Information comparison methods, devices, electronic devices and storage media

Abstract

This application relates to an information comparison method, apparatus, electronic device, and storage medium. The information comparison method includes: acquiring a reference captured image when an identity information image matching a target image file with preset matching conditions exists in an information database; performing a spatiotemporal comparison between the target captured image and the reference captured image in the target image file based on spatiotemporal information; determining a similarity threshold between the target captured image and the reference captured image based on the spatiotemporal comparison result; and determining the identity information associated with the reference captured image as the identity information of the target captured image when the similarity between the target captured image and the reference captured image is greater than the similarity threshold. This method adjusts the similarity threshold based on the spatiotemporal information of the captured image, thereby avoiding information comparison errors caused by excessively high image similarity, improving the accuracy of image information comparison, and consequently improving the accuracy of image clustering.

Description

Technical Field

[0001] This application relates to the field of image clustering, and in particular to information comparison methods, apparatus, electronic devices, and storage media. Background Art

[0002] With the development of facial recognition technology, current facial surveillance systems not only support facial recognition but also can perform facial clustering to obtain the travel trajectory of the identified individuals. Current facial clustering techniques often compare images based on their inherent features, lacking consideration of the temporal and spatial information of image acquisition. This leads to the presence of incorrectly clustered images due to excessively high facial similarity.

[0003] There is currently no effective solution to the problem of low accuracy in human face clustering results in related technologies. Summary of the Invention

[0004] This embodiment provides an information comparison method, apparatus, electronic device, and storage medium to address the problem of low accuracy in human image clustering results in related technologies.

[0005] Firstly, this embodiment provides an information comparison method, including:

[0006] Obtain the target image file; wherein the target image file is the clustering result obtained after processing the captured image based on a preset clustering algorithm;

[0007] If an identity information image exists in the information database that matches the target image file with a preset matching condition, a reference captured image whose capture time is within a preset time period and is associated with the identity information image is obtained.

[0008] Based on spatiotemporal information, a spatiotemporal comparison is performed between the target captured image in the target image archive and the reference captured image, and a similarity threshold between the target captured image and the reference captured image is determined based on the spatiotemporal comparison result; wherein, the spatiotemporal information includes the capture location information and capture time information of the target captured image, as well as the capture location information and capture time information of the reference captured image;

[0009] If the similarity between the target captured image and the reference captured image is greater than the similarity threshold, the identity information associated with the reference captured image is determined as the identity information of the target captured image.

[0010] In some embodiments, when an identity information image exists in the information database that matches the target image file with preset matching conditions, acquiring a reference captured image whose capture time is within a preset time period and is associated with the identity information image includes:

[0011] Select a preset number of images to be compared and captured from the target image archive;

[0012] If an identity information image exists in the information database that has a similarity to the image to be compared that meets a preset matching condition, a reference image that was captured within a preset time period and is associated with the identity information image is obtained.

[0013] In some embodiments, the step of performing a spatiotemporal comparison between the target captured image and the reference captured image in the target image archive based on spatiotemporal information, and determining a similarity threshold between the target captured image and the reference captured image based on the result of the spatiotemporal comparison, includes:

[0014] The capture time and capture location information of the target captured image in the target image file are obtained as the first spatiotemporal information;

[0015] The capture time and capture location information of the reference captured image are statistically analyzed, and the statistical results are determined as the second spatiotemporal information;

[0016] The first spatiotemporal information is compared with the second spatiotemporal information, and based on the comparison result of the first spatiotemporal information and the second spatiotemporal information, a similarity threshold between the target captured image and the reference captured image is determined.

[0017] In some embodiments, determining the similarity threshold between the target captured image and the reference captured image based on the comparison result of the first spatiotemporal information and the second spatiotemporal information includes:

[0018] If the comparison result shows that there is a capture location and time combination in the second spatiotemporal information that is consistent with the first spatiotemporal information, a first threshold corresponding to the comparison result is obtained based on a preset mapping relationship, and the first threshold is determined as the similarity threshold between the target capture image and the reference image.

[0019] In some embodiments, determining the similarity threshold between the target captured image and the reference captured image based on the comparison result of the first spatiotemporal information and the second spatiotemporal information further includes:

[0020] If the comparison result shows that there is only capture location information in the second spatiotemporal information that is consistent with the first spatiotemporal information, then obtain the number of captures at the capture locations in the second spatiotemporal information that are consistent with the first spatiotemporal information.

[0021] Based on a preset mapping relationship and the number of captures, a second threshold corresponding to the comparison result is obtained, and the second threshold is determined as the similarity threshold between the target capture image and the reference image; wherein, the value of the second threshold is greater than the similarity threshold corresponding to the case where the comparison result is that there is a capture location and time combination in the second spatiotemporal information that is consistent with the first spatiotemporal information, and the value of the second threshold is less than the similarity threshold corresponding to the case where the comparison result is that the second spatiotemporal information does not contain capture location information consistent with the first spatiotemporal information.

[0022] In some embodiments, determining the similarity threshold between the target captured image and the reference captured image based on the comparison result of the first spatiotemporal information and the second spatiotemporal information further includes:

[0023] If the comparison result shows that the second spatiotemporal information does not contain capture location information consistent with the first spatiotemporal information, a third threshold corresponding to the comparison result is obtained based on a preset mapping relationship, and the third threshold is determined as the similarity threshold between the target capture image and the reference capture image.

[0024] In some embodiments, the step of statistically analyzing the capture time and location information of the reference captured image and determining the statistical result as the second spatiotemporal information includes:

[0025] The capture time information of each capture location in the reference capture image is grouped and statistically analyzed to obtain the capture location time combination of the reference capture image and the number of captures at each capture location. The capture location time combination of the reference capture image and the number of captures at each capture location are determined as the second spatiotemporal information.

[0026] Secondly, this embodiment provides an information comparison device, including: an acquisition module, a matching module, a comparison module, and a determination module; wherein:

[0027] The acquisition module is used to acquire a target image file; wherein the target image file is a clustering result obtained by processing the captured image based on a preset clustering algorithm;

[0028] The matching module is used to obtain a reference captured image whose capture time is within a preset time period and which is associated with the identity information image when there is an identity information image in the information database whose matching result with the target image file meets the preset matching conditions.

[0029] The comparison module is used to perform a spatiotemporal comparison between the target captured image in the target image file and the reference captured image based on spatiotemporal information, and to determine a similarity threshold between the target captured image and the reference captured image based on the spatiotemporal comparison result; wherein, the spatiotemporal information includes capture location information and capture time information;

[0030] The determining module is used to determine the identity information associated with the reference captured image as the identity information of the target captured image when the similarity between the target captured image and the reference captured image is greater than the similarity threshold.

[0031] Thirdly, this embodiment provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the information comparison method described in the first aspect above.

[0032] Fourthly, this embodiment provides a storage medium storing a computer program that, when executed by a processor, implements the information comparison method described in the first aspect above.

[0033] Compared with related technologies, the information comparison method provided in this embodiment obtains a target image file. If an identity information image matching the target image file with preset matching conditions exists in the information database, a reference capture image whose capture time is within a preset time period and is associated with the identity information image is obtained. Based on spatiotemporal information, a spatiotemporal comparison is performed between the target capture image and the reference capture image in the target image file. A similarity threshold between the target capture image and the reference capture image is determined based on the spatiotemporal comparison result. If the similarity between the target capture image and the reference capture image is greater than the similarity threshold, the identity information associated with the reference capture image is determined as the identity information of the target capture image. This method adjusts the similarity threshold based on the spatiotemporal information of the captured images, thereby avoiding information comparison errors caused by excessively high image similarity, improving the accuracy of image information comparison, and consequently improving the accuracy of image clustering.

[0034] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0035] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0036] Figure 1 This is a hardware structure block diagram of the terminal for information comparison methods of related technologies;

[0037] Figure 2 This is a flowchart of the information comparison method in this embodiment;

[0038] Figure 3 This is a flowchart of the human image clustering method of this preferred embodiment;

[0039] Figure 4 This is a flowchart of the comparison result determination process in this preferred embodiment;

[0040] Figure 5 This is a structural block diagram of the information comparison device in this embodiment. Detailed Implementation

[0041] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0042] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning as understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.

[0043] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of the terminal for the information comparison method in this embodiment. For example... Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0044] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the information comparison method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0045] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0046] This embodiment provides an information comparison method. Figure 2 This is a flowchart of the information comparison method in this embodiment, such as... Figure 2 As shown, the process includes the following steps:

[0047] Step S210: Obtain the target image file; wherein, the target image file is the clustering result obtained after processing the captured image based on a preset clustering algorithm.

[0048] Specifically, the target image archive can be obtained by clustering several captured images using a preset image clustering algorithm. That is, the target image archive can be a collection of several captured images, and the captured objects in these images have a high probability of being the same object. It can be understood that the captured object can be pedestrians, animals, vehicles, etc. The following explanation will use a pedestrian as the captured object and a checkpoint as the capture location. For example, a camera installed at a checkpoint can capture images of pedestrians passing through the checkpoint, obtaining the captured images of the pedestrians. Furthermore, after capturing images of different pedestrians, and multiple images of each pedestrian, these multiple captured images belonging to different pedestrians can be clustered. Images belonging to the same pedestrian have a higher probability of being clustered into the same image archive. Further, during the processing of the captured images using the preset clustering algorithm, a similarity comparison can be performed between every two captured images, and a set threshold can be used to determine whether the two captured images belong to the same captured object. The preset clustering algorithm can be any algorithm suitable for image clustering, such as K-means clustering, spectral clustering, adjacency-based clustering, etc., without specific limitations.

[0049] Step S220: If there is an identity information image in the information database that matches the target image file with the preset matching conditions, obtain a reference capture image whose capture time is within a preset time period and is associated with the identity information image.

[0050] Specifically, the information database can be a database associated with the identity information of the captured object. The identity information image can be an image on a document containing identity information that is pre-registered in the information database. After obtaining the target image file in step S210, the matching results between the target image file and the identity information images containing identity information in the information database can be analyzed to further determine whether the target image file belongs to a particular captured object. Specifically, a preset number of target captured images can be selected from the target image file, and the similarity between the target captured images and the identity information images can be analyzed to determine whether the target image file matches the identity information images successfully. If the target image file matches the identity information images successfully, several reference captured images consistent with the identity information contained in the identity information images can be obtained. These reference captured images can be images captured within a historical time period with known identity information of the captured object.

[0051] For example, after obtaining the target image file a of pedestrian A based on step S210, the target image file a is matched with the image on the document containing the identity information of pedestrian B in the information database, that is, the identity information image of pedestrian B. If the similarity between the identity information image of pedestrian B and several target captured images of the target image file a is greater than a preset threshold, it can be determined that the target image file a and the identity information image of pedestrian B are successfully matched, and several reference captured images with the capture time within the past 7 days and the capture object has been identified as pedestrian B are obtained. In addition, besides using image similarity as the matching condition between the target image file and the identity information image in this embodiment, the preset matching condition can also be adjusted according to the actual application scenario, and there is no specific limitation on it.

[0052] Step S230: Based on spatiotemporal information, perform spatiotemporal comparison between the target captured image and the reference captured image in the target image file, and determine the similarity threshold between the target captured image and the reference captured image based on the spatiotemporal comparison results; wherein, the spatiotemporal information includes the capture location information and capture time information of the target captured image, as well as the capture location information and capture time information of the reference captured image.

[0053] Assuming that pedestrian B in the reference capture image and pedestrian A in the target capture image are likely to be the same person, as determined in step S220 above, to improve clustering accuracy, a similarity threshold between the target capture image and the reference capture image can be further determined based on spatiotemporal information. After obtaining the reference capture image, the capture location and capture time information of the reference capture image can be statistically analyzed to obtain the time period and number of captures for the target person in the reference capture image at each capture location. The capture location can be a checkpoint. For example, statistical analysis of all reference capture images of pedestrian B in the past 7 days yields the capture time period and number of captures for pedestrian B at each checkpoint: (Checkpoint 1, 8:00-9:00): 7 times; (Checkpoint 1, 18:00-19:00): 7 times; (Checkpoint 2, 11:30-13:00): 5 times; (Checkpoint 3, 8:30-9:00): 3 times.

[0054] The target image in the target image file is spatiotemporally compared with a reference image. Specifically, the capture location and capture time information of the target image are compared with those of the reference image. For example, if the target image of pedestrian A was captured at checkpoint 1 at 8:30, and according to the statistical results of the reference image, pedestrian B was at checkpoint 1 between 8:00 and 9:00, then it can be determined that the target image and the reference image have the same capture location and capture time, and therefore, pedestrian A and pedestrian B are likely the same person captured. In this case, a relatively low first threshold can be set between the target image and the reference image as the similarity threshold between the two images.

[0055] If the capture location of pedestrian A's current captured image is checkpoint 1, and the capture time is 12:00, then the target captured image and the reference captured image of pedestrian B only share the same capture location information. In this case, the probability that pedestrian A and pedestrian B are the same captured object is relatively low compared to the previous situation. Therefore, a second threshold greater than the first threshold can be set between the target captured image and the reference captured image as a similarity threshold between the two images. Furthermore, the value of the second threshold can also be determined based on the number of times pedestrian B is captured at checkpoint 1. Specifically, the value of the second threshold is determined based on the total number of times pedestrian B is captured at checkpoint 1, obtained statistically from the reference captured image, and the pre-established mathematical relationship between the number of captures and the second threshold. The higher the number of captures, the more frequently pedestrian B has passed through the checkpoint in the past 7 days, and the higher the probability that pedestrian A and pedestrian B are the same captured object; therefore, the lower the value of the second threshold. The minimum value of the second threshold is greater than the first threshold. Alternatively, the value of the second threshold can also be determined by other statistical results of the reference captured image, without specific limitations here.

[0056] Additionally, if the target capture image of pedestrian A is captured at checkpoint 4, and since no capture images belonging to checkpoint 4 are found in the reference capture image of pedestrian B, it can be understood that pedestrian B has never been to checkpoint 4 in the past 7 days. Therefore, it can be determined that the probability that pedestrian A and pedestrian B are the same capture object is lower than the two cases mentioned above. Thus, in order to improve the accuracy of confirming the identity information of pedestrian A, the similarity threshold between the target capture image and the reference capture image in this case can be set to a third threshold that is greater than the second threshold.

[0057] This application obtains the capture time and number of captures of the reference capture object at different capture locations by performing spatiotemporal information statistics on the reference capture image. Based on the spatiotemporal information comparison results between the target capture image and the reference capture image, a similarity threshold between the target capture image and the reference capture image is dynamically set. Compared with the current method of image clustering based solely on the similarity of the images themselves, this application can avoid erroneous clustering caused by the high similarity between the capture objects in the target capture image and the reference capture image, thereby improving the accuracy of information comparison and thus improving the accuracy of image clustering.

[0058] Step S240: If the similarity between the target captured image and the reference captured image is greater than the similarity threshold, the identity information associated with the reference captured image is determined as the identity information of the target captured image.

[0059] If the similarity based on image features between the target captured image and the reference captured image is greater than the similarity threshold determined in step S230 above, it can be determined that the captured object pedestrian B in the reference captured image and the captured object pedestrian A in the target captured image are the same captured object, thereby determining the identity information of pedestrian B as the identity information of pedestrian A.

[0060] Steps S210 to S240 involve acquiring a target image file. If an identity information image matching the target image file with preset matching conditions exists in the information database, a reference capture image whose capture time falls within a preset time period and is associated with the identity information image is acquired. Based on spatiotemporal information, a spatiotemporal comparison is performed between the target capture image and the reference capture image in the target image file. A similarity threshold between the target capture image and the reference capture image is determined based on the spatiotemporal comparison result. If the similarity between the target capture image and the reference capture image is greater than the similarity threshold, the identity information associated with the reference capture image is determined as the identity information of the target capture image. This method adjusts the similarity threshold based on the spatiotemporal information of the captured images, thereby avoiding information comparison errors caused by excessively high image similarity, improving the accuracy of image information comparison, and consequently improving the accuracy of image clustering.

[0061] Furthermore, in one embodiment, based on the above step S220, if there is an identity information image in the information database whose matching result with the target image file meets the preset matching conditions, a reference captured image whose capture time is within a preset time period and is associated with the identity information image is obtained, specifically including the following steps:

[0062] Step S221: Select a preset number of images to be compared and captured from the target image file;

[0063] Step S222: If there is an identity information image in the information database that has a similarity to the image to be compared that meets the preset matching conditions, obtain a reference image that was captured within a preset time period and is associated with the identity information image.

[0064] In another embodiment, based on step S230 above, a spatiotemporal comparison is performed between the target captured image and the reference captured image in the target image file based on spatiotemporal information, and a similarity threshold between the target captured image and the reference captured image is determined based on the spatiotemporal comparison result. This specifically includes the following steps:

[0065] Step S231: Obtain the capture time information and capture location information of the target capture image in the target image file as the first spatiotemporal information.

[0066] Step S232: Statistically analyze the capture time and capture location information of the reference captured image, and determine the statistical results as the second spatiotemporal information.

[0067] Step S233 involves comparing the first spatiotemporal information with the second spatiotemporal information, and determining a similarity threshold between the target captured image and the reference captured image based on the comparison result. Specifically, this comparison result can be the matching result between the capture time and capture location information in the first spatiotemporal information and the capture time and capture location information in the second spatiotemporal information. Determining the similarity threshold between the target captured image and the reference captured image based on the comparison result of the first and second spatiotemporal information improves the accuracy of information comparison, thereby improving the accuracy of image clustering.

[0068] Further, in one embodiment, based on step S233 above, and based on the comparison result of the first spatiotemporal information and the second spatiotemporal information, a similarity threshold between the target captured image and the reference captured image is determined. Specifically, this includes: if the comparison result shows that there is a capture location and time combination in the second spatiotemporal information that is consistent with the first spatiotemporal information, a first threshold corresponding to the comparison result is obtained based on a preset mapping relationship, and the first threshold is determined as the similarity threshold between the target captured image and the reference image. Specifically, this first threshold can be equal to the threshold used for clustering judgment in the preset clustering algorithm in step S210 above. The existence of a capture location and time combination in the second spatiotemporal information that is consistent with the first spatiotemporal information indicates that the capture time period corresponding to the capture location in the second spatiotemporal information that is consistent with the first spatiotemporal information also matches the capture time in the first spatiotemporal information. In this case, the probability that the captured object of the target captured image and the captured object of the reference captured image are the same object is high. Therefore, the threshold set by the preset clustering algorithm can be directly used as the similarity threshold.

[0069] In another embodiment, based on step S233 above, determining the similarity threshold between the target captured image and the reference captured image based on the comparison result of the first spatiotemporal information and the second spatiotemporal information further includes:

[0070] If the comparison result shows that the second spatiotemporal information only contains capture location information consistent with the first spatiotemporal information, the number of captures at the capture locations consistent with the first spatiotemporal information in the second spatiotemporal information is obtained; based on the preset mapping relationship and the number of captures, a second threshold corresponding to the comparison result is obtained, and the second threshold is determined as the similarity threshold between the target capture image and the reference image; wherein, the value of the second threshold is greater than the similarity threshold corresponding to the case where the comparison result shows that the second spatiotemporal information contains capture location time combinations consistent with the first spatiotemporal information, and the value of the second threshold is less than the similarity threshold corresponding to the case where the comparison result shows that the second spatiotemporal information does not contain capture location information consistent with the first spatiotemporal information.

[0071] Specifically, if the comparison result shows that the second spatiotemporal information only contains capture location information consistent with the first spatiotemporal information, it indicates that the reference capture image contains an image with a capture location consistent with the target capture image. However, the capture time period of the image in the reference capture image that matches the capture location of the target capture image does not match the capture time of the target capture image. Therefore, the probability that the target capture image and the reference capture image capture the same object is lower than the probability in the case of the combination of capture location and time in the first and second spatiotemporal information. A relatively high similarity threshold can be set for this type of comparison result.

[0072] Furthermore, the process of setting the second threshold can be illustrated by the following formula:

[0073]

[0074] Where β is the second threshold, and n is the total number of captures obtained by statistically analyzing the reference capture image at the capture location of the target capture image. The larger n is, the smaller β is. When n is 1, β reaches its maximum value, i.e., βmax. max The minimum value of β min It is greater than the threshold of the preset clustering algorithm mentioned above.

[0075] In another embodiment, based on the above step S233, determining the similarity threshold between the target capture image and the reference capture image based on the comparison result of the first spatiotemporal information and the second spatiotemporal information further includes: if the comparison result is that the second spatiotemporal information does not contain capture location information consistent with the first spatiotemporal information, obtaining a third threshold corresponding to the comparison result based on a preset mapping relationship, and determining the third threshold as the similarity threshold between the target capture image and the reference capture image.

[0076] In another embodiment, based on the above step S232, the capture time information and capture location information of the reference capture image are statistically analyzed, and the statistical results are determined as the second spatiotemporal information. Specifically, this includes: grouping and statistically analyzing the capture time information of each capture location in the reference capture image to obtain the capture location time combination of the reference capture image and the number of captures at each capture location, and determining the capture location time combination and the number of captures at each capture location as the second spatiotemporal information.

[0077] The present embodiment will now be described and illustrated through preferred embodiments.

[0078] Figure 3 This is a flowchart of the human face clustering method of this preferred embodiment, as shown below. Figure 3 As shown, the portrait clustering method includes the following steps:

[0079] Step S310: Obtain the portrait file a of the target pedestrian after the first clustering using a preset clustering algorithm;

[0080] Step S320: If the identity information of pedestrian B, which matches the portrait file a, exists in the information database, obtain all reference captured images of pedestrian B in the past 7 days.

[0081] Step S330: Group the reference captured images according to the checkpoint ID (identity document) and capture time, and count the number of times pedestrian B appears at each checkpoint and at each time period;

[0082] Step S340: Obtain the capture count statistics after grouping by checkpoint-time; and set the similarity threshold between the target capture image and the reference capture image based on the comparison result between the target capture image in portrait file a and the capture count statistics.

[0083] Step S350: If the similarity between the target captured image and the reference captured image is greater than the similarity threshold, then the target captured image is determined to belong to pedestrian B.

[0084] in, Figure 4 To determine the flowchart for the comparison results, in one embodiment, based on the above step S340, such as... Figure 4 As shown, based on the comparison results between the target captured image in portrait file a and the statistical results of the number of captures, a similarity threshold between the target captured image and the reference captured image is set, including the following steps:

[0085] Step S341: If the comparison result shows that both checkpoint and time are successfully matched, then the preset threshold α of the clustering algorithm is determined as the similarity threshold.

[0086] Step S342: If the comparison result is that only the checkpoint is successfully matched, then the number of times pedestrian B passed through the successfully matched checkpoint is determined based on the statistical results of the reference captured image. The threshold β is determined as the similarity threshold based on the number of times the checkpoint is matched, and β is greater than α.

[0087] In step S343, if the comparison result is that the checkpoint comparison fails, then the threshold γ that is greater than the threshold β is determined as the similarity threshold.

[0088] This embodiment also provides an information comparison device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. The terms "module," "unit," "subunit," etc., used below refer to combinations of software and / or hardware that perform a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0089] Figure 5 This is a structural block diagram of the information comparison device 50 in this embodiment, as shown below. Figure 5 As shown, the information comparison device 50 includes: an acquisition module 52, a matching module 54, a comparison module 56, and a determination module 58; wherein:

[0090] The acquisition module 52 is used to acquire the target image file; wherein, the target image file is the clustering result obtained after processing the captured image based on a preset clustering algorithm;

[0091] The matching module 54 is used to obtain a reference captured image whose capture time is within a preset time period and is associated with the identity information image when there is an identity information image in the information database whose matching result with the target image file meets the preset matching conditions.

[0092] The comparison module 56 is used to perform spatiotemporal comparison between the target captured image and the reference captured image in the target image file based on spatiotemporal information, and to determine the similarity threshold between the target captured image and the reference captured image based on the spatiotemporal comparison results; wherein, the spatiotemporal information includes capture location information and capture time information.

[0093] The determination module 58 is used to determine the identity information associated with the reference capture image as the identity information of the target capture image when the similarity between the target capture image and the reference capture image is greater than a similarity threshold.

[0094] The aforementioned information comparison device 50, by acquiring a target image file, and if an identity information image matching the target image file with preset matching conditions exists in the information database, acquires a reference captured image whose capture time is within a preset time period and is associated with the identity information image. Based on spatiotemporal information, it performs a spatiotemporal comparison between the target captured image and the reference captured image in the target image file, and determines a similarity threshold between the target captured image and the reference captured image based on the spatiotemporal comparison result. If the similarity between the target captured image and the reference captured image is greater than the similarity threshold, the identity information associated with the reference captured image is determined as the identity information of the target captured image. It adjusts the similarity threshold based on the spatiotemporal information of the captured images, thereby avoiding information comparison errors caused by excessively high image similarity, improving the accuracy of image information comparison, and consequently improving the accuracy of image clustering.

[0095] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0096] This embodiment also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0097] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0098] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0099] Obtain the target image file; wherein, the target image file is the clustering result obtained after processing the captured image based on a preset clustering algorithm;

[0100] If an identity information image exists in the information database that matches the target image file and meets the preset matching conditions, a reference captured image that was captured within a preset time period and is associated with the identity information image is obtained.

[0101] Based on spatiotemporal information, a spatiotemporal comparison is performed between the target captured image and the reference captured image in the target image archive, and a similarity threshold between the target captured image and the reference captured image is determined based on the spatiotemporal comparison results; wherein, the spatiotemporal information includes the capture location information and capture time information of the target captured image, as well as the capture location information and capture time information of the reference captured image.

[0102] If the similarity between the target captured image and the reference captured image is greater than the similarity threshold, the identity information associated with the reference captured image will be determined as the identity information of the target captured image.

[0103] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0104] Furthermore, in conjunction with the information comparison methods provided in the above embodiments, this embodiment can also provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any of the information comparison methods described in the above embodiments.

[0105] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0106] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0107] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0108] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. An information comparison method, characterized in that, include: Obtain the target image file; wherein the target image file is the clustering result obtained after processing the captured image based on a preset clustering algorithm; If an identity information image exists in the information database that matches the target image file with a preset matching condition, a reference captured image whose capture time is within a preset time period and is associated with the identity information image is obtained. Based on spatiotemporal information, a spatiotemporal comparison is performed between the target captured image in the target image archive and the reference captured image, and a similarity threshold between the target captured image and the reference captured image is determined based on the spatiotemporal comparison result; wherein, the spatiotemporal information includes the capture location information and capture time information of the target captured image, as well as the capture location information and capture time information of the reference captured image; If the similarity between the target captured image and the reference captured image is greater than the similarity threshold, the identity information associated with the reference captured image is determined as the identity information of the target captured image; wherein, the step of performing a spatiotemporal comparison between the target captured image and the reference captured image in the target image file based on spatiotemporal information, and determining the similarity threshold between the target captured image and the reference captured image based on the result of the spatiotemporal comparison, includes: The capture time and capture location information of the target captured image in the target image file are obtained as the first spatiotemporal information; The capture time and capture location information of the reference captured image are statistically analyzed, and the statistical results are determined as the second spatiotemporal information; The first spatiotemporal information is compared with the second spatiotemporal information. If the comparison result of the first spatiotemporal information and the second spatiotemporal information is that there is a capture location and time combination in the second spatiotemporal information that is consistent with the first spatiotemporal information, a first threshold corresponding to the comparison result is obtained based on a preset mapping relationship. The first threshold is determined as the similarity threshold between the target capture image and the reference capture image.

2. The information comparison method according to claim 1, characterized in that, When an identity information image exists in the information database that matches the target image file according to preset matching conditions, acquiring a reference captured image whose capture time is within a preset time period and is associated with the identity information image includes: Select a preset number of images to be compared and captured from the target image archive; If an identity information image exists in the information database that has a similarity to the image to be compared that meets a preset matching condition, a reference image that was captured within a preset time period and is associated with the identity information image is obtained.

3. The information comparison method according to claim 1, characterized in that, The method further includes: If the comparison result shows that there is only capture location information in the second spatiotemporal information that is consistent with the first spatiotemporal information, then obtain the number of captures at the capture locations in the second spatiotemporal information that are consistent with the first spatiotemporal information. Based on a preset mapping relationship and the number of captures, a second threshold corresponding to the comparison result is obtained, and the second threshold is determined as the similarity threshold between the target capture image and the reference capture image; wherein, the value of the second threshold is greater than the similarity threshold corresponding to the case where the comparison result is that there is a capture location and time combination in the second spatiotemporal information that is consistent with the first spatiotemporal information, and the value of the second threshold is less than the similarity threshold corresponding to the case where the comparison result is that the second spatiotemporal information does not contain capture location information consistent with the first spatiotemporal information.

4. The information comparison method according to claim 1, characterized in that, The method further includes: If the comparison result is that the second spatiotemporal information does not contain capture location information consistent with the first spatiotemporal information, a third threshold corresponding to the comparison result is obtained based on a preset mapping relationship, and the third threshold is determined as the similarity threshold between the target capture image and the reference capture image.

5. The information comparison method according to claim 1, characterized in that, The step of statistically analyzing the capture time and location information of the reference captured image and determining the statistical result as the second spatiotemporal information includes: The capture time information of each capture location in the reference capture image is grouped and statistically analyzed to obtain the capture location time combination of the reference capture image and the number of captures at each capture location. The capture location time combination of the reference capture image and the number of captures at each capture location are determined as the second spatiotemporal information.

6. An information comparison device, characterized in that, include: The module includes an acquisition module, a matching module, a comparison module, and a determination module; among which: The acquisition module is used to acquire a target image file; wherein the target image file is a clustering result obtained by processing the captured image based on a preset clustering algorithm; The matching module is used to obtain a reference captured image whose capture time is within a preset time period and which is associated with the identity information image when there is an identity information image in the information database whose matching result with the target image file meets the preset matching conditions. The comparison module is used to perform a spatiotemporal comparison between the target captured image in the target image archive and the reference captured image based on spatiotemporal information, and to determine a similarity threshold between the target captured image and the reference captured image based on the spatiotemporal comparison result; wherein, the spatiotemporal information includes the capture location information and capture time information of the target captured image, and the capture location information and capture time information of the reference captured image; The determining module is configured to, when the similarity between the target captured image and the reference captured image is greater than the similarity threshold, determine the identity information associated with the reference captured image as the identity information of the target captured image; wherein, the step of performing a spatiotemporal comparison between the target captured image and the reference captured image in the target image archive based on spatiotemporal information, and determining the similarity threshold between the target captured image and the reference captured image based on the result of the spatiotemporal comparison, includes: The capture time and capture location information of the target captured image in the target image file are obtained as the first spatiotemporal information; The capture time and capture location information of the reference captured image are statistically analyzed, and the statistical results are determined as the second spatiotemporal information; The first spatiotemporal information is compared with the second spatiotemporal information. If the comparison result of the first spatiotemporal information and the second spatiotemporal information is that there is a capture location and time combination in the second spatiotemporal information that is consistent with the first spatiotemporal information, a first threshold corresponding to the comparison result is obtained based on a preset mapping relationship. The first threshold is determined as the similarity threshold between the target capture image and the reference capture image.

7. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the information comparison method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the information comparison method according to any one of claims 1 to 5.

Images