Target tracking method and device, target display method and device, equipment and storage medium

Abstract

The invention provides a target tracking method and device, a target display method and device, equipment and a storage medium, and relates to the technical field of positioning. The target tracking method comprises the following steps: determining a point cloud of a first target in a detection area, and obtaining a first track and a second track of the first target based on the point cloud of the first target; the first track is a track of the first target in a first state, and the second track is a track of the first target in a second state; in the process that the first target is in the second state and the second target moves in the set range where the first target is located, the first track is kept to move along with the second target, and the first track is updated; and updating the position of the first target in the detection area according to the updated first track and the second track so as to track the first target and the second target. According to the invention, the problem of low target positioning accuracy in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of positioning technology, and specifically, to a target tracking method, a target display method, an apparatus, a device and a storage medium. Background Art

[0002] Target tracking and positioning are indispensable requirements in many application scenarios. For example, in the field of IoT technology, smart home is gaining more and more attention as the population ages. The most serious harm is caused by the elderly falling and not being able to respond in time. Therefore, it is necessary to respond to the fall quickly and effectively, and to accurately determine the location of the elderly by tracking their trajectory.

[0003] However, in multi-target scenarios, the trajectories of the targets will affect each other and even intersect, which will cause interference in the target trajectory tracking process and lead to errors in the target positioning.

[0004] From the above, it can be seen that how to reduce the problem of low target positioning accuracy in related technologies still needs to be solved. Summary of the invention

[0005] The present application provides a target tracking method, a target display method, a device, an electronic device and a storage medium, which can solve the problem of low target positioning accuracy in the related art. The technical solution is as follows:

[0006] According to one aspect of the present application, a target tracking method includes: determining a point cloud of a first target in a detection area, and acquiring a first trajectory and a second trajectory of the first target based on the point cloud of the first target; the first trajectory is a trajectory of the first target in a first state, and the second trajectory is a trajectory of the first target in a second state; when the first target is in the second state and the second target moves within a set range of the first target, the first trajectory is maintained to follow the movement of the second target, and the first trajectory is updated; according to the updated first trajectory and the second trajectory, the position of the first target in the detection area is updated to track each of the first target and the second target.

[0007] According to one aspect of the present application, a target display method includes: displaying the position of a first target within a detection area in a monitoring page corresponding to the detection area; the position is updated based on a first trajectory and a second trajectory after the first target is updated; the first trajectory is updated by keeping the first trajectory following the second target when the first target is in the second state and the second target moves within a set range of the first target; the first trajectory is the trajectory of the first target in the first state, and the second trajectory is the trajectory of the first target in the second state; if the position is updated, the updated position is displayed in the monitoring page.

[0008] According to one aspect of the present application, a target tracking device includes: a trajectory creation module, which is used to determine a point cloud of a first target in a detection area, and obtain a first trajectory and a second trajectory of the first target based on the point cloud of the first target; the first trajectory is the trajectory of the first target in a first state, and the second trajectory is the trajectory of the first target in a second state; a trajectory update module, which is used to keep the first trajectory following the movement of the second target and update the first trajectory when the first target is in the second state and the second target moves within a set range of the first target; a position update module, which is used to update the position of the first target in the detection area according to the updated first trajectory and second trajectory, so as to track each of the first target and the second target.

[0009] In an exemplary embodiment, the trajectory creation module includes: a state detection unit, used to detect the state of the first target based on the point cloud of the first target; and a trajectory creation unit, used to create the first trajectory and / or the second trajectory for the first target according to the detected state of the first target.

[0010] In an exemplary embodiment, the first state includes a motion state; the state detection unit includes: a first state detection unit, which determines that the state of the first target is the motion state if the point cloud of the first target satisfies a first state condition; the first state condition includes at least one of the number of moving point clouds in the point cloud of the first target reaching a number threshold, the speed of the moving point cloud reaching a speed threshold, and the displacement of the moving point cloud being greater than a displacement threshold.

[0011] In an exemplary embodiment, the second state includes a static state; the state detection unit includes: a second state detection unit, used to determine that the state of the first target is the static state if the point cloud of the first target satisfies a second state condition; the second state condition includes at least one of the number of moving point clouds in the point cloud of the first target being less than a second number threshold, the speed of the moving point cloud being less than a speed threshold, and the displacement of the moving point cloud being less than a displacement threshold.

[0012] In an exemplary embodiment, the first trajectory includes a motion trajectory; the trajectory creation unit includes: a first trajectory creation unit, configured to create a motion trajectory corresponding to the motion state for the first target if it is detected that the state of the first target is a motion state.

[0013] In an exemplary embodiment, the second trajectory includes a stationary trajectory; the trajectory creation unit includes: a second trajectory creation unit, which is used to create a stationary trajectory corresponding to the stationary state for the first target if it is detected that the state of the first target is a stationary state, or the state of the first target is a stationary state and the second target appears within a set range of the first target.

[0014] In an exemplary embodiment, the trajectory update module includes: a trajectory update unit, which is used to establish a binding relationship between the motion trajectory of the first target and the motion trajectory of the second target when the second target moves within a set range of the first target; through the binding relationship, the motion trajectory of the first target is updated according to the position of the second target, so that the motion trajectory of the first target follows the motion trajectory of the second target.

[0015] In an exemplary embodiment, the position update module includes: a trajectory confidence calculation unit, used to calculate a first trajectory confidence of the first trajectory and a second trajectory confidence of the second trajectory in the process of the first trajectory following the movement of the second target; a position update unit, used to delete the second trajectory if the first trajectory confidence is greater than the second trajectory confidence, and update the position of the first target according to the first trajectory.

[0016] In an exemplary embodiment, the trajectory confidence calculation unit includes: a point cloud information acquisition unit, used to determine the first valid point cloud and the second valid point cloud based on the speed of each point cloud of the first target in the process of the first trajectory following the second target moving in the detection area; the first valid point cloud includes the moving point cloud associated with the first trajectory, and the second valid point cloud includes the stationary point cloud associated with the second trajectory; a first trajectory confidence calculation unit, used to calculate the first trajectory confidence of the first trajectory according to the number and / or signal strength of the first valid point cloud detected; a second trajectory confidence calculation unit, used to calculate the second trajectory confidence according to the number and / or signal strength of the second valid point cloud detected. According to one aspect of the present application, a target display device includes: a position display module, which is used to display the position of a first target within a detection area in a monitoring page corresponding to the detection area; the position is updated according to a first trajectory and a second trajectory after the first target is updated; the first trajectory is updated by keeping the first trajectory following the second target when the first target is in the second state and the second target moves within a set range of the first target; the first trajectory is the trajectory of the first target in the first state, and the second trajectory is the trajectory of the first target in the second state; if the position is updated, the updated position is displayed in the monitoring page.

[0017] In an exemplary embodiment, the position update module includes: a position display unit, used to display the position of the first target associated with the second trajectory in the monitoring page when the first trajectory follows the second target to move within the set range of the first target; a position update unit, used to delete the second trajectory if the first trajectory confidence of the first trajectory is greater than the second trajectory confidence of the second trajectory, and display the position of the first target associated with the first trajectory in the monitoring page.

[0018] According to one aspect of the present application, an electronic device includes at least one processor and at least one memory, wherein a computer program is stored in the memory; when the processor executes the computer program, the steps of the method described above are implemented.

[0019] According to one aspect of the present application, a computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0020] According to one aspect of the present application, a computer program product includes computer-readable instructions, the computer-readable instructions are stored in a storage medium, one or more processors of an electronic device read the computer-readable instructions from the storage medium, load and execute the computer-readable instructions, so that the electronic device implements the steps of the method as described above.

[0021] The beneficial effects of the technical solution provided by this application are:

[0022] In the above technical solution, based on the point cloud of the target in the detection area, a first trajectory of the first target in the first state and a second trajectory of the first target in the second state are obtained, and the first trajectory is made to move with the second target when the first target is in the second state and the second target moves within the set range of the first target, while the second trajectory remains stationary. Finally, the position of the first target is updated by tracking the first trajectory and the second trajectory, and the tracking of the first target is achieved. That is to say, no matter whether the first target enters motion from stillness or remains still, it is assumed that the first trajectory follows the movement of the second target and the original position of the second trajectory remains stationary, so that when the first target enters motion from stillness, the position of the first target can be updated by tracking the first trajectory, and when the first target remains stationary, the position of the first target can be updated by tracking the second trajectory, which effectively prevents the wrong positioning of the position of the first target due to the false movement of the first target following the second target, eliminates the interference of the second target to the stationary first target during the movement of the second target, and effectively solves the problem of low target positioning accuracy in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0024] Figure 1 It is a schematic diagram of the implementation environment involved in this application;

[0025] Figure 2 is a flow chart of a target tracking method according to an exemplary embodiment;

[0026] Figure 3 yes Figure 2 A schematic diagram of the position of the first target in the detection area in the corresponding embodiment;

[0027] Figure 4 yes Figure 2 A schematic diagram of a clustering algorithm for determining a position of a first target within a detection area in a corresponding embodiment;

[0028] Figure 5 yes Figure 2A flowchart of step 310 in one embodiment of the corresponding embodiment;

[0029] Figure 6 yes Figure 2 A flowchart of step 330 in one embodiment corresponding to the embodiment;

[0030] Figure 7 is a schematic diagram showing a first trajectory and a second trajectory of a second target moving within a set range of a first target according to an exemplary embodiment;

[0031] Figure 8 yes Figure 2 A flowchart of step 350 in one embodiment corresponding to the embodiment;

[0032] Fig. 9 yes Figure 8 A flowchart of an embodiment corresponding to step 351 in an embodiment;

[0033] Fig.10 is a flow chart showing a method for displaying a target according to an exemplary embodiment;

[0034] Fig.11 yes Fig.10 A schematic diagram of a monitoring page corresponding to a detection area in a corresponding embodiment;

[0035] Fig.12 yes Fig.10 A flowchart of step 430 in one embodiment corresponding to the embodiment;

[0036] Fig.13 is a flow chart of an application scenario according to an exemplary embodiment;

[0037] Fig.14 is a structural block diagram of a target tracking device according to an exemplary embodiment;

[0038] Fig.15 is a structural block diagram of a target display device according to an exemplary embodiment;

[0039] Fig.16 is a hardware structure diagram of an electronic device according to an exemplary embodiment;

[0040] Fig.17 The present invention is a structural block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0041] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0042] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0043] As mentioned above, in a multi-target scenario, the trajectories of the targets will affect each other and even intersect, which will cause interference in the target trajectory tracking process and lead to errors in the target positioning.

[0044] For example, in smart homes, millimeter-wave radars are usually used as sensors to detect the position of targets in the detection area, so as to track and locate the targets in the detection area. However, for millimeter-wave radars, not only is the detection signal for stationary targets relatively weak relative to moving targets, but people as targets have characteristics such as flexibility and multiple postures. Therefore, in a multi-person environment where there are both moving and stationary people, and these people may have close intersections, it is possible to mistakenly believe that the stationary people have moved, resulting in a false phenomenon that the stationary people follow the moving people, thereby affecting the accurate application of multi-target tracking in smart homes. For example, there is target A sitting or lying still in the sofa area, and when target B passes by target A, it is easy to create the illusion that target A moves with target B, resulting in incorrect positioning of target A, such as mislocating the position of target A from its original position to the position of target B, thereby causing a false report of no target in the sofa area.

[0045] In addition, the existing technology is mainly aimed at the positioning and trajectory tracking of moving targets, but does not reflect the close-range trajectory management of the dynamic and static relationships of multiple targets, especially the interference problem of moving targets on stationary targets cannot be solved.

[0046] It can be seen from the above that the related technology still has the problem of low target positioning accuracy.

[0047] To this end, the target tracking method provided by the present application can avoid the false phenomenon of a stationary target following the movement of a moving target, thereby effectively improving the accuracy of target positioning. Accordingly, the target tracking method is suitable for a target tracking device, which can be deployed in an electronic device. The electronic device can be an intelligent device with the ability to detect targets, for example, the intelligent device includes a human body sensor configured with a millimeter wave radar, etc.; the electronic device can be a computer device configured with a von Neumann architecture, for example, the computer device includes a desktop computer, a laptop computer, a server, etc.; the electronic device can also be an electronic device with a central control function, for example, the electronic device includes a gateway, etc.

[0048] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0049] Figure 1 Schematic diagram of an implementation environment involved in a target tracking method. The implementation environment at least includes a user terminal 110, a smart device 130, a server 170, and a network device. Figure 1 In the embodiment, the network devices include a gateway 150 and a router 190, which is not specifically limited herein.

[0050] Among them, the user terminal 110, which can also be considered as a user end or terminal, can deploy (also understood as install) the client associated with the smart device 130. This user terminal 110 can be an electronic device such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart control panel, other devices with display and control functions, etc., which are not limited here.

[0051] Among them, the client is associated with the smart device 130, which essentially means that the user registers an account in the client and configures the smart device 130 in the client. For example, the configuration includes adding a device identifier to the smart device 130, so that when the client is run in the user terminal 110, it can provide the user with functions such as device display and device control of the smart device 130. This client can be in the form of an application or a web page. Accordingly, the interface for device display on the client can be in the form of a program window or a web page, which is not limited here.

[0052] The smart device 130 is deployed in the gateway 150, and communicates with the gateway 150 through its own configured communication module, and is then controlled by the gateway 150. It should be understood that the smart device 130 generally refers to one of the multiple smart devices 130, and the embodiment of the present application only takes the smart device 130 as an example, that is, the embodiment of the present application does not limit the number and device type of smart devices deployed in the gateway 150. In an application scenario, the smart device 130 accesses the gateway 150 through a local area network, and is thus deployed in the gateway 150. The process of the smart device 130 accessing the gateway 150 through the local area network includes: the gateway 150 first establishes a local area network, and the smart device 130 joins the local area network established by the gateway 150 by connecting to the gateway 150. This local area network includes, but is not limited to: ZIGBEE or Bluetooth. Among them, the smart device 130 can be a smart printer, a smart fax machine, a smart camera, a smart air conditioner, a smart door lock, a smart light, or a human body sensor equipped with a communication module, a door and window sensor, a temperature and humidity sensor, a water immersion sensor, a natural gas alarm, a smoke alarm, a wall switch, a wall socket, a wireless switch, a wireless wall sticker switch, a magic cube controller, a curtain motor, a millimeter wave radar, etc.

[0053] The interaction between the user terminal 110 and the smart device 130 can be achieved through a local area network or a wide area network. In one application scenario, the user terminal 110 establishes a communication connection between the router 190 and the gateway 150 in a wired or wireless manner. For example, the wired or wireless manner includes but is not limited to WIFI, so that the user terminal 110 and the gateway 150 are deployed in the same local area network, so that the user terminal 110 can interact with the smart device 130 through the local area network path. In another application scenario, the user terminal 110 establishes a communication connection between the server 170 and the gateway 150 in a wired or wireless manner. For example, the wired or wireless manner includes but is not limited to 2G, 3G, 4G, 5G, WIFI, etc., so that the user terminal 110 and the gateway 150 are deployed in the same wide area network, so that the user terminal 110 can interact with the smart device 130 through the wide area network path.

[0054] The server end 170 may also be considered as a cloud, a cloud platform, a platform end, a service end, etc. The server end 170 may be a server, a server cluster consisting of multiple servers, or a cloud computing center consisting of multiple servers, so as to better provide background services to a large number of user terminals 110. For example, the background service includes a target tracking service.

[0055] In an application scenario, the position of the first target in the detection area is determined by the echo signal for the first target received in the detection area by the smart device 130, and a motion point cloud and a static point cloud of a first trajectory and a second trajectory associated with the first target are obtained, so as to facilitate the process of the first trajectory following the movement of the second target in the detection area. By updating the first trajectory associated with the motion point cloud of the first target and the second trajectory associated with the static point cloud of the first target, the position of the first target in the detection area is updated, and then the position of the first target in the detection area is displayed in the monitoring page of the corresponding detection area of ​​the user terminal 110.

[0056] Of course, in other application scenarios, the above-mentioned position update process of the first target in the detection area completed by the smart device 130 can also be implemented by the server 170 / gateway 150. At this time, the smart device 130 reports the position of the first target in the detection area to the server 170 / gateway 150 to facilitate the tracking of the first target. After the server 170 / gateway 150 updates the position of the first target, the updated position of the first target is sent to the user terminal 110 via the wide area network path / local area network path, so that the user terminal 110 can display it in the monitoring page of the corresponding detection area based on the position.

[0057] See also Figure 2 The present application provides a target tracking method, which is applicable to an electronic device, which may be Figure 1 A smart device 130 is shown in an implementation environment.

[0058] In the following method embodiments, for ease of description, the execution subject of each step of the method is taken as an electronic device as an example for illustration, but this does not constitute a specific limitation.

[0059] like Figure 2 As shown, the method may include the following steps:

[0060] Step 310 , determining a point cloud of the first target within the detection area, and acquiring a first trajectory and a second trajectory of the first target based on the point cloud of the first target.

[0061] The first target refers to any object that can be tracked in the detection area, for example, the object can be a person, a pet, a robot, etc. The position of the first target in the detection area is obtained by positioning the first target in the detection area by the detection device. It should be noted that the detection device includes but is not limited to any type of sensor, and the detection device can be deployed in an environment where the first target may appear. Accordingly, the detection area refers to the area range where the detection device can effectively detect the first target.

[0062] Take the detection device as an example, which is a human body sensor equipped with a millimeter wave radar. The millimeter wave radar is equipped with an antenna array, which includes a transmitting antenna and a receiving antenna. When the human body sensor locates the first target in the detection area, it will transmit a millimeter wave signal (also considered as a sensing signal) to the first target through the transmitting antenna, and receive the echo signal (also considered as a reflection signal) formed by the millimeter wave signal reflected by the first target through the receiving antenna. After performing relevant processing on the received echo signal, the point cloud of the first target in the detection area can be determined. Here, the detection area refers to the area where the transmitting antenna of the millimeter wave radar can effectively transmit millimeter wave signals.

[0063] In this embodiment, the echo signal processing process may include the following steps:

[0064] S1. Determine the time domain signal S based on the mathematical model X=AS+N corresponding to the echo signal.

[0065] Among them, the time domain signal S is a signal related to distance, speed, and angle, expressed as f(R,v,θ).

[0066] S2. Perform fast Fourier transform (FFT) on the time domain signal S to obtain the frequency domain signal S', expressed as F(R,v,θ).

[0067] S3. Use the formula P(R,v,θ)=|F(R,v,θ)| to solve the power spectrum of the frequency domain signal S' and obtain a power spectrum signal, which is expressed as P(R,v,θ).

[0068] S4. The peak value of the power spectrum signal is taken as the movement data of the target, expressed as (R, v, θ).

[0069] Among them, R represents distance, v represents speed, and θ represents angle.

[0070] Among them, the movement data is the position of the first target in the detection area represented by the polar coordinate system. In order to more accurately and effectively describe the position of the target in the detection area, the above movement data is converted into a rectangular coordinate system to obtain a point cloud (X, Y) of the first target in the detection area, wherein X=Rsin(θ), Y=Rcos(θ).

[0071] Since the first target has a certain height and width, the point cloud obtained based on the processing of the echo signal is massive. Therefore, after the above processing, all the point clouds of the first target in the detection area can be obtained, such as Figure 3 As shown, point clouds 301, 302, and 303 in the dotted circular area represent all point clouds of target A within the detection area.

[0072] After determining all point clouds of the first target in the detection area, the electronic device can obtain the first trajectory and the second trajectory based on the point cloud of the first target. The first trajectory refers to the trajectory of the first target in the first state, and the second trajectory refers to the trajectory of the second target in the second state. It can also be considered that the first trajectory corresponds to the first state of the first target, and the second trajectory corresponds to the second state of the first target.

[0073] In a possible implementation, the first state and the second state are detected based on the point cloud of the first target. The first state is a moving state, and the second state is a stationary state, that is, the first state refers to the state when the first target is moving, and the second state refers to the state when the first target is stationary. Accordingly, the first trajectory can be understood as the trajectory formed when the first target is moving, and the second trajectory can be understood as the trajectory formed when the first target is stationary.

[0074] Step 330: When the first target is in the second state and the second target moves within a set range where the first target is located, the first trajectory is kept to follow the second target and the first trajectory is updated.

[0075] The second target refers to an object that can be tracked and moves within the detection area, for example, the object may be a person, a pet, a robot, etc.

[0076] As mentioned above, the inventors have found that when there are both moving targets and stationary targets in the detection area, and these targets may intersect at close range, the moving target may interfere with the stationary target, that is, a false phenomenon occurs in which the stationary target follows the moving target, thereby causing the position of the moving target to be incorrectly positioned. Based on this, in order to eliminate the interference of the second target on the first target, thereby avoiding the position of the first target to be incorrectly positioned, in this embodiment, when the first target is in the second state and the second target moves within the set range of the first target, the first track is kept moving with the second target, and the original position of the second track remains stationary.

[0077] The setting range can be flexibly set according to the actual needs of the application scenario. For example, in an application scenario with high tracking accuracy requirements, a larger setting range is set, for example, the setting range is 1 meter, which is not limited here.

[0078] Step 350: Update the position of the first target in the detection area according to the updated first trajectory and the second trajectory to track the first target and the second target.

[0079] As the first trajectory follows the second target to move, while the second trajectory remains stationary at its original position, then, regardless of whether the first target enters motion from being stationary or remains stationary, when the first target enters motion from being stationary, the position of the first target in the detection area can be updated by tracking the first trajectory, and when the first target remains stationary, the position of the first target in the detection area can be updated by tracking the second trajectory, thereby completing the tracking of the first target.

[0080] It should be noted that the first trajectory or the second trajectory is formed by different positions of the first target in the detection area. In other words, the first trajectory or the second trajectory reflects the different positions of the first target in the detection area. Then, by updating the first trajectory and the second trajectory, the updated position of the first target in the detection area can be obtained, and the position is obtained by clustering all the point clouds of the first target. Taking the DBSCAN (Density-Based SpatialClustering of Applications with Noise) clustering algorithm as an example, by scanning all the point clouds of the first target, if the number of point clouds within the radius R of a certain point cloud P is ≧MinPoints (core points), the point cloud P is included in the core point list, and a temporary clustering cluster with point cloud P as the core point is created. For each temporary cluster, check whether the point in it is a core point. If so, merge the temporary cluster corresponding to the point cloud with the current temporary cluster to obtain a new temporary cluster. Repeat the above operation until each point cloud in the current temporary cluster is either not in the core point list or the points directly reached by its density are already in the temporary cluster, and the temporary cluster is upgraded to a cluster. Iterate all temporary clusters and perform the same merging operation until all temporary clusters are processed.

[0081] like Figure 4 As shown in the figure, for example, MinPoints is set to 4, and through iteration, it is found that point cloud A meets the requirements for creating core point P. At the same time, it is found that point cloud B and point cloud C also meet the requirements, but point cloud B and point cloud C are at the boundary of the entire cluster, so Figure 4 The middle point cloud A is the core point of all point clouds, that is, the 6 dark points near A, that is, point cloud A is considered to represent the position of the first target in the detection area.

[0082] Through the above process, a multi-trajectory hypothesis tracking scheme for the first target is realized. In a close-range tracking environment of multiple targets with dynamic and static relationships, it can effectively prevent the wrong positioning of the first target caused by the false movement of the first target following the second target, eliminate the interference of the second target's movement to the stationary first target, and effectively solve the problem of low target positioning accuracy in related technologies.

[0083] See also Figure 5 In an exemplary embodiment, step 310 may include the following steps:

[0084] Step 311 , detecting the state of the first target based on the point cloud of the first target.

[0085] The state of the first target includes a first state and a second state. In a possible implementation, the first state is a moving state, and the second state is a stationary state, that is, the first state refers to a state when the first target is moving, and the second state refers to a state when the first target is stationary.

[0086] It can be understood that if the first target and the second target are always in the first state, there will be no false movement of the first target following the second target. However, when the first target is a stationary target and the second target is a moving target, it is possible that the second target will interfere with the first target when moving around the first target, resulting in an error in the positioning of the first target. For this reason, before tracking the first trajectory and the second trajectory, the state of the first target will be detected to determine whether the state of the first target has entered the second state before continuing the subsequent trajectory tracking, thereby avoiding unnecessary waste of hardware resources and improving the efficiency of target positioning.

[0087] In a possible implementation manner, the state of the first target is related to a moving point cloud and a stationary point cloud of the first target.

[0088] First of all, it should be noted that a moving point cloud refers to a point cloud whose speed exceeds a preset point cloud speed, and correspondingly, a stationary point cloud refers to a point cloud whose speed is less than a preset point cloud speed. In other words, according to the speeds of all point clouds of the first target, the moving point cloud and the stationary point cloud can be determined in all point clouds of the first target.

[0089] Assuming that the preset point cloud speed is 0.3m / s, when the speed of the point cloud in all the point clouds of the first target is 0.2m / s, the point cloud is determined to be a stationary point cloud; when the speed of the point cloud in all the point clouds of the first target is 0.4m / s, the point cloud is determined to be a moving point cloud.

[0090] Please refer to Figure 3 , Figure 3 A schematic diagram of all point clouds of target A is shown. Figure 3 In FIG. 3 , for all point clouds of target A, 301 represents the position of target A in the detection area, 302 represents the moving point cloud of target A, 303 represents the stationary point cloud of target A; 304 represents the position of target B in the detection area; 305 represents the position of target C in the detection area.

[0091] After determining the moving point cloud and the stationary point cloud in all point clouds of the first target, the state detection of the first target can be performed.

[0092] In one of the embodiments, if the point cloud of the first target satisfies the first state condition, the state of the first target is determined to be the first state.

[0093] Specifically, the first state condition includes at least one of the number of moving point clouds in the point cloud of the first target reaching a number threshold, the speed of the moving point cloud reaching a speed threshold, and the displacement of the moving point cloud being greater than a displacement threshold.

[0094] For example, the first quantity threshold may be set to 10, and if the number of motion point clouds of the first target obtained by statistics is 15, it is determined that the state of the first target is the first state.

[0095] In one of the embodiments, if the point cloud of the first target satisfies the second state condition, the state of the first target is determined to be the second state.

[0096] Specifically, the second state condition includes at least one of the number of moving point clouds in the point cloud of the first target being less than a second number threshold, the speed of the moving point cloud being less than a speed threshold, and the displacement of the moving point cloud being less than a displacement threshold.

[0097] For example, the second quantity threshold can be set to 5. If the number of motion point clouds of the first target obtained by statistics is 3, the state of the first target is determined to be the second state. Or, the displacement threshold is set to 0.3m. If the displacement of the motion point cloud of the first target is 0.1m, the state of the first target is determined to be the second state.

[0098] Step 313: Create a first track and / or a second track for the first target according to the detected state of the first target.

[0099] The state of the first target includes a first state and a second state, the first state includes a motion state, and the second state includes a static state. Accordingly, the first trajectory includes a motion trajectory corresponding to the motion state, and the second trajectory includes a static trajectory corresponding to the static state.

[0100] In one of the embodiments, if it is detected that the state of the first target is a motion state, a motion track corresponding to the motion state is created for the first target.

[0101] In another embodiment, if it is detected that the state of the first target is a stationary state, or the state of the first target is a stationary state and the second target appears within a set range of the first target, a stationary track corresponding to the stationary state is created for the first target.

[0102] That is to say, when the first target enters the first state, it is deemed that the first trajectory creation condition is met, and the first trajectory in the first state can be created for the first target; when the first target enters the second state, it is deemed that the second trajectory creation condition is met, and the second trajectory in the second state can be created for the first target. In addition, satisfying the second trajectory creation condition can also be based on the first target entering the second state, requiring the second target to move within the set range of the first target, that is, in the detection area, there are not only moving targets and stationary targets, but also the moving targets may interfere with the stationary targets, and only then can the first trajectory in the second state be created for the first target. It is explained here that the first target entering the second state can be entering the second state from the first state, or it can keep the second state unchanged.

[0103] Through the above process, before tracking the first trajectory and the second trajectory, the state of the first target is detected to determine the state of the first target before continuing the subsequent trajectory tracking, thereby avoiding unnecessary waste of hardware resources and improving the efficiency of target positioning.

[0104] See also Figure 6 In an exemplary embodiment, step 330 may include the following steps:

[0105] Step 331 , when the second target moves within a set range of the first target, a binding relationship is established between the motion trajectory of the first target and the motion trajectory of the second target.

[0106] As mentioned above, if the first target and the second target are always in the first state, the phenomenon of the first target following the false movement of the second target will not occur. However, when the first target is in the second state and the second target moves within the set range of the first target, the phenomenon of the first target following the false movement of the second target may occur. Based on this, in this embodiment, in order to prevent the phenomenon of the first target following the false movement of the second target, it is first assumed that the first target will follow the second target to move, that is, a binding relationship is established between the first trajectory and the movement trajectory of the second target.

[0107] Step 333: Update the motion trajectory of the first target according to the position of the second target through the binding relationship, so that the motion trajectory of the first target follows the motion trajectory of the second target.

[0108] After binding the first trajectory and the motion trajectory of the second target, it is assumed that the first target will follow the movement of the second target. At the same time, the inventor also realized that it is possible that the first target in a stationary state may not follow the movement of the second target, that is, the first target remains stationary at the original position. Based on this, in this embodiment, it is also assumed that the first target does not follow the movement of the second target but remains stationary at the original position, that is, the second trajectory of the first target in the second state remains stationary.

[0109] Figure 7 FIG. 4 is a schematic diagram showing the first trajectory and the second trajectory of the second target during the movement of the second target within the set range of the first target, as shown in FIG. Figure 7 As shown, the second target B moves from position b' through the first target A to position b" in the detection area to form a motion trajectory B1. During the above movement of the second target B, it is assumed that the first trajectory A1 of the first target A follows the second target B to move, and it is assumed that the second trajectory A2 of the first target A keeps the original position a' of the first target A stationary. By tracking the first trajectory and the second trajectory, the first trajectory A1 is formed from position a' to position a", and the second trajectory A2 is formed from position a', thereby obtaining the updated first trajectory A1 and second trajectory A2 of the first target A.

[0110] Thus, the multi-trajectory hypothesis tracking of the first target is completed, that is, the first target is assumed to enter motion from static state through the following motion of the first trajectory, and the first target is assumed to remain static through the original position static state of the second trajectory, so as to avoid the positioning error of the first target. After a period of time, the real trajectory of the first target can be determined by updating the first trajectory and the second trajectory.

[0111] In an exemplary embodiment, if Figure 8 As shown, step 350 may include the following steps:

[0112] Step 351 , in the process of the first trajectory following the movement of the second target, a first trajectory confidence of the first trajectory and a second trajectory confidence of the second trajectory are calculated.

[0113] Among them, the first trajectory confidence refers to the confidence of the first trajectory, which can also be considered as the probability that the first trajectory is the true trajectory of the first target; the second trajectory confidence refers to the confidence of the second trajectory, that is, the probability that the second trajectory is the true trajectory of the first target. It can be understood that the higher the confidence, the greater the probability that the corresponding trajectory is the true trajectory of the first target, that is, the higher the authenticity, in other words, the greater the probability that the assumption of whether the first target is following the movement or staying still is established.

[0114] Specifically, Fig. 9 As shown, step 351 may include the following steps:

[0115] Step 3511 , in the process of the first trajectory following the second target moving in the detection area, determine a first valid point cloud and a second valid point cloud based on the speed of each point cloud of the first target.

[0116] The first valid point cloud refers to the moving point cloud associated with the first trajectory, and the second valid point cloud refers to the stationary point cloud associated with the second trajectory.

[0117] When the second target moves in the detection area, the echo signal received by the millimeter wave radar is processed frame by frame to obtain all point clouds of the first trajectory and the second trajectory, and the moving point cloud associated with the first trajectory and the stationary point cloud associated with the second trajectory are obtained.

[0118] At the same time, the number of valid point clouds and signal strength of the first target and the second target are obtained based on the processing of the echo signal received by the millimeter wave radar.

[0119] Step 3513: Calculate the first trajectory confidence of the first trajectory according to the number and / or signal strength of the detected first valid point cloud.

[0120] Based on the point cloud data obtained by processing the echo signal received by the millimeter-wave radar, if the number of first valid point clouds in the current frame is greater than the threshold T1 and the sum of the signal strengths of the first valid point clouds is greater than the threshold T2, the confidence of the first trajectory associated with the first trajectory is increased by 1, otherwise the confidence of the first trajectory is reduced by 1.

[0121] Step 3515: Calculate the second trajectory confidence of the second trajectory according to the number and / or signal strength of the detected second valid point clouds.

[0122] Based on the point cloud data obtained by processing the echo signal received by the millimeter-wave radar, if the number of second valid point clouds in the current frame is greater than the threshold T1 and the sum of the signal strengths of the second valid point clouds is greater than the threshold T2, the second trajectory confidence associated with the second trajectory is increased by 1, otherwise the second trajectory confidence is reduced by 1.

[0123] If the confidence of the first trajectory is greater than the confidence of the second trajectory, it means that the first trajectory is true and the position of the first target associated with the first trajectory is more accurate, then step 353 is executed.

[0124] On the contrary, if the confidence of the second trajectory is greater than the confidence of the first trajectory, it means that the second trajectory is true and the target position associated with the second trajectory is more accurate, then step 355 is executed.

[0125] Step 353: If the confidence of the first trajectory is greater than the confidence of the second trajectory, the second trajectory is deleted, and the position of the first target is updated according to the first trajectory.

[0126] When the confidence of the first trajectory is greater than the confidence of the second trajectory, it indicates that the first trajectory is the true trajectory of the first target. At this time, it can be determined that the first target actually moves following the second target. Accordingly, the position of the first target in the detection area is determined by the first trajectory.

[0127] Step 355: If the confidence of the first trajectory is not greater than the confidence of the second trajectory, the first trajectory is deleted, and the position of the first target is updated according to the second trajectory.

[0128] When the confidence of the first trajectory is not greater than the confidence of the second trajectory, it indicates that the second trajectory is the true trajectory of the first target. At this time, it can be determined that the first target remains stationary at the original position. Accordingly, the position of the first target in the detection area is determined by the second trajectory.

[0129] Please refer to Figure 7 When the confidence of the first trajectory is greater than the confidence of the second trajectory, the position of the first target updated according to the first trajectory is a'; when the confidence of the first trajectory is not greater than the confidence of the second trajectory, the position of the first target updated according to the second trajectory is a'.

[0130] Through the above process, a multi-trajectory hypothesis tracking scheme for the first target is realized. During the movement of the second target in the detection area of ​​the second target, the different trajectories associated with the moving point cloud and the stationary point cloud of the first target are tracked, and the trajectory confidence is compared based on the tracked trajectory to obtain the trajectory actually corresponding to the first target, thereby updating the position of the first target based on the trajectory actually corresponding to the first target. In a close-range tracking environment of multiple targets with dynamic and static relationships, it is possible to effectively prevent the wrong positioning of the position of the first target due to the false movement of the first target following the second target, eliminate the interference of the second target to the stationary first target during its movement, and effectively solve the problem of low target positioning accuracy in related technologies.

[0131] See also Fig.10 The present application embodiment provides a target display method, which is applicable to an electronic device, which may be Figure 1 A user terminal 110 is shown in an implementation environment.

[0132] In the following method embodiments, for ease of description, the execution subject of each step of the method is taken as an electronic device as an example for illustration, but this does not constitute a specific limitation.

[0133] like Fig.10 As shown, the method may include the following steps:

[0134] Step 410: Display the position of the first target in the detection area in the monitoring page corresponding to the detection area.

[0135] Among them, the monitoring page can be Figure 1A specific display page in the user terminal 110 in the implementation environment is shown, and the display page is obtained by monitoring the area where the first target is located. The position of the first target in the detection area is updated according to the first trajectory and the second trajectory after the first target is updated. The first trajectory is updated by keeping the first trajectory following the second target when the first target is in the second state and the second target moves within the set range of the first target; the first trajectory is the trajectory of the first target in the first state, and the second trajectory is the trajectory of the first target in the second state.

[0136] Fig.11 A schematic diagram of the monitoring page corresponding to the detection area is shown. Fig.11 In the example, after clustering all point clouds of the first target, the user terminal 110 can display the position of the first target in the detection area as 101 in the monitoring page 401 corresponding to the detection area.

[0137] Step 430: If the location is updated, the updated location is displayed on the monitoring page.

[0138] Continue reading Fig.11 As shown, based on the update performed on the first track and / or the second track, the monitoring page 401 displays the updated position of the first target in the detection area based on the first track and / or the second track as 102 .

[0139] Specifically, if Fig.12 As shown, step 430 may include the following steps:

[0140] Step 431 , when the first track follows the second target to move within a set range of the first target, the position of the first target associated with the second track is displayed on the monitoring page.

[0141] Step 433: If the first track confidence of the first track is greater than the second track confidence of the second track, the second track is deleted, and the position of the first target associated with the first track is displayed on the monitoring page.

[0142] In this embodiment, for the user terminal, during the movement of the second target in the detection area, a surface layer (i.e., a display layer) and a hidden layer are established for the first target respectively. The surface layer is used to show the user the original position of the first target in the detection area, i.e., the position associated with the second trajectory; and the hidden layer is used to describe the first trajectory that follows the movement of the second target in the detection area.

[0143] When the first trajectory confidence of the first trajectory is greater than the second trajectory confidence of the second trajectory, the hidden layer is converted to a new surface layer, and the updated position of the first target following the movement of the second target, that is, the position associated with the first trajectory, is displayed to the user through the new surface layer. At this time, the original surface layer is converted to a new hidden layer, and the second trajectory described by the new hidden layer is deleted, so as to start a new round of positioning for the position of the first target later.

[0144] Of course, in other embodiments, it is not limited to displaying the position of the first target on the monitoring page. The second trajectory associated with the stationary point cloud can also be displayed on the monitoring page, or the first trajectory and the second trajectory can be displayed in different ways on the monitoring page when the first trajectory follows the movement of the second target. As the position is updated, only the trajectory with high confidence and the updated position of the first target in the detection area are displayed. There is no specific limitation on the display method here.

[0145] Through the above process, a display method of establishing a surface layer and a hidden layer for the first target is introduced, and the position of the first target is displayed in real time, which can better help users locate the first target in the detection area. For example, in a smart home, when an emergency occurs to the elderly, accurate rescue work can be carried out in time to reduce the damage caused to the elderly by the failure to respond in time.

[0146] See also Fig.13 , shows a schematic diagram of a specific implementation of a target tracking method in an application scenario. In the application scenario, the device for determining the point cloud of the first target in the detection area is a human body sensor equipped with a millimeter wave radar, and at the same time, the human body sensor is also used to provide target tracking according to the point cloud of the first target.

[0147] Through step 501, the human body sensor acquires point cloud data of the first target in the detection area, and then distinguishes between moving point cloud data and stationary point cloud data based on the acquired point cloud data.

[0148] After determining the moving point cloud and the stationary point cloud of the first target through step 502, the valid point cloud of the first target is determined in the process of the first trajectory following the movement of the second target in the detection area. The valid point cloud of the first target includes the valid moving point cloud and the valid stationary point cloud.

[0149] After the valid moving point cloud and the valid stationary point cloud of the first target are determined through step 503 , a first track associated with the valid moving point cloud and a second track associated with the valid stationary point cloud can be created according to the number and signal strength of the valid point clouds.

[0150] In step 504 , the confidence of the first track and the second track is calculated according to the number and signal strength of the valid point clouds, that is, it is determined whether the number of valid point clouds is greater than the threshold T1 and whether the sum of the point cloud signal strengths is greater than the threshold T2.

[0151] If yes, the confidence of the first track and the confidence of the second track are increased by 1.

[0152] Otherwise, the confidence of the first track and the confidence of the second track are reduced by 1.

[0153] In step 505, the confidence of the first trajectory and the confidence of the second trajectory after the accumulation period are statistically compared, that is, it is determined whether the confidence of the first trajectory is greater than the confidence of the second trajectory.

[0154] If yes, the second track is deleted and the first track is displayed.

[0155] Otherwise, the first track is deleted.

[0156] In this application scenario, the first target is distinguished according to the point cloud in the detection area, and the confidence comparison is performed after the trajectory associated with the threshold is bound, so as to ensure the authenticity of the trajectory of the first target following the second target in the detection area. It can effectively prevent the wrong positioning of the first target due to the false movement of the first target following the second target, eliminate the interference of the second target to the stationary first target during the movement of the second target, and effectively solve the problem of low target positioning accuracy in related technologies.

[0157] It should be understood that although Figure 2 , 5 The steps in the flowcharts of , 6, 8-10, 12-13 are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 , 5 , 6, 8-10, 12-13, at least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0158] The following is an embodiment of the device of the present application, which can be used to execute the target tracking method involved in the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the method embodiment of the target tracking method involved in the present application.

[0159] See also Fig.14 In an embodiment of the present application, a target tracking device 500 is provided, including but not limited to: a trajectory creation module 510, a trajectory update module 530, and a position update module 550.

[0160] Among them, the trajectory creation module 510 is used to determine the point cloud of the first target in the detection area, and obtain the first trajectory and the second trajectory of the first target based on the point cloud of the first target; the first trajectory is the trajectory of the first target in the first state, and the second trajectory is the trajectory of the first target in the second state.

[0161] The trajectory updating module 530 is used to keep the first trajectory following the second target in movement and update the first trajectory when the first target is in the second state and the second target moves within the set range of the first target.

[0162] The position updating module 550 is used to update the position of the first target in the detection area according to the updated first trajectory and the second trajectory, so as to track the first target.

[0163] In an exemplary embodiment, the trajectory creation module includes: a state detection unit, which is used to detect the state of the first target based on the point cloud of the first target; and a trajectory creation unit, which is used to create a first trajectory and / or a second trajectory for the first target according to the detected state of the first target.

[0164] In an exemplary embodiment, the first state includes a motion state; the state detection unit includes: a first state detection unit, which determines that the state of the first target is the motion state if the point cloud of the first target satisfies a first state condition; the first state condition includes at least one of the number of moving point clouds in the point cloud of the first target reaching a number threshold, the speed of the moving point cloud reaching a speed threshold, and the displacement of the moving point cloud being greater than a displacement threshold.

[0165] In an exemplary embodiment, the second state includes a static state; the state detection unit includes: a second state detection unit, used to determine that the state of the first target is the static state if the point cloud of the first target satisfies a second state condition; the second state condition includes at least one of the number of moving point clouds in the point cloud of the first target being less than a second number threshold, the speed of the moving point cloud being less than a speed threshold, and the displacement of the moving point cloud being less than a displacement threshold.

[0166] In an exemplary embodiment, the first trajectory includes a motion trajectory; the trajectory creation unit includes: a first trajectory creation unit, configured to create a motion trajectory corresponding to the motion state for the first target if it is detected that the state of the first target is a motion state.

[0167] In an exemplary embodiment, the second trajectory includes a stationary trajectory; the trajectory creation unit includes: a second trajectory creation unit, which is used to create a stationary trajectory corresponding to the stationary state for the first target if it is detected that the state of the first target is a stationary state, or the state of the first target is a stationary state and the second target appears within a set range of the first target.

[0168] In an exemplary embodiment, the trajectory update module includes: a trajectory update unit, which is used to establish a binding relationship between the motion trajectory of the first target and the motion trajectory of the second target during the process of the second target moving within the set range of the first target; through the binding relationship, the motion trajectory of the first target is updated according to the position of the second target, so that the motion trajectory of the first target follows the motion trajectory of the second target.

[0169] In an exemplary embodiment, the position update module includes: a trajectory confidence calculation unit, which is used to calculate a first trajectory confidence of the first trajectory and a second trajectory confidence of the second trajectory when the first trajectory follows the movement of the second target; a position update unit, which is used to delete the second trajectory if the first trajectory confidence is greater than the second trajectory confidence, and update the position of the first target according to the first trajectory; otherwise, delete the first trajectory and update the position of the first target according to the second trajectory.

[0170] In an exemplary embodiment, the trajectory confidence calculation unit includes: a point cloud information acquisition unit, used to determine the first valid point cloud and the second valid point cloud based on the speed of each point cloud of the first target in the process of the first trajectory following the second target moving in the detection area; the first valid point cloud includes the moving point cloud associated with the first trajectory, and the second valid point cloud includes the stationary point cloud associated with the second trajectory; a first trajectory confidence calculation unit, used to calculate the first trajectory confidence of the first trajectory according to the number and / or signal strength of the first valid point cloud detected; a second trajectory confidence calculation unit, used to calculate the second trajectory confidence according to the number and / or signal strength of the second valid point cloud detected.

[0171] See also Fig.15 In an embodiment of the present application, a target display device 600 is provided, including but not limited to: a position display module 610 and a position update module 630.

[0172] Among them, the position display module 610 is used to display the position of the first target in the detection area in the monitoring page corresponding to the detection area; the position is updated according to the first trajectory and the second trajectory after the first target is updated; the first trajectory is updated by keeping the first trajectory following the second target when the first target is in the second state and the second target moves within the set range of the first target; the first trajectory is the trajectory of the first target in the first state, and the second trajectory is the trajectory of the first target in the second state.

[0173] The location update module 630 is used to display the updated location in the monitoring page if the location is updated.

[0174] In an exemplary embodiment, a position display unit is used to display the position of the first target associated with the second trajectory on a monitoring page when the first trajectory follows the second target to move within a set range of the first target; and a position update unit is used to delete the second trajectory if the first trajectory confidence of the first trajectory is greater than the second trajectory confidence of the second trajectory, and display the position of the first target associated with the first trajectory on the monitoring page.

[0175] It should be noted that, when the target tracking device or display device provided in the above embodiments performs target tracking or display, distance description is only performed based on the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the target tracking device or display device will be divided into different functional modules to complete all or part of the functions described above.

[0176] In addition, the target tracking device or display device provided in the above embodiments belongs to the same concept as the embodiments of the target tracking method or display method, respectively, and the specific manner in which each module performs the operation has been described in detail in the method embodiments and will not be repeated here.

[0177] Fig.16 A schematic diagram of the structure of an electronic device according to an exemplary embodiment. The electronic device is suitable for Figure 1 A smart device 130 is shown in the environment.

[0178] It should be noted that the electronic device is only an example adapted to the present application and cannot be considered to provide any limitation on the scope of use of the present application. The electronic device cannot be interpreted as requiring dependence on or having Fig.17 One or more components of exemplary electronic device 2000 are shown.

[0179] The hardware structure of the electronic device 2000 may vary greatly due to differences in configuration or performance, such as Fig.16As shown, the electronic device 2000 includes: a power supply 210 , an interface 230 , at least one memory 250 , and at least one central processing unit (CPU) 270 .

[0180] Specifically, the power supply 210 is used to provide operating voltage for each hardware device on the electronic device 2000 .

[0181] The interface 230 includes at least one wired or wireless network interface 231 for interacting with external devices. Figure 1 The interaction between the user terminal 110 and the smart device 130 in the implementation environment is shown.

[0182] Of course, in other examples adapted by the present application, the interface 230 may further include at least one serial-to-parallel conversion interface 233, at least one input-output interface 235, and at least one USB interface 237, etc. Fig.16 As shown, this is not intended to be a specific limitation.

[0183] The memory 250 is a carrier for storing resources, which may be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon include an operating system 251, an application 253 and data 255, etc. The storage method may be temporary storage or permanent storage.

[0184] Among them, the operating system 251 is used to manage and control various hardware devices and application programs 253 on the electronic device 2000 to enable the central processor 270 to calculate and process the massive data 255 in the memory 250. It can be WindowsServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0185] The application program 253 is a program instruction or code that performs at least one specific task based on the operating system 251, and may include at least one module ( Fig.16 (not shown), each module may respectively include program instructions or codes for the electronic device 2000. For example, the target tracking device may be regarded as an application 253 deployed on the electronic device 2000.

[0186] The data 255 may be photos, pictures, etc. stored in a disk, or may be a point cloud of the first target, etc., stored in the memory 250 .

[0187] The central processor 270 may include one or more processors and is configured to communicate with the memory 250 through at least one communication bus to read the program instructions or codes stored in the memory 250, thereby realizing the operation and processing of the mass data 255 in the memory 250. For example, the target tracking method is completed by the central processor 270 reading a series of program instructions or codes stored in the memory 250.

[0188] In addition, the present application can also be implemented through hardware circuits or hardware circuits combined with software. Therefore, the implementation of the present application is not limited to any specific hardware circuits, software, or a combination of the two.

[0189] See also Fig.17 In an embodiment of the present application, an electronic device 4000 is provided, which may include: a human body sensor configured with a millimeter wave radar, etc.

[0190] exist Fig.17 In the embodiment, the electronic device 4000 includes at least one processor 4001 and at least one memory 4003.

[0191] The data interaction between the processor 4001 and the memory 4003 can be realized through at least one communication bus 4002. The communication bus 4002 may include a path for transmitting data between the processor 4001 and the memory 4003. The communication bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus 4002 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.17 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0192] Optionally, the electronic device 4000 may further include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present application.

[0193] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0194] The memory 4003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program instructions or codes in the form of instructions or data structures and can be accessed by the electronic device 400, but is not limited to this.

[0195] The memory 4003 stores program instructions or codes, and the processor 4001 can read the program instructions or codes stored in the memory 4003 through the communication bus 4002 .

[0196] When the program instructions or codes are executed by the processor 4001, the target tracking method in the above-mentioned embodiments is implemented.

[0197] In addition, an embodiment of the present application provides a storage medium on which program instructions or codes are stored. The program instructions or codes are loaded and executed by a processor to implement the target tracking method as described above.

[0198] In an embodiment of the present application, a computer program product is provided. The computer program product includes program instructions or codes. The program instructions or codes are stored in a storage medium. A processor of an electronic device reads the program instructions or codes from the storage medium, loads and executes the program instructions or codes, so that the electronic device implements the target tracking method as described above.

[0199] Compared with the related art, the present application obtains the trajectory actually corresponding to the first target by tracking the first trajectory associated with the moving point cloud of the first target and the second trajectory associated with the stationary point cloud of the first target respectively, thereby updating the position of the first target based on the trajectory, thereby realizing a multi-track hypothesis tracking scheme. In a close-range tracking environment of multiple targets with dynamic and static relationships, the interference of the moving second target on the stationary first target is eliminated, and the possibility of the first target following the false movement of the second target to form a false trajectory is avoided, so that each target in the detection area is in a real position, thereby effectively solving the problem of low target positioning accuracy in the related art.

[0200] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0201] The above description is only a partial implementation method of the present application. 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 application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A target tracking method, characterized in that: The method comprises: Determine a point cloud of a first target in a detection area, and acquire a first trajectory and a second trajectory of the first target based on the point cloud of the first target; the first trajectory is a trajectory of the first target in a first state, and the second trajectory is a trajectory of the first target in a second state; When the first target is in the second state and the second target moves within a set range where the first target is located, keep the first trajectory following the movement of the second target and update the first trajectory; According to the updated first trajectory and the second trajectory, the position of the first target in the detection area is updated to track the first target and the second target.

2. The method according to claim 1, characterized in that The acquiring the first trajectory and the second trajectory of the first target based on the point cloud of the first target includes: Detecting a state of the first target based on the point cloud of the first target; The first track and / or the second track are created for the first target according to the detected state of the first target.

3. The method according to claim 2, characterized in that The first state includes a motion state; The detecting the state of the first target based on the point cloud of the first target includes: If the point cloud of the first target satisfies a first state condition, the state of the first target is determined to be the motion state; the first state condition includes at least one of the number of motion point clouds in the point cloud of the first target reaching a number threshold, the speed of the motion point cloud reaching a speed threshold, and the displacement of the motion point cloud being greater than a displacement threshold.

4. The method according to claim 3, characterized in that The first trajectory includes a motion trajectory; The step of creating the first track and / or the second track for the first target according to the detected state of the first target includes: If it is detected that the state of the first target is a moving state, a motion track corresponding to the moving state is created for the first target.

5. The method according to claim 2, characterized in that The second state comprises a stationary state; The detecting the state of the first target based on the point cloud of the first target includes: If the point cloud of the first target satisfies the second state condition, the state of the first target is determined to be the static state; the second state condition includes at least one of the number of moving point clouds in the point cloud of the first target being less than a second number threshold, the speed of the moving point cloud being less than a speed threshold, and the displacement of the moving point cloud being less than a displacement threshold.

6. The method according to claim 5, characterized in that The second trajectory comprises a stationary trajectory; The step of creating the first track and / or the second track for the first target according to the detected state of the first target includes: If it is detected that the state of the first target is a stationary state, or the state of the first target is a stationary state and the second target appears within a set range of the first target, a stationary track corresponding to the stationary state is created for the first target.

7. The method according to claim 1, characterized in that The first trajectory comprises a moving trajectory, and the second trajectory comprises a stationary trajectory; The method of maintaining the first trajectory to follow the second target and updating the first trajectory while the first target is in the second state and the second target moves within a set range of the first target includes: When the second target moves within the set range of the first target, a binding relationship is established between the movement trajectory of the first target and the movement trajectory of the second target; Through the binding relationship, the motion trajectory of the first target is updated according to the position of the second target, so that the motion trajectory of the first target follows the motion trajectory of the second target.

8. The method according to claim 1, characterized in that The method further comprises: When the first target is in the second state and the second target moves within a set range where the first target is located, keeping the second trajectory stationary; The updating of the position of the first target in the detection area according to the updated first trajectory and the second trajectory includes: In the process of the first trajectory following the movement of the second target, calculating a first trajectory confidence of the first trajectory and a second trajectory confidence of the second trajectory; If the confidence of the first trajectory is greater than the confidence of the second trajectory, the second trajectory is deleted, and the position of the first target is updated according to the first trajectory.

9. The method according to claim 8, characterized in that The step of calculating a first trajectory confidence of the first trajectory and a second trajectory confidence of the second trajectory while the first trajectory follows the second target moving in the detection area includes: In the process that the first trajectory follows the second target moving in the detection area, determining a first valid point cloud and a second valid point cloud based on the speed of each point cloud of the first target; the first valid point cloud includes the moving point cloud associated with the first trajectory, and the second valid point cloud includes the stationary point cloud associated with the second trajectory; Calculating a first trajectory confidence of the first trajectory according to the number and / or signal strength of the first valid point cloud detected; A second trajectory confidence of the second trajectory is calculated according to the number and / or signal strength of the detected second valid point clouds.

10. A target display method, characterized in that: The method comprises: The position of the first target in the detection area is displayed in the monitoring page corresponding to the detection area; the position is updated according to the first trajectory and the second trajectory after the first target is updated; the first trajectory is updated by keeping the first trajectory following the second target when the first target is in the second state and the second target moves within the set range of the first target; the first trajectory is the trajectory of the first target in the first state, and the second trajectory is the trajectory of the first target in the second state; If the location is updated, the updated location is displayed in the monitoring page.

11. The method according to claim 10, characterized in that The displaying of the updated location in the monitoring page includes: When the first track follows the second target and moves within the set range of the first target, the position of the first target associated with the second track is displayed on the monitoring page; If the first trajectory confidence of the first trajectory is greater than the second trajectory confidence of the second trajectory, the second trajectory is deleted, and the position of the first target associated with the first trajectory is displayed on the monitoring page.

12. A target tracking device, characterized in that: The device comprises: a trajectory creation module, used to determine a point cloud of a first target in a detection area, and acquire a first trajectory and a second trajectory of the first target based on the point cloud of the first target; the first trajectory is a trajectory of the first target in a first state, and the second trajectory is a trajectory of the first target in a second state; a trajectory updating module, configured to keep the first trajectory following the movement of the second target and update the first trajectory when the first target is in the second state and the second target moves within a set range where the first target is located; The position updating module is used to update the position of the first target in the detection area according to the updated first trajectory and the second trajectory, so as to track the first target and the second target.

13. A target display device, characterized in that: The device comprises: A position display module, used for displaying the position of the first target in the detection area in the monitoring page corresponding to the detection area; the position is updated according to the first trajectory and the second trajectory after the first target is updated; the first trajectory is updated by keeping the first trajectory following the second target when the first target is in the second state and the second target moves within the set range of the first target; the first trajectory is the trajectory of the first target in the first state, and the second trajectory is the trajectory of the first target in the second state; The location update module is used to display the updated location in the monitoring page if the location is updated.

14. An electronic device comprising at least one processor and at least one memory, characterized in that: The memory stores a computer program; when the processor executes the computer program, the steps of the method according to any one of claims 1 to 11 are implemented.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

Images