A target clustering method, device and storage medium based on temporary space-time

Abstract

This application relates to a method, apparatus, and storage medium for target archiving based on temporary spatiotemporal space. The method includes: acquiring archive information of targets in a target region after target archiving; the target region includes multiple image acquisition devices; based on the target archive information, determining point-of-interest (POI) information within a first preset distance range of the image acquisition devices and distance information between the image acquisition devices; constructing a temporary spatiotemporal space of the target based on the POI information of the image acquisition devices and the distance information between the image acquisition devices; and archiving the acquired shooting data based on the temporary spatiotemporal space of the target. By constructing the temporary spatiotemporal space of the target based on the POI information of the image acquisition devices and the distance information between the image acquisition devices, and then archiving the acquired shooting data based on the temporary spatiotemporal space of the target, the recall rate of target archiving is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image processing, and in particular to a target clustering method and device based on temporary space-time and a storage medium. BACKGROUND

[0002] With the continuous progress of target clustering technology, the target archives formed according to face recognition technology have become important reference information for relevant departments. The relevant personnel's track is restored based on the target archives, and key information such as the same person is found based on the track.

[0003] The existing target clustering technology is based on the target pictures captured by a camera, and the target pictures are analyzed by deep learning technology to form feature vectors, and then similarity calculation is performed based on the feature vectors to perform target clustering. However, due to different capture distances, capture angles, and capture devices, the similarity of pictures of the same target may not meet the clustering conditions, resulting in the phenomenon of one person having multiple archives, and the target track cannot be completely restored. Therefore, how to effectively improve the recall rate of target clustering is a problem to be solved. SUMMARY

[0004] In the present embodiment, a target clustering method and device based on temporary space-time and a storage medium are provided to solve the problem of how to effectively improve the recall rate of target clustering in the prior art.

[0005] In a first aspect, a target clustering method based on temporary space-time is provided in the present embodiment, and the method comprises:

[0006] Obtaining archive information of a target after target clustering in a target area; the target area comprises a plurality of image acquisition devices;

[0007] Based on the archive information of the target, determining interest point information within a first preset distance range of the image acquisition device and distance information between the image acquisition devices;

[0008] According to the interest point information of the image acquisition device and the distance information between the image acquisition devices, constructing a temporary space-time of the target;

[0009] According to the temporary space-time of the target, the obtained shooting data is clustered.

[0010] In some embodiments, based on the archive information of the target, the interest point information within the first preset distance range of the image acquisition device and the distance information between the image acquisition devices are determined, comprising:

[0011] Obtaining a plurality of continuous shooting data in the archive information of the target; each of the shooting data comprises image acquisition device information and shooting time information;

[0012] Based on the image acquisition device information, determine the interest point information within a first preset distance range of the image acquisition device in the continuous multiple pieces of shooting data and the distance information between the image acquisition devices.

[0013] In some embodiments, according to the interest point information of the image acquisition device and the distance information between the image acquisition devices, construct the temporary space-time of the target, including:

[0014] According to the distance information between the image acquisition devices, obtain the distance between the image acquisition devices that shoot the target;

[0015] According to the shooting time information, obtain the shooting time difference in the continuous multiple pieces of shooting data of the target;

[0016] If the distance between the image acquisition devices is less than a second preset distance, and the maximum value of the shooting time difference in the continuous multiple pieces of shooting data of the target is greater than a first preset time, then determine the temporary space-time of the target according to the continuous multiple pieces of shooting data.

[0017] In some embodiments, the determination of the temporary space-time of the target according to the continuous multiple pieces of shooting data includes:

[0018] Obtain the intersection of the interest point information within the first preset distance range of the image acquisition device;

[0019] Determine the interest point information of the temporary space-time of the target according to the intersection of the interest point information within the first preset distance range of the image acquisition device.

[0020] In some embodiments, the construction of the temporary space-time of the target according to the interest point information of the image acquisition device and the distance information between the image acquisition devices includes:

[0021] According to the distance information between the image acquisition devices, obtain the distance between the image acquisition devices that shoot the target;

[0022] According to the shooting time information, obtain the shooting time difference in the continuous multiple pieces of shooting data of the target;

[0023] If the distance between the image acquisition devices is less than a third preset distance, and the maximum value of the shooting time difference in the continuous multiple pieces of shooting data of the target is greater than a second preset time, then determine the temporary space-time of the target according to the continuous multiple pieces of shooting data; wherein the third preset distance is less than the second preset distance.

[0024] In some embodiments, the step of archiving the obtained shooting data according to the temporary space-time of the target comprises:

[0025] When the interest point information of the temporary space-time of the two targets intersects, the temporary space-time of the two targets is taken as a union to obtain an extended temporary space-time;

[0026] The obtained shooting data is archived based on the extended temporary space-time.

[0027] In some embodiments, the step of archiving the obtained shooting data according to the temporary space-time of the target comprises:

[0028] When the ratio of the number of the first image collection devices to the number of the second image collection devices is greater than a preset value, the temporary space-time of the two targets is taken as a union to obtain an extended temporary space-time; the number of the first image collection devices is the number of the same image collection devices in the temporary space-time of the two targets, and the number of the second image collection devices is the sum of the number of the image collection devices of the temporary space-time of the two targets;

[0029] The obtained shooting data is archived based on the extended temporary space-time.

[0030] In some embodiments, the step of archiving the obtained shooting data according to the temporary space-time of the target comprises:

[0031] The obtained shooting data is archived according to the periodicity or correlation of the temporary space-time of the target.

[0032] In a second aspect, the present embodiment provides a target archiving device based on temporary space-time, which comprises:

[0033] A first obtaining module is configured to obtain the archive information of a target after target archiving in a target area; the target area comprises a plurality of image collection devices;

[0034] A second obtaining module is configured to determine the interest point information within a first preset distance range of the image collection devices and the distance information between the image collection devices based on the archive information of the target;

[0035] A constructing module is configured to construct the temporary space-time of the target according to the interest point information of the image collection devices and the distance information between the image collection devices;

[0036] An archiving module is configured to archive the obtained shooting data according to the temporary space-time of the target.

[0037] In a third aspect, a computer readable storage medium is provided in the present embodiment, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to perform the steps of the target aggregation method based on temporary space-time of the first aspect.

[0038] Compared with the prior art, the target aggregation method, device and storage medium based on temporary space-time provided in the present embodiment improve the recall rate of target aggregation by constructing the temporary space-time of the target according to the interest point information of the image acquisition device and the distance information between the image acquisition devices, and aggregating the captured data according to the temporary space-time of the target.

[0039] Details of one or more embodiments of the present application are presented in the following drawings and description to make other features, objects and advantages of the present application more apparent. BRIEF DESCRIPTION OF DRAWINGS

[0040] The drawings described herein are intended to provide further understanding of the present application, and form a part of the present application. The schematic embodiments of the present application and the description thereof are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0041] Figure 1 is a hardware structure block diagram of a terminal for performing the target aggregation method based on temporary space-time of the present embodiment;

[0042] Figure 2 is a flowchart of the target aggregation method based on temporary space-time of the present embodiment;

[0043] Figure 3 is another flowchart of the target aggregation method based on temporary space-time of the present embodiment;

[0044] Figure 4 is another flowchart of the target aggregation method based on temporary space-time of the present embodiment;

[0045] Figure 5 is another flowchart of the target aggregation method based on temporary space-time of the present embodiment;

[0046] Figure 6 is a flowchart of the portrait aggregation method based on temporary space-time of the present preferred embodiment;

[0047] Figure 7 is a structure block diagram of the target aggregation device based on temporary space-time of the present embodiment. DETAILED DESCRIPTION

[0048] In order to more clearly understand the objects, technical solutions and advantages of the present application, the present application is described and explained in the following with reference to the drawings and embodiments.

[0049] 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.

[0050] 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 a terminal executing a temporary spatiotemporal target aggregation method according to an embodiment of this application. 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.

[0051] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to a temporary spatiotemporal target aggregation 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 aforementioned 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.

[0052] 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.

[0053] This embodiment provides a target aggregation method based on temporary spatiotemporal conditions. Figure 2 This is a flowchart of a target archiving method based on temporary spatiotemporal context according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0054] Step S210: Obtain the target archive information of the target area after target aggregation; the target area includes multiple image acquisition devices.

[0055] Specifically, the target area here refers to the area where target archiving is required. This target area includes multiple image acquisition devices used to capture or photograph targets, which can be human figures or objects. After archiving the targets in the target area, target profile information is formed. This profile information includes multiple pieces of shooting data, including but not limited to captured images, information about the image acquisition device that captured the images, and the time the images were captured. For example, the image acquisition devices here include, but are not limited to, cameras, checkpoint devices, and high-definition cameras. Furthermore, for example, the image acquisition device information here includes, but is not limited to, the identifier of the image acquisition device, the name of the image acquisition device, and the latitude and longitude information of the image acquisition device.

[0056] Step S220: Based on the target's archive information, determine the point of interest information within a first preset distance range of the image acquisition device and the distance information between the image acquisition devices.

[0057] Specifically, based on the shooting data in the target's archive information obtained in step S210, the latitude and longitude information of the image acquisition device capturing the image in each shooting data is obtained. Based on the latitude and longitude information of the image acquisition device, point-of-interest (POI) information within a first preset distance range of the image acquisition device is obtained from existing map information. Furthermore, based on the latitude and longitude information of the image acquisition device, the distance information between the image acquisition device and other image acquisition devices is obtained from existing map information. Here, the POI information includes the identifier or name of the POI, and the distance information includes the distance between the image acquisition device and other image acquisition devices.

[0058] Step S230: Construct a temporary spatiotemporal representation of the target based on the point of interest information of the image acquisition device and the distance information between the image acquisition devices.

[0059] Specifically, based on the point of interest information of the image acquisition devices and the distance information between the image acquisition devices determined in step S220, a temporary spatiotemporal space of the target is constructed. Each target can correspond to a temporary spatiotemporal space.

[0060] Step S240: Based on the temporary spatiotemporal context of the target, the acquired shooting data is archived.

[0061] Specifically, based on the temporary spatiotemporal space of the target constructed in step S230, the un-archived shooting data acquired by the image acquisition device is archived.

[0062] In this embodiment, a temporary spatiotemporal space of the target is constructed based on the point of interest information of the image acquisition device and the distance information between the image acquisition devices. Based on the temporary spatiotemporal space of the target, the acquired shooting data is clustered, thereby improving the recall rate of target clustering.

[0063] In some embodiments, step S220 involves determining, based on the target's profile information, point-of-interest information within a first preset distance range of the image acquisition device and distance information between the image acquisition devices, such as... Figure 3 As shown, it includes the following steps:

[0064] Step S221: Obtain multiple consecutive shooting data from the target's archive information; each shooting data includes image acquisition device information and shooting time information.

[0065] Specifically, the target's file information includes multiple sets of shooting data, each set containing information about the image acquisition device and the shooting time. Based on the shooting time information of each set, the multiple sets of shooting data in the target's file information are sorted by shooting time. Then, based on the sorted data, multiple consecutive sets of shooting data are obtained. The image acquisition device information here includes, but is not limited to, the identifier of the image acquisition device, the name of the image acquisition device, and the latitude and longitude information of the image acquisition device.

[0066] Step S222: Based on the image acquisition device information, determine the point of interest information and the distance information between the image acquisition devices within a first preset distance range of the image acquisition device in multiple consecutive shooting data.

[0067] Specifically, based on the latitude and longitude information of the image acquisition device in the image acquisition device information, point-of-interest (POI) information within a first preset distance range of the image acquisition device is obtained from existing map information. Furthermore, based on the latitude and longitude information of the image acquisition device, distance information between the image acquisition device and other image acquisition devices is obtained from existing map information. The POI information here includes the identifier or name of the POI, and the distance information includes the distance between the image acquisition device and other image acquisition devices.

[0068] In some embodiments, step S230 involves constructing a temporary spatiotemporal representation of the target based on the point of interest information of the image acquisition devices and the distance information between the image acquisition devices, such as... Figure 4 As shown, it includes:

[0069] Step S231: Obtain the distance between the image acquisition devices of the target based on the distance information between the image acquisition devices.

[0070] Specifically, based on the distance information between image acquisition devices, the distance between the current image acquisition device and other image acquisition devices is determined, thereby obtaining the distance between the image acquisition devices of the target being captured.

[0071] Step S232: Based on the shooting time information, obtain the shooting time difference in multiple consecutive shooting data of the target.

[0072] Specifically, based on the shooting time information in each shooting data, the shooting time difference between the shooting data in the consecutive multiple shooting data is determined.

[0073] Step S233: If the distance between the image acquisition devices is less than the second preset distance, and the maximum value of the shooting time difference in the multiple consecutive shooting data of the target is greater than the first preset time, then the temporary spatiotemporal space of the target is determined based on the multiple consecutive shooting data.

[0074] Specifically, based on the distance between the image acquisition devices of the target, it is determined whether the distance between the image acquisition devices is less than a second preset distance; based on the shooting time difference between the shooting data in multiple consecutive shooting data, the maximum value of the shooting time difference is determined. When the distance between the image acquisition devices is less than the second preset distance, and the maximum value of the shooting time difference in multiple consecutive shooting data of the target is greater than a first preset time, the multiple consecutive shooting data are determined as the temporary spatiotemporal space of the target.

[0075] More specifically, the intersection of point-of-interest (POI) information within a first preset distance range of the image acquisition device is obtained, and the temporary spatiotemporal POI information of the target is determined based on the intersection of the POI information within the first preset distance range of the image acquisition device. The set of POIs obtained by intersecting the POI information of the image acquisition device is the POI information of this temporary spatiotemporal location.

[0076] In some embodiments, step S230 involves constructing a temporary spatiotemporal representation of the target based on the point of interest information of the image acquisition devices and the distance information between the image acquisition devices, such as... Figure 5 As shown, it also includes:

[0077] Step S235: Obtain the distance between the image acquisition devices of the target based on the distance information between the image acquisition devices.

[0078] Specifically, based on the distance information between image acquisition devices, the distance between the current image acquisition device and other image acquisition devices is determined, thereby obtaining the distance between the image acquisition devices of the target being captured.

[0079] Step S236: Based on the shooting time information, obtain the shooting time difference in multiple consecutive shooting data of the target.

[0080] Specifically, based on the shooting time information in each shooting data, the shooting time difference between the shooting data in the consecutive multiple shooting data is determined.

[0081] Step S237: If the distance between the image acquisition devices is less than the third preset distance, and the maximum value of the shooting time difference in the multiple consecutive shooting data of the target is greater than the second preset time, then the temporary spatiotemporal space of the target is determined based on the multiple consecutive shooting data; wherein, the third preset distance is less than the second preset distance.

[0082] Specifically, based on the distance between the image acquisition devices of the target, it is determined whether the distance between the image acquisition devices is all less than a third preset distance; based on the shooting time difference between multiple consecutive shooting data, the maximum value of the shooting time difference is determined. When the distance between the image acquisition devices is all less than the third preset distance, and the maximum value of the shooting time difference between multiple consecutive shooting data of the target is greater than a second preset time, the multiple consecutive shooting data are determined as the temporary spatiotemporal region of the target. Here, the second preset time can be the same as the first preset time, or it can be the same as but different from the first preset time. No specific limitation is made here.

[0083] In some of these embodiments, the process of clustering the acquired shooting data based on the temporary spatiotemporal space of the target includes: when the point of interest information of the temporary spatiotemporal spaces of two targets intersects, taking the union of the temporary spatiotemporal spaces of the two targets to obtain an expanded temporary spatiotemporal space; and clustering the acquired shooting data based on the expanded temporary spatiotemporal space.

[0084] In some embodiments, the aggregation of acquired shooting data based on the temporary spatiotemporal space of the target includes: when the ratio of the number of first image acquisition devices to the number of second image acquisition devices is greater than a preset value, taking the union of the temporary spatiotemporal spaces of the two targets to obtain an expanded temporary spatiotemporal space; the number of first image acquisition devices is the number of identical image acquisition devices in the temporary spatiotemporal spaces of the two targets, and the number of second image acquisition devices is the sum of the number of image acquisition devices in the temporary spatiotemporal spaces of the two targets; and the aggregation of acquired shooting data based on the expanded temporary spatiotemporal space.

[0085] In some of these embodiments, the acquired shooting data is clustered according to the temporary spatiotemporal nature of the target, including: clustering the acquired shooting data according to the periodicity or correlation of the temporary spatiotemporal nature of the target.

[0086] The embodiments of this application will be described and illustrated below through preferred embodiments.

[0087] Figure 6 This is a flowchart of a temporary spatiotemporal portrait aggregation method according to a preferred embodiment of the present invention, such as... Figure 6 As shown, this method for capturing images based on temporary spatiotemporal conditions includes the following steps:

[0088] Step S610: Obtain the portrait archives of all portraits within the specified area for the past N days.

[0089] Specifically, obtain all the portrait files after portrait aggregation within the specified area in the recent N days, including captured pictures, captured checkpoints, capture times, longitude and latitude of the captured checkpoints, etc. The specified area here is the area where portrait aggregation needs to be performed. The checkpoint here is equivalent to the image acquisition device in the foregoing embodiment, and the portrait here is equivalent to the target described in the foregoing embodiment. For example, after portrait aggregation of all portraits within the specified area in the recent N days, multiple portrait files are generated. P m is one of the portrait files. Each portrait file includes multiple captured data. The captured data here is equivalent to the captured data in the foregoing embodiment. Sort the captured data in the file according to the capture time. The sorted portrait file P m is as shown in formula (1).

[0090]

[0091] Among them, (T mi , C mi , G mi ) is a piece of captured data. T mi is the capture time corresponding to the i-th captured picture in the portrait file P m . C mi is the corresponding captured checkpoint, and G mi is the longitude and latitude of the corresponding captured checkpoint. The portrait file P m also includes n captured pictures. Among them, i is an integer from 1 to n, and n is an integer greater than 1.

[0092] Step S620, obtain the point-of-interest information of the checkpoints and the shortest walking distance between the checkpoints, and mine the temporary spatio-temporal of the file trajectory.

[0093] Specifically, obtain all the portrait captured checkpoint information within the specified area. Based on the longitude and latitude of the checkpoint on the map, obtain the set of all POI (point of interest) information within M meters around each checkpoint. Then, based on the longitude and latitude of the checkpoint on the map, obtain the shortest walking distance between two checkpoints and record it as the walking distance between the checkpoints. Among them, M>0, and M is a configurable parameter. Mine the temporary spatio-temporal of the file trajectory for each portrait file. When a continuous segment of captured data in the file meets one of the following situations, the spatio-temporal information corresponding to this continuous segment of captured data is a temporary spatio-temporal of this file: (1) If there are multiple consecutive captured data in the file, the shortest walking distance between the captured checkpoints is less than the distance D1 for each pair, and there is an intersection in the set of POI information within M meters around all checkpoints. At the same time, the maximum capture time difference is greater than the time T, and the POI set after the intersection of the checkpoints is the POI information of this temporary spatio-temporal. (2) If there are multiple consecutive captured data in the file, the shortest walking distance between the captured checkpoints is less than the distance D2 (where D2<D1), and at the same time, the maximum capture time difference is greater than T.

[0094] For example, a portrait file P m The continuous capture data includes checkpoint C m1 C-gate m2 C-gate m3 Checkpoint C m1 C-gate m2 C-gate m3 The distance between the two routes is less than D1, and the POI information within M meters of these three checkpoints is all shopping mall A, while also satisfying T. m3 -T m1 >T, then (T m1 C m1 G m1 ),(T m2 C m2 G m2 ),(T m3 C m3 G m3 These three sets of captured data form a portrait profile (P). m A temporary spacetime.

[0095] Step S630: Explore the temporary spatiotemporal characteristics of each portrait file to assist in portrait aggregation.

[0096] Specifically, based on the temporary spatiotemporal context of each file, the study aims to determine whether the file exhibits periodic characteristics, including daily, weekly, and monthly periods. For example, there exists a portrait file P. m Every Sunday afternoon from 2 PM to 4 PM, a temporary Point of Interest (POI) is generated at a checkpoint near Mall A, specifically for Mall A. However, on a certain Sunday afternoon from 2 PM to 4 PM, the image file P... m Since there is no snapshot data, it can be determined that the issue is likely due to multiple settings. Therefore, the portrait file can be edited. m and portrait archives P m The POI information is used to capture images of people at the checkpoint near shopping mall A during the time period (2:00 to 4:00). The image merging threshold can be slightly lowered to retrieve the files.

[0097] Specifically, based on the temporary spatiotemporal space of each file, the similarity of the temporary spatiotemporal space is calculated to mine highly similar temporary spatiotemporal spaces, thereby finding out whether there are cases where some captured data is missing from the archive. When two temporary spatiotemporal spaces of a portrait file meet one of the following conditions, the two temporary spatiotemporal spaces are considered highly similar temporary spatiotemporal spaces: (1) when the POI information corresponding to the two temporary spatiotemporal spaces has an intersection; (2) when the number of intersections of the checkpoints of the two temporary spatiotemporal spaces exceeds the percentage threshold of the total number of checkpoints in the two temporary spatiotemporal spaces.

[0098] For example, information mining is performed based on different checkpoints between multiple highly similar temporary spatiotemporal points, such as file P. m There exist two highly similar temporary spacetimes, temporary spacetime K1 and temporary spacetime K2, wherein temporary spacetime K1 includes (T m1 C m1 G m1 ),(T m2 C m2 G m2 ),(T m3 C m3 G m3 Three capture data points, temporary spatiotemporal K2 includes (T m(n-3) C m(n-3) G m(n-3) ), (T m(n-2) C m(n-2) G m(n-2) ), (T m(n-1) C m(n-1) G m(n-1) Three capture data points, of which temporary spatiotemporal K1 passed through checkpoint C. m1 C-gate m2 C-gate m3 Temporary spacetime K2 passes through checkpoint C m(n-3) C-gate m(n-2) C-gate m(n-1) And C m1 ≠C m(n-3) C m2 =C m(n-2) C m3 =C m(n-1) So when the portrait file P m When passing through temporary spacetime K1, there may be a checkpoint C. m(n-3) The captured data failed to be successfully archived, similarly when the portrait file P... m When passing through temporary spacetime K2, C may exist. m1 The data captured at the checkpoint was not successfully archived. Therefore, the portrait file was P... m The facial and body images corresponding to the three snapshot data points of temporary spacetime K1 are compared with [T] m1 -θ,T m3 +θ] This time period is at checkpoint C m(n-3) The captured face image and body image are compared for similarity (with a slightly lowered clustering threshold). If the similarity between the face image and body image is greater than the clustering threshold (which can be a similarity threshold), they are merged. Here, θ is an adjustable time parameter. Similarly, the portrait file P is... m The facial and body images corresponding to the three capture data points of the temporary spacetime K2 are compared with [ m(n-3) -,T m(n-1)+] This time period is at checkpoint C m1 The captured face image and body image are compared for similarity (with a slightly lowered clustering threshold). If the similarity between the face image and body image is greater than the clustering threshold (which can be a similarity threshold), they are merged. Here, θ is an adjustable time parameter.

[0099] Specifically, based on the temporary spatiotemporal context of each archive, we explore whether there are any correlations between the temporary spatiotemporal contexts of the archives. (Image archive P) m Including temporary spacetime K3 and temporary spacetime K4, and portrait archive P m If a person appears in temporary spacetime K3 and then reappears in temporary spacetime K4 every X hours, then the person profile P is considered to be... m Temporary spacetimes K3 and K4 are related. When there is a portrait file P m If a subject appears in temporary timespace K3 but does not appear in temporary timespace K4 within X hours, it is considered that multiple snapshots may have occurred, causing the snapshot data in temporary timespace K4 to be inconsistent with the portrait file P. m Successfully assembled the files, therefore the portrait file P m The captured data and all images appearing in temporary spacetime K4 within X hours after temporary spacetime K3 are combined into a portrait file, and the portrait file merging threshold can be slightly lowered to retrieve the file. Here, the portrait file P... m It appears in temporary spacetime K3 and will appear in temporary spacetime K4 every time within X hours. After obtaining a capture data for the checkpoint in temporary spacetime K3, it will obtain a capture data for the checkpoint in temporary spacetime K4 every time within X hours.

[0100] Specifically, based on the temporary spatiotemporal context of each file, temporary spatiotemporal preferences are mined. First, the POI information within a specified area is functionally divided, for example, into residential areas, office areas, hospitals, schools, etc. For example, for a portrait file P... m If a person's profile frequently appears at night in various temporary locations where their POI information indicates their residence, then that person's profile can be considered m. m The corresponding users are those who prefer nighttime residences, so the data captured by checkpoints near nighttime residences can be slightly reduced compared to the image profile. m The threshold for portrait clustering is used to assist in portrait clustering.

[0101] In this embodiment, based on the temporary spatiotemporal characteristics of the archives, the features of these temporary spatiotemporal characteristics are mined, such as periodicity, highly similar temporary spatiotemporal characteristics, spatiotemporal correlations, and preferences. Based on these characteristics, the time and region where archives may have been missed in clustering are identified, assisting in the clustering of facial images and thus improving the recall rate of facial image archives.

[0102] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0103] This embodiment also provides a temporary spatiotemporal portrait aggregation device, which is used to implement 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 implement 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.

[0104] Figure 7 This is a structural block diagram of a target aggregation device based on temporary spatiotemporal space according to an embodiment of this application, such as... Figure 7 As shown, the device includes:

[0105] The first acquisition module 710 is used to acquire the file information of the target after target aggregation in the target area; the target area includes multiple image acquisition devices;

[0106] The second acquisition module 720 is used to determine, based on the target's archive information, point of interest information within a first preset distance range of the image acquisition device and distance information between the image acquisition devices;

[0107] Module 730 is used to construct a temporary spatiotemporal structure of the target based on the point of interest information of the image acquisition device and the distance information between the image acquisition devices;

[0108] The aggregation module 740 is used to aggregate the acquired shooting data based on the temporary spatiotemporal context of the target.

[0109] 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.

[0110] This embodiment also provides an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0111] 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.

[0112] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0113] S1, acquire the target archive information of the target area after target aggregation; the target area includes multiple image acquisition devices;

[0114] S2, based on the target's archive information, determine the point of interest information and the distance information between the image acquisition devices within a first preset distance range;

[0115] S3, construct a temporary spatiotemporal structure of the target based on the point of interest information of the image acquisition device and the distance information between the image acquisition devices;

[0116] S4 aggregates the acquired shooting data based on the target's temporary spatiotemporal context.

[0117] 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.

[0118] Furthermore, in conjunction with the target archiving method based on temporary spatiotemporal space provided in the above embodiments, this embodiment can also provide a storage medium for implementation. The storage medium stores a computer program; when executed by a processor, the computer program implements the steps of any of the target archiving methods based on temporary spatiotemporal space provided in the above embodiments.

[0119] It should be noted that the user information (including but not limited to user device information, user personal information, user target information, user facial image information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively 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. A target aggregation method based on temporary spatiotemporal conditions, characterized in that, The method includes: The system acquires the target archive information of the target area after target aggregation; the target area includes multiple image acquisition devices. Based on the target's archive information, determine the point of interest information within a first preset distance range of the image acquisition device and the distance information between the image acquisition devices; Based on the point of interest information of the image acquisition device and the distance information between the image acquisition devices, a temporary spatiotemporal structure of the target is constructed; The step of constructing the temporary spatiotemporal space of the target based on the point of interest information of the image acquisition devices and the distance information between the image acquisition devices includes: obtaining the distance between the image acquisition devices that captured the target based on the distance information between the image acquisition devices; obtaining the shooting time difference in the continuous multiple shooting data of the target based on the shooting time information of each shooting data in the continuous multiple shooting data of the target; if the distance between the image acquisition devices is less than a second preset distance, and the maximum value of the shooting time difference in the continuous multiple shooting data of the target is greater than a first preset time, then determining the temporary spatiotemporal space of the target based on the continuous multiple shooting data; Based on the temporary spatiotemporal context of the target, the acquired shooting data is archived.

2. The target aggregation method based on temporary spatiotemporal conditions according to claim 1, characterized in that, The determination of point-of-interest information within a first preset distance range of the image acquisition device and distance information between the image acquisition devices based on the archive information of the target includes: Acquire multiple consecutive data entries from the target's archive information; each data entry includes image acquisition device information and shooting time information; Based on the image acquisition device information, the point of interest information within a first preset distance range of the image acquisition device and the distance information between the image acquisition devices are determined in the continuous multiple shooting data.

3. The target aggregation method based on temporary spatiotemporal conditions according to claim 1, characterized in that, The step of determining the temporary spatiotemporal location of the target based on the continuous multiple sets of captured data includes: Obtain the intersection of point-of-interest information within a first preset distance range of the image acquisition device; The temporary spatiotemporal point of interest information of the target is determined based on the intersection of point of interest information within a first preset distance range of the image acquisition device.

4. The target aggregation method based on temporary spatiotemporal conditions according to claim 2, characterized in that, The step of constructing a temporary spatiotemporal representation of the target based on the point of interest information of the image acquisition device and the distance information between the image acquisition devices includes: Based on the distance information between the image acquisition devices, the distance between the image acquisition devices capturing the target is obtained; Based on the shooting time information, obtain the shooting time difference in multiple consecutive shooting data of the target; If the distance between the image acquisition devices is less than a third preset distance, and the maximum value of the shooting time difference in multiple consecutive shooting data of the target is greater than a second preset time, then the temporary spatiotemporal space of the target is determined based on the multiple consecutive shooting data; wherein the third preset distance is less than the second preset distance.

5. The target aggregation method based on temporary spatiotemporal conditions according to claim 2, characterized in that, The step of clustering the acquired shooting data according to the temporary spatiotemporal context of the target includes: When the interest point information of the temporary spatiotemporal spaces of two targets intersect, the union of the temporary spatiotemporal spaces of the two targets is taken to obtain the expanded temporary spatiotemporal space. The acquired shooting data is aggregated based on the extended temporary spatiotemporal space.

6. The target aggregation method based on temporary spatiotemporal conditions according to claim 2, characterized in that, The step of clustering the acquired shooting data according to the temporary spatiotemporal context of the target includes: When the ratio of the number of first image acquisition devices to the number of second image acquisition devices is greater than a preset value, the union of the temporary spatiotemporal spaces of the two targets is taken to obtain the extended temporary spatiotemporal space; the number of first image acquisition devices is the number of identical image acquisition devices in the temporary spatiotemporal spaces of the two targets, and the number of second image acquisition devices is the sum of the number of image acquisition devices in the temporary spatiotemporal spaces of the two targets; The acquired shooting data is aggregated based on the extended temporary spatiotemporal space.

7. The target aggregation method based on temporary spatiotemporal conditions according to claim 1, characterized in that, The step of clustering the acquired shooting data according to the temporary spatiotemporal context of the target includes: Based on the temporary spatiotemporal periodicity or correlation of the target, the acquired shooting data is archived.

8. A target aggregation device based on temporary spatiotemporal conditions, characterized in that, The device includes: The first acquisition module is used to acquire the file information of the target after target aggregation in the target area; the target area includes multiple image acquisition devices; The second acquisition module is used to determine, based on the archive information of the target, point of interest information within a first preset distance range of the image acquisition device and distance information between the image acquisition devices; A construction module is used to construct a temporary spatiotemporal structure of the target based on the point of interest information of the image acquisition device and the distance information between the image acquisition devices; The construction module is further configured to: obtain the distance between the image acquisition devices that capture the target based on the distance information between the image acquisition devices; obtain the shooting time difference in the continuous multiple shooting data of the target based on the shooting time information of each shooting data in the continuous multiple shooting data of the target; if the distance between the image acquisition devices is less than a second preset distance, and the maximum value of the shooting time difference in the continuous multiple shooting data of the target is greater than a first preset time, then determine the temporary spatiotemporal location of the target based on the continuous multiple shooting data; The data aggregation module is used to aggregate the acquired shooting data according to the temporary spatiotemporal context of the target.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the target aggregation method based on temporary spatiotemporal space as described in any one of claims 1 to 7.

Images