Monitoring method and device based on target tracking, equipment and medium

Abstract

The invention relates to the technical field of monitoring, in particular to a monitoring method and device based on target tracking, equipment and a medium, and the method comprises the steps: judging whether a monitoring target moves from a first monitoring region of a first monitoring camera to a common monitoring region of the first monitoring camera and a second monitoring camera or not; if yes, judging whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera; if yes, improving the monitoring quality of the second monitoring camera to a preset quality standard; and in response to the monitoring quality of the second monitoring camera reaching the preset quality standard, controlling the second monitoring camera as a main monitoring camera for monitoring the target. According to the method and the device, the problems that in the prior art, when a camera monitors and tracks and monitors a specific target, the view angle becomes poor when a main monitoring camera is switched, and in a complex scene, due to the fact that the view angle becomes poor, the tracking target is lost easily are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of monitoring, in particular to a monitoring method and device based on target tracking, equipment and medium. BACKGROUND

[0002] In the prior art, when monitoring a target, multiple cameras are usually arranged to track and monitor the target in linkage, and the switching control of the cameras is performed by judging whether the target moves to the overlapping area of the cameras, for example, a Chinese invention patent with the publication date of January 17, 2020 and the publication number of CN107666590B discloses a target monitoring method, camera, controller and target monitoring system, which triggers the switching of the cameras when the position of the target in the first monitoring picture is in the overlapping area. Another example is a Chinese invention patent with the publication date of May 30, 2025 and the publication number of CN120075592A, which discloses a multi-camera tracking linkage control method, device, terminal and medium, which also transfers the tracking permission to the adjacent camera when the target moves to the overlapping monitoring grid area of the adjacent camera.

[0003] However, the above conventional method has disadvantages. Due to the differences in angle parameters and real-time environment, the monitoring quality of different cameras has a large gap, and in order to save energy consumption, the cameras usually adopt a low-power and low-resolution mode for monitoring. This mode can meet the daily ordinary monitoring needs, but when tracking and monitoring a specific target, if it is temporarily switched to the main monitoring camera, the low-power monitoring mode may cause the angle of view and the monitoring picture to be poor when switching the main monitoring camera, and in a complex scene, the tracking target may be lost due to the poor angle of view and the monitoring picture. SUMMARY

[0004] Therefore, it is necessary to provide a monitoring method, device, equipment and medium based on target tracking to solve the problem that in the prior art, when monitoring a target, the cameras adopt a low-power and low-resolution mode for monitoring in order to save energy consumption, and when tracking and monitoring a specific target, the low-resolution monitoring mode may cause the angle of view to be poor when switching the main monitoring camera, and in a complex scene, the tracking target may be lost due to the poor angle of view.

[0005] The technical scheme of the present application is as follows: A monitoring method based on target tracking, the method comprising: judging whether a monitoring target moves from a first monitoring area of a first monitoring camera to a common monitoring area of the first monitoring camera and a second monitoring camera; if the judgment is yes, judging whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera. if the judgment is yes, improving the monitoring quality of the second monitoring camera to a preset quality standard; in response to the monitoring quality of the second monitoring camera reaching the preset quality standard, controlling the second monitoring camera to be the main monitoring camera for the monitoring target.

[0006] Optionally, judging whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera comprises: calculating a first monitoring quality of the first monitoring camera; calculating a second monitoring quality of the second monitoring camera; judging whether the first monitoring quality is greater than the second monitoring quality.

[0007] Optionally, calculating the first monitoring quality of the first monitoring camera comprises: extracting a region of interest containing the monitoring target from a monitoring picture of the first monitoring camera; calculating monitoring feature scores of monitoring quality features based on the region of interest; weighting and calculating each monitoring feature score to obtain an instantaneous view angle quality; time-smoothing the instantaneous view angle quality to generate the first monitoring quality.

[0008] Optionally, improving the monitoring quality of the second monitoring camera to a preset quality standard comprises: calculating a monitoring quality difference between the first monitoring camera and the second monitoring camera; according to the monitoring quality difference, improving the pixel height and the definition of the second monitoring camera and reducing the occlusion rate of the second monitoring camera.

[0009] Optionally, the common monitoring area comprises a first area and a second area with the same area, and the distance between the center of the first area and the center of the first monitoring area is less than the distance between the center of the second area and the center of the first monitoring area. if the judgment is yes, improving the monitoring quality of the second monitoring camera to a preset quality standard; judging whether the monitoring target moves from the first area to the second area in the common monitoring area; if the judgment is no, keeping the first monitoring camera as the main monitoring camera for the monitoring target; if the judgment is yes, judging whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera.

[0010] Optionally, the method further comprises: when it is detected that the monitoring target completely enters or is about to enter a second main area, and the monitoring quality of the second monitoring camera does not reach a preset quality standard, wherein the second main area is an area in the second monitoring area except the common monitoring area; controlling the second monitoring camera to be the main monitoring camera of the monitoring target, and setting a degradation switching mark; according to the degradation switching mark, improving the monitoring quality of the second monitoring camera to no less than a preset minimum monitoring parameter.

[0011] Optionally, the method further comprises: testing the first monitoring camera when monitoring according to a plurality of preset groups of debugging parameters, and generating a plurality of debugging results; obtaining a critical control parameter according to each of the debugging results; upgrading the critical control parameter according to a preset margin to generate a minimum monitoring parameter.

[0012] Optionally, the method further comprises: in response to controlling the second monitoring camera to be the main monitoring camera of the monitoring target, generating a backup monitoring instruction; controlling the first monitoring camera to monitor the monitoring target according to a preset backup monitoring time according to the backup monitoring instruction, and generating backup monitoring data; storing the backup monitoring data.

[0013] Optionally, a monitoring device based on target tracking is also provided, and the device comprises: a target moving area judgment module, configured to judge whether a monitoring target moves from a first monitoring area of a first monitoring camera to a common monitoring area of the first monitoring camera and a second monitoring camera; a target monitoring quality judgment module, configured to, if the judgment is yes, judge whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera; a target monitoring quality improvement module, configured to, if the judgment is yes, improve the monitoring quality of the second monitoring camera to a preset quality standard; a target monitoring main body switching module, configured to, in response to the monitoring quality of the second monitoring camera reaching the preset quality standard, control the second monitoring camera to be the main monitoring camera of the monitoring target.

[0014] Optionally, the target monitoring quality judgment module is further configured to: calculate a first monitoring quality of the first monitoring camera; calculate a second monitoring quality of the second monitoring camera; and judge whether the first monitoring quality is greater than the second monitoring quality.

[0015] Optionally, the target monitoring quality determining module is further configured to: extract a region of interest containing the monitoring target from a monitoring image of the first monitoring camera; calculate monitoring feature scores of monitoring quality features based on the region of interest; calculate an instantaneous visual angle quality by weighting the monitoring feature scores; and generate the first monitoring quality by time smoothing the instantaneous visual angle quality.

[0016] Optionally, the target monitoring quality improving module is further configured to: calculate a monitoring quality difference between the first monitoring camera and the second monitoring camera; and improve a pixel height and a definition of the second monitoring camera and reduce an occlusion rate of the second monitoring camera according to the monitoring quality difference.

[0017] Optionally, the common monitoring area includes a first area and a second area with the same area, and a distance between a center of the first area and a center of the first monitoring area is less than a distance between a center of the second area and the center of the first monitoring area; and the target monitoring quality determining module is further configured to: determine whether the monitoring target moves from the first area to the second area in the common monitoring area; if no, maintain the first monitoring camera as the main monitoring camera of the monitoring target; and if yes, determine whether the first monitoring camera is greater than the second monitoring camera in monitoring quality.

[0018] Optionally, the target monitoring subject switching module is further configured to: when detecting that the monitoring target completely enters or is about to enter a second main area and monitoring quality of the second monitoring camera does not reach a preset quality standard, wherein the second main area is an area of the second monitoring area except the common monitoring area; control the second monitoring camera as the main monitoring camera of the monitoring target and set a downgrade switching flag; and improve the monitoring quality of the second monitoring camera by no less than a preset minimum monitoring parameter according to the downgrade switching flag.

[0019] Optionally, the target monitoring subject switching module is further configured to: test the first monitoring camera according to a plurality of preset groups of debugging parameters and generate a plurality of groups of debugging results; obtain critical control parameters according to the groups of debugging results; and upgrade the critical control parameters according to a preset margin to generate the minimum monitoring parameter.

[0020] Optionally, the target monitoring subject switching module is further configured to: in response to controlling the second monitoring camera as the main monitoring camera of the monitoring target, generate a backup monitoring instruction; control the first monitoring camera to monitor the monitoring target according to a preset backup monitoring time and generate backup monitoring data according to the backup monitoring instruction; and store the backup monitoring data.

[0021] Optionally, a computer device is also provided, comprising a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above-mentioned target tracking-based monitoring method when executing the computer program.

[0022] Optionally, a computer readable storage medium is also provided, which stores a computer program, and the computer program implements the steps of the above-mentioned target tracking-based monitoring method when executed by a processor.

[0023] The present application achieves the following technical effects: The above-mentioned target tracking-based monitoring method, device, equipment and medium judge whether the monitoring target moves from the first monitoring area of the first monitoring camera to the common monitoring area of the first monitoring camera and the second monitoring camera; if yes, judge whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera; if yes, improve the monitoring quality of the second monitoring camera to a preset quality standard; in response to the monitoring quality of the second monitoring camera reaching the preset quality standard, control the second monitoring camera to be the main monitoring camera of the monitoring target; the present application does not directly switch when there is an overlapping area, but judges whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera; if no, it is determined that the monitoring quality is qualified; if yes, the monitoring quality of the second monitoring camera is improved to a preset quality standard, solving the problem that in the prior art, the camera adopts a low-power and low-resolution mode for monitoring in order to save energy consumption; when tracking and monitoring a specific target, the low-resolution monitoring mode is prone to cause the view angle to deteriorate when switching the main monitoring camera, and in a complex scene, the target is prone to be lost due to the deteriorated view angle. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 It is a flowchart of the target tracking-based monitoring method in one embodiment; Figure 2 It is a structural block diagram of the target tracking-based monitoring device in one embodiment. DETAILED DESCRIPTION

[0025] In the following description, specific details are set forth such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the present application. However, persons skilled in the art will understand that the present application can be practiced without these specific details. In other instances, well-known structures, devices, circuits, and methods have not been described in detail in order to avoid obscuring the present application.

[0026] It should be understood that the word “comprise” or variations such as “comprises” or “comprising”, when used in this specification and in the accompanying claims, specify the presence of stated features, integers, steps, operations, elements, components and / or groups of features, integers, steps, operations, elements, components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0027] It should also be understood that the term “and / or” when used in this specification and in the following claims is to be interpreted as an inclusive-inclusive rather than an exclusive-inclusive. That is, unless it is otherwise specified, “and / or” should be interpreted to mean one and only one of the items in the list is present or one or more of the items in the list are present.

[0028] As used in this specification and claims, the terms “if’ and “when” can, depending upon the context, be interpreted to mean either “when...” or “if...” or “when...” or “in response to a determination” or “in response to detecting.” Similarly, the phrase “if determined” or “if [the recited condition or event] is detected” can, depending upon the context, be interpreted to mean “upon being determined” or “in response to a determination” or “upon detecting [the recited condition or event]” or “in response to detecting [the recited condition or event].”

[0029] In addition, the terms “first”, “second”, “third”, etc. as used in the description of the application and the appended claims are used only to distinguish descriptions and are not to be interpreted as indicating or implying relative importance.

[0030] Reference in the specification to “one embodiment” or “some embodiments” or “an embodiment” or “some implementations” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrases “in one embodiment”, “in some embodiments”, “in other embodiments”, “in additional embodiments” or the like in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily referring to some, but not all embodiments, unless otherwise indicated. The terms “including”, “comprising”, “having” and variations thereof herein are meant to be broad and encompass the terms “consisting of” and “consisting essentially of” unless otherwise indicated.

[0031] In one embodiment, a terminal is provided, the terminal is configured to: determine whether a monitoring target moves from a first monitoring area of a first monitoring camera to a common monitoring area of the first monitoring camera and a second monitoring camera; if the determination is positive, determine whether the first monitoring camera is greater than a monitoring quality of the second monitoring camera; if the determination is positive, improve the monitoring quality of the second monitoring camera to a preset quality standard; and in response to the monitoring quality of the second monitoring camera reaching the preset quality standard, control the second monitoring camera to be a main monitoring camera for the monitoring target.

[0032] The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices.

[0033] In one embodiment, as shown in Figure 1 A target tracking-based monitoring method is provided, and the method comprises: Step S100: determining whether a monitoring target moves from a first monitoring area of a first monitoring camera to a common monitoring area of the first monitoring camera and a second monitoring camera; Step S200: if it is determined that the monitoring target moves from the first monitoring area of the first monitoring camera to the common monitoring area of the first monitoring camera and the second monitoring camera, determining whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera; Step S300: if it is determined that the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera, improving the monitoring quality of the second monitoring camera to a preset quality standard; Step S400: in response to the monitoring quality of the second monitoring camera reaching the preset quality standard, controlling the second monitoring camera to be the main monitoring camera for the monitoring target.

[0034] In this embodiment, the first monitoring camera has a first monitoring area, and the second monitoring camera has a second monitoring area. When the monitoring target is in the first monitoring area, the first monitoring camera is the main monitoring camera for the monitoring target. The overlapping area of the first monitoring area and the second monitoring area is the common monitoring area, which is an area that can be monitored by both the first monitoring camera and the second monitoring camera.

[0035] When the monitoring target moves from the first monitoring area of the first monitoring camera to the common monitoring area of the first monitoring camera and the second monitoring camera, it is determined that the monitoring target has the possibility of leaving the first monitoring area of the first monitoring camera and entering the second monitoring area. When the monitoring target leaves the first monitoring area, the first monitoring camera cannot monitor the monitoring target. In order to track and monitor the monitoring target, it is necessary to switch other cameras as the main monitoring camera for the monitoring target in advance.

[0036] The camera in the prior art usually adopts a low-power and low-resolution mode to monitor in order to save energy consumption. This mode can meet the daily ordinary monitoring demand, but for tracking and monitoring of a specific target, the low-resolution monitoring mode is prone to cause the problem of tracking target loss due to poor view angle when switching the main monitoring camera, and the ordinary technical personnel in the field usually only consider camera switching when designing a target tracking method without considering the pros and cons of the view angle after switching. Therefore, when the main monitoring camera needs to be switched in the present application, the first monitoring camera is not directly switched when there is an overlapping area, but whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera is judged. If the judgment is no, it is judged that the monitoring quality is qualified, and the second monitoring camera can be further controlled as the main monitoring camera of the monitoring target; if the judgment is yes, the monitoring quality of the second monitoring camera is improved to a preset quality standard, and the second monitoring camera is controlled as the main monitoring camera of the monitoring target in response to the monitoring quality of the second monitoring camera reaching the preset quality standard, thereby avoiding the problem of switching to a worse view angle after switching the main monitoring camera.

[0037] In one embodiment, in step S200, whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera is judged, including: Step S210: calculating the first monitoring quality of the first monitoring camera; Step S220: calculating the second monitoring quality of the second monitoring camera; Step S230: judging whether the first monitoring quality is greater than the second monitoring quality.

[0038] In the present embodiment, the first monitoring quality of the first monitoring camera and the second monitoring quality of the second monitoring camera are calculated respectively, and whether the second monitoring camera to be switched meets the standard is judged based on the first monitoring quality and the second monitoring quality.

[0039] In one embodiment, step S210: calculating the first monitoring quality of the first monitoring camera, includes: Step S211: extracting a region of interest containing the monitoring target from the monitoring picture of the first monitoring camera; Step S212: calculating a monitoring feature score of a monitoring quality feature based on the region of interest; Step S213: weighting and calculating each monitoring feature score to obtain an instantaneous view angle quality; Step S214: time smoothing the instantaneous view angle quality and generating a first monitoring quality.

[0040] In this embodiment, by extracting the region of interest containing the monitoring target from the monitoring picture of the first monitoring camera, the calculation range is shrunk from the whole frame to the region of interest ROI around the monitoring target, avoiding the background disturbance such as sky, ground light, and advertising screen from affecting the evaluation of the monitoring quality.

[0041] In step S220, the monitoring quality features are calculated based on the region of interest, and the monitoring quality features are normalized to obtain the monitoring feature scores. By normalization, each monitoring quality feature is placed in the same scale.

[0042] In step S230, to prevent a single monitoring quality feature from affecting the overall monitoring quality and to avoid the problem of large fluctuations in monitoring quality evaluation in the case of small disturbance, the instantaneous visual angle quality is obtained by weighted calculation.

[0043] In step S240, to prevent the problem of instantaneous visual angle quality caused by compression GOP, network jitter, short-time occlusion, etc., the instantaneous visual angle quality is time-smoothed to generate the first monitoring quality, which has the technical effect of suppressing measurement noise and instantaneous fluctuations.

[0044] In another embodiment, the monitoring quality features in step S220 include pixel height, occlusion rate, and definition. The pixel height represents the pixel size occupied by the monitoring target on the imaging plane. A high enough pixel density can ensure that the enlarged image details are sampled and recorded, thereby avoiding detail loss. Therefore, the pixel height is one of the factors for measuring the monitoring quality. The occlusion rate represents the visible area proportion of the monitoring target on the image. The definition is used to represent whether the edges and textures of the image of the monitoring target are clear.

[0045] The monitoring feature score corresponding to the pixel height is calculated as follows: wherein, is the pixel height of the detection frame; is the detection frame of the monitoring target, which is output by the detector; is the pixel height extraction symbol of the detection frame.

[0046] is the monitoring feature score corresponding to the pixel height; is the pixel height linearly normalized to [0, 1]; is the lowest calibration threshold; The lowest calibration threshold and the highest calibration threshold are set by a person skilled in the art according to the target category, and exemplarily, the lowest calibration threshold and the highest calibration threshold of the pedestrian are 80px and 240px respectively under the 1080p setup.

[0047] The monitoring feature score corresponding to the pixel height is calculated as follows: If is less than , the value of is , and the value of is also , and the value of is 0, that is, the monitoring feature score corresponding to the pixel height is 0, indicating that the pixel height is too small and not clear.

[0048] On the contrary, is greater than , the value of is , and the value of is , and the value of is 1.

[0049] If is between and , the value of belongs to the value between 0 and 1.

[0050] The monitoring feature score corresponding to the occlusion rate is calculated as follows: Wherein, is the occlusion rate; is the set of visible pixels of the monitoring target in the detection frame, represents the number of visible pixels in the set of visible pixels, and the fewer the number of visible pixels, the higher the occlusion rate ; is the set of all pixels in the detection frame, represents the total number of pixels in the set of all pixels.

[0051] is the monitoring feature score corresponding to the occlusion rate; represents linear normalization of the occlusion rate to [0, 1]; The acceptable upper limit of occlusion is set in advance by a person skilled in the art according to actual needs, and in general, when the visibility is greater than 40%, the tracking of the target and the basic judgment of the target form can be stably maintained, so the acceptable upper limit of occlusion may be set to 0.6; based on the needs of different monitoring targets, may be set to a value other than 0.6.

[0052] Further, regarding the calculation of the monitoring feature score corresponding to the occlusion rate, the following is specific: If is greater than , the actual occlusion rate is greater than the acceptable upper limit of occlusion, and at this time the monitoring feature score corresponding to the occlusion rate is 0, indicating that the occlusion rate is unqualified. Substituting the above formula, is greater than , the value of is 0, the value of is 1, and substituting , the monitoring feature score corresponding to the occlusion rate is 0.

[0053] If is less than , the value of is , the value of is a value between 0 and 1, and substituting , the monitoring feature score corresponding to the occlusion rate can be obtained.

[0054] The monitoring feature score corresponding to the sharpness is calculated as follows: First, the sharpness is represented by the Laplacian variance of the ROI gray scale image. Edges and textures belong to high-frequency details, and when focusing is good, the Laplacian response fluctuates greatly and the variance is high; on the contrary, if it is out of focus or motion blur, the high frequency is smoothed, the response is close to a constant, and the variance is low. Specifically, first take the discrete Laplacian response on the ROI, and then calculate the variance, which is denoted by the symbol .

[0055] Next, based on the preset minimum sharpness threshold and the maximum sharpness threshold , the sharpness is normalized to obtain the corresponding monitoring feature score: wherein The resolution is assigned as the monitoring feature score. By setting the logarithmic function, the interference of extreme large values ​​on the resolution can be suppressed, thus improving the accuracy of the monitoring feature score.

[0056] In one embodiment, a minimum resolution threshold is set. and highest resolution threshold At that time, the lowest quantile of historical samples was used as... High quartile as The high percentile can be the 95th percentile, and the low percentile can be the 5th percentile.

[0057] In one embodiment, a minimum resolution threshold is set. and highest resolution threshold First, collect sample fragments covering day and night, near and far, and different exposures, clearly labeling them as usable or unusable according to ROI. Then, statistically analyze the usable and unusable sets. Value distribution, which will be the distribution of each clearly available sample in the available set. The low quantile of the value is set as The clearly available samples in the available set. The high quantile of the value is set as .

[0058] In another embodiment, in step S230, the instantaneous viewpoint quality at time t is calculated based on the following formula: in, For instantaneous visual quality, This serves as a sequence index for monitoring quality characteristics. The weight coefficient corresponding to the k-th monitoring quality feature is... This is the monitoring feature score corresponding to the kth monitoring quality feature.

[0059] In this embodiment, The value of is 3. The monitoring feature scores are respectively for pixel height, occlusion rate, and sharpness. , and . They are respectively the corresponding , and The weighting coefficients, The sum is 1.

[0060] In one embodiment, the weighting coefficient Set to the same value, that is , and are all 1 / 3. In this way, the pixel height, the occlusion rate and the definition take the same proportion in the calculation of the instantaneous visual angle quality.

[0061] In another embodiment, in order to ensure the details of the monitoring target, the weight of is slightly higher, exemplarily, , and are respectively 0.45, 0.3 and 0.25.

[0062] In another embodiment, if it is night monitoring, in order to ensure the continuous tracking stability and clarity, the weight of is slightly higher, exemplarily, , and are respectively 0.3, 0.3 and 0.4.

[0063] In another embodiment, in step S240, the first monitoring quality is generated based on the following formula: wherein, is the first monitoring quality corresponding to t moment; is the time smoothing intensity; is the first monitoring quality corresponding to t-1 moment; is the instantaneous visual angle quality at t moment.

[0064] The greater the value of the time smoothing intensity is, the more sensitive it is. The time smoothing intensity is equivalent to the weighted average of the most recent frames: Exemplarily, if 5 frames are desired to be smoothed, the value of the time smoothing intensity is about 0.33, and if 10 frames are desired to be smoothed, the value of the time smoothing intensity is about 0.18. Therefore, according to the number of frames desired to be smoothed, the time smoothing intensity can be set.

[0065] When the first monitoring quality is calculated, the initial value needs to be set in advance. In this embodiment, 3-frame preheating is used to set the initial value , which is set as the average value of the instantaneous visual angle quality calculated by 3 frames. For a newly started camera, the instantaneous visual angle quality of the first frame can be directly taken as the initial value .

[0066] It should be noted that the calculation method of the monitoring quality of the first monitoring camera and the second monitoring camera is the same, and the person skilled in the art should calculate the second monitoring quality according to the calculation method of the first monitoring quality, so the present application will not be described again.

[0067] In addition, in actual monitoring, the monitoring quality characteristics not only include the pixel height, the occlusion rate and the definition, and the person skilled in the art should select more monitoring quality characteristics according to the actual needs to track control, and the present application is not limited.

[0068] In one embodiment, in step S300, the monitoring quality of the second monitoring camera is improved to a preset quality standard, including: Step S310: calculating the monitoring quality difference between the first monitoring camera and the second monitoring camera; Step S320: improving the pixel height and the definition of the second monitoring camera according to the monitoring quality difference, and reducing the occlusion rate of the second monitoring camera.

[0069] In the present embodiment, the monitoring quality difference is to compare the pixel height, the occlusion rate and the definition of the first monitoring camera with the pixel height, the occlusion rate and the definition of the second monitoring camera respectively, so as to screen out the monitoring quality characteristics of the second monitoring camera that need to be improved.

[0070] When the pixel height of the first monitoring camera is higher than that of the second monitoring camera, the monitoring target is pulled closer by controlling the second monitoring camera to appropriately zoom, and the composition is slightly adjusted to make the monitoring target more centered, so that the target is larger in the picture, so as to improve the pixel height of the second monitoring camera.

[0071] When the occlusion rate of the first monitoring camera is lower than that of the second monitoring camera, the view angle is changed by controlling the second monitoring camera to slightly pan and tilt, so as to avoid the occlusion path of the large occlusion object, or when the crowd or the traffic flow is crowded, the zoom is slightly reduced or the composition is adjusted in advance, so that the monitoring target has a larger interval with the neighbors, so as to reduce the occlusion rate of the second monitoring camera.

[0072] When the definition of the first monitoring camera is higher than that of the second monitoring camera, the exposure is shortened to suppress motion blur, the gain or the light compensation is improved, and the appropriate noise reduction and sharpening are matched, so as to improve the definition of the second monitoring camera.

[0073] Therefore, by calculating the monitoring quality difference, the monitoring quality is targeted improved until the preset quality standard is reached.

[0074] In another embodiment, in step S300, the monitoring quality of the second monitoring camera is improved to a preset quality standard by a preset monitoring quality improvement instruction. The monitoring quality improvement instruction is an instruction preset for controlling the second monitoring camera, which is preconfigured to comprehensively improve the pixel height, the occlusion rate and the definition in the fastest way, so as to achieve the purpose of improving the monitoring quality of the second monitoring camera as soon as possible in the shortest time.

[0075] In one embodiment, in step S400, the monitoring quality of the second monitoring camera reaches the preset quality standard in response. Reaching the preset quality standard means that the first monitoring quality recalculated after improving the second monitoring camera is less than or equal to the second monitoring quality.

[0076] In steps S100 to S400, the premise is that the monitoring target is still in the common monitoring area, so that the monitoring quality of the first monitoring camera and the second monitoring camera can be calculated.

[0077] Generally, when improving the pixel height of the second monitoring camera, the zooming needs 0.3 to 1.5 seconds. When reducing the occlusion rate of the second monitoring camera, slight panning and tilting are needed to change the angle of view, which takes about 1 second. When improving the definition of the second monitoring camera, shortening the exposure and suppressing the motion blur takes about 0.7 seconds. Therefore, the total time for improving the monitoring quality of the second monitoring camera to the preset quality standard is about 3.2 seconds. The area of the common monitoring area is preset to be slightly larger, so that the monitoring target generally does not leave the common monitoring area within 3 seconds after entering the common monitoring area, thereby avoiding the situation that the monitoring target has left the common monitoring area when the monitoring quality of the second monitoring camera does not meet the standard, so that the main monitoring camera after switching can maintain the monitoring quality of the original main camera for tracking and monitoring the monitoring target, thereby avoiding the problems of early switching and poor monitoring angle after switching in the prior art, and even the problem of tracking loss in extreme cases. Therefore, the present application adopts a completely opposite technical concept to the prior art, that is, the camera is not switched immediately after detecting the target entering the common monitoring area, but is switched under the premise of ensuring the monitoring quality, thereby improving the reliability of target tracking.

[0078] In one embodiment, the common monitoring area includes a first area and a second area with the same area, and the distance between the center of the first area and the center of the first monitoring area is less than the distance between the center of the second area and the center of the first monitoring area. In step S200, if it is determined that the monitoring target moves from the first monitoring area of the first monitoring camera to a common monitoring area of the first monitoring camera and the second monitoring camera, the following steps are included: Step S201: determining whether the monitoring target moves from a first area to a second area in the common monitoring area. Step S202: if it is determined that the monitoring target does not move from the first area to the second area, the first monitoring camera remains as the main monitoring camera for the monitoring target. Step S203: if it is determined that the monitoring target moves from the first area to the second area, determining whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera.

[0079] In this embodiment, in the common monitoring area, the first area and the second area are arranged in sequence according to the direction of the first monitoring area towards the second monitoring area. From the perspective of the first monitoring area, the first area is closer to the center area of the first monitoring area, the first area is in the internal area of the first monitoring area, and the second area is at the edge of the first monitoring area. From the perspective of the second monitoring area, the second area is closer to the center of the second monitoring area, the second area is in the internal area of the second monitoring area, and the first area is at the edge of the second monitoring area.

[0080] When the monitoring target moves to the first area in the common monitoring area, there is a case that the monitoring target still wants to move in the first monitoring area, and there is a possibility that the monitoring target returns to the main area of the first monitoring area from the first area. Since the monitoring target is closer to the first monitoring camera, and the second monitoring camera is farther away, it should be monitored by the first monitoring camera, and the monitoring is clearer and the monitoring resources consumed are less. Therefore, if the second monitoring camera is switched at this time, it is easy to cause the problem of poor switching of the view angle and early switching. For the case that the monitoring target returns to the main area of the first monitoring area from the first area, switching the camera at this time causes the problem of switching error. In order to solve this problem, the common monitoring area is divided into the first area and the second area in advance in the present application. When it is judged that the monitoring target moves from the first area in the common monitoring area to the second area, the monitoring target has moved to the edge area of the first monitoring area and is close to the inside of the second monitoring area at this time. At this time, there is a high probability that the monitoring target will move to the second monitoring area, so preparation work for switching the camera needs to be done. Specifically, it is judged whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera, so that the camera switching judgment can be made when the monitoring target has a tendency to completely enter the monitoring area of the second monitoring camera. On the one hand, the accurate tracking and monitoring of the monitoring target by the first monitoring camera are ensured, and on the other hand, the monitoring work of the second monitoring camera is not disturbed when the monitoring target does not have a high probability of entering the second monitoring area.

[0081] In addition, compared with the way of predicting the action of the target by using the motion state detection algorithm in the prior art, the present application triggers whether to judge whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera by judging whether the monitoring target moves to the first area and the second area in a step shape, thereby saving the operation resources and making the judgment simple and convenient.

[0082] In one embodiment, the method further comprises: Step S510: When it is detected that the monitoring target completely enters or is about to enter the second main area, and the monitoring quality of the second monitoring camera does not reach the preset quality standard, wherein the second main area is an area in the second monitoring area except the common monitoring area; Step S521: Control the second monitoring camera to be the main monitoring camera for the monitoring target, and set a degradation switching flag; Step S522: According to the degradation switching flag, the monitoring quality of the second monitoring camera is improved by no less than the preset minimum monitoring parameter.

[0083] In this embodiment, when it is detected that the monitoring target completely enters or is about to enter the second main area, and the monitoring quality of the second monitoring camera does not reach the preset quality standard, in order to prevent the tracking target from being lost, the second monitoring camera is directly switched to the main monitoring camera of the monitoring target. At this time, the monitoring quality of the second monitoring camera cannot reach the standard of not being lower than that of the first monitoring camera, but at least meets the standard of not losing the tracking target. The minimum monitoring parameter is determined in real time when the first monitoring camera monitors the tracking target, and the tracking target is monitored by the camera controlled by the minimum monitoring parameter, so that the target is not lost.

[0084] In step S522, in response to setting the downgrade switching flag, the real-time control parameter of the current second monitoring camera is first acquired, and the real-time control parameter is compared with the minimum monitoring parameter. When the pixel height, the occlusion rate and the definition corresponding to the real-time control parameter are better than those of the minimum monitoring parameter, the improvement can be continued. If the pixel height, the occlusion rate and the definition corresponding to the minimum monitoring parameter are better than those of the minimum monitoring parameter, the specific differences of the pixel height, the occlusion rate and the definition are acquired, and targeted improvement is performed, so that the minimum standard is reached in the shortest time, so that the tracking target is not lost after the camera is switched.

[0085] In one embodiment, the method further comprises: Step S501: testing when the first monitoring camera is monitored according to a plurality of preset groups of debugging parameters, and generating a plurality of groups of debugging results; Step S502: obtaining a critical control parameter according to each debugging result; Step S503: upgrading the critical control parameter according to a preset margin to generate a minimum monitoring parameter.

[0086] In this embodiment, when the first monitoring camera is monitored, a plurality of groups of debugging parameters are set, and the first monitoring camera is controlled according to each debugging parameter. One group of debugging parameters corresponds to one group of debugging results. Based on the control of the plurality of groups of debugging parameters, the pixel height and the definition are gradually reduced, and the occlusion rate is gradually increased, until the debugging parameter of losing the monitoring target is obtained, which is taken as the critical control parameter.

[0087] The critical control parameter is upgraded according to a preset margin to generate a lowest monitoring parameter. The pixel height and definition corresponding to the lowest monitoring parameter are higher than the pixel height and definition corresponding to the critical control parameter, and the occlusion rate corresponding to the lowest monitoring parameter is lower than the occlusion rate corresponding to the critical control parameter. The preset margin is generally set to 5%-10%. Ideally, the tracking target is just ensured not to be lost by controlling according to the critical control parameter, but in actual monitoring, critical fluctuations caused by unknown interference are prone to occur, and therefore the preset margin is set to enhance the critical control parameter, so as to avoid the problem that the target is lost due to critical fluctuations caused by unknown interference.

[0088] In order to ensure the accuracy of the critical control parameter, a plurality of groups of original critical control parameters are obtained through a plurality of times of debugging based on a plurality of groups of debugging parameters, and the average value of the plurality of groups of original critical control parameters is calculated as the final critical control parameter.

[0089] In one embodiment, after the debugging parameter for losing the monitoring target is obtained, the control state of the last frame before loss is recorded, and the control state includes but is not limited to target frame, speed estimation, appearance feature, and camera pose and control parameter; the first monitoring camera is immediately returned to the control state to re-monitor the tracking target.

[0090] Therefore, in the embodiment, the lowest monitoring parameter for not losing the tracking target is determined in advance when the first monitoring camera monitors the tracking target, which is used to ensure that the tracking target is not lost when the second monitoring camera cannot meet the preset quality standard and has to be switched. Since the first monitoring area and the second monitoring area are adjacent, the environment in the overall area is similar, and therefore the lowest monitoring parameter obtained based on the first monitoring camera is more matched to the second monitoring camera, thereby reducing the probability of losing the tracking target.

[0091] In one embodiment, the method further comprises: Step S410: generating a backup monitoring instruction in response to controlling the second monitoring camera as the main monitoring camera for the monitoring target; Step S420: controlling the first monitoring camera to monitor the monitoring target according to the preset backup monitoring time according to the backup monitoring instruction, and generating backup monitoring data; Step S430: storing the backup monitoring data.

[0092] In the embodiment, different from the prior art, when the second monitoring camera is switched to the main monitoring camera of the monitoring target, in order to prevent the monitoring target from returning to the first area or the main area of the first monitoring area, or when the second monitoring camera cannot track the monitoring target due to failure, the first monitoring camera is controlled to monitor the monitoring target according to a preset backup monitoring time through the backup monitoring instruction, and backup monitoring data is generated. The above problem is avoided through storage of the backup monitoring data, and backup storage of the monitoring data of target tracking is realized.

[0093] In one embodiment, as shown in Figure 2 A monitoring device based on target tracking is also provided, and the device comprises: A target moving area determination module is configured to determine whether the monitoring target moves from the first monitoring area of the first monitoring camera to a common monitoring area of the first monitoring camera and the second monitoring camera. A target monitoring quality determination module is configured to determine whether the monitoring quality of the first monitoring camera is greater than the monitoring quality of the second monitoring camera if it is determined that the monitoring target moves from the first monitoring area of the first monitoring camera to the common monitoring area of the first monitoring camera and the second monitoring camera. A target monitoring quality improvement module is configured to improve the monitoring quality of the second monitoring camera to a preset quality standard if it is determined that the monitoring quality of the first monitoring camera is greater than the monitoring quality of the second monitoring camera. A target monitoring subject switching module is configured to control the second monitoring camera to be the main monitoring camera of the monitoring target in response to the monitoring quality of the second monitoring camera reaching the preset quality standard.

[0094] In one embodiment, the target monitoring quality determination module is further configured to calculate the first monitoring quality of the first monitoring camera, calculate the second monitoring quality of the second monitoring camera, and determine whether the first monitoring quality is greater than the second monitoring quality.

[0095] In one embodiment, the target monitoring quality determination module is further configured to extract a region of interest containing the monitoring target from a monitoring picture of the first monitoring camera, calculate a monitoring feature score of a monitoring quality feature based on the region of interest, calculate an instantaneous visual angle quality by weighting each monitoring feature score, and generate the first monitoring quality by time smoothing the instantaneous visual angle quality.

[0096] In one embodiment, the target monitoring quality improvement module is further configured to calculate a monitoring quality difference between the first monitoring camera and the second monitoring camera, improve the pixel height and definition of the second monitoring camera according to the monitoring quality difference, and reduce the occlusion rate of the second monitoring camera.

[0097] In one embodiment, the common monitoring area comprises a first area and a second area with same area, a center of the first area is closer to a center of the first monitoring area than a center of the second area; the target monitoring quality judging module is further configured to judge whether the monitoring target moves from the first area to the second area in the common monitoring area; if not, keep the first monitoring camera as the main monitoring camera of the monitoring target; if yes, judge whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera.

[0098] In one embodiment, the target monitoring subject switching module is further configured to: when detecting that the monitoring target completely enters or is about to enter a second main area and the monitoring quality of the second monitoring camera does not reach a preset quality standard, wherein the second main area is an area in the second monitoring area except the common monitoring area; control the second monitoring camera as the main monitoring camera of the monitoring target and set a downgrade switching flag; and improve the monitoring quality of the second monitoring camera by no less than a preset minimum monitoring parameter according to the downgrade switching flag.

[0099] In one embodiment, the target monitoring subject switching module is further configured to: test the first monitoring camera according to a plurality of preset groups of debugging parameters when the first monitoring camera is monitoring and generate a plurality of groups of debugging results; obtain critical control parameters according to the debugging results; and upgrade the critical control parameters according to a preset margin to generate the minimum monitoring parameter.

[0100] In one embodiment, the target monitoring subject switching module is further configured to: in response to controlling the second monitoring camera as the main monitoring camera of the monitoring target, generate a backup monitoring instruction; control the first monitoring camera to monitor the monitoring target according to a preset backup monitoring time according to the backup monitoring instruction and generate backup monitoring data; and store the backup monitoring data.

[0101] It should be noted that the information interaction, execution process and the like between the above modules are based on the same concept as the method embodiments of the present application, and the specific functions and the technical effects brought by the same can be referred to the method embodiments part, which will not be described here.

[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the above described functions. Each functional unit or module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit. In addition, the specific name of each functional unit or module is only for convenient distinction, and does not limit the protection scope of the present application. The specific working process of the unit or module in the system can refer to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0103] The embodiments of the present application further provide a network device, comprising at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the above method embodiments when executing the computer program.

[0104] The embodiments of the present application further provide a computer readable storage medium, which stores a computer program, wherein the computer program is executable by a processor to implement the steps in any of the above method embodiments.

[0105] The embodiments of the present application provide a computer program product, which, when running on a mobile terminal, enables the mobile terminal to implement the steps in any of the above method embodiments.

[0106] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the present application can implement all or part of the processes in the above-mentioned embodiment methods through a computer program to instruct relevant hardware to complete, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium can not be an electrical carrier signal and a telecommunication signal.

[0107] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0108] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0109] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / network device and method can be implemented in other ways. For example, the apparatus / network device embodiments described above are only schematic. The division of the modules or units is only a logical function division, and there can be another division in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0110] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e., may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0111] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

[0112] An embodiment of the present application further provides a computer device, the computer device of the embodiment comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the above methods when executing the computer program.

[0113] The computer device can include, but is not limited to, a processor, a memory. Those skilled in the art can understand that the above description is an example of the computer device, and does not constitute a limitation on the computer device, and can include more or less components than the above description, or combine certain components, or different components, for example, can also include input / output devices, network access devices, etc.

[0114] The processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0115] The memory can be an internal storage unit of the computer device in some embodiments, such as a hard disk or a memory of the computer device. The memory can also be an external storage device of the computer device in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like. Further, the memory can include both an internal storage unit and an external storage device of the computer device. The memory is used to store an operating system, an application program, a boot loader, data, and other programs, such as program codes of the computer program, and the like. The memory can also be used to temporarily store data that has been output or is to be output.

[0116] The technical features of the above embodiments can be combined in any manner. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described, but it should be understood that any combination of the technical features is within the scope of the present disclosure as long as the combination does not result in a contradiction.

[0117] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the present application. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, and these are within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A monitoring method based on target tracking, characterized in that, The method includes: Determine whether the monitored target has moved from the first monitoring area of ​​the first monitoring camera to the common monitoring area of ​​the first monitoring camera and the second monitoring camera; If the determination is yes, then determine whether the monitoring quality of the first surveillance camera is greater than that of the second surveillance camera; If the determination is yes, the monitoring quality of the second surveillance camera is improved to the preset quality standard; In response to the second surveillance camera achieving a preset quality standard, the second surveillance camera is controlled to become the primary surveillance camera for the monitored target.

2. The monitoring method based on target tracking according to claim 1, characterized in that, Determining whether the monitoring quality of the first surveillance camera is greater than that of the second surveillance camera includes: Calculate the first monitoring quality of the first surveillance camera; Calculate the second monitoring quality of the second surveillance camera; Determine whether the quality of the first monitoring is greater than that of the second monitoring.

3. The monitoring method based on target tracking according to claim 2, characterized in that, Calculating the first monitoring quality of the first surveillance camera includes: Extract the region of interest containing the monitored target from the monitoring screen of the first surveillance camera; The monitoring feature score is calculated based on the region of interest to determine the monitoring quality characteristics. The instantaneous viewpoint quality is obtained by weighting the scores of each of the aforementioned monitoring features. The instantaneous viewpoint quality is smoothed over time to generate the first monitoring quality.

4. The monitoring method based on target tracking according to claim 1, characterized in that, Improve the monitoring quality of the second surveillance camera to a preset quality standard, including: Calculate the difference in monitoring quality between the first surveillance camera and the second surveillance camera; Based on the difference in monitoring quality, the pixel height and clarity of the second monitoring camera are improved, and the occlusion rate of the second monitoring camera is reduced.

5. The monitoring method based on target tracking according to claim 1, characterized in that, The common monitoring area includes a first area and a second area with the same area, and the distance between the center of the first area and the center of the first monitoring area is less than the distance between the center of the second area and the center of the first monitoring area. If it is determined that the monitored target has moved from the first monitoring area of ​​the first monitoring camera to the common monitoring area of ​​the first and second monitoring cameras; including: Determine whether the monitored target has moved from the first area to the second area within the shared monitoring area; If the determination is negative, then the first surveillance camera remains the primary surveillance camera for the monitored target; If the determination is yes, then determine whether the monitoring quality of the first surveillance camera is greater than that of the second surveillance camera.

6. The monitoring method based on target tracking according to claim 1, characterized in that, The method further includes: When it is detected that the monitored target has fully entered or is about to enter the second main area, and the monitoring quality of the second monitoring camera does not meet the preset quality standard, wherein the second main area is the area in the second monitoring area excluding the common monitoring area; Control the second surveillance camera as the primary surveillance camera for the monitored target, and set a downgrade switching flag; According to the downgrade switching flag, the monitoring quality of the second surveillance camera is improved to a minimum monitoring parameter that is not lower than the preset minimum.

7. The monitoring method based on target tracking according to claim 6, characterized in that, The method further includes: The test is performed on the first surveillance camera while it is monitoring, according to multiple preset sets of debugging parameters, and multiple sets of debugging results are generated. The critical control parameters are obtained based on the debugging results described above. The critical control parameters are upgraded according to a preset margin to generate the minimum monitoring parameters.

8. A monitoring device based on target tracking, characterized in that, The device includes: The target movement area determination module is used to determine whether the monitored target has moved from the first monitoring area of ​​the first monitoring camera to the common monitoring area of ​​the first monitoring camera and the second monitoring camera. The target monitoring quality determination module is used to determine whether the monitoring quality of the first monitoring camera is greater than that of the second monitoring camera if the determination is yes. The target monitoring quality improvement module is used to improve the monitoring quality of the second monitoring camera to a preset quality standard if the determination is yes. The target monitoring subject switching module is used to control the second monitoring camera as the main monitoring camera of the monitoring target in response to the monitoring quality of the second monitoring camera reaching a preset quality standard.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. 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 steps of the method according to any one of claims 1 to 7.

Images