Virtual positioning method and device, virtual positioning system

Abstract

The present invention discloses a virtual positioning method and device, and a virtual positioning system. The method includes: obtaining target positioning data of a target in a first camera cluster, wherein the first camera cluster is a camera used in a positioning system, and the positioning system is used to perform a target tracking task to generate positioning data; sending the target positioning data to a positioning system, wherein the positioning system uses a target mapping model and the target positioning data to generate virtual positioning data of the target in a second camera cluster, and the target mapping model is used to describe the spatial mapping relationship between the first camera cluster and the second camera cluster; and virtually positioning the target according to the virtual positioning data. The present invention solves the technical problem in related technologies that image sensors are relatively single in application and cannot be used for large-scale collaborative tracking.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a virtual positioning method and device, and a virtual positioning system. Background Art

[0002] With the exponential development of technology, the production cost of image sensors will continue to decline year by year, and the scale of production will also increase exponentially. This will also give rise to various new applications, such as chained image sensor technology. As image sensors are widely used in social scenarios, a technology that can coordinate tracking of multiple image sensors is also needed to meet users' target tracking needs.

[0003] Currently, the use of image sensors for positioning and tracking is widespread, with examples including advanced tracking systems like PTAM (Parallel Tracking and Mapping) and ACTS (Automatic Camera Tracking System). While different positioning and tracking technologies have varying degrees of superiority and maturity, all are used for identification, positioning, and tracking within a single surveillance camera.

[0004] Currently, there is a lack of tracking technology that can coordinate large-scale image sensors.

[0005] With regard to the problem that the image sensors in the above-mentioned related technologies are relatively single in application and cannot be used for large-scale collaborative tracking, no effective solution has been proposed so far. Summary of the Invention

[0006] The embodiments of the present invention provide a virtual positioning method and device, and a virtual positioning system to at least solve the technical problem in related technologies that image sensors are relatively single in application and cannot be used for large-scale collaborative tracking.

[0007] According to one aspect of an embodiment of the present invention, a virtual positioning method is provided, including: obtaining target positioning data of a target in a first camera cluster, wherein the first camera cluster is a camera used in a positioning system, and the positioning system is used to perform a target tracking task to generate positioning data; sending the target positioning data to the positioning system, wherein the positioning system uses a target mapping model and the target positioning data to generate virtual positioning data of the target in a second camera cluster, and the target mapping model is used to describe the spatial mapping relationship between the first camera cluster and the second camera cluster; and virtually positioning the target according to the virtual positioning data.

[0008] Optionally, the target mapping model is a mapping model obtained by the positioning system from a mapping model system, wherein the mapping model system generates a mapping model including the relationship between each camera position and viewing angle in a predetermined application scenario by initializing modeling.

[0009] Optionally, before virtually positioning the target according to the virtual positioning data, the virtual positioning method further includes: verifying the virtual positioning data; wherein, verifying the virtual positioning data includes: obtaining the actual positioning data of the target in the second camera cluster; using predetermined verification rules to determine the similarity between the actual positioning data and the virtual positioning data, so as to verify the consistency between the virtual positioning data and the actual positioning data.

[0010] Optionally, the virtual positioning method also includes: responding to a relay tracking request signal and determining the best sampling camera in the second camera cluster based on the virtual positioning data; setting the attributes of the best sampling camera to the first camera cluster to obtain an updated first camera cluster; obtaining the image information stream collected by the updated first camera cluster; sending the image information stream to the positioning system, wherein the positioning system generates target positioning data of the target in the updated first camera cluster based on the image information stream.

[0011] Optionally, responding to a relay tracking request signal includes: determining the distribution density of cameras in a predetermined application scenario where the first camera cluster and the second camera cluster are located; when it is determined that the distribution density is less than a predetermined value, responding to the relay tracking request signal when the target is located at a predetermined position at the edge of the viewing area of ​​the first camera cluster; or, when it is determined that the distribution density is not less than a predetermined value, responding to the relay tracking request signal when the target leaves the middle position of the viewing area of ​​the first camera cluster.

[0012] Optionally, responding to the relay tracking request signal includes: determining that the positioning accuracy of the target is lower than a predetermined threshold; and responding to the relay tracking request signal.

[0013] Optionally, after virtually positioning the target according to the virtual positioning data, the virtual positioning method further includes: in response to an identification matching task, determining that the second camera cluster includes at least one camera of the target; obtaining frame image information of the at least one camera; identifying feature identifiers in the frame image information, and generating target identification information of the target based on the feature identifiers.

[0014] Optionally, the target is virtually positioned according to the virtual positioning data, including: responding to a target query instruction of a terminal device and obtaining target identification information of the target query instruction; determining a viewfinder camera based on the target identification information combined with the target positioning data and / or the virtual positioning data; and feeding back the video stream of the target captured by the viewfinder camera to the terminal device.

[0015] Optionally, before virtually positioning the target according to the virtual positioning data, the virtual positioning method also includes: in response to a tracking task request, determining a positioning calibration camera in the second camera cluster according to the virtual positioning data; obtaining frame image cache information of the positioning calibration camera; generating calibration positioning data of the target in the positioning calibration camera based on the frame image cache information; and correcting the target positioning data according to the calibration positioning data.

[0016] Optionally, the initiation condition of the tracking task request includes one of the following: the target is lost, the determination accuracy of the target is lower than a predetermined threshold, and the predetermined plan of the target tracking task.

[0017] Optionally, the virtual positioning method further includes: determining a framing camera according to a predetermined rule based on the target positioning data and / or the virtual positioning data; and sending frame image information captured by the framing camera to a predetermined storage medium.

[0018] According to another aspect of an embodiment of the present invention, a virtual positioning device is also provided, including: an acquisition unit, used to acquire target positioning data of a target in a first camera cluster, wherein the first camera cluster is a camera used in a positioning system, and the positioning system is used to perform a target tracking task to generate positioning data; a sending unit, used to send the target positioning data to the positioning system, wherein the positioning system uses a target mapping model and the target positioning data to generate virtual positioning data of the target in a second camera cluster, and the target mapping model is used to describe the spatial mapping relationship between the first camera cluster and the second camera cluster; a virtual positioning unit, used to virtually position the target according to the virtual positioning data.

[0019] Optionally, the target mapping model is a mapping model obtained by the positioning system from a mapping model system, wherein the mapping model system generates a mapping model including the relationship between each camera position and viewing angle in a predetermined application scenario by initializing modeling.

[0020] Optionally, the virtual positioning device also includes: a verification unit, used to verify the virtual positioning data before virtually positioning the target based on the virtual positioning data; wherein, the verification unit includes: a first acquisition module, used to obtain the actual positioning data of the target in the second camera cluster; a verification module, used to determine the similarity between the actual positioning data and the virtual positioning data using predetermined verification rules, so as to verify the consistency between the virtual positioning data and the actual positioning data.

[0021] Optionally, the virtual positioning device also includes: a first determination unit, used to respond to the relay tracking request signal and determine the best sampling camera in the second camera cluster based on the virtual positioning data; a setting unit, used to set the attributes of the best sampling camera to the first camera cluster to obtain an updated first camera cluster; the acquisition unit, used to obtain the image information stream collected by the updated first camera cluster; the sending unit, used to send the image information stream to the positioning system, wherein the positioning system generates target positioning data of the target in the updated first camera cluster based on the image information stream.

[0022] Optionally, the first determination unit includes: a first determination module for determining the distribution density of cameras in a predetermined application scenario where the first camera cluster and the second camera cluster are located; a second determination module for responding to the relay tracking request signal when the distribution density is less than a predetermined value and the target is located at a predetermined position at the edge of the viewing area of ​​the first camera cluster; or a third determination module for responding to the relay tracking request signal when the distribution density is not less than a predetermined value and the target leaves the middle position of the viewing area of ​​the first camera cluster.

[0023] Optionally, the first determining unit includes: a fourth determining module, configured to determine that the positioning accuracy of the target is lower than a predetermined threshold; and a responding module, configured to respond to the relay tracking request signal.

[0024] Optionally, the virtual positioning device also includes: a second determination unit, used to determine, in response to an identification matching task, after virtually positioning the target according to the virtual positioning data, that the second camera cluster includes at least one camera of the target; the acquisition unit, used to acquire frame image information of the at least one camera; and a first generation unit, used to identify feature identifiers in the frame image information and generate target identification information of the target based on the feature identifiers.

[0025] Optionally, the virtual positioning unit includes: a second acquisition module, used to respond to the target query instruction of the terminal device and obtain the target identification information of the target query instruction; a fifth determination module, used to determine the viewfinder camera based on the target identification information combined with the target positioning data and / or the virtual positioning data; and a feedback module, used to feed back the video stream of the target captured by the viewfinder camera to the terminal device.

[0026] Optionally, the virtual positioning device also includes: a third determination unit, used to determine the positioning calibration camera in the second camera cluster according to the virtual positioning data in response to a tracking task request before virtually positioning the target according to the virtual positioning data; the acquisition unit, used to acquire the frame image cache information of the positioning calibration camera; a second generation unit, used to generate the calibration positioning data of the target in the positioning calibration camera based on the frame image cache information; and a correction unit, used to correct the target positioning data according to the calibration positioning data.

[0027] Optionally, the initiation condition of the tracking task request includes one of the following: the target is lost, the determination accuracy of the target is lower than a predetermined threshold, and the predetermined plan of the target tracking task.

[0028] Optionally, the virtual positioning device also includes: a fourth determination unit, used to determine the viewfinder camera according to predetermined rules based on the target positioning data and / or the virtual positioning data; and the sending unit, used to send the frame image information captured by the viewfinder camera to a predetermined storage medium.

[0029] According to another aspect of an embodiment of the present invention, a virtual positioning system is provided, which uses any one of the virtual positioning methods described above.

[0030] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored computer program, wherein when the computer program is executed by a processor, the device where the computer storage medium is located is controlled to execute any of the above-mentioned virtual positioning methods.

[0031] According to another aspect of an embodiment of the present invention, a processor is further provided, wherein the processor is configured to run a computer program, wherein the computer program executes any one of the above-mentioned virtual positioning methods when running.

[0032] In an embodiment of the present invention, target positioning data of a target in a first camera cluster is obtained, wherein the first camera cluster is a camera used in a positioning system, and the positioning system is used to perform a target tracking task to generate positioning data; the target positioning data is sent to the positioning system, wherein the positioning system uses a target mapping model and the target positioning data to generate virtual positioning data of the target in a second camera cluster, and the target mapping model is used to describe the spatial mapping relationship between the first camera cluster and the second camera cluster; the target is virtually positioned according to the virtual positioning data, and the virtual positioning method provided by the embodiment of the present invention realizes the purpose of collaboratively positioning the target through the camera cluster, and achieves the technical effect of improving the accuracy of positioning the target, thereby solving the technical problem in the related art that the application of image sensors is relatively single and large-scale collaborative tracking cannot be performed using image sensors. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0034] Figure 1 is a flowchart of a virtual positioning method according to an embodiment of the present invention;

[0035] Figure 2 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 1 ;

[0036] Figure 3 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 2 ;

[0037] Figure 4 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 3 ;

[0038] Figure 5 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 4 ;

[0039] Figure 6 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 5 ;

[0040] Figure 7 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 6 ;

[0041] Figure 8 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 7 ;

[0042] Figure 9 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 8 ;

[0043] FIG10( a ) is a schematic diagram of a scenic area according to an embodiment of the present invention. Figure 1 ;

[0044] FIG10( b ) is a schematic diagram of a scenic area according to an embodiment of the present invention. Figure 2 ;

[0045] Figure 11 is a schematic diagram of a logistics transfer station according to an embodiment of the present invention;

[0046] Figure 12 is a schematic diagram of a traffic monitoring area according to an embodiment of the present invention;

[0047] Figure 13 is a schematic diagram of a kindergarten according to an embodiment of the present invention;

[0048] Figure 14 is a schematic diagram of a subway operating company according to an embodiment of the present invention;

[0049] Figure 15 is a schematic diagram of a virtual positioning device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0051] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0052] According to an embodiment of the present invention, a method embodiment of a virtual positioning method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0053] Figure 1 is a flow chart of a virtual positioning method according to an embodiment of the present invention. Figure 1 As shown, the virtual positioning method includes the following steps:

[0054] Step S102 : acquiring target positioning data of a target in a first camera cluster, wherein the first camera cluster is a camera used in a positioning system, and the positioning system is used to perform a target tracking task to generate positioning data.

[0055] Optionally, the first camera cluster here is a sampling camera of a tracking and positioning system (ie, a positioning system), and the tracking and positioning system is configured to perform a target tracking task to generate positioning data.

[0056] In step S104, the target positioning data is sent to the positioning system, wherein the positioning system generates virtual positioning data of the target in the second camera cluster using the target mapping model and the target positioning data. The target mapping model is used to describe the spatial mapping relationship between the first camera cluster and the second camera cluster.

[0057] Optionally, the cameras in the second camera cluster and the cameras in the first camera cluster are fixed cameras with fixed positions and angles, allowing for acquisition of frame image information with a static background. As long as the camera positions and angles remain fixed, zooming the camera does not change the perspective of the image capture, but only the framing area. By determining the relationship between changes in focal length and framing area, the correspondence between the position coordinates before and after the zoom can be determined. Similarly, as long as the cameras have preset zoom parameters, the position coordinates of the target can be calculated for various zoom states.

[0058] Furthermore, lens distortion can occur during zooming in some cameras, particularly wide-angle and fisheye cameras. Distortion correction techniques can be used to eliminate the effects of zooming on target positioning. Therefore, given known camera zoom parameters, lens distortion parameters, and the initial focal length of the model, target positioning data and virtual positioning data can be unaffected by camera zoom and lens distortion.

[0059] It should be noted that, in the embodiment of the present invention, the second camera cluster may also include a chain image acquisition device, wherein multiple cameras of the chain image acquisition device are distributed in a chain shape in the same data transmission bus.

[0060] In addition, in an embodiment of the present invention, the tracking and positioning system may include one or more target tracking algorithms, such as frame difference method, background compensation method, expectation maximization method, optical flow method, statistical model method, level set method, parallel tracking and mapping PTAM (Parallel Tracking and Mapping, abbreviated as PTAM), automatic camera tracking system ACTS (Automatic Camera Tracking System, abbreviated as ACTS), etc., and may also include a deep neural network to achieve target tracking and positioning through machine learning and other means.

[0061] Step S106: Virtually locate the target according to the virtual positioning data.

[0062] From the above, it can be seen that in an embodiment of the present invention, target positioning data of the target in the first camera cluster can be obtained, wherein the first camera cluster is a camera used in the positioning system, and the positioning system is used to perform target tracking tasks to generate positioning data; the target positioning data is sent to the positioning system, wherein the positioning system uses the target mapping model and the target positioning data to generate virtual positioning data of the target in the second camera cluster, and the target mapping model is used to describe the spatial mapping relationship between the first camera cluster and the second camera cluster; the target is virtually positioned according to the virtual positioning data, thereby achieving the purpose of positioning the target through collaborative positioning of the camera cluster and achieving the technical effect of improving the accuracy of positioning the target.

[0063] Therefore, the virtual positioning method provided by the embodiment of the present invention solves the technical problem in the related art that the application of image sensors is relatively single and large-scale collaborative tracking cannot be performed using image sensors.

[0064] In an optional embodiment, the target mapping model is a mapping model obtained by the positioning system from a mapping model system, wherein the mapping model system generates a mapping model including the relationship between each camera position and viewing angle in a predetermined application scenario by initializing modeling.

[0065] In this embodiment, the camera cluster mapping model is a spatial model generated by the mapping model system through initialization modeling, which includes the relationship between the position and viewing angle of each camera in the application scene, and describes the spatial mapping relationship between the first camera cluster and the second camera cluster.

[0066] It should be noted that, in the embodiment of the present invention, the mapping model can be one of a two-dimensional model, a three-dimensional model, and a dynamic model; wherein, the two-dimensional model is basically generated by analyzing the overlapping areas in the initialization modeling frame image information collected by each camera. The two-dimensional model has the problems of low positioning accuracy and susceptibility to the influence of the three-dimensional environment in the specific practical application process. It is only suitable for application scenarios with low positioning accuracy requirements; wherein, the three-dimensional model can establish a three-dimensional function mapping relationship of each camera in the spatial model by analyzing more than three common position points in the initialization modeling frame image information collected by each camera during the modeling initialization process; the three-dimensional model can also be modeled by analyzing the position coordinates of a target at different times during the modeling initialization process; since the camera clusters in the embodiment of the present invention are all fixed positions and fixed viewing angles The background of each camera's viewing area is the same at different times. The same target moves to more than three positions. By analyzing the position coordinates of the target position in each camera's viewing area, the three-dimensional function mapping relationship of each camera in the spatial model can be constructed; among them, the dynamic model is a different spatial model corresponding to different conditions. The standardized position repetition correspondence is a prerequisite for building a dynamic model. For example, the subway train will stop at the same position accurately after arriving at the station. The spatial mapping relationship of the cameras inside and outside the subway train door is a prerequisite for the train to stop at the platform accurately. For example, the elevator stopping at each floor is a scene with repeated and standardized positions. After constructing the dynamic model, different three-dimensional models can be triggered according to different elevator stop conditions to obtain two-dimensional or three-dimensional mapping relationships of different camera clusters.

[0067] Figure 2 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 1 ,like Figure 2 As shown, the first camera cluster will send the collected image frame information stream to the service system, and the service system will send the frame image information stream of the first camera cluster to the tracking and positioning system. The tracking and positioning system will generate positioning data based on the frame image information stream and return the positioning data to the service system. The service system will send the positioning data of the target in the first camera cluster to the virtual positioning system. The virtual positioning system will send a mapping model request to the mapping model system and receive the target mapping model fed back by the mapping model system based on the mapping model request. Based on the target mapping model and the positioning data of the target in the first camera cluster, the virtual positioning data of the target in the second camera cluster will be generated, and the virtual positioning data will be fed back to the service system.

[0068] That is, in this embodiment, the camera cluster mapping model can be extracted by obtaining the positioning data of the target in the first camera cluster; and the virtual positioning data corresponding to the target in the second camera cluster can be generated based on the mapping model and the target positioning data.

[0069] In an optional embodiment, before virtually positioning the target based on the virtual positioning data, the virtual positioning method may further include: verifying the virtual positioning data; wherein, verifying the virtual positioning data includes: obtaining the actual positioning data of the target in the second camera cluster; using predetermined verification rules to determine the similarity between the actual positioning data and the virtual positioning data, so as to verify the consistency between the virtual positioning data and the actual positioning data.

[0070] In this embodiment, the positioning data in the second camera cluster is target positioning data generated by the second tracking system, and the second target positioning system is configured to sample the second camera cluster, perform target tracking, and generate target positioning data.

[0071] It should be noted that the second tracking and positioning system and the second camera cluster can be attached to a monitoring service system external to the service system. The two service systems only exchange limited data during initial modeling and target verification. The external camera cluster does not actually exist in the local service system; it is merely a virtual mapping of cameras in the mapping model. By verifying the consistency between the virtual positioning data and the actual positioning data, the authenticity and effectiveness of target tracking can be verified, achieving rigorous process control of the target tracking task.

[0072] Figure 3 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 2 ,like Figure 3 As shown, the virtual positioning method includes Figure 2 In addition to the virtual positioning method in the above, it also includes the process of verifying the virtual positioning data; specifically, Figure 3 As shown, the second camera cluster will send the collected frame image information stream to the second tracking and positioning system. The second tracking and positioning system will generate actual positioning data (i.e., target positioning data) based on the received frame image information stream, and send the actual positioning data to the service system. The service system can verify the virtual positioning data based on the actual positioning data.

[0073] That is, the second tracking and positioning system receives the positioning data of the second camera cluster of the target, and verifies the virtual positioning data of the target and the positioning data of the second camera cluster according to a predetermined rule to generate a verification result of the positioning data of the target in the second camera cluster.

[0074] In an optional embodiment, the virtual positioning method also includes: responding to a relay tracking request signal and determining the best sampling camera in the second camera cluster based on the virtual positioning data; setting the attributes of the best sampling camera to the first camera cluster to obtain an updated first camera cluster; obtaining an image information stream collected by the updated first camera cluster; sending the image information stream to the positioning system, wherein the positioning system generates target positioning data of the target in the updated first camera cluster based on the image information stream.

[0075] In this embodiment, in response to the relay tracking request of the target tracking task, the best sampling camera in the second camera cluster can be determined based on the virtual positioning data of the second camera cluster, and the best camera attributes can be converted into the first camera cluster; wherein, after the best sampling camera attributes here are converted into the first camera cluster, they are used to take over the original tracking task on-site sampling camera and relay the frame image information sampling of the target tracking task.

[0076] It should be noted that, in this embodiment of the present invention, the initiation condition for the target tracking task relay tracking request is that the target is located in the predetermined viewing area of ​​the first camera cluster and / or the target judgment accuracy is lower than a threshold. Detailed description is given below.

[0077] In one aspect, responding to a relay tracking request signal includes: determining the distribution density of cameras in a predetermined application scenario where the first camera cluster and the second camera cluster are located; when it is determined that the distribution density is less than a predetermined value, responding to the relay tracking request signal when the target is located at a predetermined position at the edge of the viewing area of ​​the first camera cluster; or, when it is determined that the distribution density is not less than a predetermined value, responding to the relay tracking request signal when the target leaves the middle position of the viewing area of ​​the first camera cluster.

[0078] In this embodiment, the relay tracking request for the target tracking task can set the starting criteria for the relay tracking request based on the density of the camera on-site layout. For example, in a scene with low camera density, the overlap of the camera framing areas is low, and the relay tracking request can be set to start when the tracked target is within a predetermined range at the edge of the framing area of ​​the sampling camera of the first camera cluster; for example, in a scene with high camera density, the overlap of the camera framing areas is high, and the relay tracking request can be set to start when the tracked target leaves the predetermined range in the middle of the framing area of ​​the sampling camera. For example, if the camera density of the chain image acquisition device is very high, a relay tracking request condition with a high starting criteria can be set to achieve a follow-up target tracking record.

[0079] In another aspect, responding to the relay tracking request signal includes: determining that the positioning accuracy of the target is lower than a predetermined threshold; and responding to the relay tracking request signal.

[0080] Figure 4 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 3 ,like Figure 4 As shown, in addition to including Figure 2 In addition to the virtual positioning method in the method, the following steps are also included: the service system starts the target tracking task relay tracking request, then determines the best sampling camera in the second camera cluster, and sends the specified best sampling camera to the second camera cluster, the second camera cluster converts the properties of the best sampling camera to the first camera cluster, and receives the updated frame image information stream sent by the first camera cluster, the service system will send the received frame image information stream to the tracking and positioning system, the tracking and positioning system will generate target positioning data according to the frame image information stream sent by the updated first camera cluster, and send the target positioning data to the service system.

[0081] Through the relay tracking in the embodiment of the present invention, the consistency of the target tracking task can be ensured and the target positioning accuracy can be improved.

[0082] In an optional embodiment, after virtually positioning the target according to the virtual positioning data, the virtual positioning method may further include: in response to the identification matching task, determining at least one camera in the second camera cluster that contains the target; obtaining frame image information of at least one camera; identifying feature identifiers in the frame image information, and generating target identification information of the target based on the feature identifiers.

[0083] In this embodiment, the identification features in the recognition frame image information can be image features, such as human facial features, object contour features, color features, barcodes or QR codes, etc.; the feature identification can be multiple identifications that are matched and associated with the same tracked target. For example, when performing feature identification on a car, the color identification of the car can be associated based on the color feature, the type identification of the car can be associated based on the contour feature, and the license plate number identification of the car can be associated based on the license plate recognition.

[0084] It should be noted that, in actual applications, other non-image features may also be matched and associated, such as RFID radio frequency features, sound features, visible light stroboscopic features, or motion features.

[0085] In addition, the service system can set different conditions for starting the identification matching task, such as setting a fixed start interval for the target matching task, for example, in response to the target determination accuracy of the target tracking task being lower than a threshold, for example, in response to the target being lost in the target tracking task, for example, in response to an identification verification instruction from a user terminal, and so on. When the identification verification task is started, the service system determines the camera in the second camera cluster that contains the target through the virtual positioning data of the second camera cluster, and mainly requests the frame image cache information of the camera that contains the target. The identification verification task generates target identification information by analyzing the frame image information of the cameras that contain the target in the first camera cluster and the second camera cluster, and matches it with the tracked target, thereby improving the accuracy of the tracking results, reducing the target tracking task bias that leads to the incorrect association and matching of the tracked target and the target identification, and facilitating the retrieval query of the target.

[0086] Figure 5 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 4 ,like Figure 5 As shown, in addition to including Figure 2 In addition to the virtual positioning method process shown in , the following process can also be included: the service system can start the identification matching task, and based on the identification matching task, determine the camera in the second camera cluster that contains the target, and then request the frame image information of the specified camera from the second camera cluster, identify the identification features in the frame image information, and generate the identification information of the target.

[0087] In an optional embodiment, the target is virtually positioned according to the virtual positioning data, including: responding to a target query instruction of the terminal device and obtaining target identification information of the target query instruction; determining a viewfinder camera based on the target identification information combined with the target positioning data and / or virtual positioning data; and feeding back a video stream of the target captured by the viewfinder camera to the terminal device.

[0088] In this embodiment, it is possible to respond to a target query instruction of a user terminal and match the target identifier of the query instruction; determine the framing lens according to predetermined rules based on the positioning data of the first camera cluster and / or the virtual positioning data of the second camera cluster; and send the frame image information captured by the framing camera to the user terminal for query by the user terminal.

[0089] Figure 6 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 5 ,like Figure 6 As shown, the virtual positioning method includes the following Figure 2In addition to the method shown, the following steps are also included: the service system generates target identification information, and determines the preferred framing camera upon receiving the matching queried target identification from the user terminal; obtains the frame image information stream of the framing camera in the determined first camera cluster, and / or obtains the frame image information stream of the framing camera in the determined second camera cluster, and then sends the generated video information stream to the user terminal based on the information; wherein the user terminal will preferably select the framing camera to be located in the first camera cluster or the second camera cluster.

[0090] In an optional embodiment, the virtual positioning method provided by the embodiment of the present invention can also respond to the display angle switching instruction of the user terminal, and switch the viewfinder camera according to predetermined rules based on the positioning data of the first camera cluster and / or the virtual positioning data of the second camera cluster; the frame image information captured by the switched viewfinder camera is sent to the user terminal.

[0091] Figure 7 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 6 ,like Figure 7 As shown, the method and Figure 6 Basically the same, specifically, Figure 7 The service system responds to the display viewing angle switching instruction sent by the user terminal.

[0092] In an optional embodiment, before virtually positioning the target based on the virtual positioning data, the virtual positioning method may further include: in response to a tracking task request, determining a positioning calibration camera in a second camera cluster based on the virtual positioning data; obtaining frame image cache information of the positioning calibration camera; generating calibration positioning data of the target in the positioning calibration camera based on the frame image cache information; and correcting the target positioning data based on the calibration positioning data.

[0093] In this embodiment, the target can be assisted in positioning; specifically, in response to a target tracking task request, a positioning calibration camera in the second camera cluster can be determined based on the virtual positioning data of the second camera cluster; the frame image cache information of the positioning calibration camera can be obtained; the positioning data of the target in the positioning calibration camera can be generated based on the frame image cache information; and the target positioning data can be corrected based on the positioning data of the positioning calibration camera.

[0094] The initiation conditions of the tracking task request include one of the following: target loss, target determination accuracy is lower than a predetermined threshold, and a predetermined plan for the target tracking task.

[0095] Figure 8 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 7 ,like Figure 8 As shown, the virtual positioning method includes the following processing Figure 2In addition to the steps shown, the following steps may also be included: the service system initiates an assisted positioning request based on the target tracking task, and determines the positioning calibration camera in the second camera cluster, requests the frame image cache information of the specified camera from the second camera cluster, and obtains the frame image cache information fed back by the second camera cluster. The service system sends the virtual positioning data and frame image cache information of the positioning calibration camera to the tracking and positioning system based on the frame image cache information to generate the positioning data of the target in the positioning calibration camera, and sends the positioning data of the target in the positioning calibration camera to the service system. The service system corrects the target positioning data based on the positioning data.

[0096] That is, in this embodiment, the service system corrects the target positioning data according to the positioning data of the target in the positioning calibration camera to realize the recovery of target tracking; through assisted positioning, it can solve the problem that the existing technology is difficult to continue tracking when the tracking is lost due to factors such as occlusion, and the original tracking target is easily lost; the assisted positioning request can also be a request planning task for the target tracking task, and the target tracking task is configured with a plan to start the target tracking auxiliary request at a time, dynamically extract the image information of different camera frames, and improve the accuracy of the tracking results.

[0097] In an optional embodiment, the virtual positioning method may further include: determining a viewfinder camera according to predetermined rules based on the target positioning data and / or the virtual positioning data; and sending frame image information captured by the viewfinder camera to a predetermined storage medium.

[0098] In this embodiment, the framing camera can be determined according to predetermined rules based on the positioning data of the first camera cluster and / or the virtual positioning data of the second camera cluster, and the frame image information captured by the framing camera is sent to the storage system.

[0099] Figure 9 is the timing of the virtual positioning method according to an embodiment of the present invention Figure 8 ,like Figure 9 As shown, the virtual positioning method includes the following processing Figure 2 In addition to the steps shown, the following steps may also be included: using the service system to generate target identification information, and generating the best framing camera based on the identification information, and selecting the acquisition camera in the first camera cluster and the second camera cluster, and obtaining the frame image information stream of the sampling camera, generating a video information stream based on the obtained frame image information stream, and sending the generated video information stream to the user terminal.

[0100] The embodiments of the present invention are described below with reference to different scenarios.

[0101] Scenario Example 1

[0102] FIG10( a ) is a schematic diagram of a scenic area according to an embodiment of the present invention. Figure 1 The scenic spot provides tourists with an MV art short film service. The scenic spot's service system can automatically generate MV art short films with tourists as the protagonists after recognizing their facial features. The starting part of the MV art short film template is set to the video footage of the tourists walking towards the front of each scenic spot. The service system searches the video library of the camera collection group of each scenic spot for video footage containing the facial features of the tourists, and inserts the retrieved video footage containing facial features into the starting part of the MV art short film. The ending part of the MV art short film template is set to the video footage of the tourists walking towards the back of each scenic spot. The service system cannot retrieve the back of the tourists without facial features through existing technology.

[0103] The following content is the implementation process of the service system matching the tourist's body virtual identification information with the video screen.

[0104] FIG10( b ) is a schematic diagram of a scenic area according to an embodiment of the present invention. Figure 2 As shown in Figure 10(b), the corridor of the scenic area is respectively equipped with three viewing cameras, namely camera1, camera2, and camera3. The mapping model system includes three-dimensional mapping model data of the three viewing cameras. The three-dimensional mapping model data can be modeled in a variety of ways. For example, a triangular template is placed between the three viewing cameras. Based on the actual shape and size of the triangular template and the coordinate positions of the three corners of the triangle in the viewing image of each camera, the corresponding function mapping relationship of the three cameras in three-dimensional space can be constructed. The initialization modeling process of the mapping model system is not specifically limited in the embodiments of the present invention.

[0105] In this embodiment, camera1 and camera2 are configured as the first camera cluster, and camera3 is configured as the second camera cluster. The tracking and positioning system processes the frames captured by camera1 and camera2 in the first camera cluster to generate the visitor's location data. The service system uses facial feature recognition to match the location data with the visitor's identification information.

[0106] In addition, the service system here extracts the three-dimensional model data of the first camera cluster and the second camera cluster in the mapping model system to obtain the three-dimensional mapping relationship between camera1, camera2 and camera3; and the service system extracts the tourist positioning data generated by the tracking and positioning system, combines the three-dimensional mapping relationship, and obtains the corresponding virtual positioning data of the tourist in camera3 through calculation and processing.

[0107] Furthermore, by searching for virtual positioning data, the service system can obtain frame image information containing the back of the visitor, meeting the material requirements of the MV art short film service. Different material requirements can also be met by setting different virtual positioning data search conditions. For example, if the virtual positioning data is set to search for the visitor's face in the middle of the viewfinder, image materials showing the upper body can be obtained; if the virtual positioning data is set to search for the visitor's face in a predetermined area above the outside of the viewfinder, image materials showing only the feet and legs can be obtained.

[0108] Scenario Example 2

[0109] Figure 11 This is a schematic diagram of a logistics transfer station according to an embodiment of the present invention. As shown in the figure, the logistics transfer station is equipped with a material monitoring and handover service system in the cargo receiving and sending link, which can complete the seamless handover of materials between the transfer station tracking and monitoring system and the transport vehicle monitoring system, and realize the full monitoring and traceability of materials in the logistics process.

[0110] In the illustrated embodiment, the logistics transfer station and the transport vehicle each have a full-process monitoring system. The first tracking and positioning system of the two monitoring systems is deployed at the logistics transfer station and serves as the local tracking and positioning system for the material monitoring and handover service system. The second tracking and positioning system of the two monitoring systems is deployed at the transport vehicle and serves as the mobile tracking and positioning system for the material monitoring and handover service system. In this embodiment, cameras from a first camera cluster are installed at the material conveyor of the logistics transfer station and are configured as sampling cameras for the first tracking and positioning system. The first tracking and positioning system is configured to generate positioning data for the first camera cluster of the target. Cameras from a second camera cluster are installed in the cargo compartment of the transport vehicle and are configured as sampling cameras for the second tracking and positioning system. The second tracking and positioning system is configured to generate positioning data for the second camera cluster of the target. The second camera cluster is an external camera of the local monitoring system of the transfer station. Its attributes in the local monitoring system of the transfer station are local virtual cameras, not local physical cameras. The attributes of the second camera cluster in the monitoring system of the transport vehicle are the first camera cluster, and it is a local physical camera of the monitoring system of the transport vehicle.

[0111] It should be noted that the first tracking and positioning system and the second tracking and positioning system match the identification information by scanning the material barcode. The material barcode is generated by logistics workers manually scanning the material label with a handheld barcode scanner at the material handover location.

[0112] The local mapping model system needs to perform initialization modeling before monitoring the handover of materials and establish two-dimensional model data of the first camera cluster and the second camera cluster. The two-dimensional mapping data is the mapping model that performs overlapping analysis on the image information collected by the first camera cluster and the second camera cluster to construct the corresponding mapping relationship of each camera in the two-dimensional model. In this embodiment, the image information is overlapped and analyzed, and the partially overlapping areas in the image information are analyzed. As shown in the figure, most of the viewing areas of the two viewing cameras are covered by obstructions such as the cargo door, and only a small part of the two sets of image information overlap. During the initialization modeling process, the mapping model system of this embodiment must, on the one hand, avoid the influence of obstructions on the modeling process, and on the other hand, avoid the influence of different brightness of the camera viewing environments inside and outside the car on the modeling process.

[0113] The material monitoring and handover service system also has the following functions: extracting two-dimensional model data from the mapping model system to obtain a two-dimensional mapping relationship between the first camera cluster and the second camera cluster; extracting material location data generated by the first tracking and positioning system, combining this two-dimensional mapping relationship with computational processing to obtain the corresponding virtual location data of the material in the second camera cluster; receiving location data of the material in the second camera cluster generated by the second tracking and positioning system deployed on the transport vehicle, and verifying the consistency of the location data of the material in the second camera cluster with the virtual location data. If the consistency exceeds a predetermined threshold, the material handover process in the two monitoring systems is determined to be complete, and the material monitoring and handover system determines that the local tracking and positioning system and the mobile tracking and positioning system have passed the material handover verification. The two tracking and positioning systems mutually verify the material tracking thread, facilitating the simultaneous retrieval of material traceability.

[0114] Scenario Example 3

[0115] Figure 12 3 is a schematic diagram of a traffic monitoring area according to an embodiment of the present invention. As shown in the figure, the urban transportation department installs dense cameras in key traffic monitoring areas to achieve tracking monitoring of road vehicles.

[0116] In this embodiment, cameras are densely packed, with each vehicle simultaneously within the viewing areas of multiple cameras. When the service system initiates a tracking task thread for a particular vehicle, the service system samples tracking task images from one of the cameras whose viewing area contains the vehicle, according to a predetermined rule. The sampled camera is assigned to the first camera cluster, while the remaining cameras are assigned to the second camera cluster for the tracking task thread.

[0117] The service system analyzes the characteristics of the tracked target based on the collected images and can generate three types of target identifiers: vehicle color, vehicle type, and vehicle license plate. For example, by identifying the characteristics of the sampled image, the service system can simultaneously match the target identifiers "No. 002 Red Car," "No. 005 Sedan," and "License Plate 88888" to the target. The service system can use these three identifiers to retrieve the vehicle's monitoring records.

[0118] The mapping model system in the service system generates two-dimensional model data of all cameras through initialization modeling. The two-dimensional model data is constructed by the mapping model system through overlapping analysis of image information collected by each camera to construct the corresponding mapping relationship of each camera in the two-dimensional model.

[0119] The tracking and positioning system generates the tracking vehicle's location data within the first camera cluster, combined with the two-dimensional model data extracted from the mapping model system. Through computational processing, the tracked vehicle's corresponding virtual location data within the second camera cluster is obtained. Due to the dense density of cameras, the tracked vehicle's target is matched with virtual location data from multiple cameras simultaneously.

[0120] Once the tracked vehicle reaches the predetermined range of the sampling camera's viewing area, continuing to use that camera as the sampling camera for the tracking task thread will affect target tracking accuracy and may even result in loss of the tracked target. In response to the target tracking task's relay tracking request, the service system determines the optimal sampling camera in the second camera cluster based on the virtual positioning data, converts the camera's attributes to those of the first camera cluster, and uses it to take over the sampling of frame image information for the target tracking task, replacing the original sampling camera in the tracking task thread. This relay tracking ensures the continuity of the target tracking task.

[0121] In this embodiment, the service system's identification matching task is initiated every five seconds to reduce the possibility of target tracking errors leading to incorrect association and matching of the tracked target and target identification. When the identification verification task is initiated, the service system uses the virtual positioning data of the second camera cluster to determine which camera in the second camera cluster contains the target. The main operation then requests frame image information from the camera containing the target. The identification verification task analyzes the frame image information of the cameras containing the target in both the first and second camera clusters to generate target identification information, which is then matched to the tracked target, improving the accuracy of the tracking results.

[0122] Scenario Example 4

[0123] Figure 132 is a schematic diagram of a kindergarten according to an embodiment of the present invention. As shown in the figure, the kindergarten provides parents with a real-time video service for viewing children's activities from multiple perspectives. All public places in the kindergarten are equipped with chain image acquisition devices.

[0124] The distance between each camera in the chain image acquisition device is 0.2 meters. The mapping model system analyzes the overlapping areas of the image information collected by the existing cameras to construct the corresponding mapping relationship of each camera in the two-dimensional model.

[0125] In this embodiment, the service system identifies one of the 20 adjacent cameras in the chained image acquisition device as a sampling camera for the target tracking task. This sampling camera is then assigned to the first camera cluster, while the remaining cameras not assigned to the first camera cluster are assigned to the second camera cluster. In applications where cameras are densely deployed, if every camera were used for sampling and tracking, the system would be overburdened. Furthermore, oversampling for tracking and positioning tasks would result in a significant waste of system resources.

[0126] In this embodiment, the tracking and positioning system incorporates multiple target detection algorithms, including frame difference, background subtraction, expectation maximization, optical flow, statistical modeling, and level set methods, enabling real-time switching of target detection algorithms based on scenario requirements. The service system pre-stores facial features of the tracked object and performs identification verification on the tracked target at a predetermined frequency, achieving identity matching for the tracked target.

[0127] In an embodiment, after the virtual positioning system receives the positioning data of each identity identifier, it extracts the two-dimensional model data of the first camera cluster and the second camera cluster in the mapping model system, obtains the two-dimensional mapping relationship of all cameras, and obtains the corresponding virtual positioning data of each identity identifier in each camera in the second camera cluster through calculation and processing.

[0128] As shown in the figure, the service system receives a target query instruction generated by the child's parent through the user terminal operation, and in response to the target query instruction, matches the identity identifier of the query instruction (that is, matches the facial feature identifier of the child target that the parent needs to query). The service system determines the camera containing the target within the viewing range (that is, determines the camera containing the child to be queried within the viewing range) by retrieving the positioning data and virtual positioning data of the corresponding identity identifier. From the cluster of cameras containing the target within the viewing range, the preferred camera whose target is closest to the middle area of ​​the viewing range is selected as the viewing camera. Frame image information is extracted from the determined preferred viewing camera, converted into a video information stream and sent to the user terminal for display to the user.

[0129] As shown in the figure, the service system receives a display viewing angle switching instruction generated by the child's parent through the user terminal operation. The service system determines the camera containing the target within the framing range by retrieving the positioning data and virtual positioning data of the corresponding identity identifier, and switches the camera containing the target within the framing range as the framing camera according to the switching direction of the display viewing angle switching instruction; the frame image captured by the framing camera is converted into a video information stream and sent to the user terminal for display to the operator.

[0130] Scenario Example 5

[0131] Figure 14 The figure is a schematic diagram of a subway operating company according to an embodiment of the present invention. As shown, the subway operating company deploys a multi-perspective tracking camera surveillance and recording system. This system uses chained image acquisition devices with different viewing directions to simultaneously record multiple angles of a tracked target. The chained image acquisition device captures frame image information using different cameras, then samples clusters of these frames according to predetermined rules to generate video. This enables video surveillance recording of the camera following the target's movements. By deploying the chained image acquisition device, the subway operating company can initiate a continuous tracking camera surveillance and recording thread for each passenger entering a subway station. This can include the passenger's entire journey, from entering a first subway station, boarding a subway train to depart the first station, boarding a subway train, disembarking a subway train to enter a second station, and finally exiting the second station. Each tracking camera surveillance and recording thread corresponds to a single tracked target, and multiple tracking cameras can each correspond to multiple tracked targets. The number of activated recording threads is determined by the computing power of the service system. The dense deployment of multiple chain-type image acquisition devices can realize multi-angle tracking video recording of passengers entering the subway station. A tracking camera recording thread can contain images from multiple angles, and the corresponding system administrators can simultaneously view and query the tracking camera records of multiple angles of the tracked target in real time.

[0132] Because subway stations are public places, privacy laws in some regions prohibit the use of facial recognition technology on the public. In this embodiment, the identification verification device is installed at the subway station gate. The identification verification device is the subway ticket's RFID tag or the ticket's image code tag. Querying a target's tracking history through the service system can only be performed using the ticket's corresponding tag; it cannot use target features that involve personal privacy, including facial recognition, as an identifier.

[0133] The distance between each camera in the chain image acquisition device is 0.4 meters, and a low-frame-rate 1fps dynamic lens tracking video can be performed within the framing area. For example, target tracking is performed according to the frame-by-frame acquisition rules of the chain image acquisition device, and a follow-up video presentation effect can be generated in which the framing lens moves 0.4 meters per second.

[0134] The mapping model system uses an artificial intelligence system to analyze the image information captured simultaneously by all cameras in each chained image acquisition device, constructing a mapping relationship between all cameras in all chained image acquisition devices within the system and the corresponding 3D model. The mapping model system also includes a pre-installed dynamic model, which creates different 3D models corresponding to different conditions. The mapping relationship between camera clusters in subway stations and camera clusters in different subway trains, as well as the mapping relationship between camera clusters in subway trains and camera clusters in different subway stations, is determined after the prerequisites for subway trains to stop at subway stations are determined.

[0135] In an embodiment, chain image acquisition devices are densely distributed, and chain image acquisition devices in opposite viewing directions are relatively parallel distributed. The service system selects sampling cameras for target tracking tasks through artificial intelligence analysis. The attributes of the sampling cameras for target tracking tasks are configured as a first camera cluster, and other cameras not configured as the first camera cluster are configured as a second camera cluster. By selecting sampling cameras for target tasks through artificial intelligence analysis, it is possible to track and sample targets with a minimum number of cameras, reduce the amount of computation required by the system to perform target tracking tasks, and reduce system load. The tracking and positioning system uses a deep neural network to track and locate various targets in various locations and generate positioning data for each target.

[0136] In this embodiment, the virtual positioning system extracts dynamic model data from the first and second camera clusters in the mapping model system and updates the three-dimensional mapping relationship between all cameras under currently determined conditions after the subway train stops at the platform. The virtual positioning system obtains the positioning data of each target generated by the tracking and positioning system, combines it with the three-dimensional mapping relationship, and calculates and processes it to obtain the corresponding virtual positioning data for each target in each camera of the second camera cluster.

[0137] The service system determines the tracked target and the camera containing the target within the viewing range according to the positioning data of the first camera cluster and the virtual positioning data of the second camera cluster, corresponding to the target tracking task, and selects the best viewing camera in each image acquisition chain.

[0138] The service system obtains the frame image information of the best-viewing camera, converts it into a video information stream, and sends it to the storage system. The storage system stores the received video information stream for retrieval and query by service system administrators.

[0139] In a target tracking task, if the tracking target is lost or the target determination accuracy is lower than a threshold, the target tracking task starts to initiate an assisted positioning request. In response to the assisted positioning request, the service system determines that the camera in the second camera cluster that meets the predetermined conditions is a positioning calibration camera based on the virtual positioning data, obtains the frame image cache information of the positioning calibration camera, performs target tracking and positioning analysis based on the virtual positioning data and frame image cache information of the positioning calibration camera, and generates the positioning data of the target in the positioning calibration camera. The service system corrects the target positioning data based on the positioning data of the target in the positioning calibration camera to achieve target tracking recovery. Through assisted positioning, the problem of the existing technology that it is difficult to continue tracking when the tracking is lost due to factors such as occlusion during tracking, and the original tracking target is easily lost, can be solved. The assisted positioning request can also be a request plan task of the target tracking task. The target tracking task is configured with a plan to start the target tracking auxiliary request at a fixed time, dynamically extract the frame image information of different cameras, and improve the accuracy of the tracking results.

[0140] According to another aspect of the embodiments of the present invention, a virtual positioning device is provided. Figure 15 is a schematic diagram of a virtual positioning device according to an embodiment of the present invention. Figure 15 As shown, the virtual positioning device includes: an acquisition unit 1501, a sending unit 1503 and a virtual positioning unit 1505. The virtual positioning device is described below.

[0141] The acquisition unit 1501 is configured to acquire target positioning data of a target in a first camera cluster, wherein the first camera cluster is a camera used in a positioning system, and the positioning system is used to perform a target tracking task to generate positioning data.

[0142] The sending unit 1503 is used to send the target positioning data to the positioning system, wherein the positioning system uses the target mapping model and the target positioning data to generate virtual positioning data of the target in the second camera cluster. The target mapping model is used to describe the spatial mapping relationship between the first camera cluster and the second camera cluster.

[0143] The virtual positioning unit 1505 is used to virtually position the target according to the virtual positioning data.

[0144] It should be noted that the acquisition unit 1501, the sending unit 1503, and the virtual positioning unit 1505 correspond to steps S102 to S106 in Example 1. The examples and application scenarios implemented by the above units and the corresponding steps are the same, but are not limited to the contents disclosed in Example 1. It should be noted that the above units, as part of the apparatus, can be executed in a computer system, such as a set of computer-executable instructions.

[0145] As can be seen from the above, in the above embodiments of the present application, the acquisition unit can be used to acquire the target positioning data of the target in the first camera cluster, wherein the first camera cluster is a camera used in the positioning system, and the positioning system is used to perform target tracking tasks to generate positioning data; then the target positioning data is sent to the positioning system by the sending unit, wherein the positioning system uses the target mapping model and the target positioning data to generate virtual positioning data of the target in the second camera cluster, and the target mapping model is used to describe the spatial mapping relationship between the first camera cluster and the second camera cluster; and the virtual positioning unit is used to virtually position the target according to the virtual positioning data. The virtual positioning device provided by the embodiment of the present invention realizes the purpose of positioning the target through the collaborative use of the camera cluster, achieves the technical effect of improving the accuracy of positioning the target, and solves the technical problem in the related art that the application of image sensors is relatively single and it is impossible to use image sensors for large-scale collaborative tracking.

[0146] According to another aspect of an embodiment of the present invention, a virtual positioning device is also provided, including: an acquisition unit, used to acquire target positioning data of a target in a first camera cluster, wherein the first camera cluster is a camera used in a positioning system, and the positioning system is used to perform a target tracking task to generate positioning data; a sending unit, used to send the target positioning data to the positioning system, wherein the positioning system uses a target mapping model and the target positioning data to generate virtual positioning data of the target in a second camera cluster, and the target mapping model is used to describe the spatial mapping relationship between the first camera cluster and the second camera cluster; a virtual positioning unit, used to virtually position the target according to the virtual positioning data.

[0147] In an optional embodiment, the target mapping model is a mapping model obtained by the positioning system from a mapping model system, wherein the mapping model system generates a mapping model including the relationship between each camera position and viewing angle in a predetermined application scenario by initializing modeling.

[0148] In an optional embodiment, the virtual positioning device also includes: a verification unit, which is used to verify the virtual positioning data before virtually positioning the target based on the virtual positioning data; wherein the verification unit includes: a first acquisition module, which is used to obtain the actual positioning data of the target in the second camera cluster; a verification module, which is used to determine the similarity between the actual positioning data and the virtual positioning data using predetermined verification rules, so as to verify the consistency between the virtual positioning data and the actual positioning data.

[0149] In an optional embodiment, the virtual positioning device also includes: a first determination unit, used to respond to the relay tracking request signal and determine the best sampling camera in the second camera cluster based on the virtual positioning data; a setting unit, used to set the attributes of the best sampling camera to the first camera cluster to obtain an updated first camera cluster; an acquisition unit, used to obtain the image information stream collected by the updated first camera cluster; and a sending unit, used to send the image information stream to the positioning system, wherein the positioning system generates target positioning data of the target in the updated first camera cluster based on the image information stream.

[0150] In an optional embodiment, the first determination unit includes: a first determination module for determining the distribution density of cameras in a predetermined application scenario where the first camera cluster and the second camera cluster are located; a second determination module for determining that when the distribution density is less than a predetermined value, when the target is located at a predetermined position at the edge of the viewing area of ​​the first camera cluster, the relay tracking request signal is responded to; or, a third determination module for determining that when the distribution density is not less than a predetermined value, when the target leaves the middle position of the viewing area of ​​the first camera cluster, the relay tracking request signal is responded to.

[0151] In an optional embodiment, the first determining unit includes: a fourth determining module, configured to determine whether the positioning accuracy of the target is lower than a predetermined threshold; and a responding module, configured to respond to the relay tracking request signal.

[0152] In an optional embodiment, the virtual positioning device also includes: a second determination unit, used to determine at least one camera containing the target in the second camera cluster in response to an identification matching task after virtually positioning the target according to the virtual positioning data; an acquisition unit, used to acquire frame image information of at least one camera; and a first generation unit, used to identify feature identifiers in the frame image information and generate target identification information of the target based on the feature identifiers.

[0153] In an optional embodiment, the virtual positioning unit includes: a second acquisition module, used to respond to the target query instruction of the terminal device and obtain the target identification information of the target query instruction; a fifth determination module, used to determine the viewfinder camera based on the target identification information combined with the target positioning data and / or virtual positioning data; and a feedback module, used to feed back the video stream of the target captured by the viewfinder camera to the terminal device.

[0154] In an optional embodiment, the virtual positioning device also includes: a third determination unit, used to determine the positioning calibration camera in the second camera cluster according to the virtual positioning data in response to a tracking task request before virtually positioning the target according to the virtual positioning data; an acquisition unit, used to acquire the frame image cache information of the positioning calibration camera; a second generation unit, used to generate the calibration positioning data of the target in the positioning calibration camera based on the frame image cache information; and a correction unit, used to correct the target positioning data according to the calibration positioning data.

[0155] In an optional embodiment, the initiation condition of the tracking task request includes one of the following: target loss, target determination accuracy is lower than a predetermined threshold, and a predetermined plan for the target tracking task.

[0156] In an optional embodiment, the virtual positioning device also includes: a fourth determination unit, used to determine the viewfinder camera according to predetermined rules based on the target positioning data and / or virtual positioning data; and a sending unit, used to send the frame image information captured by the viewfinder camera to a predetermined storage medium.

[0157] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored computer program, wherein when the computer program is executed by a processor, the device where the computer storage medium is located is controlled to execute any of the above-mentioned virtual positioning methods.

[0158] According to another aspect of an embodiment of the present invention, a processor is further provided, and the processor is configured to run a computer program, wherein the computer program executes any one of the above-mentioned virtual positioning methods when running.

[0159] According to another aspect of an embodiment of the present invention, a virtual positioning system is provided. The virtual positioning system uses any one of the above virtual positioning methods.

[0160] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0161] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0162] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0163] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0164] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0165] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0166] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A virtual positioning method, characterized in that: include: Obtaining target positioning data of a target in a first camera cluster, wherein the first camera cluster is a camera used in a positioning system, and the positioning system is used to perform a target tracking task to generate positioning data; Sending the target positioning data to the positioning system, wherein the positioning system generates virtual positioning data of the target in the second camera cluster using a target mapping model and the target positioning data, wherein the target mapping model is used to describe a spatial mapping relationship between the first camera cluster and the second camera cluster; Performing virtual positioning of the target according to the virtual positioning data; In response to the relay tracking request signal, and based on the virtual positioning data, the best sampling camera in the second camera cluster is determined; the attributes of the best sampling camera are set to the first camera cluster to obtain an updated first camera cluster; the image information stream collected by the updated first camera cluster is obtained; the image information stream is sent to the positioning system, wherein the positioning system generates target positioning data of the target in the updated first camera cluster based on the image information stream.

2. The method according to claim 1, characterized in that The target mapping model is a mapping model obtained by the positioning system from a mapping model system, wherein the mapping model system generates a mapping model including the relationship between the position of each camera and the viewing angle in a predetermined application scene by initializing modeling.

3. The method according to claim 1, characterized in that Before virtually positioning the target according to the virtual positioning data, the method further includes: verifying the virtual positioning data; The step of verifying the virtual positioning data includes: Obtaining actual positioning data of the target in the second camera cluster; The similarity between the actual positioning data and the virtual positioning data is determined using a predetermined verification rule, so as to verify the consistency between the virtual positioning data and the actual positioning data.

4. The method according to claim 3, characterized in that Responding to the relay tracking request signal, comprising: Determining a distribution density of cameras in a predetermined application scenario where the first camera cluster and the second camera cluster are located; When it is determined that the distribution density is less than a predetermined value, and when the target is located at a predetermined edge position of the first camera cluster viewing area, responding to the relay tracking request signal; or, When it is determined that the distribution density is not less than a predetermined value, and when the target leaves the middle position of the first camera cluster viewing area, respond to the relay tracking request signal.

5. The method according to claim 4, characterized in that Responding to the relay tracking request signal, comprising: Determining that the positioning accuracy of the target is below a predetermined threshold; In response to the relay tracking request signal.

6. The method according to claim 1, characterized in that After virtually positioning the target according to the virtual positioning data, the method further includes: In response to the identification matching task, determining that the second camera cluster includes at least one camera of the target; Acquiring frame image information of the at least one camera; A feature identifier in the frame image information is identified, and target identification information of the target is generated based on the feature identifier.

7. The method according to claim 6, characterized in that Performing virtual positioning on the target according to the virtual positioning data includes: Responding to a target query instruction of a terminal device and obtaining target identification information of the target query instruction; Determining a framing camera based on the target identification information in combination with the target positioning data and / or the virtual positioning data; The video stream of the target captured by the viewfinder camera is fed back to the terminal device.

8. The method according to any one of claims 1 to 7, characterized in that Before virtually positioning the target according to the virtual positioning data, the method further includes: In response to a tracking task request, determining a positioning calibration camera in the second camera cluster according to the virtual positioning data; Obtaining frame image cache information of the positioning calibration camera; Generating calibration positioning data of the target in the positioning calibration camera based on the frame image cache information; The target positioning data is corrected based on the calibration positioning data.

9. The method according to claim 8, characterized in that The initiation condition of the tracking task request includes one of the following: the target is lost, the determination accuracy of the target is lower than a predetermined threshold, and the target tracking task is scheduled.

10. The method according to claim 8, characterized in that Also includes: Determining a framing camera according to a predetermined rule based on the target positioning data and / or the virtual positioning data; The frame image information collected by the viewfinder camera is sent to a predetermined storage medium.

11. A virtual positioning device, characterized in that: include: an acquiring unit, configured to acquire target positioning data of a target in a first camera cluster, wherein the first camera cluster is a camera used in a positioning system, and the positioning system is used to perform a target tracking task to generate positioning data; a sending unit, configured to send the target positioning data to the positioning system, wherein the positioning system generates virtual positioning data of the target in the second camera cluster using a target mapping model and the target positioning data, wherein the target mapping model is used to describe a spatial mapping relationship between the first camera cluster and the second camera cluster; a virtual positioning unit, configured to virtually position the target according to the virtual positioning data; a first determining unit, configured to respond to the relay tracking request signal and determine an optimal sampling camera in the second camera cluster according to the virtual positioning data; A setting unit, configured to set the attribute of the optimal sampling camera as the first camera cluster to obtain an updated first camera cluster; The acquisition unit is configured to acquire the updated image information stream collected by the first camera cluster; The sending unit is configured to send the image information stream to the positioning system, wherein the positioning system generates target positioning data of the target in the updated first camera cluster based on the image information stream.

12. The device according to claim 11, characterized in that The target mapping model is a mapping model obtained by the positioning system from a mapping model system, wherein the mapping model system generates a mapping model including the relationship between the position of each camera and the viewing angle in a predetermined application scene by initializing modeling.

13. The device according to claim 11, characterized in that Also includes: a verification unit, configured to verify the virtual positioning data before virtually positioning the target according to the virtual positioning data; Wherein, the verification unit includes: A first acquisition module is used to obtain actual positioning data of the target in the second camera cluster; The verification module is used to determine the similarity between the actual positioning data and the virtual positioning data using a predetermined verification rule, so as to verify the consistency between the virtual positioning data and the actual positioning data.

14. The device according to claim 11, characterized in that The first determining unit includes: A first determining module is configured to determine a distribution density of cameras in a predetermined application scenario where the first camera cluster and the second camera cluster are located; A second determining module is configured to respond to the relay tracking request signal when determining that the distribution density is less than a predetermined value and when the target is located at a predetermined edge position of the first camera cluster viewing area; or The third determining module is configured to respond to the relay tracking request signal when it is determined that the distribution density is not less than a predetermined value and when the target leaves a middle position of the first camera cluster viewing area.

15. The device according to claim 14, characterized in that The first determining unit includes: a fourth determining module, configured to determine whether the positioning accuracy of the target is lower than a predetermined threshold; A response module is used to respond to the relay tracking request signal.

16. The device according to claim 11, characterized in that Also includes: a second determining unit, configured to, after virtually positioning the target according to the virtual positioning data, determine, in response to an identification matching task, that at least one camera in the second camera cluster includes the target; The acquisition unit is configured to acquire frame image information of the at least one camera; The first generating unit is configured to identify a feature identifier in the frame image information and generate target identification information of the target based on the feature identifier.

17. The device according to claim 16, characterized in that The virtual positioning unit includes: A second acquisition module, configured to respond to a target query instruction of a terminal device and acquire target identification information of the target query instruction; A fifth determining module is configured to determine a framing camera based on the target identification information in combination with the target positioning data and / or the virtual positioning data; A feedback module is used to feed back the video stream of the target captured by the viewfinder camera to the terminal device.

18. The device according to any one of claims 11 to 17, characterized in that Also includes: a third determining unit, configured to determine, in response to a tracking task request, a positioning calibration camera in the second camera cluster according to the virtual positioning data before virtually positioning the target according to the virtual positioning data; The acquisition unit is used to acquire the frame image cache information of the positioning and calibration camera; A second generating unit is configured to generate calibration positioning data of the target on the positioning calibration camera based on the frame image cache information; A correction unit is used to correct the target positioning data according to the calibration positioning data.

19. The device according to claim 18, characterized in that The initiation condition of the tracking task request includes one of the following: the target is lost, the determination accuracy of the target is lower than a predetermined threshold, and the target tracking task is scheduled.

20. The device according to claim 18, characterized in that Also includes: a fourth determining unit, configured to determine a framing camera according to a predetermined rule based on the target positioning data and / or the virtual positioning data; The sending unit is used to send the frame image information collected by the viewfinder camera to a predetermined storage medium.

21. A virtual positioning system, characterized in that: Use the virtual positioning method described in any one of claims 1 to 10 above.

22. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed by a processor, the device where the computer storage medium is located is controlled to execute the virtual positioning method according to any one of claims 1 to 10.

23. A processor, characterized in that: The processor is configured to run a computer program, wherein the computer program executes the virtual positioning method according to any one of claims 1 to 10 when running.

Images