Target object tracking method, device, apparatus, and storage medium
By acquiring parameters such as the lifespan and rotation distance of moving point cameras through panoramic camera equipment, the scheduling of moving point cameras is optimized, solving the problem of poor scheduling performance in the monitoring system and achieving more efficient target object tracking and extended equipment lifespan.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHEJIANG UNIVIEW TECH CO LTD
- Filing Date
- 2024-12-19
- Publication Date
- 2026-06-23
AI Technical Summary
The scheduling of multiple moving camera devices in the existing monitoring system is not optimized enough, resulting in poor scheduling performance.
By acquiring target parameters such as the lifespan and rotation distance of the moving point camera through panoramic camera equipment, the optimal target moving point camera is determined for tracking.
It improved the scheduling performance of moving camera equipment in the monitoring system, balanced equipment usage, and enhanced tracking efficiency and equipment lifespan.
Smart Images
Figure CN122269138A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of surveillance technology, and in particular to a method, apparatus, device, and storage medium for tracking target objects. Background Technology
[0002] With the increasing awareness of security among people, a linked tracking monitoring system has emerged in the field of intelligent security. This system can detect target objects such as people or objects through panoramic cameras, and track the detected target objects through moving cameras.
[0003] Currently, when there are multiple moving point camera devices in the monitoring system, after the panoramic camera device detects the target object, it will sequentially determine whether each moving point camera device is in an idle state. If it is determined that a certain moving point camera device is in an idle state, it will be scheduled to track the target object.
[0004] However, the above methods can lead to suboptimal scheduling of moving camera equipment, resulting in poor scheduling performance of the monitoring system. Summary of the Invention
[0005] This invention provides a method, apparatus, device, and storage medium for tracking target objects, in order to address the shortcomings of poor scheduling performance in existing monitoring systems, optimize the scheduling of moving point camera equipment, and improve the scheduling performance of monitoring systems.
[0006] This invention provides a target object tracking method applied to a panoramic camera device, the method comprising: When the panoramic camera detects a target object, the target parameters corresponding to at least two moving point cameras are acquired. The target parameters include the lifespan utilization rate of the moving point camera and / or the rotation distance of the moving point camera to the target position. The target position is the position where the moving point camera can detect the target object. Based on the target parameters, the target moving point camera device is determined; Control the target moving point camera device to track the target object.
[0007] According to the present invention, a method for tracking a target object is provided, wherein the target parameters include the lifetime utilization rate and the rotation distance; The step of determining the target moving point camera device based on each of the target parameters includes: For each of the aforementioned moving point camera devices, the usage weight of the moving point camera device is determined based on its lifespan utilization rate and rotation distance; The target moving point camera device is determined based on the usage weights described above.
[0008] According to a target object tracking method provided by the present invention, determining the usage weight of the moving point camera device based on its lifetime utilization rate and rotation distance includes: Determine the difference between the preset value and the lifespan utilization rate of the moving point camera device; The product of the difference and the reciprocal of the rotation distance of the moving point camera is determined as the usage weight of the moving point camera. The determination of the target moving point camera device based on each of the usage weights includes: If the target object is the first object detected, the moving point camera device with the maximum usage weight will be determined as the target moving point camera device.
[0009] According to a target object tracking method provided by the present invention, the method further includes: For each of the aforementioned moving point camera devices, the total number of first movements in the horizontal direction and the total number of second movements in the vertical direction of the pan-tilt unit corresponding to the moving point camera device are obtained respectively; Based on the first total number of movements and the preset maximum number of movements, the first lifespan utilization rate of the pan-tilt unit corresponding to the moving point camera device in the horizontal direction is determined; Based on the second total number of movements and the preset maximum number of movements, determine the second lifespan utilization rate of the pan-tilt unit corresponding to the moving point camera device in the vertical direction; The maximum value between the first lifespan utilization rate and the second lifespan utilization rate is determined as the lifespan utilization rate of the moving point camera device.
[0010] According to a target object tracking method provided by the present invention, the method further includes: Determine the first position of the target object in the shooting frame corresponding to the panoramic camera device; For each of the aforementioned moving point camera devices, based on the first position and the correspondence between the coordinate positions of each moving point camera device and the coordinate positions of pixels in the corresponding shooting image of the panoramic camera device, the target position of the target object in the moving point camera device is determined; Based on the target position and the current position of the moving point camera, the rotation distance of the moving point camera is determined.
[0011] According to a target object tracking method provided by the present invention, the method further includes: If it is determined that the gimbal corresponding to the target moving point camera cannot rotate, a target mark is added to the target moving point camera. The target mark is used to indicate that the gimbal corresponding to the target moving point camera cannot rotate.
[0012] The present invention also provides a target object tracking device, comprising: The acquisition module is used to acquire target parameters corresponding to at least two moving point cameras when the panoramic camera detects a target object. The target parameters include the lifespan utilization rate of the moving point camera and / or the rotation distance of the moving point camera to the target position. The target position is the position where the moving point camera can detect the target object. The determination module is used to determine the target moving point camera device based on each of the target parameters; The control module is used to control the target moving point camera device to track the target object.
[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the target object tracking method as described above.
[0014] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the target object tracking method as described above.
[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the target object tracking method as described above.
[0016] The present invention provides a target object tracking method, apparatus, device, and storage medium. When a panoramic camera detects a target object, it acquires target parameters corresponding to at least two moving point cameras. These target parameters include the lifetime utilization rate of the moving point cameras and / or the rotation distance of the moving point cameras to the target position, where the target position is the location where the moving point cameras can monitor the target object. Based on these target parameters, a target moving point camera is determined, and the target moving point camera is controlled to track the target object. Since the optimal target moving point camera can be selected from at least two moving point cameras for target object tracking based on the lifetime utilization rate and / or rotation distance of each moving point camera, the uneven usage of moving point cameras, which occurs in existing technologies where scheduling is based on the idle state of the moving point cameras each time, is avoided. This improves the scheduling performance of moving point cameras in the monitoring system. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0018] Figure 1 This is a schematic diagram of a monitoring system provided in an embodiment of the present invention.
[0019] Figure 2 This is a flowchart illustrating the target object tracking method provided in an embodiment of the present invention.
[0020] Figure 3 This is a schematic diagram of the target object tracking device provided in an embodiment of the present invention.
[0021] Figure 4 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0023] In scenarios where a monitoring system is used for coordinated tracking, when multiple moving point cameras exist within the system, existing technologies typically query the status of each camera individually. Once an idle camera is found, it is scheduled to track the target object. However, this scheduling method suffers from suboptimal allocation of tracking tasks, resulting in poor system performance. For example, a monitoring system might include a panoramic camera and moving point cameras 1, 2, and 3. The panoramic camera detects the target object. If moving point camera 1 is found to be idle, it is scheduled to track the target object. However, this scheduling method can lead to situations where moving point camera 1 is immediately reassigned to track the target object after just stopping operation, while moving point cameras 2 and 3 remain unscheduled, resulting in uneven usage across the cameras. Furthermore, there might be situations where moving camera 1 needs to rotate a considerable distance to track the target object, while moving camera 2 only needs to rotate a smaller distance, but ultimately moving camera 1 is scheduled to track the target object. In summary, the scheduling method in the existing technology results in poor scheduling performance of the monitoring system.
[0024] In view of the above problems, embodiments of the present invention provide a target object tracking method. In this method, when a panoramic camera detects a target object, it can acquire the target parameters corresponding to each moving point camera. These target parameters include the lifespan utilization rate of the moving point camera and / or the rotation distance of the moving point camera when it rotates to a target position where it can monitor the target object. Based on the above target parameters, a target moving point camera can be determined from at least two moving point cameras, and the target moving point camera can be controlled to track the target object. Since the lifespan utilization rate and / or rotation distance of each moving point camera are considered, the optimal target moving point camera can be determined from at least two moving point cameras, enabling more reasonable allocation of target object tracking tasks and improving the scheduling performance of the monitoring system for moving point camera devices.
[0025] The following is combined with Figures 1-2 The target object tracking method provided in the embodiments of the present invention will be described. Figure 1 This is a schematic diagram of a monitoring system provided in an embodiment of the present invention, such as... Figure 1 As shown, the system includes a panoramic camera and n moving point cameras. The panoramic camera is used to detect target objects in the monitoring screen. When a target object is detected, the target moving point camera needs to be selected from the n moving point cameras to control the target moving point camera to continuously track the target object.
[0026] The entity executing this method can be, for example, as follows: Figure 1 The panoramic camera equipment, computer, server, server cluster or specially designed target object tracking equipment, etc., can be the target object tracking device set in the electronic equipment. The target object tracking device can be implemented by software, hardware or a combination of both.
[0027] Figure 2 This is a flowchart illustrating the target object tracking method provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the method includes: Step 201: When the panoramic camera detects the target object, acquire the target parameters corresponding to at least two moving point cameras. The target parameters include the lifespan utilization rate of the moving point camera and / or the rotation distance of the moving point camera to the target position. The target position is the position of the target object that the moving point camera can monitor.
[0028] Specifically, the target object can include pedestrians, vehicles, or any other object that needs to be monitored or tracked. When the panoramic camera in the monitoring system detects a target object in the monitored area, it acquires the target parameters of each moving camera in the monitoring system. These target parameters may include only the lifespan utilization rate of the moving camera, only the rotation distance of the moving camera to the target position, or both the lifespan utilization rate and the rotation distance of the moving camera to the target position.
[0029] The lifespan utilization rate of a moving point camera can be understood as the ratio of the number of times the pan-tilt unit has been used since installation to the expected total number of uses. The rotation distance can be understood as the angular distance that the moving point camera needs to rotate from its current position to a target position where it can monitor the target object. The shorter the rotation distance, the less time and energy the moving point camera needs to adjust to the target position, and the higher the response speed and efficiency when tracking the target object.
[0030] Step 202: Determine the target moving point camera device based on each target parameter.
[0031] In this step, after determining the target parameters of each moving point camera device, the target moving point camera device for tracking the target object can be determined from at least two moving point camera devices based on the target parameters of each moving point camera device.
[0032] In one possible implementation, if the target parameter only includes the lifetime utilization rate of the moving point camera, the moving point camera with the lowest lifetime utilization rate can be selected as the target moving point camera. This balances the number of times and duration of use of the pan / tilt unit for each moving point camera, thereby maximizing the usage time of the pan / tilt unit for each moving point camera.
[0033] In another possible implementation, if the target parameters only include the rotation distance of the moving camera to the target position, the moving camera with the smallest rotation distance can be selected as the target moving camera. This ensures that the target moving camera can quickly track the target object, guaranteeing tracking efficiency.
[0034] In another possible implementation, if the target parameters include both the lifetime utilization rate of the moving camera and the rotation distance of the moving camera to the target position, different weights can be assigned to the lifetime utilization rate and the rotation distance respectively. Using the lifetime utilization rate and rotation distance of each moving camera, along with their respective weights, a usage score for each moving camera can be calculated. The moving camera with the highest score is then selected as the final target camera. In this approach, because both lifetime utilization rate and rotation distance are considered simultaneously, the usage of the pan / tilt unit of each moving camera can be fully balanced while ensuring the tracking efficiency of the target object, maximizing the usage time of each pan / tilt unit.
[0035] Step 203: Control the target moving point camera device to track the target object.
[0036] In this step, after the target moving point camera device is identified, the panoramic camera device sends the target position corresponding to the target moving point camera device to the target moving point camera device through a preset network protocol. The target moving point camera device will control the pan-tilt unit to rotate to the target position, thereby tracking the target object detected by the panoramic camera device.
[0037] In some possible implementations, since the target's motion direction and the target device's rotation direction may be in the same direction or opposite directions, after initially determining the target position, the time required for rotation can be roughly estimated based on the current position of the moving point device, the target position, and the motor speed. The target position can then be updated based on this rotation time to reduce tracking corrections caused by target motion. Furthermore, the selection of the target camera device can also consider the relationship between the rotation direction and the target's motion direction, while also taking into account the mechanical lifespan of the motor components. For example, when an important, fast-moving target is detected, prioritizing efficiency, if two candidate target devices require equal or similar times to rotate to the initial target position but in different directions, since reverse rotation is a "meeting" situation and same-direction rotation is a "chasing" situation, reverse rotation is chosen. Conversely, if a slow-moving target is detected, prioritizing lifespan, since reverse rotation requires motor braking after the "meeting" before resuming tracking, further consuming the mechanical lifespan of the motor components, same-direction rotation is chosen.
[0038] The target object tracking method provided in this invention, when a panoramic camera detects a target object, acquires target parameters corresponding to at least two moving point cameras. These target parameters include the lifetime utilization rate of the moving point cameras and / or the rotation distance of the moving point cameras to the target position, which is the location where the moving point cameras can monitor the target object. Based on these target parameters, a target moving point camera is determined, and the target moving point camera is controlled to track the target object. Since the optimal target moving point camera can be selected from at least two moving point cameras for target object tracking based on the lifetime utilization rate and / or rotation distance of each moving point camera, the uneven usage of moving point cameras, which occurs in existing technologies where scheduling is based on the idle state of the moving point cameras each time, is avoided. This improves the scheduling performance of moving point cameras in the monitoring system.
[0039] For example, based on the above embodiments, when the target parameters include lifespan utilization and rotation distance, when determining the target moving point camera device based on each target parameter, the usage weight of the moving point camera device can be determined based on the lifespan utilization and rotation distance of each moving point camera device, and the target moving point camera device can be determined based on each usage weight.
[0040] Specifically, for each moving point camera device, both its lifespan utilization rate and rotation distance can be considered simultaneously, and its usage weight can be determined based on these two factors. This usage weight characterizes the relative merits of each moving point camera device in performing the target object tracking task under the current conditions. Furthermore, based on the usage weights of each moving point camera device, the tracking task can be distributed, and the optimal target moving point camera device can be selected for tracking the target object.
[0041] By comprehensively considering the lifespan and rotation distance of the moving point camera to select the optimal target moving point camera, the tracking efficiency can be guaranteed while improving the overall performance of the monitoring system when controlling the target moving point camera to track the target object.
[0042] For example, based on the above embodiments, when determining the usage weight of the moving point camera based on its lifespan utilization rate and rotation distance, it can be done in the following way: The difference between the preset value and the lifespan utilization rate of the moving point camera is determined, and the product of this difference and the reciprocal of the rotation distance of the moving point camera is used to determine the usage weight of the moving point camera. Accordingly, when determining the target moving point camera based on each usage weight, if the target object is the object detected for the first time, the moving point camera with the maximum usage weight can be determined as the target moving point camera.
[0043] Specifically, the preset value can be 1, or other values. For a given moving-point camera device, assuming its lifespan utilization rate is... The rotation distance is Then the weight K of the moving point camera can be determined according to the following formula (1): (1) Therefore, according to formula (1), the set of usage weights for each moving camera device in the monitoring system can be obtained. ,in, This represents the usage weight of the nth moving point camera device.
[0044] According to formula (1), the lifespan utilization rate can be seen. The smaller the value, the larger the weight K, and the greater the rotation distance. The smaller the value, the larger the weight K should be.
[0045] Therefore, when the target object is determined to be the first detected object, the moving point camera with the highest usage weight can be selected from the usage weight set A as the target moving point camera. The highest usage weight means that the target moving point camera has a low lifespan utilization rate and a low rotation distance. A low lifespan utilization rate indicates that the target moving point camera has a long service life. By using this target camera to track the target object, the overall lifespan of the monitoring system can be extended, and the maintenance cost of the monitoring system can be reduced. A low rotation distance indicates that the target moving point camera can rotate to the target position more quickly, enabling faster tracking of the target object and improving the tracking efficiency.
[0046] It should be noted that panoramic camera devices can detect target objects using depth algorithms and identify the same target object with the same identification (ID) based on the object's features and location information. Therefore, if the target object's ID is not the first time it appears, to ensure the continuity of the tracking process, the moving camera that previously tracked the target object will continue the tracking action. When it is determined that the target object's ID is the first time it appears, the moving camera with the highest usage weight in weight set A will be selected to perform the tracking action.
[0047] In this embodiment, after determining the usage weight of each moving point camera based on the difference between the preset value and the lifespan utilization rate of the moving point camera, and the reciprocal of the rotation distance of the moving point camera, the moving point camera corresponding to the maximum usage weight is determined as the target camera to perform the tracking action. In this way, the number of times each moving point camera is used in the monitoring system can be balanced, and the tracking efficiency of the target object can be guaranteed.
[0048] For example, based on the above embodiments, the lifespan utilization rate of the moving point camera device can be determined in the following manner: For each moving point camera device, the total number of first movements in the horizontal direction and the total number of second movements in the vertical direction of the pan-tilt unit corresponding to the moving point camera device are obtained respectively. Based on the total number of first movements and a preset upper limit, the first lifespan utilization rate of the pan-tilt unit corresponding to the moving point camera device in the horizontal direction is determined, and based on the total number of second movements and the preset upper limit, the second lifespan utilization rate of the pan-tilt unit corresponding to the moving point camera device in the vertical direction is determined. Thus, the maximum value between the first lifespan utilization rate and the second lifespan utilization rate is determined as the lifespan utilization rate of the moving point camera device.
[0049] Specifically, the pan-tilt unit (PTZ) of a motion camera includes horizontal and vertical motion motors, with vertical motion referring to longitudinal movement. Typically, the lifespan of a PTG unit is based on the number of round trips of the motors. Each time a motor turns around horizontally or vertically (i.e., one round trip), the total number of movements in that direction increases by one. Furthermore, according to actual testing, each PTG unit has a maximum number of round trips for its motors, limiting the total number of uses for the PTG unit.
[0050] For each moving point camera device, the total number of first movements in the horizontal direction and the total number of second movements in the vertical direction corresponding to the moving point camera device can be obtained separately. Combined with a preset upper limit for the number of movements, the lifespan utilization rate of the pan-tilt unit corresponding to the moving point camera device can be determined. Taking the horizontal direction as an example, assuming the preset upper limit for the number of movements is N, that is, the rated maximum number of round trips is N, the current total number of first movements in the horizontal direction is... The first lifespan utilization rate of the pan-tilt unit corresponding to the starting point camera device in the horizontal direction can be determined based on the following formula (2). : (2) Among them, the first lifespan utilization rate of the pan-tilt unit corresponding to the moving point camera equipment in the horizontal direction. This can also be understood as the first lifetime utilization rate of the pan-tilt unit corresponding to the moving-point camera in the P direction. .
[0051] Similarly, the second lifetime utilization rate of the pan-tilt unit corresponding to the starting point camera device in the vertical direction, i.e., the T direction, can be determined according to the method shown in formula (2). .
[0052] Furthermore, the lifespan utilization rate of the moving point camera equipment can be determined according to formula (3). : (3) In this embodiment, by considering the total number of movements of the pan-tilt unit in the horizontal and vertical directions respectively, a first lifespan utilization rate in the horizontal direction and a second lifespan utilization rate in the vertical direction are determined based on the total number of movements. Based on the first lifespan utilization rate and the second lifespan utilization rate, the lifespan utilization rate of the moving point camera device is determined, thereby enabling a more comprehensive assessment of the usage status of the moving point camera device and improving the accuracy of the determined lifespan utilization rate.
[0053] For example, based on the above embodiments, the rotation distance of the moving-point camera device can be determined in the following manner: The first position of the target object in the shooting frame corresponding to the panoramic camera is determined. For each moving point camera, based on the first position and the correspondence between the coordinate positions of each moving point camera and the coordinate positions of the pixels in the shooting frame corresponding to the panoramic camera, the target position of the target object in the moving point camera is determined. Based on the target position and the current position of the moving point camera, the rotation distance of the moving point camera is determined.
[0054] Specifically, panoramic camera devices can detect target objects using depth algorithms, thereby determining the first position of the target object in the corresponding shooting frame of the panoramic camera device. The first position can be understood as the pixel coordinates of the target object in the shooting frame.
[0055] For each moving point camera device, the correspondence between the coordinate positions of each moving point camera device and the coordinate positions of the pixels in the corresponding shooting image of the panoramic camera device can be pre-calibrated. Therefore, based on this correspondence, the first position can be transformed to obtain the target position corresponding to each moving point camera device. The target position can be PT coordinates, which can be represented by the following formula (4): (4) in, This represents the PT coordinates corresponding to the nth moving point camera, and the nth moving point camera rotates from its current position to... Once the target object is located, it can appear in the monitoring screen of the nth moving point camera.
[0056] Assume the current position of the moving camera is The rotation distance D of the moving point camera can be determined by the following formula (5): (5) Where (P,T) represents the target position of the target object on the moving point camera device.
[0057] Therefore, the set of rotation distances of all moving cameras in the monitoring system can be calculated. The weights to be used can be determined based on the rotation distance of each moving camera device in the set.
[0058] In this embodiment, by using the first position of the target object in the shooting frame corresponding to the panoramic camera device, and the correspondence between the coordinate positions of each coordinate position of the pre-calibrated moving point camera device and the coordinate positions of the pixels in the shooting frame corresponding to the panoramic camera device, the target position when the moving point camera device can monitor the target object can be determined. Based on the target position and the current position, the rotation distance of the moving point camera device can be determined. Subsequently, the tracking task can be optimized and allocated based on this rotation distance, improving the efficiency and accuracy of tracking, and reducing the wear and tear of the moving point camera device, thus extending its service life.
[0059] Furthermore, based on the above embodiments, after controlling the target moving point camera device to perform the tracking action, it is also necessary to verify whether the movement of the target moving point camera device is as expected, that is, whether the target object is being tracked correctly. If it is determined that the gimbal corresponding to the target moving point camera device cannot rotate, a target marker is added to the target moving point camera device. The target marker is used to indicate that the gimbal corresponding to the target moving point camera device cannot rotate.
[0060] Specifically, when it is determined that the pan-tilt unit corresponding to the target moving point camera cannot rotate in a certain direction, it indicates that the pan-tilt unit may have malfunctioned. In this case, a target marker can be added to the target moving point camera. This way, the target moving point camera will not be scheduled again during subsequent tracking of the target object. Specifically, when marking, the total number of current movements of the pan-tilt unit in that direction can be set to a preset value, such as 1001xN. The lifespan utilization rate and usage weight of the target moving point camera are then updated based on this set total number of current movements. Since the current total number of movements is large, the calculated usage weight will be relatively small; therefore, the target moving point camera will not be scheduled in subsequent tracking processes.
[0061] It should be noted that during this tracking process, the moving point camera corresponding to the second largest weight can be selected from the set of weights to re-track the target object.
[0062] By using the above methods, we can ensure the correct tracking of the target object this time, and also ensure that the target moving point camera will not be rescheduled to the faulty target next time, thus improving the monitoring performance of the monitoring system.
[0063] In addition, if the target moving point camera can rotate to the target position normally, the target position of the target moving point camera will be updated to the current position, and the number of times the pan-tilt motor moves back and forth in the horizontal and vertical directions during the process of the target moving point camera rotating to the target position will be obtained. The lifespan utilization rate of the target moving point camera will be updated based on the number of back and forth movements, so as to serve as the basis for determining the new target moving point camera during the next tracking and scheduling.
[0064] The target object tracking device provided by the present invention is described below. The target object tracking device described below and the target object tracking method described above can be referred to in correspondence.
[0065] Figure 3 This is a schematic diagram of the target object tracking device provided in an embodiment of the present invention, with reference to... Figure 3 As shown, the target object tracking device 300 includes: The acquisition module 11 is used to acquire target parameters corresponding to at least two moving point cameras when the panoramic camera detects a target object. The target parameters include the lifespan utilization rate of the moving point camera and / or the rotation distance of the moving point camera to the target position. The target position is the position where the moving point camera can detect the target object. The determining module 12 is used to determine the target moving point camera device based on each of the target parameters; The control module 13 is used to control the target moving point camera device to track the target object.
[0066] In one example embodiment, the target parameters include the lifetime utilization rate and the rotation distance; the determining module 12 is specifically used for: For each of the aforementioned moving point camera devices, the usage weight of the moving point camera device is determined based on its lifespan utilization rate and rotation distance; The target moving point camera device is determined based on the usage weights described above.
[0067] In one example embodiment, the determining module 12 is specifically used for: Determine the difference between the preset value and the lifespan utilization rate of the moving point camera device; The product of the difference and the reciprocal of the rotation distance of the moving point camera is determined as the usage weight of the moving point camera. The determination of the target moving point camera device based on each of the usage weights includes: If the target object is the first object detected, the moving point camera device with the maximum usage weight will be determined as the target moving point camera device.
[0068] In one example embodiment, the acquisition module 11 is further configured to acquire, for each of the moving point camera devices, the first total number of times the pan-tilt unit corresponding to the moving point camera device moves in the horizontal direction and the second total number of times it moves in the vertical direction. The determining module 12 is further configured to determine the first lifespan utilization rate of the pan-tilt unit corresponding to the moving point camera device in the horizontal direction based on the first total number of movements and the preset upper limit of the number of movements; The determining module 12 is further configured to determine the second lifespan utilization rate of the pan-tilt unit corresponding to the moving point camera device in the vertical direction based on the second total number of movements and the preset upper limit of the number of movements; The determining module 12 is further configured to determine the maximum value of the first lifespan utilization rate and the second lifespan utilization rate as the lifespan utilization rate of the moving point camera device.
[0069] In one example embodiment, the determining module 12 is further configured to: Determine the first position of the target object in the shooting frame corresponding to the panoramic camera device; For each of the aforementioned moving point camera devices, based on the first position and the correspondence between the coordinate positions of each moving point camera device and the coordinate positions of pixels in the corresponding shooting image of the panoramic camera device, the target position of the target object in the moving point camera device is determined; Based on the target position and the current position of the moving point camera, the rotation distance of the moving point camera is determined.
[0070] In one example embodiment, the device further includes: a tagging module, wherein: The marking module is used to add a target mark to the target moving point camera when it is determined that the pan-tilt unit corresponding to the target moving point camera cannot rotate. The target mark is used to indicate that the pan-tilt unit corresponding to the target moving point camera cannot rotate.
[0071] The apparatus of this embodiment can be used to execute the method of any embodiment in the target object tracking method side embodiment. Its specific implementation process and technical effects are similar to those in the target object tracking method side embodiment. For details, please refer to the detailed description in the target object tracking method side embodiment, which will not be repeated here.
[0072] Figure 4 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as... Figure 4As shown, the electronic device may include a processor 410, a communications interface 420, a memory 430, and a communication bus 440, wherein the processor 410, communications interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a target object tracking method. This method includes: when the panoramic camera detects a target object, acquiring target parameters corresponding to at least two moving point cameras, the target parameters including the lifespan utilization rate of the moving point camera and / or the rotation distance of the moving point camera to the target position, the target position being the position where the moving point camera can detect the target object; determining a target moving point camera based on each of the target parameters; and controlling the target moving point camera to track the target object.
[0073] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, 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 a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0074] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the target object tracking method provided by the above methods. The method includes: when the panoramic camera device detects a target object, acquiring target parameters corresponding to at least two moving point camera devices, the target parameters including the lifespan utilization rate of the moving point camera device and / or the rotation distance of the moving point camera device to the target position, the target position being the position where the moving point camera device can detect the target object; determining a target moving point camera device based on each of the target parameters; and controlling the target moving point camera device to track the target object.
[0075] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a target object tracking method provided by the above methods. The method includes: when the panoramic camera detects a target object, acquiring target parameters corresponding to at least two moving point camera devices, the target parameters including the lifetime utilization rate of the moving point camera device and / or the rotation distance of the moving point camera device to a target position, the target position being the position where the moving point camera device can monitor the target object; determining a target moving point camera device based on each of the target parameters; and controlling the target moving point camera device to track the target object.
[0076] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. 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 network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0077] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A tracking method of a target object, characterized by, Applied to panoramic camera equipment, the method includes: When the panoramic camera detects a target object, the target parameters corresponding to at least two moving point cameras are acquired. The target parameters include the lifespan utilization rate of the moving point camera and / or the rotation distance of the moving point camera to the target position. The target position is the position where the moving point camera can detect the target object. Based on the target parameters, the target moving point camera device is determined; Control the target moving point camera device to track the target object.
2. The tracking method of a target object according to claim 1, characterized by, The target parameters include the lifespan utilization rate and the rotation distance; The step of determining the target moving point camera device based on each of the target parameters includes: For each of the aforementioned moving point camera devices, the usage weight of the moving point camera device is determined based on its lifespan utilization rate and rotation distance; The target moving point camera device is determined based on the usage weights described above.
3. The tracking method of a target object according to claim 2, wherein The determination of the usage weight of the moving point camera based on its lifespan utilization rate and rotation distance includes: Determine the difference between the preset value and the lifespan utilization rate of the moving point camera device; The product of the difference and the reciprocal of the rotation distance of the moving point camera is determined as the usage weight of the moving point camera. The determination of the target moving point camera device based on each of the usage weights includes: If the target object is the first object detected, the moving point camera device with the maximum usage weight will be determined as the target moving point camera device.
4. The tracking method of a target object according to claim 1, characterized by, The method further includes: For each of the aforementioned moving point camera devices, the total number of first movements in the horizontal direction and the total number of second movements in the vertical direction of the pan-tilt unit corresponding to the moving point camera device are obtained respectively; Based on the first total number of movements and the preset maximum number of movements, the first lifespan utilization rate of the pan-tilt unit corresponding to the moving point camera device in the horizontal direction is determined; Based on the second total number of movements and the preset maximum number of movements, determine the second lifespan utilization rate of the pan-tilt unit corresponding to the moving point camera device in the vertical direction; The maximum value between the first lifespan utilization rate and the second lifespan utilization rate is determined as the lifespan utilization rate of the moving point camera device.
5. The tracking method of a target object according to claim 1, characterized by, The method further includes: Determine the first position of the target object in the shooting frame corresponding to the panoramic camera device; For each of the aforementioned moving point camera devices, based on the first position and the correspondence between the coordinate positions of each moving point camera device and the coordinate positions of pixels in the corresponding shooting image of the panoramic camera device, the target position of the target object in the moving point camera device is determined; Based on the target position and the current position of the moving point camera, the rotation distance of the moving point camera is determined.
6. The target object tracking method according to any one of claims 1-5, characterized in that, The method further includes: If it is determined that the gimbal corresponding to the target moving point camera cannot rotate, a target mark is added to the target moving point camera. The target mark is used to indicate that the gimbal corresponding to the target moving point camera cannot rotate.
7. A target object tracking device, characterized in that, include: The acquisition module is used to acquire target parameters corresponding to at least two moving point cameras when the panoramic camera detects a target object. The target parameters include the lifespan utilization rate of the moving point camera and / or the rotation distance of the moving point camera to the target position. The target position is the position where the moving point camera can detect the target object. The determination module is used to determine the target moving point camera device based on each of the target parameters; The control module is used to control the target moving point camera device to track the target object.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the target object tracking method as described in any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the target object tracking method as described in any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the target object tracking method as described in any one of claims 1 to 6.