Target tracking method and device, camera and storage medium

By determining the change in the action content of the target in real time, determining the priority and duration, the problem of invalid priority and duration during multi-target tracking is solved, and targeted target tracking and equipment protection are achieved.

CN119068403APending Publication Date: 2024-12-03ZHEJIANG UNIVIEW TECH CO LTD

Patent Information

Application Number
CN202310636176.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-31
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In a three-dimensional scenario, when multiple targets simultaneously intrude into the radar detection area, the prior art cannot effectively determine the tracking priority and duration, resulting in the gimbal camera that can only track one target at will.

Method used

By determining the amount of changes in the action content of each tracking target in real time, determining the tracking priority and time length based on the amount of changes in the action content, and tracking in the order of priority from high to low.

Benefits of technology

Targeted tracking of goals is achieved, ensuring that emergency or important goals are paid attention to in a timely manner, and equipment damage caused by excessive tracking of a single goal is avoided.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068403A_ABST
    Figure CN119068403A_ABST
Patent Text Reader

Abstract

The invention discloses a target tracking method and device, a camera and a storage medium. The method comprises the steps that when at least two tracking targets are detected in a preset detection area, the action content variation of each tracking target is determined in real time; according to the action content variable quantity of each tracking target, the tracking priority and the tracking duration of each tracking target are determined, and the larger the action content variable quantity is, the higher the corresponding tracking priority is and the longer the tracking duration is; and according to a sequence of tracking priorities from high to low, tracking the corresponding tracking targets based on the tracking duration in sequence. Through the technical scheme provided by the embodiment of the invention, the tracking priority and the tracking duration of the tracking target can be determined according to the action content variation of the tracking target, so that the tracking of the target is more targeted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of target tracking, and in particular to a target tracking method, device, camera and storage medium. Background Art

[0002] Currently, radar is used for intrusion detection in three-dimensional scenes. When a target invades the detection area, it is necessary to link the gimbal camera to continue tracking until the target leaves the detection area. However, when multiple targets invade the monitoring range of a radar at the same time, and the radar is configured with only one gimbal camera for tracking the target, the gimbal can only track one target at random.

[0003] In the related technology, there are mainly three mainstream solutions: Solution 1, time priority tracking solution: that is, the camera is linked to track the target that enters the radar monitoring area earlier, until the target leaves the detection area, and the next target is tracked in chronological order after the tracking is completed; Solution 2, distance priority tracking solution: the camera is linked to track the target that is close to the radar position, until the target leaves the detection area, and the next target is tracked in the order of current distance after the tracking is completed; Solution 3, polling tracking solution: each target is tracked in a pre-set order. When the tracking time of one target reaches the set time, other targets are tracked until all targets are tracked and then tracking starts from the first target.

[0004] Obviously, the above scheme has no effective basis for the order of tracking targets and the tracking time of targets, and is not targeted. Summary of the invention

[0005] The present invention provides a target tracking method, a device, a camera and a storage medium, which can track the target in a targeted manner according to the change amount of the action content of the target.

[0006] According to one aspect of the present invention, a target tracking method is provided, comprising:

[0007] When at least two tracking targets are detected in a preset detection area, a change amount of the motion content of each tracking target is determined in real time;

[0008] According to the change amount of the action content of each tracking target, the tracking priority and tracking duration of each tracking target are determined respectively, wherein the greater the change amount of the action content, the higher the corresponding tracking priority and the longer the tracking duration;

[0009] In descending order of tracking priority, corresponding tracking targets are tracked based on the tracking duration.

[0010] According to another aspect of the present invention, there is provided a target tracking device, comprising:

[0011] An action content change amount determination module, used to determine the action content change amount of each tracking target in real time when at least two tracking targets are detected in a preset detection area;

[0012] A tracking priority determination module, used to determine the tracking priority and tracking duration of each tracking target according to the change amount of the action content of each tracking target, wherein the greater the change amount of the action content, the higher the corresponding tracking priority and the longer the tracking duration;

[0013] The target tracking module is used to track the corresponding tracking targets based on the tracking duration in descending order of tracking priority.

[0014] According to another aspect of the present invention, there is provided a camera, the camera comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the target tracking method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the target tracking method described in any embodiment of the present invention when executed.

[0019] The target tracking scheme of the embodiment of the present invention, when at least two tracking targets are detected in a preset detection area, determines the change in the motion content of each tracking target in real time; determines the tracking priority and tracking duration of each tracking target according to the change in the motion content of each tracking target, wherein the greater the change in the motion content, the higher the corresponding tracking priority and the longer the tracking duration; and tracks the corresponding tracking targets in order of tracking priority from high to low based on the tracking duration. Through the technical scheme provided by the embodiment of the present invention, the tracking priority and tracking duration of the tracking target can be determined according to the change in the motion content of the tracking target, making the tracking of the target more targeted.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a target tracking method provided according to Embodiment 1 of the present invention;

[0023] Figure 2 is a flow chart of a target tracking method provided according to Embodiment 2 of the present invention;

[0024] Figure 3 is a schematic diagram of the structure of a target tracking device provided according to Embodiment 3 of the present invention;

[0025] Figure 4 It is a schematic diagram of the structure of a camera for implementing the target tracking method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1A flow chart of a target tracking method is provided for the first embodiment of the present invention. This embodiment is applicable to the case of tracking a target. The method can be executed by a target tracking device. The target tracking device can be implemented in the form of hardware and / or software. The target tracking device can be configured in a camera. Figure 1 As shown, the method includes:

[0030] S110: When at least two tracking targets are detected in a preset detection area, determine the change amount of the motion content of each tracking target in real time.

[0031] Among them, the preset detection area can be the monitoring area of ​​the camera, the detection area of ​​the radar, or the detection area preset by the user. Exemplarily, the spatial coordinates of the radar set in the three-dimensional scene are (X, Y, Z), whereby the point coordinates O (X, Z) obtained by projecting the radar observation point to the ground, with this point O as the center and R as the radius, is the preset detection area. Among them, R can be controlled by the tracking height Y set by the user in combination with a proportional constant, such as R = m*Y, (m is a constant). The advantage of such a setting is that it can avoid detecting and tracking all targets, such as filtering out high-altitude targets, such as birds, to facilitate tracking of targets that users are more concerned about. Exemplarily, the radar detection area can be used for target detection by radar equipment, and the number of tracking targets in the radar detection area is determined according to the radar detection data. When at least two tracking targets are detected in the radar detection area, the change in the action content of each tracking target is determined in real time.

[0032] In the embodiment of the present invention, the amount of change in the action content can be understood as the action change information of the tracking target, and the amount of change in the action content can be associated with the volume size, movement speed and behavior action of the tracking target. Optionally, the amount of change in the action content of each tracking target is determined in real time, including: for each tracking target, determining the first feature information of the current tracking target in real time, and determining the amount of change in the action content of the current tracking target according to the first feature information; wherein the first feature information includes at least one of the volume size, movement speed and behavior type.

[0033] Exemplarily, the change amount of the motion content of each tracking target can be determined according to any one of the volume size, moving speed and behavior type of each tracking target, and the change amount of the motion content of each tracking target can also be determined according to any two of the volume size, moving speed and behavior type of each tracking target. Optionally, the volume size, moving speed and behavior type of each tracking target are determined in real time, and the change amount of the motion content of each tracking target is determined according to the volume size, moving speed and behavior type of each tracking target. Among them, the volume size of the tracking target can be identified when the tracking target enters the preset area detection, and the volume size of the tracking target is fixed, so the volume size of the tracking target is a constant C. The moving speed of the tracking target can be calculated by the following formula. Assuming that the position coordinates of the tracking target P at time N are (x, y), and at N+t, the position coordinates of the tracking target P are (x', y'), then the moving distance of the tracking target P in the time period t is Therefore, the moving speed of the tracking target is The behavior types of the tracked target may include area intrusion, height detection, standing detection, reverse detection, violent movement and fast movement, etc. Specifically, the size, movement speed and behavior type of each tracked target can be determined through radar detection data. Among them, the movement speed of the tracked target can change in real time over time, and the behavior type of the tracked target can be the same or different at different time points.

[0034] Exemplarily, the volume size, moving speed and behavior type of the tracking target can be input into a pre-trained action content change determination model, and the action content change of the tracking target can be determined based on the output result of the action content change determination model. The action content change determination model is a pre-trained machine learning model. Optionally, the action content change of the current tracking target is determined based on the first feature information, including: obtaining a correspondence between a preset behavior type and a behavior score; determining the behavior score of the current tracking target based on the behavior type and the correspondence; determining the action content change of the current tracking target based on the volume size, the moving speed and the behavior score. Users can set the behavior scores corresponding to different behavior types according to real scenarios, thereby forming a correspondence between behavior types and behavior scores, wherein the sum of the behavior scores corresponding to all behavior types that may be involved in the tracking target can be set to 100 points. Table 1 is a table of correspondence between behavior types and behavior scores provided in an embodiment of the present invention:

[0035] Table 1 Correspondence between behavior types and behavior scores

[0036]

[0037] The behavior score of the current tracking target is determined based on the correspondence between the pre-set behavior type and the behavior score and the behavior type of the tracking target. Among them, the behavior type of the tracking target can be all the behavior types involved in the tracking target in the time period from the preset starting time point to the current time point. The behavior type of the tracking target can be one or more. The embodiment of the present invention does not limit the number of behavior types of the tracking target. When there are multiple behavior types of the tracking target, the behavior score of the tracking target is the sum of the behavior scores corresponding to each behavior type of the tracking target. According to the volume size, moving speed and behavior score of the tracking target, the change in the action content of the current tracking target is determined. For example, the change in the action content of the tracking target can be the sum of the volume size, moving speed and behavior score of the tracking target.

[0038] Optionally, the change in the action content of the current tracking target is determined based on the volume size, the moving speed and the behavior score, including: calculating the change in the action content of the current tracking target according to the following formula: T = ∫f(t)dt = ∫(k1*C+k2*V+k3*S)dt; wherein T represents the change in the action content of the current tracking target, f(t) represents the change in the action of the current tracking target within time t, C represents the volume size, V represents the moving speed, S represents the behavior score, and k1, k2, and k3 are coefficient constants, respectively. Among them, the coefficient constants k1, k2, and k3 can be the weight values ​​set by the user for the volume size, moving speed, and behavior score, respectively, according to the scenario. The change in the action content of the tracking target can be understood as the cumulative sum of the change in the action content of the tracking target at each time point in the time period from the preset initial time t0 to the current time point t1. Therefore,

[0039] Optionally, the change amount of the action content of each tracking target is determined according to any two quantities of the volume size, moving speed and behavior type of each tracking target, including: for each tracking target, the weighted sum of any two quantities of the volume size, moving speed and behavior type of the current tracking target is used as the change amount of the action content of the current tracking target. Exemplarily, when the change amount of the action content of the current tracking target is determined according to the volume size and moving speed of the current tracking target, it can be calculated according to the following formula: T = k4*C+k5*V, where C is the volume size of the current tracking target, V represents the moving speed of the current tracking target, k4 represents the weight occupied by the volume size, and k5 represents the weight occupied by the moving speed.

[0040] S120, determining the tracking priority and tracking duration of each tracking target according to the change amount of the action content of each tracking target, wherein the greater the change amount of the action content, the higher the corresponding tracking priority and the longer the tracking duration.

[0041] In the embodiment of the present invention, the greater the change in the action content of the tracking target, the higher the possibility that the tracking target is in an emergency situation with respect to the intrusion area, or the higher the possibility that personnel are required to check it. Therefore, the tracking priority of the tracking target is determined according to the change in the action content of the tracking target, wherein the greater the change in the action content, the higher the tracking priority of the corresponding tracking target, and the longer the tracking time.

[0042] Optionally, the tracking priority of each tracking target is determined separately according to the change in action content of each tracking target, including: when there are at least two second targets with the same change in action content among the tracking targets, the target information of each second target is determined; wherein the target information is feature information determined from second feature information; the second feature information includes at least one of a behavior score, a volume size, a moving speed and a distance from a previous tracking target; according to the target information of each second target, the tracking priority and tracking duration of each second target are determined separately; wherein, the larger the target information, the higher the corresponding tracking priority and the longer the tracking duration.

[0043] Exemplarily, when there are two or more tracking targets with the same amount of change in action content among each tracking target, the tracking target with the same amount of change in action content is used as the second target. Determine the target information of each second target, and determine the tracking priority and tracking duration of each second target according to the size of the target information of each second target, wherein the larger the target information, the higher the tracking priority corresponding to the second target, and the longer the tracking duration. The target information is any one of the behavior score, volume size, moving speed, and distance from the previous tracking target. For example, the behavior score is used as the target information. Among the five tracking targets A, B, C, D, and E, the action content changes of the tracking targets B, C, and D are the same, then the behavior scores of B, C, and D are determined respectively, and the tracking priority and tracking duration of B, C, and D are determined according to the size of the behavior scores.

[0044] Optionally, the target information may also be feature information determined from the second feature information in order of priority from high to low; the second feature information includes the behavior score, volume size, moving speed and distance from the last tracked target in descending order of priority; when there are at least two targets with the largest target information in the second target, the feature information of the next priority in the second feature information is used as the target information. For example, if the behavior scores of B and C are the same among B, C and D, the volume scores of B and C are obtained respectively, and the tracking priority and tracking duration of B and C are determined according to the volume scores, and so on.

[0045] S130 , tracking corresponding tracking targets based on the tracking duration in descending order of tracking priority.

[0046] In the embodiment of the present invention, the corresponding tracking targets can be tracked for different time lengths in order of tracking priority from high to low, wherein the higher the tracking priority, the longer the corresponding tracking time length. For example, the tracking time length of the corresponding tracking target can be determined according to the change amount of the action content of each tracking target, wherein the greater the change amount of the action content, the longer the tracking time length of the corresponding tracking target. For example, assuming that the time length set by the camera for a single tracking is L, that is, within the time L, each tracking target needs to be tracked in turn, assuming that there are tracking targets A, B, C, and D in the radar detection area within the same period of time, for any tracking target, the tracking time is L / 4 on average, because the action content of each tracking target changes with time, the target has an emergency situation in the invasion area, or the possibility that personnel need to check is higher, if the action change of the tracking target in the invasion area remains basically unchanged, then its importance and priority in this time period are lower, so the camera can be made to track the tracking target for a shorter time, and the tracking priority is lower, so that the tracking target with a high change amount of action content in the preset detection area has a high tracking priority and a long tracking time.

[0047] The target tracking method of the embodiment of the present invention, when at least two tracking targets are detected in a preset detection area, determines the change amount of the action content of each tracking target in real time; determines the tracking priority and tracking duration of each tracking target according to the change amount of the action content of each tracking target, wherein the greater the change amount of the action content, the higher the corresponding tracking priority and the longer the tracking duration; and tracks the corresponding tracking targets in order from high to low tracking priority based on the tracking duration. Through the technical solution provided by the embodiment of the present invention, the tracking priority and tracking duration of the tracking target can be determined according to the change amount of the action content of the tracking target, so that the tracking of the target is more targeted.

[0048] In some embodiments, the corresponding tracking targets are tracked in descending order of tracking priority based on the tracking duration, including: in the process of tracking the first target with the highest tracking priority, the latest action content change of each tracking target is obtained in real time; among the latest action content change of each tracking target, it is determined whether the latest action content change of the first target is the largest, and if so, the tracking duration of the first target is re-determined, and the first target is continued to be tracked based on the re-determined tracking duration.

[0049] For example, tracking targets A, B, C, and D are detected in the radar detection area, and the change amounts of the action contents of tracking targets A, B, C, and D determined at the current time are T and A 、T B 、T C 、T D , if T A >T B >T C >T D ,Obviously, the tracking target A has the highest tracking priority. Therefore, the tracking target A can be taken as the first target, and the camera will prioritize tracking the first target A. In the process of tracking the first target A, the latest action content changes of the tracking targets A, B, C, and D are obtained in real time. If the latest action content changes of the tracking targets A, B, C, and D are T' respectively A , T' B , T' C , T' D If the latest action content change T' A , T' B , T' C , T' D Middle T' A Maximum, the tracking time of the tracking target A is redetermined, and the tracking target A is continued to be tracked based on the redetermined tracking time. Among them, the redetermined tracking time of the first target may be greater than the tracking time originally configured for the first target, or may be less than the tracking time originally configured. For example, the tracking time of the first target may be redetermined based on the latest change in the action content of each tracking target, or the tracking time may be delayed based on the tracking time originally configured for the first target. When continuing to track the first target based on the redetermined tracking time, it may be that after the tracking of the first target reaches the originally configured tracking time, the tracking of the first target continues for the redetermined tracking time, or it may be that when it is determined that the latest change in the action content of the first target is still the maximum, the tracking of the first target continues for the redetermined tracking time.

[0050] Optionally, the corresponding tracking targets are tracked in order from high to low tracking priority based on the tracking time, including: in the process of tracking the first target with the highest tracking priority, obtaining the current latest action content change of each tracking target in real time; among the latest action content change of each tracking target, judging whether the latest action content change of the first target is the largest, and if so, continuing to track the first target until the continuous tracking time of the first target reaches a second preset time, reducing the tracking priority of the first target to the lowest, and tracking the target with the largest latest action content change among the third targets as the new target, until the sum of the tracking time of each tracking target reaches a third preset time, or, completing the tracking of each tracking target once; wherein, the third target is the target other than the first target among the tracking targets currently detected in the preset detection area.

[0051] For example, if the latest change in the action content of the first target A is still the largest, the first target A will continue to be tracked until the continuous tracking time of the first target A reaches the first preset time. At this time, the tracking priority of the first target A is reduced to the lowest (to level 4), and the camera switches the tracking target from the first target A to other tracking targets. The first preset time can be understood as the maximum tracking time of the first target A, t max The advantage of such a setting is that it prevents the camera from continuously tracking only a single target. In an embodiment of the present invention, when the continuous tracking time of the first target A reaches the first preset time, the target with the largest latest action content change among the third targets is tracked as the new target. Because the camera has reduced the tracking priority of the first target A to the lowest before switching to the new target for tracking, and the updated action content change of the new target after switching is the largest, the tracking priority of the new target after switching is the highest at this time. The new target after switching can be used as the first target with the highest tracking priority. In the process of tracking the first target with the highest tracking priority, the operation of obtaining the latest action content change of each tracking target in real time is repeatedly performed until the sum of the tracking time of each tracking target reaches the second preset time, or each tracking target is tracked once. At this time, a new round of calculation of the action content change of each tracking target in the preset detection area is started. For example, if the new target is tracking target B, the new first target B can be tracked in the same way as the first target A. After the tracking of the new first target B is completed, the tracking priority of target A can be adjusted to level 3, and the tracking priority of target B can be reduced to the lowest level 4, and so on.

[0052] It should be noted that the third target is the tracking target other than the first target among all the tracking targets currently detected in the preset detection area. Since the tracking targets detected in the preset detection area at different time points may be the same or different, the third target may be the tracking targets B, C, D other than the first target A (that is, the tracking target currently detected in the preset detection area remains unchanged from before), or the tracking targets B, C, D, E (that is, the original tracking target is currently retained in the preset detection area and a new tracking target is detected), or the tracking targets B, D, F (that is, the original tracking target C in the preset detection area is removed and a new tracking target is detected).

[0053] In some embodiments, among the latest action content changes of the tracking targets, if the latest action content change of the first target is not the largest, then the tracking priority and tracking duration of each tracking target are re-determined based on the latest action content change of each tracking target, and the tracking of the first target with the highest tracking priority is returned to be executed. A , T' B , T' C , T' D Middle T' A If it is not the largest, then based on the latest change in the motion content of each tracking target T' A , T' B , T' C , T' D , re-determine the tracking priority and tracking duration of the tracking targets A, B, C, and D. The greater the latest change in the action content, the greater the tracking priority and the longer the tracking duration. For example, T' C >T' B >T' A >T' D , then the tracking priorities of tracking targets C, B, A, and D decrease in sequence. Obviously, the tracking priority of tracking target C is the highest at this time, so tracking target C is taken as the first target, and the execution returns to track the first target with the highest tracking priority, and the tracking duration of target C is the newly determined tracking duration.

[0054] In some embodiments, the target with the largest change in action content after update among the third targets is tracked as a new target, including: when there are at least two fourth targets with the largest change in action content after update among the third targets, determining the target information of each fourth target; wherein the target information is feature information determined from the second feature information in order of priority from high to low; the second feature information includes the behavior score, volume size, moving speed and distance from the last tracked target in descending order of priority; the target with the largest target information among the fourth targets is tracked as a new target; wherein, when there are at least two targets with the largest target information among the fourth targets, the feature information of the next priority in the second feature information is used as the target information.

[0055] In an embodiment of the present invention, when there is one fourth target with the largest change in action content after update in the third target, the fourth target (the tracking target with the largest change in action content after update in the third target) can be directly tracked as a new target. When there are multiple fourth targets with the largest change in action content after update in the third target, a fourth target can be randomly selected as a new target for tracking. Optionally, when there are multiple fourth targets, the behavior scores of each fourth target can be determined respectively, and the tracking target with the largest behavior score among the fourth targets can be tracked as a new target. When there is one fifth target with the largest behavior score among the fourth targets, the fifth target can be directly tracked as a new target. When there are multiple fifth targets (the tracking target with the largest behavior score among the fourth targets), a fifth target can be randomly selected as a new target for tracking. Optionally, when there are multiple fifth targets, the volume size of each fifth target can be determined respectively, and the tracking target with the largest volume size among the fifth targets can be tracked as a new target. When there are one sixth target with the largest volume size among the fifth targets, the sixth target with the largest volume size can be directly tracked as a new target. When there are multiple sixth targets, a sixth target can be randomly selected as a new target for tracking. Optionally, when there are multiple sixth targets, the moving speed of each sixth target can be determined respectively, and the tracking target with the fastest moving speed among the sixth targets can be tracked as a new target. When there is only one seventh target with the fastest moving speed among the sixth targets, the seventh target can be directly tracked as a new target. When there are multiple seventh targets, a seventh target can be randomly selected as a new target to track. Optionally, when there are multiple seventh targets, the distance between each seventh target and the previous tracking target can be determined respectively, and the tracking target among the seventh targets that is closest to the previous tracking target can be tracked as a new target. Among them, when there are multiple eighth targets among the seventh targets that are closest to the previous tracking target, an eighth target can be randomly selected as a new target to track.

[0056] Exemplarily, the third target includes tracking targets B, C, and D, and the updated action content changes of tracking targets B, C, and D are T' respectively. B , T' C , T' D , if T' B With T' C The difference is within the preset range and is greater than T' D , it can be considered that T' B =T' C >T' D , then one of the tracking targets B and C is selected for tracking first, and the behavior score of tracking target B is compared. B and the behavior score of tracking target C C The target with the largest behavior score among tracking targets B and C is tracked as the new tracking target. B With Score C If the difference is within the preset range, then Score B =Score C , the volume of tracking targets B and C is compared, and the larger one is tracked as the new target. If the volume difference between tracking targets B and C is also within the set threshold, the distance between tracking targets B and C and the previous tracking target A is determined respectively, and the tracking target closest to tracking target A is tracked as the new target. This can minimize the rotation of the camera, thereby protecting the camera's pan / tilt.

[0057] In some embodiments, the corresponding tracking targets are tracked based on the tracking duration in order of tracking priority from high to low, including: judging whether the change in action content of the tracking target corresponding to the current tracking priority is less than a preset action content threshold in order of tracking priority from high to low; when the change in action content of the current tracking target corresponding to the current tracking priority is less than the preset action content threshold, continuously tracking the current tracking target for a preset duration, wherein the preset duration is greater than the tracking duration corresponding to the current tracking target.

[0058] Within the preset tracking time period L, if the change in the motion content of each tracking target is very small, the tracking time for each tracking target will become smaller and smaller, and finally the time may approach zero, resulting in the phenomenon that the camera switches back and forth to track the target, which is easy to damage the camera. Therefore, according to the order of tracking priority from high to low, it is determined whether the change in the motion content of the tracking target corresponding to the current tracking priority is less than the preset motion content threshold. If so, it means that the change in the motion content of the current tracking target is very small. In order to avoid the situation where the camera switches back and forth to track the target, the current tracking target is continuously tracked for a preset time, where the preset time can be understood as the minimum tracking time for continuously tracking the current tracking target.

[0059] In some embodiments, before tracking the first target with the highest tracking priority, it also includes: determining whether the change in action content of the first target is less than a preset action content threshold; in the process of tracking the first target with the highest tracking priority, obtaining the current latest action content change of each tracking target in real time, including: when the change in action content of the first target is less than the preset action content threshold, continuously tracking the first target for a third preset time period, and in the tracking process after the continuous tracking time of the first target reaches the third preset time period, obtaining the current latest action content change of each tracking target in real time.

[0060] Similarly, within the preset tracking time period L, if the change in the motion content of each tracking target is very small, the tracking time for each tracking target will become smaller and smaller, and finally the time may approach zero, resulting in the phenomenon that the camera switches back and forth to track the target, which is easy to damage the camera. Therefore, before tracking the first target with the highest tracking priority, it is determined whether the change in the motion content of the first target with the highest tracking priority is less than the preset motion content threshold. If so, it means that the change in the motion content of each tracking target is very small. In order to avoid the situation where the camera switches back and forth to track the target, the first target is continuously tracked for the third preset time length, where the third preset time length can be understood as the minimum tracking time length t for continuously tracking the first target. min When the continuous tracking time of the first target reaches the third preset time, the latest action content change amount of each tracking target is obtained in real time, so as to switch to a new target for tracking according to the latest action content change amount.

[0061] In some embodiments, in the process of continuously tracking the first target for a third preset time, when an alarm event of the first target is detected, the third preset time is updated; wherein the updated third preset time is greater than the third preset time before the update. In the process of continuously tracking the first target for a third preset time, if an alarm event of the first target is detected, it means that the user may pay more attention to the motion trajectory of the first target. At this time, the third preset time is increased. It should be noted that the embodiment of the present invention does not limit the increase in the third preset time, which can be a random time. Optionally, when an alarm event of the first target is detected, updating the third preset time includes: when an alarm event of the first target is detected, determining the alarm level of the alarm event; determining the duration increment of the third preset time according to the alarm level, and updating the third preset time according to the duration increment. Exemplarily, in the process of continuously tracking the first target for a third preset time, if an alarm event of the first target is detected, the alarm level of the alarm event is determined, and the duration increment of the third preset time is determined according to the alarm level, wherein the higher the alarm level, the larger the duration increment. Then, the third preset time length is updated according to the time length increment. It can be understood that when an alarm event of the first target is detected, the continuous tracking time length of the first target is increased, thereby better meeting user needs.

[0062] Embodiment 2

[0063] Figure 2 A flow chart of a target tracking method provided in Embodiment 2 of the present invention is shown in FIG. Figure 2 As shown, the method includes:

[0064] S210: When at least two tracking targets are detected in the preset detection area, first feature information of the current tracking target is determined in real time for each tracking target, wherein the first feature information includes volume size, moving speed, and behavior type.

[0065] S220: Determine the behavior score of the current tracking target according to the behavior type and the pre-set correspondence between the behavior type and the behavior score.

[0066] S230: Determine the change in the action content of the current tracking target according to the volume, movement speed and behavior score.

[0067] S240, determining the tracking priority and tracking duration of each tracking target according to the change amount of the action content of each tracking target, wherein the greater the change amount of the action content, the higher the corresponding tracking priority and the longer the tracking duration.

[0068] S250: Track a first target with the highest tracking priority based on the corresponding tracking duration, and in the process of tracking the first target, obtain the latest action content change of each tracking target in real time.

[0069] S260. Among the latest changes in the motion contents of the various tracking targets, determine whether the latest change in the motion contents of the first target is the largest. If so, execute S270; otherwise, execute S280.

[0070] S270: Re-determine the tracking time of the first target, and continue to track the first target based on the re-determined tracking time.

[0071] S280 , re-determine the tracking priority and tracking duration of each tracking target based on the latest change in the action content of each tracking target, and return to execute S250 .

[0072] The target tracking method of the embodiment of the present invention can update the change in the action content of the tracking target in real time, and adjust the tracking order and tracking duration of the target according to the updated change in the action content, so that the tracking order and tracking duration of the target are more targeted.

[0073] Embodiment 3

[0074] Figure 3 This is a schematic diagram of the structure of a target tracking device provided by Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0075] The motion content change amount determination module 310 is used to determine the motion content change amount of each tracking target in real time when at least two tracking targets are detected in a preset detection area;

[0076] A tracking priority determination module 320, for determining the tracking priority and tracking duration of each tracking target according to the change amount of the action content of each tracking target, wherein the greater the change amount of the action content, the higher the corresponding tracking priority and the longer the tracking duration;

[0077] The target tracking module 330 is used to track the corresponding tracking targets based on the tracking duration in descending order of tracking priority.

[0078] Optionally, the action content change amount determination module includes:

[0079] The action content change amount determination unit determines, for each tracking target, first feature information of the current tracking target in real time, and determines the action content change amount of the current tracking target according to the first feature information; wherein the first feature information includes at least one of volume size, movement speed and behavior type.

[0080] Optionally, the action content change amount determining unit includes:

[0081] A corresponding relationship acquisition subunit is used to acquire the corresponding relationship between the preset behavior type and the behavior score;

[0082] A behavior score determination subunit, configured to determine a behavior score of the current tracking target according to the behavior type and the corresponding relationship;

[0083] The action content change amount determining subunit is used to determine the action content change amount of the current tracking target according to the volume size, the moving speed and the behavior score.

[0084] Optionally, the target tracking module includes:

[0085] An action content change amount updating unit, used for obtaining the latest action content change amount of each tracking target in real time during the process of tracking the first target with the highest tracking priority based on the corresponding tracking duration;

[0086] The first target continuous tracking unit is used to determine whether the latest action content change of the first target is the largest among the latest action content changes of the various tracking targets. If so, re-determine the tracking time of the first target and continue to track the first target based on the re-determined tracking time.

[0087] Optionally, the device further comprises:

[0088] The tracking priority redetermining module is used to redetermine the tracking priority and tracking duration of each tracking target based on the latest action content change of each tracking target, if the latest action content change of the first target is not the largest among the latest action content change of each tracking target, and return to execute tracking of the first target with the highest tracking priority.

[0089] Optionally, the tracking priority determination module is used to:

[0090] When there are at least two second targets with the same amount of change in action content among the tracking targets, target information of each second target is determined; wherein the target information is feature information determined from the second feature information; the second feature information includes at least one of a behavior score, a volume size, a moving speed, and a distance from a previous tracking target;

[0091] According to the target information of each second target, the tracking priority and tracking duration of each second target are determined respectively; wherein, the larger the target information, the higher the corresponding tracking priority and the longer the tracking duration.

[0092] Optionally, the target tracking module is used to:

[0093] According to the order of tracking priority from high to low, determine whether the change amount of the action content of the tracking target corresponding to the current tracking priority is less than the preset action content threshold;

[0094] When the change amount of the action content of the current tracking target corresponding to the current tracking priority is less than the preset action content threshold, the current tracking target is continuously tracked for a preset time period, wherein the preset time period is greater than the tracking time period corresponding to the current tracking target.

[0095] The target tracking device provided by the embodiment of the present invention can execute the target tracking method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0096] Embodiment 4

[0097] Figure 4 A schematic diagram of a camera 10 that can be used to implement an embodiment of the present invention is shown. The camera is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The camera can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0098] like Figure 4 As shown, the camera 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the camera 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0099] A number of components in the camera 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the camera 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0100] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a target tracking method.

[0101] In some embodiments, the target tracking method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the camera 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the target tracking method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the target tracking method in any other suitable manner (e.g., by means of firmware).

[0102] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0103] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0104] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0105] To provide interaction with a user, the systems and techniques described herein can be implemented on a camera having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the camera. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0106] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0107] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0108] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0109] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A target tracking method, characterized in that: include: When at least two tracking targets are detected in a preset detection area, a change amount of the motion content of each tracking target is determined in real time; According to the change amount of the action content of each tracking target, the tracking priority and tracking duration of each tracking target are determined respectively, wherein the greater the change amount of the action content, the higher the corresponding tracking priority and the longer the tracking duration; In descending order of tracking priority, corresponding tracking targets are tracked based on the tracking duration.

2. The method according to claim 1, characterized in that Determining in real time the amount of change in the content of the action of each tracking target, including: For each tracking target, first feature information of the current tracking target is determined in real time, and a change amount of the action content of the current tracking target is determined according to the first feature information; wherein the first feature information includes at least one of volume size, moving speed and behavior type.

3. The method according to claim 2, characterized in that Determining the change amount of the action content of the current tracking target according to the first feature information includes: Obtaining the correspondence between the pre-set behavior type and the behavior score; Determining a behavior score of the current tracking target according to the behavior type and the corresponding relationship; The amount of change in the action content of the current tracking target is determined according to the volume size, the moving speed, and the behavior score.

4. The method according to claim 1, characterized in that: In descending order of tracking priority, the corresponding tracking targets are tracked based on the tracking duration, including: In the process of tracking the first target with the highest tracking priority based on the corresponding tracking duration, obtaining the latest action content change amount of each tracking target in real time; Among the latest action content changes of the tracking targets, determine whether the latest action content change of the first target is the largest. If so, redetermine the tracking time of the first target and continue to track the first target based on the redetermined tracking time.

5. The method according to claim 4, characterized in that Also includes: Among the latest action content changes of each tracking target, if the latest action content change of the first target is not the largest, the tracking priority and tracking duration of each tracking target are re-determined based on the latest action content change of each tracking target, and return to track the first target with the highest tracking priority.

6. The method according to claim 1, characterized in that Determining the tracking priority of each tracking target according to the change amount of the action content of each tracking target, including: When there are at least two second targets with the same amount of change in action content among the tracking targets, target information of each second target is determined; wherein the target information is feature information determined from the second feature information; the second feature information includes at least one of a behavior score, a volume size, a moving speed, and a distance from a previous tracking target; According to the target information of each second target, the tracking priority and tracking duration of each second target are determined respectively; wherein, the larger the target information, the higher the corresponding tracking priority and the longer the tracking duration.

7. The method according to claim 1, characterized in that In descending order of tracking priority, the corresponding tracking targets are tracked based on the tracking duration, including: According to the order of tracking priority from high to low, determine whether the change amount of the action content of the tracking target corresponding to the current tracking priority is less than the preset action content threshold; When the change amount of the action content of the current tracking target corresponding to the current tracking priority is less than the preset action content threshold, the current tracking target is continuously tracked for a preset time period, wherein the preset time period is greater than the tracking time period corresponding to the current tracking target.

8. A target tracking device, characterized in that: include: An action content change amount determination module, used to determine the action content change amount of each tracking target in real time when at least two tracking targets are detected in a preset detection area; A tracking priority determination module, used to determine the tracking priority and tracking duration of each tracking target according to the change amount of the action content of each tracking target, wherein the greater the change amount of the action content, the higher the corresponding tracking priority and the longer the tracking duration; The target tracking module is used to track the corresponding tracking targets based on the tracking duration in descending order of tracking priority.

9. A camera, characterized in that: The camera comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the target tracking method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the target tracking method according to any one of claims 1 to 7 when executed.

Citation Information

Patent Citations

  • An abnormal target early warning tracking system and method based on behavior characteristic intelligent analysis

    CN109829382A

  • Abnormal object monitoring method and device for vehicle-mounted monitoring

    CN115359434A

  • Object tracking display method, device and system, storage medium and electronic device

    CN115984774A

  • Target tracking method and device

    CN116188537A

  • Forestry information management systems and methods streamlined by automatic biometric data prioritization

    US20170103263A1

Cited By

  • Object tracking method and system, electronic equipment, storage medium and program product

    CN120993400A