is more conducive to identity matching for two reasons: first, the probability of the driver being the vehicle owner is higher than that of the passenger; second, due to driving, the facial image corresponding to the driver's image is more regular, increasing the probability of matching identity information. Therefore, the identity matching device filters the facial images in the initial file data... Pass Filter and retain the driver's image, that is, the driver's face image.

[0059] Furthermore, considering the checkpoint setup issue, the initial file data may contain images that do not contain the corresponding license plate information. To improve the accuracy of identity matching, the identity matching device filters out images that do not contain license plate information, so that license plate information can be obtained based on images that contain license plate information.

[0060] In the case of filtering license plate information, the identity matching device filters the license plate information based on the number of license plate information entries in the initial file data. Specifically, it determines whether the number of license plate information entries in the initial file data is equal to one. If the number of license plate information entries in the initial file data is equal to one, the license plate information in the initial file data is identified as the license plate information in the target file data and used for subsequent identity matching. If the number of license plate information entries in the initial file data is greater than one, the number of each license plate information entry in the initial file data is determined, and the target license plate information and other license plate information in the initial file data are obtained. The target license plate information is the license plate information with the largest number of entries. Then, the ratio between the number of entries of other license plate information and the number of entries of the target license plate information is calculated. Other license plate information with a ratio greater than a ratio threshold, along with the target license plate information, are used as the filtered license plate information. Other license plate information with a ratio less than or equal to the ratio threshold is filtered out. It should be noted that the ratio threshold in this embodiment can be 0.5.

[0061] Step S330: The filtered license plate information is determined as the license plate information of the vehicle driven by the target object in the target file data.

[0062] As can be seen, this embodiment of the application obtains the initial file data of the target object; filters the license plate information in the initial file data according to the amount of license plate information in the initial file data to obtain filtered license plate information; and determines the filtered license plate information as the license plate information of the vehicle driven by the target object in the target file data. Thus, by filtering the license plate information and facial information in the obtained initial file data, the problem of inaccurate matching caused by matching based on too much invalid data is avoided.

[0063] It should be further noted that the entity executing the identity matching method can be a terminal device, a server, or other processing device. The terminal device can be a user equipment (UE), computer, mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, wearable device, etc. The entity executing the identity matching method can also be an identity matching device. In some possible implementations, the identity matching method can be implemented by a processor calling computer-readable instructions stored in memory.

[0064] Figure 4 This is a block diagram illustrating an identity matching device as shown in an exemplary embodiment of this application. Figure 4As shown, the exemplary identity matching device 400 includes: an acquisition module 410, a determination module 420, and a matching module 430. Specifically:

[0065] The acquisition module 410 is used to acquire target file data of the target object, which includes the captured facial image of the target object driving the vehicle and the identified license plate information.

[0066] The determination module 420 is used to determine the target identity information based on the license plate information in the target file data and the identity information associated with the license plate information in the preset vehicle registration data. The preset vehicle registration data includes the associated identity information and license plate information.

[0067] The matching module 430 is used to match the face image in the target file data with the identity image in the target identity information in response to the number of target identity information associated with each license plate information in the target file data being equal to one, and obtain the identity matching result.

[0068] In this exemplary identity matching device, based on the license plate information in the target file data, the identity information associated with the license plate information in the preset vehicle registration data is determined as the target identity information corresponding to the license plate information. In response to the condition that the number of target identity information associated with each license plate information in the target file data equals one, the facial image in the target file data is matched with the identity image in the target identity information to obtain the identity matching result. Therefore, based on establishing the association between identity information and vehicle information, further matching the images in the target file data according to the number of target identity information associated with each license plate information in the target file data enables accurate identity matching, avoiding the problem of low accuracy caused by a single matching attempt.

[0069] The functions of each module can be found in the embodiment of the identity matching method, and will not be repeated here.

[0070] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of an embodiment of the electronic device of this application. The electronic device 50 includes a memory 51 and a processor 52. The processor 52 is used to execute program instructions stored in the memory 51 to implement the steps in any of the above-described identity matching method embodiments. In a specific implementation scenario, the electronic device 50 may include, but is not limited to, a microcomputer or a server. In addition, the electronic device 50 may also include mobile devices such as laptops and tablets, which are not limited here.

[0071] Specifically, processor 52 controls itself and memory 51 to implement the steps in any of the above-described identity matching method embodiments. Processor 52 may also be referred to as a CPU (Central Processing Unit). Processor 52 may be an integrated circuit chip with signal processing capabilities. Processor 52 may also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor. Furthermore, processor 52 may be implemented using integrated circuit chips.

[0072] The above scheme, based on the license plate information in the target file data, identifies the identity information associated with the license plate information in the preset vehicle registration data as the target identity information for the corresponding license plate information. Responding to the condition that the number of target identity information associated with each license plate information in the target file data is equal to one, the facial image in the target file data is matched with the identity image in the target identity information to obtain the identity matching result. Therefore, based on establishing the association between identity information and vehicle information, further matching the images in the target file data according to the number of target identity information associated with each license plate information in the target file data can achieve accurate identity matching and avoid the problem of low accuracy caused by a single matching attempt. Please refer to [link to relevant documentation]. Figure 6 , Figure 6 This is a schematic diagram of a computer-readable storage medium according to an embodiment of the present application. The computer-readable storage medium 60 stores program instructions 61 that can be executed by a processor. The program instructions 61 are used to implement the steps in any of the above-described embodiments of the identity matching method.

[0073] The above scheme, based on the license plate information in the target file data, identifies the identity information associated with the license plate information in the preset vehicle registration data as the target identity information for the corresponding license plate information. Responding to the condition that the number of target identity information associated with each license plate information in the target file data is equal to one, the facial image in the target file data is matched with the identity image in the target identity information to obtain the identity matching result. Therefore, based on establishing the association between identity information and vehicle information, further matching the images in the target file data according to the number of target identity information associated with each license plate information in the target file data can achieve accurate identity matching and avoid the problem of low accuracy caused by a single matching attempt.

[0074] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0075] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus implementations described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0077] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. An identity matching method, characterized in that, The method includes: Acquire target profile data of the target object, the target profile data including a captured facial image of the target object while driving a vehicle and the identified license plate information; Based on the license plate information in the target file data, the identity information associated with the license plate information in the preset vehicle registration data is used as the target identity information. The preset vehicle registration data includes the associated identity information and license plate information. Determine whether the information data of the target identity information associated with each license plate information in the target file data is equal to one; If the number of target identity information associated with each license plate information in the target file data is equal to one, the face image in the target file data is matched with the identity image in the target identity information to obtain the identity matching result; If the number of target identity information associated with each license plate information in the target file data is greater than one, then the facial image and other images captured when the target object drives the vehicle corresponding to each license plate information in the target file data are obtained. The other images include images in the target file data whose image quality is among the top in a preset ranking. Based on the matching results between the other images and the identity images in the target identity information corresponding to each license plate information in the target file data, the identity images in the target identity information corresponding to each license plate information in the target file data are determined as the target identity images. The identity image in the target identity information corresponding to each license plate information in the target file data is matched with the face image to obtain the identity matching result.

2. The method according to claim 1, characterized in that, The step of determining the identity image in the target identity information corresponding to each license plate information in the target file data as the target identity image based on the matching result between the other images and the identity images in the target identity information corresponding to each license plate information in the target file data includes: Calculate the average value of the feature similarity between each other image and the identity image in the target identity information corresponding to the license plate information in the target file data, and obtain the average value of multiple feature similarities; The identity image corresponding to the maximum average value among the multiple feature similarities is determined as the target identity image.

3. The method according to claim 1, characterized in that, The step of matching the facial image in the target file data with the identity image in the target identity information to obtain the identity matching result includes: Calculate the image feature similarity between the face image in the target file data and the identity image in the target identity information; If the image feature similarity is greater than the similarity threshold, then the identity matching result is a successful match.

4. The method according to claim 1, characterized in that, The step of obtaining the target file data of the target object includes: Obtain the initial file data of the target object; The license plate information in the initial archive is filtered based on the number of license plate information entries in the initial archive data to obtain filtered license plate information. The filtered license plate information is determined as the license plate information of the vehicle driven by the target object in the target file data.

5. The method according to claim 4, characterized in that, The step of filtering the license plate information in the initial file based on the number of license plate information entries in the initial file data to obtain filtered license plate information includes: If the number of license plate information entries in the initial file data is equal to one, then the license plate information in the initial file data is determined as the license plate information in the target file data; If the number of license plate information entries in the initial file data is greater than one, then the number of license plate information entries in the initial file data is determined. Obtain the target license plate information and other license plate information from the initial file data, wherein the target license plate information is the license plate information with the most information among all license plate information; Other license plate information whose ratio of the number of information items of other license plates to the number of information items of the target license plate is greater than a ratio threshold, and the target license plate information are used as the filtered license plate information.

6. The method according to claim 4, characterized in that, The step of obtaining the initial file data of the target object includes: Acquire image data of each target object within a preset spatiotemporal range; Clustering is performed on the image features of the acquired images in the acquired image data to obtain the initial file data of each target object.

7. The method according to claim 1, characterized in that, The step of using the license plate information in the target file data as the target identity information, and using the identity information associated with the license plate information in the preset vehicle registration data, includes: Select the license plate information that is the same as the license plate information from the preset vehicle registration data; The identity information corresponding to the same license plate information in the preset vehicle registration data is determined as the target identity information corresponding to the license plate information.

8. An identity matching device, characterized in that, include: The acquisition module is used to acquire target file data of the target object, which includes a captured facial image of the target object driving a vehicle and the identified license plate information. The determination module is used to determine the target identity information based on the license plate information in the target file data and the identity information associated with the license plate information in the preset vehicle registration data. The preset vehicle registration data includes the associated identity information and license plate information. The matching module is used to determine whether the number of target identity information associated with each license plate information in the target file data is equal to one. If the number of target identity information associated with each license plate information in the target file data is equal to one, the facial image in the target file data is matched with the identity image in the target identity information to obtain an identity matching result. In response to the number of target identity information associated with each license plate information in the target file data being greater than one, the facial image and other images captured when the target object drives the vehicle corresponding to each license plate information in the target file data are obtained. The other images include images in the target file data whose image quality is among the top in a preset ranking. Based on the matching results between the other images and the identity images in the target identity information corresponding to each license plate information in the target file data, the identity images in the target identity information corresponding to each license plate information in the target file data are determined as the target identity images. The identity image in the target identity information corresponding to each license plate information in the target file data is matched with the face image to obtain the identity matching result.

9. An electronic device, characterized in that, The method includes a memory and a processor, the processor being configured to execute program instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that, When the program instructions are executed by the processor, they implement the method described in any one of claims 1 to 7.

Images