Target tracking method and device, electronic equipment, storage medium and computer program product

Abstract

The invention provides a target tracking method and device, electronic equipment, a storage medium and a computer program product, and relates to the technical field of computers. The method comprises the following steps: acquiring an object identifier of a target object; acquiring image data of the target object based on the object identifier of the target object; the image data is obtained by shooting the target object appearing in the corresponding scene by a plurality of image acquisition devices deployed in at least one scene; and displaying the acquired image data. According to the invention, the problem that the target object cannot be effectively tracked in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular, the present application relates to a target tracking method and device, electronic equipment, storage medium and computer program product. BACKGROUND

[0002] With the development of image recognition and video monitoring technology, more and more monitoring systems are deployed in family, park, commercial place and other scenes, which are used for real-time monitoring and behavior recording of personnel, vehicle, animal and other target objects.

[0003] At present, the target object can be continuously photographed by using the camera, and the obtained video data can be uploaded to the server for centralized processing and management, and the video of different target objects photographed in the same camera device can be distinguished and displayed, that is, the user can view the video clips corresponding to each object based on the recognition result in the video stream of a single camera.

[0004] However, when the same target object continuously moves in the coverage area of multiple cameras, the system cannot identify it as the same target object, and thus cannot effectively aggregate the video data of the target object under multiple cameras, so as to effectively track the activity of the target object in different scenes.

[0005] As known from the above, the problem of effectively tracking the target object still needs to be solved. SUMMARY

[0006] The present application provides a target tracking method, device, electronic equipment and storage medium, which can solve the problem of ineffective tracking of target objects in related technologies. The technical solution is as follows:

[0007] According to one aspect of the present application, a target tracking method comprises: obtaining an object identifier of a target object; obtaining image data of the target object based on the object identifier of the target object; the image data is obtained by a plurality of image acquisition devices deployed in at least one scene respectively photographing the target object appearing in the corresponding scene; and displaying the obtained image data.

[0008] According to one aspect of the present application, a target tracking device comprises: an identifier obtaining module, configured to obtain an object identifier of a target object; an image obtaining module, configured to obtain image data of the target object based on the object identifier of the target object; the image data is obtained by a plurality of image acquisition devices deployed in different scenes respectively photographing the target object appearing in the corresponding scene; and a data display module, configured to display the obtained image data.

[0009] In an example embodiment, the object identifier obtaining module is further configured to display the selectable object identifiers; and determine the object identifier of the target object in response to detecting that one of the object identifiers is selected.

[0010] In an example embodiment, the image obtaining module is further configured to display at least one picture identifier, each of the picture identifiers corresponding to the image data of the target object in a different scene.

[0011] In an example embodiment, the target tracking apparatus is further configured to determine a target scene corresponding to the selected picture identifier in response to detecting that one of the picture identifiers is selected; and display the image data of the target object in the target scene on the target tracking page.

[0012] In an example embodiment, the data displaying module is further configured to display a video viewing entry for the target object; and in response to detecting an operation triggered by the video viewing entry, synthesize the image data of the target object in different scenes and / or the image data of the target object in different time periods in the same scene; and play a synthesized video of the target object on the target tracking page.

[0013] In an example embodiment, the data displaying module is further configured to, if the image data of the target object in different scenes are completely overlapped in time period, perform overlay processing on the image data that are completely overlapped in time period to obtain a synthesized video of the target object; the synthesized video comprises a plurality of video clips, each of the video clips corresponding to the image data in different scenes but overlapped in time period.

[0014] In an example embodiment, the data displaying module is further configured to, if the image data of the target object in different scenes are not completely overlapped in time period, perform overlay processing on the image data that are overlapped in time period to obtain an intermediate video comprising a plurality of video clips, each of the video clips corresponding to the image data in different scenes but overlapped in time period; and perform splicing processing on the image data in different scenes but not overlapped in time period and the intermediate video in time sequence to obtain a synthesized video of the target object.

[0015] In an example embodiment, the data displaying module is further configured to, in response to detecting an operation triggered by a time period filtering entry on the target tracking page, determine a target time period; and play a video clip corresponding to the target time period in the synthesized video on the target tracking page.

[0016] In an example embodiment, the data display module is further configured to display a play progress bar of the synthesized video on the target tracking page; the play progress bar is divided into a plurality of play time periods by different markers, each marker is used to represent different video clips associated with the play time period, and each video clip associated with the play time period is obtained by photographing the target object by different image acquisition devices; detecting a selection operation on one of the play time periods, determining the selected video clip associated with the play time period as a target video clip; and playing the target video clip in the synthesized video on the target tracking page.

[0017] In an example embodiment, the marker is further used to represent different numbers of video clips associated with the play time period; the plurality of video clips associated with the play time period are obtained by photographing the target object by different image acquisition devices; the data display module is further configured to, as the synthesized video is played, if the play progress of the synthesized video slides to a target play time period on the play progress bar, display a video clip filtering entry for the target play time period on the target tracking page; the target play time period refers to the play time period associated with a plurality of video clips; detecting an operation triggered by the video clip filtering entry, determining the selected video clip as the target video clip; and playing the target video clip in the synthesized video on the target tracking page.

[0018] In an example embodiment, the target tracking device is further configured to display an identified object adding entry; the identified object adding entry is used to add the object identifier of an identified object; detecting an operation triggered by the identified object adding entry, obtaining image data of the identified object; and generating the object identifier of the identified object based on the image data of the identified object.

[0019] In an example embodiment, the image acquisition module is further configured to display an image data uploading entry; the image data uploading entry is used to add the image data of the identified object; detecting an operation triggered by the image data uploading entry, obtaining the image data of the identified object.

[0020] In an example embodiment, the target tracking apparatus is further configured to display at least one to-be-identified object to-be-identified identifier, the to-be-identified identifier being obtained by the image acquisition device photographing the to-be-identified object appearing in the corresponding scene, and determine the selected to-be-identified identifier by detecting an operation triggered by any one of the to-be-identified identifiers, and convert the to-be-identified identifier of the to-be-identified object into the object identifier of the identified object by editing the selected to-be-identified identifier.

[0021] In an example embodiment, the target tracking apparatus is further configured to send the object identifier of the identified object to a server to instruct the server to share the object identifier of the identified object among the image acquisition devices deployed in different scenes, and instruct each of the image acquisition devices to photograph the identified object appearing in the corresponding scene by sharing the object identifier of the identified object among the image acquisition devices.

[0022] In an example embodiment, the target object includes a person, an animal, a vehicle, or a package.

[0023] According to an aspect of the present application, an electronic device includes at least one processor and at least one memory, wherein the memory has stored thereon a computer program, and the computer program is executed by the processor to implement the target tracking method as described above.

[0024] According to an aspect of the present application, a storage medium has stored thereon a computer program, and the computer program is executed by one or more processors to implement the target tracking method as described above.

[0025] According to an aspect of the present application, a computer program product includes a computer program, and the computer program is executed by one or more processors to implement the target tracking method as described above.

[0026] The technical scheme provided by the present application has the beneficial effects that:

[0027] In the above technical scheme, the automatic collection, association, and display of target object image data can be achieved, the unique object identifier is allocated to each target object, the activity process of the target object in multiple scenes can be continuously tracked and identified, the object identification confusion or tracking interruption can be avoided, multiple image acquisition devices are respectively deployed in at least one scene and photograph the target object, the image data of the target object in different scenes can be completely obtained, the time-space coverage range and integrity of the image data are enhanced, and thus the problem that the target object cannot be effectively tracked in the related art can be effectively solved. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0029] Figure 1 is a schematic diagram of an implementation environment according to the present application;

[0030] Figure 2 is a hardware structure diagram of a user terminal according to an exemplary embodiment;

[0031] Figure 3 is a flowchart of a target tracking method according to an exemplary embodiment;

[0032] Figure 4 is Figure 3 is a specific implementation diagram of a page where an object identifier corresponding to an embodiment is located;

[0033] Figure 5 is a specific implementation diagram of a target tracking page according to an exemplary embodiment;

[0034] Figure 6 is a specific implementation diagram of a target tracking page according to another exemplary embodiment;

[0035] Figure 7 is a specific implementation diagram of a target tracking page according to another exemplary embodiment;

[0036] Figure 8 is a specific implementation diagram of a play progress bar according to an exemplary embodiment;

[0037] Figure 9 is a specific implementation diagram of a target tracking page according to another exemplary embodiment;

[0038] Figure 10 is a specific implementation diagram of a page corresponding to an image data upload entry according to an exemplary embodiment;

[0039] Figure 11 is a specific implementation diagram of a page where an identifier of an object to be identified is located according to an exemplary embodiment;

[0040] Figure 12 is a specific implementation diagram of a target tracking method in an application scenario;

[0041] Figure 13is a structural block diagram of a target tracking device according to an exemplary embodiment;

[0042] Figure 14 is a structural block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0043] Embodiments of the present application are described in detail below with reference to examples illustrated in the accompanying drawings, in which the same or similar elements or elements having the same or similar functions are denoted by the same or similar reference numerals throughout. The embodiments described below by reference to the accompanying drawings are exemplary and are intended only for explanation of the present application, and cannot be interpreted as limiting the present application.

[0044] Those skilled in the art can understand that, unless specifically stated, the singular forms "a", "an" and "the" used herein also include the plural forms. It should be further understood that the use of the term "include" in the specification of the present disclosure means that the features, integers, steps, operations, elements and / or components described exist, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we say an element is "connected" or "coupled" to another element, it can be directly connected or coupled to the other element, or there can be intermediate elements. In addition, "connected" or "coupled" used herein can include wireless connection or wireless coupling. The phrase "and / or" used herein includes all or any single unit and all combinations of the associated listed items.

[0045] As mentioned earlier, when the same target object is continuously active within the coverage areas of multiple cameras, the system cannot identify it as the same target object, and thus cannot effectively aggregate the video data of the target object under multiple cameras, so as to effectively track the activity of the target object in different scenes.

[0046] Specifically, the current system usually processes the video collected by each camera as an independent data source, lacks a unified object identification management mechanism, and thus users often can only browse or roughly screen frame by frame based on the existing video content, and cannot directly select a target object to view its complete video record in each camera, especially in the case of multiple object cross-activity and frequent scene switching, the video correlation accuracy and continuity are difficult to guarantee.

[0047] As can be seen from the above, there is still a defect that the target object cannot be effectively tracked in the related art.

[0048] To this end, the target tracking method provided in the present application can effectively improve the accuracy of target tracking, and accordingly, the target tracking method is applicable to a target tracking device, which can be deployed in an electronic device, which can also be a portable mobile electronic device, for example, the electronic device includes a smart phone, a tablet computer, etc.; the electronic device can also be a smart control panel.

[0049] To make the purposes, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0050] Figure 1 A schematic diagram of an implementation environment related to a target tracking method. The implementation environment at least includes a user terminal 110, a smart device 130, a server end 170, and a network device, in which Figure 1 The network device includes a gateway 150 and a router 190, which are not specifically limited here.

[0051] The user terminal 110, which can also be considered as a user end or a terminal, can be deployed (also understood as installed) with a client associated with the smart device 130, and the user terminal 110 can be an electronic device such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart control panel, and other devices with display and control functions, which are not limited here.

[0052] The client is associated with the smart device 130, and in essence, the user registers an account in the client and configures the smart device 130 in the client, for example, the configuration includes adding a device identifier to the smart device 130, so that when the client runs in the user terminal 110, the user can be provided with device display and device control functions of the smart device 130, the client can be in the form of an application program or a web page, and accordingly, the interface for device display of the client can be in the form of a program window or a web page, which are not limited here.

[0053] The smart device 130 is deployed in the gateway 150 and communicates with the gateway 150 through a communication module configured by itself, and is controlled by the gateway 150. It should be understood that the smart device 130 generally refers to one of a plurality of smart devices 130, and the embodiments of the present application are only exemplified by the smart device 130, that is, the number and type of smart devices deployed in the gateway 150 are not limited in the embodiments of the present application. In one application scenario, the smart device 130 accesses the gateway 150 through a local area network, so as to be deployed in the gateway 150. The process of the smart device 130 accessing the gateway 150 through the local area network includes: first establishing a local area network by the gateway 150, and the smart device 130 connects the gateway 150 to join the local area network established by the gateway 150. The local area network includes but is not limited to ZIGBEE or Bluetooth. The smart device 130 can be a smart printer, a smart fax machine, a smart camera, a smart air conditioner, a smart door lock, a smart lamp, or a human body sensor, a door and window sensor, a temperature and humidity sensor, a water immersion sensor, a natural gas alarm, a smoke alarm, a wall switch, a wall socket, a wireless switch, a wireless wall switch, a magic cube controller, a curtain motor, a millimeter wave radar, etc. configured with a communication module.

[0054] The interaction between the user terminal 110 and the smart device 130 can be realized through a local area network, and can also be realized through a wide area network. In one application scenario, the user terminal 110 establishes a wired or wireless communication connection between the router 190 and the gateway 150, for example, the wired or wireless communication connection includes but is not limited to WIFI, etc., so that the user terminal 110 and the gateway 150 are deployed in the same local area network, and then the user terminal 110 can realize the interaction with the smart device 130 through a local area network path. In another application scenario, the user terminal 110 establishes a wired or wireless communication connection between the server 170 and the gateway 150, for example, the wired or wireless communication connection includes but is not limited to 2G, 3G, 4G, 5G, WIFI, etc., so that the user terminal 110 and the gateway 150 are deployed in the same wide area network, and then the user terminal 110 can realize the interaction with the smart device 130 through a wide area network path.

[0055] The server 170 can also be referred to as a cloud, a cloud platform, a platform, a server, etc. The server 170 can be a server or a server cluster composed of a plurality of servers, or a cloud computing center composed of a plurality of servers, so as to better provide background services to a large number of user terminals 110. For example, the background services include target tracking services.

[0056] In one application scenario, the user terminal 110 acquires an object identifier of a target object; based on the object identifier of the target object, acquires image data of the target object; the image data is obtained by a plurality of image acquisition devices deployed in at least one scene respectively photographing the target object appearing in the corresponding scene; and the acquired image data is displayed, thereby providing more effective target tracking service for the user.

[0057] Please refer to Figure 2 , Figure 2 is a hardware structure diagram of a user terminal according to an exemplary embodiment. The terminal is suitable for Figure 1 the user terminal 110 in the implementation environment shown.

[0058] It should be noted that the terminal is only an example suitable for the present application, and should not be considered as providing any limitation on the scope of use of the present application. The terminal should also not be interpreted as requiring reliance on or must have Figure 2 one or more components in the exemplary terminal 100 shown in the

[0059] As shown in Figure 2 , the terminal 100 includes a memory 101, a storage controller 103, one or more (only one is shown in the Figure 2 ) processor 105, a peripheral interface 107, a radio frequency module 109, a positioning module 111, a camera module 113, an audio module 115, a touch screen 117, and a key module 119. These components communicate with each other through one or more communication buses / signal lines 121.

[0060] Among them, the memory 101 can be used to store computer programs, such as the computer programs corresponding to the target tracking method and device in the exemplary embodiments of the present application, and the processor 105 reads the computer programs stored in the memory 101 to perform various functions and data processing, that is, to complete the target tracking method.

[0061] The memory 101 as a carrier for resource storage can be a random access memory, for example, a high-speed random access memory, a non-volatile memory, such as one or more magnetic storage devices, a flash memory, or other solid-state memories. The storage mode can be temporary storage or permanent storage.

[0062] The peripheral interface 107 can include at least one wired or wireless network interface, at least one serial-parallel conversion interface, at least one input / output interface, and at least one USB interface, etc., for coupling external various input / output devices to the memory 101 and the processor 105 to realize communication with external various input / output devices.

[0063] The radio frequency module 109 is used to transmit and receive electromagnetic waves, realizing the mutual conversion between electromagnetic waves and electrical signals, thereby enabling communication with other devices through a communication network. The communication network includes cellular telephone networks, wireless local area networks, or metropolitan area networks, and these communication networks can use various communication standards, protocols, and technologies.

[0064] The positioning module 111 is used to obtain the current geographical location of the terminal 100. Examples of positioning modules 111 include, but are not limited to, Global Positioning System (GPS), positioning technologies based on wireless local area networks or mobile communication networks.

[0065] The camera module 113 is part of the camera and is used to capture pictures or videos. The captured pictures or videos can be stored in the memory 101 or transmitted to the host computer via the radio frequency module 109.

[0066] The audio module 115 provides an audio interface to the user, which may include one or more microphone jacks, one or more speaker jacks, and one or more headphone jacks. Audio data is exchanged with other devices through the audio interface. Audio data can be stored in the memory 101 and can also be transmitted via the radio frequency module 109.

[0067] The touchscreen 117 provides an input / output interface between the terminal 100 and the user. Specifically, the user can perform input operations through the touchscreen 117, such as clicking, touching, and swiping gestures, so that the terminal 100 can respond to the input operations. The terminal 100 then displays the output content, which is any form or combination of text, images, or videos, to the user through the touchscreen 117.

[0068] The button module 119 includes at least one button, providing an interface for users to input information into the terminal 100. Users can press different buttons to enable the terminal 100 to perform different functions. For example, the volume adjustment button allows users to adjust the volume of the sound played by the terminal 100.

[0069] Understandable. Figure 2 The structure shown is for illustrative purposes only; the terminal 100 may also include components that are more advanced than those shown. Figure 2 The more or fewer components shown, or having the same Figure 2 The different components are shown. Figure 2 The components shown can be implemented using hardware, software, or a combination thereof.

[0070] Please see Figure 3 This application provides a target tracking method, which is applicable to electronic devices, for example, [missing information]. Figure 1 The user terminal 110 shown in the implementation environment can also be an intelligent control panel with control functions. The hardware structure of this electronic device can be as follows:Figure 2 As shown.

[0071] In the following method embodiments, for the convenience of description, the execution subject of each step of the method is taken as an electronic device for example, but this does not constitute a specific limitation.

[0072] As Figure 3 shown, the method can include the following steps:

[0073] Step 310, obtaining the object identifier of the target object.

[0074] Wherein, the target object refers to any object that can be tracked, for example, the object can be a person, an animal, a vehicle or a package, etc.; the object identifier is used to uniquely identify and distinguish each target object, and in the subsequent tracking, identification and / or analysis process, the target object is continuously associated and processed.

[0075] Step 330, based on the object identifier of the target object, obtaining the image data of the target object.

[0076] Wherein, the image data is obtained by a plurality of image collection devices deployed in at least one scene respectively photographing the target object appearing in the corresponding scene.

[0077] Regarding the scene, it can refer to the physical space area or functional area where the target object is located, for example, a living room, a bedroom, etc., and it can also refer to the monitoring area corresponding to each image collection device, for example, under the same living room physical space, there can be multiple cameras deployed, covering the sofa area, the tea table area or the television area, etc., which is not specifically limited here.

[0078] The image data of the target object is obtained by photographing and collecting the scene where the target object is located by the image collection device. Wherein, the image collection device can be an electronic device with image collection function, for example, a video camera, a smart phone with camera, etc. The image collection device can be deployed around the scene where the target object is located, for example, if the target object is a person, the image collection device can be deployed on the column in the building where the target object appears; if the target object is a vehicle, the image collection device can be deployed on the lamp post on the roadside.

[0079] It can be understood that the shooting can be single shooting, and can also be continuous shooting. For the same target object, a video can be obtained for continuous shooting, and the image data can be any frame of picture in the video. For multiple shooting, multiple photos can be obtained, and the image data can be any one of the multiple photos. In other words, the image in the embodiment can come from a dynamic image, such as multiple frames of pictures in a video or multiple photos, or come from a static image, such as any frame of picture in a video or any one of the multiple photos. Correspondingly, the target tracking in the embodiment is performed in units of frames.

[0080] Regarding the acquisition of the image data, the image data can come from images captured and collected by the image collection device in real time, or from images captured and collected by the image collection device in a historical time period and stored in the electronic device in advance. Then, for the electronic device, after the image collection device captures and collects the image data, the image data can be processed in real time, or can be stored in advance and then processed, for example, the image data is processed when the CPU of the electronic device is low, or the image data is processed according to the indication of the staff. Therefore, the target tracking in the embodiment can be performed on the image data acquired in real time, or on the image data acquired in a historical time period, which is not specifically limited here.

[0081] Further, since the object identifier is used to uniquely identify the target object, if the target object appears in a scene where the image collection device is deployed, the corresponding image collection device can capture the target object based on the object identifier of the target object, thereby acquiring image data corresponding to the target object.

[0082] It should be noted that the target object can move from one scene to another. If the above two scenes are both deployed with image collection devices, when the target object enters different scenes, the corresponding image collection devices can capture the target object and acquire its image data in each scene. Therefore, the image data related to the same target object captured by multiple image collection devices can be associated through the object identifier, and further image recording and information integration of the target object in multiple scenes can be realized.

[0083] For example, if the target object is a user A, the user A first enters a first scene (e.g., a living room) and then enters a second scene (e.g., a bedroom), and the above two scenes are both deployed with image collection devices, the image collection device of the entrance area will shoot an image of the user A entering the living room, and the image collection device of the bedroom will shoot an image of the user A in the bedroom. The system can match and associate the image data obtained in the above two scenes through the object identifier corresponding to the user A, thereby forming complete image data of the target object in multiple scenes.

[0084] At step 350, the obtained image data is displayed.

[0085] Specifically, the image data related to the target object can be displayed in a client interface, a control terminal, a monitoring platform, or other electronic devices. By displaying the obtained image data, the user can intuitively view the image data of the target object in a specific scene, thereby assisting in completing target identification, behavior judgment, or security analysis, and the like.

[0086] Further, the image data can be image frames shot in real time by the image collection device, or image data records related to the historical activities of the target object. The system can determine the source device and time period of the image data according to the object identifier, and present the corresponding image data on the user interface, thereby improving the interpretability and traceability of the data.

[0087] In one possible implementation, the image data of the target object shot at multiple time points and in at least one scene can be displayed in a time axis manner at the user end.

[0088] Through the above process, automatic collection, association, and display of the image data of the target object can be achieved. By assigning a unique object identifier to each target object, the activities of the target object in multiple scenes can be continuously tracked and identified, thereby avoiding object identification confusion or tracking interruption. Since multiple image collection devices are respectively deployed in at least one scene and shoot the target object, the image data of the target object in different scenes can be completely obtained, thereby enhancing the spatiotemporal coverage range and integrity of the image data.

[0089] In an exemplary embodiment, the above method can further include the following steps: displaying selectable object identifiers; detecting an operation of selecting one of the object identifiers to obtain the object identifier of the target object.

[0090] The selection operation is that the user selects one of the selectable object identifiers to obtain the object identifier of the target object.

[0091] Figure 4 A specific implementation diagram of a page of an object identifier is shown in FIG. 5, which shows a page of an object identifier. Figure 4As shown, page 401 displays object identifiers 403 corresponding to multiple target objects. Clicking the "younger brother" object identifier will allow you to obtain the object identifier corresponding to the target object, which is the younger brother.

[0092] As described in the above embodiments, by displaying multiple object identifiers on the page, users can quickly browse all object identifiers on the page and select one of them to obtain the object identifier corresponding to the target object, avoiding tedious manual input or multi-level filtering operations and significantly improving interaction efficiency.

[0093] In an exemplary embodiment, the above method may further include the following steps: displaying at least one image identifier, wherein each image identifier corresponds to image data of the target object in different scenes.

[0094] Specifically, based on the object identifier of the target object, image data captured by image acquisition devices in different scenarios can be obtained, and then a corresponding image identifier can be generated for the image data corresponding to each scenario.

[0095] The aforementioned image identifier can be a thumbnail of the image data (e.g., a preview of a video frame, keyframe, or still image).

[0096] Please see back Figure 4 ,like Figure 4 As shown, clicking the "younger brother" object icon will retrieve the object icon corresponding to the target object—the younger brother. Simultaneously, multiple image icons 405 are displayed on page 401, each corresponding to image data of the target object in different scenarios, such as... Figure 4 The living room sign, kitchen sign, and bedroom sign.

[0097] Through the above process, image icons are displayed on the user interface, allowing users to intuitively view and select image data of the target object appearing at different times and locations, thereby assisting in completing operations such as trajectory playback and event confirmation of the target object.

[0098] In an exemplary embodiment, the above method may further include the following steps: detecting an operation in which one of the image identifiers is selected, determining the target scene corresponding to the selected image identifier; and displaying image data of the target object in the target scene on the target tracking page.

[0099] As described above, the image identifier is generated based on the image data corresponding to the target object in different scenes, and thus each image identifier can be associated with a specific target scene. Then, when a user clicks an image identifier on the page, the electronic device can detect the selection operation and determine the target scene corresponding to the image identifier, so as to enter the target tracking page and view the image data of the target object in the target scene on the target tracking page.

[0100] Referring back to Figure 4 As shown in Figure 4 , the page 401 displays a plurality of image identifiers 405, and clicking the image identifier 405 corresponding to the kitchen scene, as shown in Figure 5 , can enter the target tracking page 501, so as to view the image data of the target object “brother” in the target scene “kitchen” corresponding to the image identifier 405 on the target tracking page, and thus understand the activity of the brother in the kitchen.

[0101] Through the above process, the image data of the target object in multiple scenes is displayed in the form of image identifiers, the user can intuitively select the target scene of interest, and quickly jump from the image identifier to the image data without complex filtering operations. Of course, each image identifier corresponds to a specific scene, which helps the user to quickly understand the scene in which the target object is located based on spatial cognition, thereby improving the usability and friendliness of the system.

[0102] In an exemplary embodiment, step 330 can further include the following steps: displaying a video viewing entry for the target object; detecting an operation triggered by the video viewing entry; synthesizing the image data of the target object in different scenes and / or the image data of the target object in different shooting time periods in the same scene; and playing the synthesized video of the target object on the target tracking page.

[0103] The video viewing entry is a control entry for viewing the synthesized video of the target object. If the user wants to view the synthesized video corresponding to a target object, the user can trigger the video viewing entry to view the synthesized video.

[0104] Regarding the synthesized video, it can include a video of the image data of the target object in different scenes and / or different shooting time periods in the same scene. It can be understood that the target object may appear in multiple different scenes during actual activities, or appear multiple times in the same scene at different time periods.

[0105] Then, different image collection devices can capture the target object in different scenes and / or different time periods, and obtain corresponding image data. Based on these scattered image data, time sequence arrangement, spatial matching and / or image stitching can be performed, so as to generate a synthesized video with stronger continuity and more complete information.

[0106] In one possible implementation, the synthesized video can include image data of the target object captured in multiple different scenes, for example, image data corresponding to the complete moving process from the "living room" to the "kitchen" to the "balcony".

[0107] In one possible implementation, the synthesized video can also include activity clips of the target object in multiple different time periods in the same scene, for example, image data of entering the "study" at 8 am and 4 pm.

[0108] For example, if the target object is user A (for example, user A is the younger brother), who appears in multiple scenes such as the living room, the kitchen, the study, etc. in a day, the image data of the user A in each scene can be automatically stitched into a continuous synthesized video. The user only needs to click the video viewing entrance corresponding to the "younger brother" in the page, and can view the synthesized video in the target tracking page to understand the activity path and behavior process of the younger brother in a day.

[0109] Referring back to Figure 4 As shown in Figure 4 , the page 401 displays a synthesized video viewing entrance 407 (i.e., a video viewing entrance). Clicking the synthesized video viewing entrance 407, as shown in Figure 6 , enters the target tracking page 601, so as to view the synthesized video corresponding to the target object "younger brother" on the target tracking page 601.

[0110] Under the action of the above embodiment, the image data of the target object in different scenes and / or different time periods is automatically integrated and a synthesized video is generated. This not only improves the integration efficiency of cross-scene image data, but also provides a stronger continuous behavior playback effect, simplifies the user operation process, and enables the user to view the complete activity video of the target object through only one click. This further enhances the tracking visualization capability of the system in the time and space dimensions of the target object, and is suitable for various practical application scenarios such as trajectory analysis and security.

[0111] In an example embodiment, the above method can further include the following steps: if the image data of the target object in different scenes completely coincide in the shooting time period, the image data with completely coinciding shooting time periods is superimposed to obtain a synthesized video of the target object.

[0112] The synthetic video comprises a plurality of video clips, each of which corresponds to image data captured in different scenes but in a same time period.

[0113] Specifically, if it is detected that image data captured by the image acquisition device in two or more different scenes has a same time period, the image data in the time period can be superimposed to generate a video clip with more spatial coverage and perspective integrity, and further to form the synthetic video of the target object. The superimposition can be implemented based on frame-level superimposition, picture splicing, multi-view fusion, etc., which is not limited herein.

[0114] For example, if the target object is captured by cameras arranged at both ends of a corridor while passing through the corridor, the image data recorded by the two cameras can have a same time period. Then, the image data in the time period can be superimposed to form a complete video clip, which is included in the synthetic video to show the all-around activity track and behavior details of the target object in the time period.

[0115] In one possible implementation, if two image data in different scenes have a same time period, the image data in the time period is stored as two video clips, and the video clip acquired first is superimposed on the upper layer and played preferentially. Of course, the user can manually switch to the video clip in the lower layer.

[0116] Through the above process, the image data with a same time period can be effectively integrated when the target object appears in multiple scenes (or is captured by multiple image acquisition devices) at the same time, to provide multi-angle presentation of the same behavior and to make up for the visual angle blind area of a single camera angle.

[0117] In an example embodiment, the above method can further include the following steps: if the image data of the target object in different scenes does not have a same time period, superimposing the image data with a same time period to obtain an intermediate video comprising a plurality of video clips; and splicing the image data in different scenes with a different time period and the intermediate video in time sequence to obtain the synthetic video of the target object.

[0118] The synthetic video comprises a plurality of video clips, each of which corresponds to image data captured in different scenes but in a same time period.

[0119] Specifically, if the target object is captured by the image acquisition device in two or more scenes in a same time period, for example, the target object appears in a “living room” and a “passage” in a same time period, the image data in the time period can be superimposed to generate an intermediate video comprising a plurality of video clips.

[0120] The video clips correspond to image data partially overlapped in time in different scenes, and the superimposition processing can preserve multi-view information and improve image continuity and completeness of behavior expression.

[0121] Further, image data not overlapped in time can be spliced with the intermediate video in time sequence.

[0122] The image data not overlapped in time refers to image data in which the target object is only photographed in a specific scene and does not appear in other scenes at the same time. By sorting and merging based on time sequence, the intermediate video and image data in the time period before and after the intermediate video are spliced into a complete synthetic video.

[0123] Through the above process, in the case that the target object moves in multiple scenes and the image data is not completely overlapped in time, the image data overlapped in time can be flexibly superimposed to generate an intermediate video containing multi-view content, and the image data not overlapped in time can be spliced in order to generate a synthetic video with complete time axis and rich visual expression.

[0124] In an exemplary embodiment, the method can further include the steps of: detecting an operation of triggering a time period filtering portal on the target tracking page, determining a selected target time period; playing a video clip corresponding to the target time period in the synthetic video on the target tracking page.

[0125] The time period filtering portal is a control portal for selecting a specific time period. If a user wants to select a specific time period, the user can trigger the time period filtering portal to select the specific time period. The selected time period is regarded as the target time period.

[0126] For the electronic device, the corresponding video clip in the synthetic video can be determined according to the target time period, and the video clip can be displayed on the target tracking page.

[0127] Figure 7 A specific implementation diagram of a target tracking page is shown in FIG. 1, which shows a target tracking page. Figure 7As shown, the user clicks the time period filtering entry 702 on the target tracking page 701, and a time period filtering area 703 is displayed, which includes filtering items corresponding to all time and custom time period. The user can click the control entry 704 corresponding to all time, so that the video clip corresponding to all time is displayed on the target tracking page 705. In addition, all time can be configured as a default option. The user can also click the custom time period entry 706 to display the time period selection area 707. By selecting the desired target time period in the time period selection area 707, the video clip corresponding to the target time period is displayed on the target tracking page 705.

[0128] Taking the target tracking of user A (brother) as an example, it is assumed that the user clicks the object identifier corresponding to "brother" in the client, and the system obtains the synthesized video corresponding to "brother" in multiple image acquisition devices from the cloud based on the object identifier of "brother". The user clicks the time period filtering entry 702 on the target tracking page 701, and the system displays the time period filtering area 703 on the page, which includes filtering items corresponding to all time and custom time. The user can click the custom time period entry 704 to enter the time period selection area 707 and manually select the target time period as "September 30 to October 1", and then click save. Then, the video clip corresponding to the above time period can be displayed on the target tracking page 705.

[0129] Through the above process, the user can flexibly and accurately select the time period to be concerned in the target tracking page, and quickly locate and play the corresponding video clip based on the selected target time period, so as to realize accurate backtracking and viewing of the activities of the target object in the time dimension.

[0130] In an example embodiment, the above method can further include the following steps: displaying a play progress bar of the synthesized video on the target tracking page; detecting a selection operation on one of the play time periods, determining the video clip associated with the selected play time period as a target video clip; and playing the target video clip in the synthesized video on the target tracking page.

[0131] The play progress bar is divided into multiple play time periods by different markers, and each marker is used to represent different video clips associated with the play time period. The video clips associated with each play time period are obtained by different image acquisition devices shooting the target object.

[0132] It should be understood that the play time period refers to a time section in the synthesized video, that is, a section represented by the time axis of the video during the user's watching of the video of the target object. Each play time period corresponds to a video clip in the synthesized video.

[0133] If the target object appears in different scenes at different times and is photographed by image capture devices deployed in each scene, a corresponding video clip can be obtained according to the image data generated by each image capture device, and the image data can be sorted based on the shooting time of the video clip to splice a synthetic video of the target object. Subsequently, the synthetic video is divided into several playback time periods according to the position order of the video clip on the time axis, and corresponding markers are generated on the playback progress bar.

[0134] Based on this, each playback time period and its corresponding video clip can be mapped and associated by setting corresponding markers on the playback progress bar, so that the user can intuitively identify the video clip corresponding to each playback time period.

[0135] Figure 8 A specific implementation diagram of a playback progress bar is shown in FIG. 1, as shown in FIG. 1, camera 1 photographs video clips related to event 1 and event 2 in different shooting time periods. Based on the order of the video clips corresponding to event 1 and event 2 on the time axis, the synthetic video can be divided into three playback time periods: the first playback time period corresponds to the video clip of event 1, the second playback time period is the interval time between event 1 and event 2 (which can be a blank segment or a transition segment), and the third playback time period corresponds to the video clip of event 2. The above playback time periods are mapped to the playback progress bar and distinguished by different markers, so that the user can identify different video clips. Figure 8

[0136] Then, one of the playback time periods can be selected to determine the video clip associated with the selected playback time period as the target video clip, and the target video clip in the synthetic video is played on the target tracking page.

[0137] For example, the first playback time period corresponding to event 1 is selected, the first playback time period is the target video clip, and the target video clip is played.

[0138] In the above process, through the design of the above playback progress bar, the user can quickly locate any playback time period and view the target video clip in the synthetic video associated with the playback time period on the target tracking page, so as to realize more targeted video clip backtracking on the target tracking page.

[0139] In an exemplary embodiment, the markers are also used to represent that the number of video clips associated with the playback time period is different; the multiple video clips associated with the playback time period are obtained by photographing the target object by different image capture devices.

[0140] ​The method can further include the following steps: displaying, on the target tracking page, a video clip filtering entry for the target playing time period as the playing of the synthetic video slides to the target playing time period on the playing progress bar; detecting an operation triggered on the video clip filtering entry, and determining the selected video clip as a target video clip; and playing the target video clip in the synthetic video on the target tracking page.

[0141] The target playing time period refers to a playing time period associated with a plurality of video clips.

[0142] In one possible implementation, the target playing time period can refer to a playing time period corresponding to the intermediate video.

[0143] As described above, since there are a plurality of image acquisition devices capturing the target object in the same or partially overlapping time period, the corresponding image data is identified as image data with overlapping shooting time periods, so that the intermediate video is obtained through superimposition processing, and the intermediate video includes a plurality of video clips.

[0144] Referring back to Figure 8 As shown in Figure 8 , the camera 2 records the video clips corresponding to the events 3 and 4 in its shooting time period, and the camera 3 shoots the video clip corresponding to the event 5 in a specific shooting time period.

[0145] First of all, in this embodiment, each event is generated by an image acquisition device shooting a specific target object in its shooting area and detecting a specific activity, so there is a one-to-one or one-to-many association relationship between the event and the target object.

[0146] Specifically, the events 1 and 3 both involve the video clips of the target object A (such as the user A, i.e. the younger brother) in different positions and shot by different cameras (camera 1 and camera 2); the events 2, 4 and 5 are all related to the continuous or partially overlapping activities of the target object A in another time period, wherein the event 2 is shot by the camera 1, the event 4 is shot by the camera 2, and the event 5 is shot by the camera 3. Since the above events are all identified as being associated with the same target object A, they can be attributed to the same target object (such as the younger brother).

[0147] It should be noted that the video clip corresponding to event 3 overlaps with the video clip of event 1 in part of the shooting time period, i.e. 9 / 3 08:00:03 to 9 / 3 08:00:05; the video clip of event 4 overlaps with the video clip of event 2 in part of the shooting time period, i.e. 10 / 0 10:00:02 to 10 / 0 10:00:04; the video clip of event 5 overlaps with the video clips of event 2 and event 4 in part of the shooting time period, i.e. 10 / 0 10:00:00 to 10:00:05 and 10 / 0 10:00:02 to 10 / 0 10:00:04.

[0148] Therefore, the multiple video clips with overlapping shooting time periods need to be superimposed to generate intermediate videos. Specifically, the video clip of event 3 overlaps with the video clip of event 1 in a time period (9 / 3 08:00:03-08:00:05), and based on the image data corresponding to the overlapping time period, it is superimposed into a first intermediate video; event 4 overlaps with event 2 in a time period of 10 / 0 10:00:02-10:00:04 to generate a second intermediate video; event 5 not only overlaps with event 2 (10:00:00-10:00:05) but also partially overlaps with event 4 (10:00:02-10:00:04), so the image data corresponding to the above two overlapping time periods jointly constitute a third intermediate video.

[0149] Subsequently, each video clip without time overlap and its corresponding shooting time period, as well as the above generated intermediate video and its corresponding shooting time period, are mapped into the playing time period according to their order on the time axis, and corresponding markers are generated on the playing progress bar.

[0150] It should be noted that since there is no image data about the target object in the time period of 9 / 3 08:00:08 to 10 / 0 10:00:00, the system can intelligently simplify the display of the playing progress bar, i.e. compress or skip this time period, so that the user can more efficiently focus on the effective playing section containing the target object, and avoid the redundant display caused by the long data-free area on the time axis. Finally, the playing progress bar 801 is composed of multiple playing time periods, and each marker not only indicates that the playing time period has playable video, but also identifies whether the playing time period contains intermediate video or only single-source video clip through shape, color, size, etc.

[0151] In the embodiment, the different gray scales are used to mark the playing progress bar 801, wherein a single video clip corresponds to a dark gray mark, an intermediate video generated by two video clips corresponds to a gray mark, an intermediate video generated by three or more video clips corresponds to a light gray mark, and so on, thereby constructing a visual playing progress bar with clear content structure.

[0152] It is further explained that a video clip is a continuous data stream generated by an image acquisition device for a certain event, in other words, a video clip is saved or uploaded for each event. Therefore, each mark section in the playing progress bar 801 of the synthetic video represents not only a playing time period, but also the number of corresponding events in the playing time period.

[0153] Then, in the process of playing the synthetic video, if the current playing progress enters the target playing time period (i.e., the playing time period of the intermediate video) or the user selects a specific playing time period as the target playing time period, the video clip filtering entry can be presented in the target tracking page.

[0154] The video clip filtering entry is used to select one of the multiple video clips included in the target playing time period. If the user wants to select one of the video clips, the video clip filtering entry can be triggered. The selected video clip is regarded as the target video clip, thereby playing the target video clip in the synthetic video in the target tracking page.

[0155] Figure 9 FIG. 9 shows a specific implementation schematic diagram of a target tracking page, as shown in Figure 9 As shown in FIG. 9, in the target tracking page 901, if the current playing progress enters the target playing time period 902, the video clip filtering entry 903 is displayed. Clicking the video clip filtering entry 903 displays the multiple video clips included in the target playing time period, selects one of the video clips 904, and displays the target video clip 906 in the target tracking page 905.

[0156] Specifically, the user is reviewing the synthetic video related to his younger brother (user A) in the target tracking page 901. When the synthetic video is played to the target playing time period 902 of 9 / 3122:00:00-10 / 017:00:05, the video clip filtering entry 903 is displayed. Clicking the video clip filtering entry 903 displays the video clip 1, the video clip 2, and the video clip 3 included in the target playing time period. Clicking the control entry 904 corresponding to the video clip 3 can view the video clip 3 in the target tracking page 905.

[0157] Through the combination of the above embodiments, based on the mapping relationship between playback time periods and video segments, the synthesized video is divided into multiple playback time periods, and the source and quantity of segments are distinguished by markers. In particular, the markers for the target playback time period can further reflect that multiple video segments are contained within the target playback time period, thereby providing users with intuitive prompts. In addition, users can quickly locate the desired video segment content and switch playback by combining the markers on the playback progress bar and the video segment filtering entry on the target tracking page.

[0158] In an exemplary embodiment, prior to step 310, the method may further include the following steps: displaying an entry point for adding an identified object; detecting an operation triggered by adding an entry point for an identified object and acquiring image data of the identified object; generating an object identifier for the identified object based on the image data of the identified object.

[0159] The "Add Identified Object" entry is used to add object identifiers for identified objects. Identified objects refer to target objects that have completed identity verification but have not yet generated object identifiers.

[0160] In one possible implementation, if a user wants to add a corresponding object identifier to the identified object so that the identified object can be tracked later, the entry point for adding the identified object can be triggered to obtain the image data of the identified object collected by the image acquisition device, and then generate the object identifier of the identified object based on the image data.

[0161] Figure 10 The diagram illustrates a specific implementation of the page corresponding to the image data upload entry, such as... Figure 10 As shown, the object identification management page 1001 displays an entry point 1002 for adding identified objects. Clicking on the entry point 1002 allows you to obtain image data of the identified objects acquired by the image acquisition device; for example... Figure 10 As shown on the image data acquisition page 1003, image data 1004 of the identified objects is displayed. Clicking save will allow you to view the object identifier 1006 of the identified objects generated based on the above image data on the object identifier management page 1005.

[0162] For example, such as Figure 10 As shown, the uncle can click the "Add Person" button (identified object addition entry 1002) on the object identification management page 1001 to automatically activate an image acquisition device (such as the front camera of a mobile phone) to capture image data. Figure 10As shown in the image data obtaining page 1003, the image data 1004 corresponding to the uncle is displayed, and after the save button is clicked, the object identifier 1006 of the uncle generated based on the image data can be viewed in the object identifier management page 1005. Through the above process, the effective management of the identified but not yet identified target object is realized, the user can add an entry through the identified object, generate a clear object identifier for the identified object based on the image data corresponding to the identified object, so as to realize the continuous target tracking, behavior recording and scene association in the subsequent process.

[0163] In an exemplary embodiment, the step 530 can include the following steps: displaying an image data uploading entry; detecting an operation triggered to the image data uploading entry to obtain the image data of the identified object.

[0164] The image data uploading entry is used to add the image data of the identified object. It can be understood that the image data uploading entry can support the user to manually upload the image data related to the identified object in addition to the active identification of the image acquisition device, so as to complete the generation of the object identifier of the identified object.

[0165] Referring back to Figure 10 As shown in the image data obtaining page 1003, the image data 1004 of the uncle is obtained, and the save button is clicked, so that the object identifier of the identified object is generated based on the image data of the identified object, and the newly added object identifier 1006 is displayed in the object identifier management page 1005. Figure 10 Figure 10 For example, as shown in the image data obtaining page 1003, the image data 1004 of the uncle is obtained, and the save button is clicked, so that the object identifier of the identified object is generated based on the image data of the identified object, and the newly added object identifier 1006 is displayed in the object identifier management page 1005.

[0166] For example, as shown in the image data obtaining page 1003, the image data 1004 of the uncle is obtained, and the save button is clicked, so that the object identifier of the identified object is generated based on the image data of the identified object, and the newly added object identifier 1006 is displayed in the object identifier management page 1005. Figure 10 For example, as shown in the image data obtaining page 1003, the image data 1004 of the uncle is obtained, and the save button is clicked, so that the object identifier of the identified object is generated based on the image data of the identified object, and the newly added object identifier 1006 is displayed in the object identifier management page 1005. Figure 10 As shown in the image data obtaining page 1003, the image data 1004 of the uncle is obtained, and the save button is clicked, so that the object identifier of the identified object is generated based on the image data of the identified object, and the newly added object identifier 1006 is displayed in the object identifier management page 1005.​Figure 10 As shown, the newly added object identifier 1006 (uncle) is successfully added to the identified object list for subsequent object screening and target tracking.

[0167] Through the above process, an image data upload portal for uploading image data can be provided for the user, thereby providing different ways to supplement the image data of the identified object. Not only can image data be obtained through image acquisition devices, but image data can also be supplemented through user-initiated uploading, thereby enhancing the richness and completeness of the image data.

[0168] In an exemplary embodiment, before step 310, the method can further include the following steps: displaying a to-be-identified identifier of at least one to-be-identified object; detecting an operation triggered by clicking any to-be-identified identifier, determining the selected to-be-identified identifier; and converting the to-be-identified identifier of the to-be-identified object into an object identifier of an identified object through editing processing of the selected to-be-identified identifier.

[0169] The to-be-identified identifier is image data obtained by the image acquisition device by photographing the to-be-identified object appearing in the corresponding scene. The to-be-identified object is a target object whose identity has not been determined. In a possible implementation, the to-be-identified identifier is image data obtained by the image acquisition device by photographing the to-be-identified object.

[0170] For example, when a stranger is photographed by an image acquisition device deployed in a scene for the first time and is recognized by the system as a new target object (i.e., a to-be-identified object) through a target detection algorithm, but the target object has not been assigned an object identifier at this time, i.e., the stranger has not completed identity confirmation.

[0171] Figure 11 A specific implementation diagram of a page where a to-be-identified identifier of a to-be-identified object is located is shown in FIG. 11. Figure 11 As shown, a plurality of to-be-identified objects and corresponding to-be-identified identifiers 1102 are displayed in the to-be-identified identifier page 1101. Clicking any to-be-identified identifier 1102 displays a to-be-identified object editing page 1103. The to-be-identified object editing page 1103 displays an identifier editing portal 1104. Clicking the identifier editing portal 1105 can add a corresponding name to the to-be-identified identifier, and based on the name, the to-be-identified identifier of the to-be-identified object is converted into an object identifier of an identified object, and the newly added object identifier 1107 is displayed in the object identifier page 1106.

[0172] For example, in a cell entrance and exit monitoring scenario, the image collection device identifies an unregistered face "stranger_A", and the system displays it as a to-be-identified identifier. After the administrator clicks on the to-be-identified identifier, it is identified as cleaning auntie Li, and the name "Li" is input. The system can convert the to-be-identified identifier of "stranger_A" to the object identifier of "Li", and automatically label it as "Li" in subsequent behavior tracking, realizing the identity confirmation from a stranger to a familiar object.

[0173] Through the above process, by displaying the to-be-identified identifier corresponding to the to-be-identified object, the user can be guided to quickly identify the target object without the need for manual retrieval, greatly improving the identification efficiency and accuracy.

[0174] In an exemplary embodiment, the above method can further include the following steps: sending the object identifier of the identified object to the server to instruct the server to share the object identifier of the identified object among image collection devices deployed in different scenes; and sharing the object identifier of the identified object among the image collection devices to instruct each image collection device to take a picture of the identified object appearing in the corresponding scene.

[0175] First of all, the image collection device can automatically identify the identified object, and the user can manually upload the identified object to obtain the corresponding object identifier, and send each object identifier to the cloud.

[0176] In addition, if the image collection device takes a picture of a to-be-identified object that has not been identified, a corresponding to-be-identified identifier will also be generated and sent to the cloud.

[0177] Then, by sending the object identifier of the identified object and the to-be-identified identifier of the to-be-identified object to the server, the server can distribute and synchronize the object identifier and the to-be-identified identifier among multiple image collection devices deployed in different scenes, complete the sharing, and when the identified object or the to-be-identified object moves between multiple scenes, each image collection device can automatically identify and take a picture of the target object appearing in the corresponding scene based on the received object identifier and to-be-identified identifier, thereby obtaining continuous and multi-angle image data and constructing a complete object activity track.

[0178] Through the above process, by sending the object identifier of the identified object to the server, the server can synchronize and distribute these identifiers to multiple image collection devices deployed in different scenes, so that each image collection device remains consistent in identification logic, thereby accurately identifying the target object when it moves across scenes, so that the activity behavior of the target object in the entire monitoring area can be continuously tracked, avoiding interruption of recording due to switching cameras or scenes.

[0179] In one exemplary embodiment, the target object includes a person, animal, vehicle, or package.

[0180] Among these, "humans" refers to individuals appearing in the monitored scene, such as family members, visitors, and delivery personnel. These targets can typically be identified and tracked using methods such as facial recognition. "Animal" includes domestic pets (such as cats and dogs) or other animals that may appear in the scene; the system can detect and identify these animals based on their contours, movement patterns, or fur texture features to achieve target tracking. "Vehicles" includes motor vehicles, bicycles, and electric vehicles; identification methods can include license plate recognition, vehicle type classification, and appearance feature comparison to achieve target tracking. "Packages" can be identified through barcodes, tracking numbers, and size comparison to achieve target tracking.

[0181] Through the above process, by adopting differentiated recognition technologies (such as face recognition, license plate recognition, animal outline feature extraction, barcode recognition, etc.) for different types of target objects, it is possible to accurately distinguish and identify various target objects, covering a variety of practical application scenarios from home security, pet care, vehicle access monitoring to express parcel management, thereby improving comprehensive adaptability.

[0182] Figure 12 This is a detailed implementation description of a target tracking method in an application scenario that includes cameras, cloud, and user terminals.

[0183] Now combined Figure 12 To explain this application scenario, firstly, the camera captures images of various scenes. If an object to be identified exists in the scene, i.e., a target object whose identity has not yet been determined, the object to be identified and its identifier (i.e., the image data corresponding to the object to be identified) are sent to the user terminal so that at least one identifier of the object to be identified can be displayed on the user terminal. If an operation triggered by any identifier to be identified is detected on the user terminal, the selected identifier is determined. Through editing the selected identifier, the identifier of the object to be identified is transformed into the object identifier of the identified object.

[0184] like Figure 12 In the "Automatic Device Recognition" process in the upper left corner, camera 1 captures images of "Stranger 1" and "Unknown Vehicle 1" awaiting recognition. These objects have not yet been identified, so they are marked as objects to be recognized by the system, and a recognition identifier is generated and uploaded to the cloud. The user can display these identifiers and wait for user confirmation. For example, if the user labels "Stranger 1" as "Stranger A1" on the user's device, the system will upgrade the recognition identifier corresponding to "Stranger A1" to a semantically recognized object identifier "Stranger A1" and synchronize it to the cloud.

[0185] In addition, the user can upload image data of the identified object through the user terminal. It can be understood that the user uploads the image data of the identified object, which can be regarded as that the user completes the identity confirmation of the identified object. Then, the corresponding image identifier can be generated based on the identified object and the corresponding image data.

[0186] As shown in the "user manual upload" part in FIG. 7, the user uploads image data of "face 2" and "face 3". These image data are not automatically identified from the camera, but are image data provided by the user. After uploading, the system can generate object identifiers "face 2" and "face 3". Figure 12

[0187] Then, the user terminal uploads the object identifier of the identified object to the cloud to instruct the cloud to share the object identifier of the identified object among image collection devices deployed in different scenes. Through the sharing of the object identifier of the identified object among the image collection devices, the image collection devices are instructed to respectively capture the identified object appearing in the corresponding scene.

[0188] As shown in the "user manual upload" part in FIG. 7, the user uploads image data of "face 2" and "face 3". These image data are not automatically identified from the camera, but are image data provided by the user. After uploading, the system can generate object identifiers "face 2" and "face 3". Figure 12 As shown on the right, the identified objects "stranger 1", "face 2", "face 3", etc. are stored in the cloud and shared among the cameras in different scenes. For example, camera 2 and camera 3 also identify "stranger 1", and the system generates events face1.2 and face1.3, respectively. Each event has corresponding image data and is automatically attributed to the object identifier "stranger 1".

[0189] It should be noted that in addition to capturing the identified object, the image collection device can also capture the to-be-identified object. That is, the target object can include the identified object or the to-be-identified object.

[0190] As for the image data captured by the image collection devices, if the image data of the target object in different scenes completely coincide in the shooting time period, the image data that completely coincide in the shooting time period are superimposed to obtain a synthesis video of the target object. If the image data of the target object in different scenes do not completely coincide in the shooting time period, the image data that coincide in the shooting time period are superimposed to obtain an intermediate video containing multiple video segments. The image data that do not coincide in the shooting time period in different scenes and the intermediate video are spliced in time sequence to obtain a synthesis video of the target object.

[0191] ​Then, if the user expects to view image data corresponding to a target object, the user can view display of selectable object identifiers in the client; an operation of detecting selection of one of the object identifiers is detected, an object identifier of the target object is obtained, and a video viewing entry for the target object is displayed on the user side; if an operation of triggering the video viewing entry is detected, a synthesized video of the target object is played on the target tracking page.

[0192] As Figure 12 As shown in the lower right corner, the App side can provide the user with object identifiers for filtering, for example, the user clicks "Stranger 1", and the system will gather image data corresponding to all related events (face1.1, face1.2, face1.3) according to the object identifiers in the cloud, that is, generate a synthesized video, and display it as a complete video viewing entry.

[0193] It should be noted that the object identifier of the currently recognized object can be displayed on the page, and the to-be-recognized identifier of the to-be-recognized object can also be displayed on the page. Of course, the to-be-recognized identifier is different from the object identifier.

[0194] Among them, the recognized object can refer to a target object that has completed identity confirmation or attribute annotation, for example, a person whose identity information has been bound through face recognition, a vehicle whose license plate number has been recognized, or a package whose logistics information has been matched, etc. The object identifier thereof usually has a clear semantic attribute, such as "Zhang San", "Guangdong B·12345", "Package #56789", etc. The to-be-recognized object can refer to a target object that has not completed identity confirmation or attribute annotation, and the object identifier thereof is usually a temporary identifier automatically generated by the system, such as "Stranger_001", "Car_XYZ", "Unknown_03", etc.

[0195] It can be understood that by displaying the to-be-recognized object identifier and the recognized object identifier on the page respectively, the user can intuitively distinguish the annotation state of the target object, and facilitate filtering, supplementing annotation or tracking operation. For example, the user can preferentially select the to-be-recognized object for annotation, or can view detailed information or image data of the recognized object by clicking the object identifier of the recognized object.

[0196] Further, a play progress bar of the synthesized video is displayed on the target tracking page; an operation of selecting one of the play time periods is detected, and a video clip associated with the selected play time period is determined as a target video clip; and the target video clip in the synthesized video is played on the target tracking page.

[0197] It should be noted that, as the synthetic video is played, if the playing progress of the synthetic video slides to a target playing time period on the playing progress bar, the target playing time period refers to a playing time period associated with a plurality of video clips. It can be understood that the target playing time period can refer to a playing time period corresponding to the intermediate video.

[0198] Then, in the process of playing the synthetic video, if the current playing progress enters the target playing time period (i.e., the playing time period corresponding to the intermediate video) or the user selects a specific playing time period as the target playing time period, the video clip filtering entry can be presented in the target tracking page.

[0199] The video clip filtering entry is used to select one of the plurality of video clips included in the target playing time period. If the user expects to select one of the video clips, the video clip filtering entry can be triggered. The selected video clip is regarded as a target video clip, so that the target video clip in the synthetic video is played on the target tracking page.

[0200] In the application scenario, the scheme supports automatic camera recognition and manual user image data upload to generate object identifiers for target objects, and simultaneously supports user editing of automatically generated to-be-recognized identifiers to convert them into recognized objects, thereby greatly improving the flexibility and accuracy of target object identity confirmation. By uploading the object identifiers of the recognized objects to the cloud and synchronously sharing them between image acquisition devices in different scenarios, continuous and cross-scenario tracking of the target objects is achieved. The scheme also supports superimposition processing of image data obtained by multiple devices based on the coincidence relationship of the shooting time periods, thereby optimizing video continuity and target tracking integrity.

[0201] It should be understood that, although each step in the flowchart of the accompanying drawings is displayed in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be alternately executed with at least part of other steps or sub-steps or stages of other steps.

[0202] The following is an apparatus embodiment of the present application, which can be used to execute the target tracking method involved in the present application. For details not disclosed in the apparatus embodiment of the present application, please refer to the method embodiment of the target tracking method involved in the present application.

[0203] Please refer to Figure 9The embodiment of the present application provides a target tracking device 900, which comprises but is not limited to an identification obtaining module 910, an image obtaining module 930 and a data display module 950.

[0204] The identification obtaining module is used for obtaining the object identification of the target object.

[0205] The image obtaining module is used for obtaining image data of the target object based on the object identification of the target object; the image data is obtained by a plurality of image collection devices arranged in different scenes and shooting the target object appearing in the corresponding scene.

[0206] The data display module displays the obtained image data.

[0207] In an example embodiment, the identification obtaining module is further used for displaying selectable object identifications; and the object identification of the target object is obtained by detecting an operation of selecting one of the object identifications.

[0208] In an example embodiment, the image obtaining module is further used for displaying at least one picture identification; and each picture identification corresponds to the image data of the target object in a different scene.

[0209] In an example embodiment, the target tracking device is further used for detecting an operation of selecting one of the picture identifications, determining the target scene corresponding to the selected picture identification, and displaying the image data of the target object in the target scene on a target tracking page.

[0210] In an example embodiment, the data display module is further used for displaying a video viewing entry for the target object; and the image data of the target object in different scenes and / or the image data in different shooting time periods in the same scene are synthesized by detecting an operation triggered on the video viewing entry; and a synthesized video of the target object is played on the target tracking page.

[0211] In an example embodiment, the data display module is further used for, if the shooting time periods of the image data of the target object in different scenes completely coincide, performing superposition processing on the image data with the completely coinciding shooting time periods to obtain a synthesized video of the target object; and the synthesized video comprises a plurality of video clips, and each video clip corresponds to the image data in a different scene but with a coinciding shooting time period.

[0212] In an example embodiment, the data display module is further configured to, if the image data of the target object in different scenes do not completely overlap in the shooting time period, perform superposition processing on the image data that overlap in the shooting time period to obtain an intermediate video containing multiple video clips, each of the video clips corresponding to the image data in different scenes but overlapping in the shooting time period, and perform splicing processing on the image data in different scenes that do not overlap in the shooting time period and the intermediate video in time sequence to obtain the synthetic video of the target object.

[0213] In an example embodiment, the data display module is further configured to, after detecting an operation triggered on the time period filtering entry on the target tracking page, determine the target time period selected, and play the video clip corresponding to the target time period in the synthetic video on the target tracking page.

[0214] In an example embodiment, the data display module is further configured to display a play progress bar of the synthetic video on the target tracking page, divide the play progress bar into multiple play time periods by different markers, each of the markers being used to represent that the video clips associated with the play time periods are different, and the video clips associated with each of the play time periods being obtained by shooting the target object by different image acquisition devices, detect a selection operation on one of the play time periods, determine the video clip associated with the selected play time period as the target video clip, and play the target video clip in the synthetic video on the target tracking page.

[0215] In an example embodiment, the marker is further used to represent the number of the video clips associated with the play time period, and the multiple video clips associated with the play time period are obtained by shooting the target object by different image acquisition devices, the data display module is further configured to, as the synthetic video is played, if the play progress of the synthetic video slides to a target play time period on the play progress bar, display a video clip filtering entry for the target play time period on the target tracking page, the target play time period refers to the play time period associated with multiple video clips, detect an operation triggered on the video clip filtering entry, determine the selected video clip as the target video clip, and play the target video clip in the synthetic video on the target tracking page.

[0216] In an example embodiment, the target tracking device is further configured to display an identified object adding entry, the identified object adding entry being used to add the object identifier of the identified object, detect an operation triggered on the identified object adding entry, obtain the image data of the identified object, and generate the object identifier of the identified object based on the image data of the identified object.

[0217] In an example embodiment, the image acquisition module is further configured to display an image data upload portal; the image data upload portal is configured to add image data of the identified object; and the image data of the identified object is obtained by detecting an operation triggered on the image data upload portal.

[0218] In an example embodiment, the target tracking device is further configured to display at least one to-be-identified identifier of a to-be-identified object; the to-be-identified identifier is obtained by the image acquisition device capturing the to-be-identified object appearing in the corresponding scene; the selected to-be-identified identifier is determined by detecting an operation triggered on any one of the to-be-identified identifiers; and the to-be-identified identifier of the to-be-identified object is converted into the object identifier of the identified object by editing the selected to-be-identified identifier.

[0219] In an example embodiment, the target tracking device is further configured to send the object identifier of the identified object to the server, so as to instruct the server to share the object identifier of the identified object among the image acquisition devices deployed in different scenes; and the image acquisition devices are instructed to capture the identified object appearing in the corresponding scene by sharing the object identifier of the identified object among the image acquisition devices.

[0220] It should be noted that the target tracking device provided in the above embodiments is only used as an example to illustrate the division of the above functional modules, and in actual applications, the above functions can be distributed to different functional modules according to needs, that is, the internal structure of the target tracking device is divided into different functional modules to complete all or part of the functions described above.

[0221] In addition, the embodiments of the target tracking device and the target tracking method provided in the above embodiments belong to the same concept, and the specific manner in which each module performs operations has been described in detail in the method embodiments, which will not be described here.

[0222] Please refer to Figure 14 In the embodiments of the present application, an electronic device 4000 can include a smart phone, a tablet computer, a smart control panel, etc.

[0223] In Figure 10 the electronic device 4000 includes at least one processor 4001 and at least one memory 4003.

[0224] Data interaction between the processor 4001 and the memory 4003 can be implemented through at least one communication bus 4002. The communication bus 4002 can include a channel for transmitting data between the processor 4001 and the memory 4003. The communication bus 4002 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 4002 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is shown in the figure, but it does not mean that there is only one bus or only one type of bus.

[0225] Optionally, the electronic device 4000 can further include a transceiver 4004, which can be used for data interaction, such as data sending and / or data receiving, between the electronic device and other electronic devices. It should be noted that the transceiver 4004 is not limited to one in actual application, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0226] The processor 4001 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure content of the present application. The processor 4001 can also be a combination for realizing a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0227] The memory 4003 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, a magnetic disk storage or other magnetic storage devices, or any other medium capable of storing computer programs in the form of instructions or data structures and that can be accessed by the electronic device 400, but is not limited thereto.

[0228] The memory 4003 stores a computer program, and the processor 4001 can read the computer program stored in the memory 4003 through the communication bus 4002.

[0229] The computer program is executed by the one or more processors 4001 to implement the target tracking method in the above embodiments.

[0230] In addition, the present application provides a storage medium, which stores a computer program, and the computer program is executed by one or more processors to implement the target tracking method as described above.

[0231] The present application provides a computer program product, which includes a computer program, and the computer program is executed by one or more processors to implement the target tracking method as described above.

[0232] Compared with the related art, the present application can realize automatic collection, association and display of target object image data. By assigning a unique object identifier to each target object, the activity process of the target object in multiple scenes can be continuously tracked and identified, avoiding object identification confusion or tracking interruption. Since multiple image collection devices are respectively deployed in at least one scene and photograph the target object, the image data of the target object in different scenes can be completely obtained, enhancing the spatiotemporal coverage range and integrity of the image data.

[0233] The above only describes some embodiments of the present application. It should be noted that, for those skilled in the art, without departing from the principles of the present application, some improvements and refinements can be made, which should also be considered as the protection scope of the present application.

Claims

1. A target tracking method characterized by, The method comprises: obtaining an object identifier of a target object; based on the object identifier of the target object, obtaining image data of the target object; the image data is obtained by a plurality of image collection devices deployed in at least one scene respectively shooting the target object appearing in the corresponding scene; displaying the obtained image data.

2. The method of claim 1, wherein, The method comprises: displaying the object identifier that can be selected; detecting the operation of selecting one of the object identifiers to obtain the object identifier of the target object.

3. The method of claim 1, wherein, The method comprises: displaying at least one picture identifier; each picture identifier corresponds to the image data of the target object in different scenes.

4. The method of claim 3, wherein, After displaying the at least one picture identifier, the method further comprises: detecting the operation of selecting one of the picture identifiers to determine the target scene corresponding to the selected picture identifier; displaying the image data of the target object in the target scene on the target tracking page.

5. The method of claim 1, wherein, The method comprises: displaying a video viewing entry for the target object; detecting the operation triggered by the video viewing entry, synthesizing the image data of the target object in different scenes and / or the image data in different shooting time periods in the same scene; playing the synthesized video of the target object on the target tracking page.

6. The method of claim 5, wherein, The method comprises: if the shooting time periods of the image data of the target object in different scenes completely coincide, superimposing the image data with completely coinciding shooting time periods to obtain the synthesized video of the target object; the synthesized video comprises a plurality of video clips, and each video clip corresponds to the image data in different scenes but with coinciding shooting time periods.

7. The method of claim 5, wherein, The method comprises: if the shooting time periods of the image data of the target object in different scenes do not completely coincide, superimposing the image data with coinciding shooting time periods to obtain an intermediate video comprising a plurality of video clips; each video clip corresponds to the image data in different scenes but with coinciding shooting time periods; splicing the image data with non-coinciding shooting time periods in different scenes and the intermediate video in time sequence to obtain the synthesized video of the target object.

8. The method of claim 5, wherein, The method comprises: detecting the operation of triggering the time period filtering entry on the target tracking page to determine the target time period; playing the video clip corresponding to the target time period in the synthesized video on the target tracking page.

9. The method of claim 5, wherein, The method comprises: The target tracking page displays a play progress bar of the synthesized video; the play progress bar is divided into multiple play time periods by different markers, each marker is used to represent different video clips associated with the play time period, and each play time period is associated with the video clips obtained by different image collection devices capturing the target object; Detecting a selection operation on one of the play time periods, and determining the video clip associated with the selected play time period as a target video clip; The target tracking page plays the target video clip in the synthesized video.

10. The method of claim 9, wherein, The marker is also used to represent the number of video clips associated with the play time period; the multiple video clips associated with the play time period are obtained by different image collection devices capturing the target object; The target tracking page plays the target video clip in the synthesized video further includes: As the synthesized video is played, if the play progress of the synthesized video slides to a target play time period on the play progress bar, the target tracking page displays a video clip filtering entry for the target play time period; the target play time period refers to the play time period associated with multiple video clips; Detecting an operation triggered by the video clip filtering entry, and determining the selected video clip as the target video clip; The target tracking page plays the target video clip in the synthesized video.

11. The method of claim 1, wherein, Before the object identifier of the target object is obtained, the method further includes: Display an identified object adding entry; the identified object adding entry is used to add the object identifier of an identified object; Detecting an operation triggered by the identified object adding entry, and obtaining image data of the identified object; Generating the object identifier of the identified object based on the image data of the identified object.

12. The method of claim 11, wherein, The image data of the identified object is obtained by: Displaying an image data uploading entry; the image data uploading entry is used to add the image data of the identified object; Detecting an operation triggered by the image data uploading entry, and obtaining the image data of the identified object.

13. The method of claim 1, wherein, Before the object identifier of the target object is obtained, the method further includes: Displaying a to-be-identified identifier of at least one to-be-identified object; the to-be-identified identifier is obtained by the image collection device capturing the to-be-identified object appearing in a corresponding scene; Detecting an operation triggered by any one of the to-be-identified identifiers, and determining the selected to-be-identified identifier; Through editing processing on the selected to-be-identified identifier, the to-be-identified identifier of the to-be-identified object is converted into the object identifier of an identified object.

14. The method of any one of claims 1 to 13, wherein, The method further includes: Sending the object identifier of the identified object to a server, to instruct the server to share the object identifier of the identified object among the image collection devices deployed in different scenes; and The sharing of the object identifier of the identified object among the image acquisition devices indicates each image acquisition device to capture the identified object appearing in the corresponding scene.

15. The method of any one of claims 1 to 13, wherein, The target object includes a person, an animal, a vehicle, or a package.

16. A target tracking device, characterized by The device includes: an object identifier acquisition module configured to acquire an object identifier of a target object; an image acquisition module configured to acquire image data of the target object based on the object identifier of the target object, the image data being obtained by multiple image acquisition devices deployed in different scenes capturing the target object appearing in the corresponding scene respectively; a data display module configured to display the acquired image data.

17. An electronic device comprising at least one processor and at least one memory, wherein, The memory stores a computer program, and the computer program is executed by the processor to implement the target tracking method in any one of claims 1 to 15.

18. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by one or more processors to implement the target tracking method in any one of claims 1 to 15.

19. A computer program product comprising a computer program, characterized in that, The computer program is executed by one or more processors to implement the target tracking method in any one of claims 1 to 15.

Images