Target shielding method, target shielding device, monitoring system and storage medium

Abstract

The present application relates to a target shielding method, a target shielding device, a monitoring system and a storage medium, wherein the target shielding method comprises: when it is determined that the front adjacent device detects the shielding target, the real-time position information of the shielding target is calculated according to the detection result of the front adjacent device for the shielding target; when the real-time position information meets the preset pre-shielding condition, the edge area that the shielding target is about to enter is pre-shielded within the monitoring range; the image features extracted from the edge area are matched with the target image features of the shielding target acquired in advance, and when the matching result indicates that the shielding target has entered the edge area, the shielding target is shielded in real time based on the detection frame of the shielding target, and the pre-shielding of the edge area is cancelled. It can estimate the monitoring screen area that the shielding target is about to enter based on the information between multiple camera devices, thereby realizing the pre-shielding of the shielding target in the monitoring screen.

Description

Technical Field

[0001] The present application relates to the field of video surveillance, and in particular to a target shielding method, a target shielding device, a monitoring system and a storage medium. Background Art

[0002] In order to improve the privacy protection needs of video data, or to avoid showing people or objects that are not originally desired to be shown in the video screen, a variety of video masking technologies have been applied. Among them, current video masking can often be divided into two stages. The first stage extracts the area that needs to be masked, such as extracting a pre-designated privacy area, and the second stage performs masking processing. The technologies applied to the first stage involve moving object extraction, face detection and recognition, human posture estimation, etc., to determine whether a human object or object object in the video screen belongs to the area that needs to be masked for subsequent processing. The technology applied to the second stage involves video display protection (also known as pre-coding protection, pixel domain protection), which uses masking, blurring, pixelation, and face replacement to perform masking processing.

[0003] In the current related technologies, occlusion processing is often performed on targets that have already appeared in the picture. When the target just enters the picture, there is a problem that it cannot be occluded in time, which leads to information leakage.

[0004] With regard to the problem in related technologies that a target cannot be blocked in time when it just enters the picture, no effective solution has been proposed yet. Summary of the invention

[0005] In this embodiment, a target shielding method, a target shielding device, a monitoring system and a storage medium are provided to solve the problem in the related art that a target cannot be shielded in time when it just enters the picture.

[0006] In a first aspect, a target shielding method is provided in this embodiment, which is used in a monitoring system, wherein the monitoring system includes at least two camera devices, and the method includes:

[0007] When it is determined that the preceding adjacent device has detected an occluding target, calculating the real-time position information of the occluding target according to the detection result of the preceding adjacent device for the occluding target; the preceding adjacent device is an adjacent camera device that has detected the occluding target;

[0008] When the real-time position information meets the preset pre-blocking condition, pre-blocking is performed on the edge area into which the blocking target is expected to enter within the monitoring range;

[0009] The image features extracted from the edge area are matched with the target image features of the occluded target acquired in advance. When the matching result indicates that the occluded target has entered the edge area, the occluded target is occluded in real time based on the detection frame of the occluded target, and the pre-occlusion of the edge area is canceled.

[0010] In some embodiments, when it is determined that the preceding adjacent device detects an obstructing target, calculating the real-time position information of the obstructing target according to the detection result of the preceding adjacent device for the obstructing target includes:

[0011] The real-time position information of the occluding target is calculated according to the movement speed of the occluding target detected by the front adjacent device and the distance of the occluding target relative to a preset reference object when the occluding target is detected in the front adjacent device.

[0012] In some embodiments, the method further comprises:

[0013] When the real-time position information is within a preset pre-blocking range, it is confirmed that the real-time position information meets the pre-blocking condition.

[0014] In some embodiments, the method further comprises:

[0015] When the matching result indicates that the occluding target has not entered the edge region and the duration of pre-occluding the edge region reaches a preset duration threshold, the pre-occluding of the edge region is cancelled.

[0016] In some embodiments, the method further comprises:

[0017] When the real-time position information of the occluding target meets the preset pre-leaving condition, the detection result for the occluding target is sent to the rear adjacent device to trigger the rear adjacent device to pre-occlude the occluding target; the rear adjacent device is an adjacent camera device that predicts that the occluding target will be detected.

[0018] In some embodiments, when the real-time position information of the blocking target meets the preset pre-leaving condition, sending the detection result of the blocking target to the rear adjacent device to trigger the rear adjacent device to pre-block the blocking target includes:

[0019] When the real-time position information of the obstructing target meets the preset pre-exit condition, the rear adjacent device that will detect the obstructing target is predicted from multiple adjacent camera devices based on the real-time position information and moving direction of the obstructing target, and the detection result for the obstructing target is sent to the rear adjacent device.

[0020] In some of the embodiments, the distances between different camera devices are determined in advance based on reference points within the monitoring range corresponding to each camera device.

[0021] In a second aspect, a target shielding device is provided in this embodiment, which is used in a monitoring system, wherein the monitoring system includes at least two camera devices, and the target shielding device includes: a position calculation module, a first shielding module, and a second shielding module; wherein:

[0022] The position calculation module is used to calculate the real-time position information of the occluding target according to the detection result of the preceding adjacent device for the occluding target when it is determined that the preceding adjacent device has detected the occluding target; the preceding adjacent device is an adjacent camera device that has detected the occluding target;

[0023] The first shielding module is used to pre-shield the edge area where the shielding target is expected to enter within the monitoring range when the real-time position information meets the preset pre-shielding condition;

[0024] The second occlusion module is used to match the image features extracted from the edge area with the target image features of the occlusion target acquired in advance. When the matching result indicates that the occlusion target has entered the edge area, the occlusion target is occluded in real time based on the detection frame of the occlusion target, and the pre-occlusion of the edge area is canceled.

[0025] In a third aspect, a monitoring system is provided in this embodiment, comprising at least two camera devices;

[0026] The camera device is used for target detection; wherein:

[0027] Among all the camera devices, at least one camera device is also used to execute the target shielding method described in the first aspect above.

[0028] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the program is executed by a processor, the target shielding method described in the first aspect is implemented.

[0029] Compared with the related art, the present embodiment provides a target occlusion method, a target occlusion device, a monitoring system and a storage medium. The target occlusion method, when determining that the front adjacent device detects the occlusion target, calculates the real-time position information of the occlusion target according to the detection result of the front adjacent device for the occlusion target; the front adjacent device is an adjacent camera device that has detected the occlusion target; when the real-time position information meets the preset pre-occlusion condition, the edge area that the occlusion target is about to enter is pre-occluded within the monitoring range; the image features extracted from the edge area are matched with the target image features of the occlusion target obtained in advance, and when the matching result indicates that the occlusion target has entered the edge area, the occlusion target is occluded in real time based on the detection frame of the occlusion target, and the pre-occlusion of the edge area is canceled. It can estimate the monitoring screen area that the occlusion target is about to enter based on the information between multiple camera devices, thereby realizing the pre-occlusion of the occlusion target in the monitoring screen.

[0030] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0032] Figure 1 is a hardware structure block diagram of a terminal of the target shielding method according to an embodiment of the present application;

[0033] Figure 2 is a flow chart of a target occlusion method according to an embodiment of the present application;

[0034] Figure 3 is a schematic diagram of the movement of an obstructing target in an embodiment of the present application;

[0035] Figure 4 is a schematic diagram of an edge area where an occluding target is expected to enter according to an embodiment of the present application;

[0036] Figure 5a is a schematic diagram of an embodiment of the present application showing an obstruction target entering an edge area;

[0037] Figure 5b is a schematic diagram of an embodiment of the present application in which an occluding target does not enter an edge area;

[0038] Figure 6 is a schematic diagram of distance calibration of a camera device in an embodiment of the present application;

[0039] Figure 7is a flow chart of a target occlusion method of some embodiments of the present application;

[0040] Figure 8 It is a structural block diagram of the target shielding device according to an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0042] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with general skills in the technical field to which this application belongs. The words "one", "a", "the", "these" and the like in this application do not indicate a quantitative limitation, and they may be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone. Generally, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0043] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a hardware structure diagram of a terminal of the target shielding method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 and a memory 104 for storing data, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0044] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the target shielding method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0045] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0046] In this embodiment, a target shielding method is provided for a monitoring system, wherein the monitoring system includes at least two camera devices. Figure 2 is a flow chart of the target shielding method of this embodiment. Figure 2 As shown, the process includes the following steps:

[0047] Step S210, when it is determined that the front adjacent device detects the occluding target, the real-time position information of the occluding target is calculated according to the detection result of the front adjacent device for the occluding target; the front adjacent device is the adjacent camera device that has detected the occluding target.

[0048] Among them, the monitoring system can be a system composed of multiple camera devices. The number and installation location of multiple camera devices can be set according to the needs of the actual application scenario, and this embodiment does not specifically limit this. It is worth mentioning that the monitoring system can also include more devices, such as servers or other electronic devices with data computing capabilities and communication capabilities. The target occlusion method of this embodiment can be run in any camera device of the monitoring system, or in a server or other electronic device with data computing capabilities and communication capabilities in the monitoring system. It should be noted that among multiple camera devices, due to the different distribution locations of different camera devices, the order in which different camera devices detect the occlusion target may be different in the time dimension. For example, the monitoring system includes camera device A and camera device B. When a human object with occlusion requirements appears in the scene deployed by the monitoring system, as the human object moves, it first appears in the monitoring range of camera device A, and then leaves the monitoring range of camera device A and moves to the monitoring range of camera device B. Then, camera device A can be used as the front adjacent device of camera device B, and camera device B can be used as the rear adjacent device of camera device A. That is, the preceding adjacent device is an adjacent camera device that detects the occluding target earlier than the current camera device.

[0049] The detection result for the occluded target may include the extracted target image features, movement speed, and position within the monitoring range of the occluded target. For example, camera device A extracts the target image features during the movement of the occluded target, and transmits the movement speed and target image features of the occluded target to camera device B to ensure that camera device B estimates the position of the occluded target. The camera device in the above-mentioned monitoring system may be a camera device equipped with a graphic detection function. When the front adjacent device detects the appearance of the occluded target, the above-mentioned detection result can also be extracted while the occlusion processing is performed on the occluded target. Afterwards, the front adjacent device transmits the corresponding detection result to the current camera device. After receiving the above-mentioned detection result, the current camera device calculates the real-time position information of the occluded target to determine whether the occluded target is about to enter its own monitoring range. The position-related information involved in this embodiment can all belong to a unified coordinate system established by pre-calibrating the position relationship of multiple camera devices. It is understandable that, for the camera device that first detects the occluded target, timely occlusion processing can be performed on the detected occluded target based on the occlusion method involved in the existing related technology.

[0050] In particular, for an occluding target within the monitoring range of a front adjacent device, the movement speed of the occluding target can be calculated through calibration information. The calibration information can be a reference point pre-set within the monitoring range, such as the center point within the monitoring range. The movement speed of the occluding target is determined based on the distance change information between the occluding target and the reference point combined with the time information. Figure 3 FIG. 1 is a schematic diagram of the movement of an obstructing target in this embodiment. Figure 3 As shown, the occluding target T is within the monitoring range of the camera device A ( Figure 3 In the figure, the monitoring range of camera device B ( Figure 3 During the movement, the moving speed of the occluding target T can be determined based on the distance between a reference point (not shown in the figure, which can be set as the center of the circle in the figure) set within the monitoring range of the camera device A and the occluding target T that changes over time, as well as time information.

[0051] The above-mentioned occlusion target can be any target that has an occlusion requirement and is not desired to be displayed on the screen, such as a face target, a license plate target, a document target, etc., which is not specifically limited in this embodiment. Those skilled in the art can set the target type that needs to be occluded in advance according to the requirements of the actual application scenario. During the actual detection process, the camera device performs target detection and performs occlusion processing according to the target type that needs to be occluded.

[0052] Step S220 , when the real-time position information meets the preset pre-blocking condition, pre-blocking is performed on the edge area where the blocking target is expected to enter within the monitoring range.

[0053] The above-mentioned pre-occlusion condition is used to determine whether the occluded target is about to enter the monitoring range of the current camera device. The pre-occlusion condition can specifically be a certain pre-occlusion range set in advance, and the pre-occlusion range is set at the edge of the monitoring range. When the calculated real-time position information is in the pre-occlusion range, it is determined that the real-time position information meets the pre-occlusion condition. When the real-time position information meets the pre-occlusion condition, it indicates that the occluded target is about to enter the monitoring range of the current camera device, so it is necessary to perform a pre-occlusion operation in advance according to the edge area that the occluded target is about to enter. The pre-occlusion operation includes but is not limited to one or more combinations of video display protection processing such as masking, blurring, pixelation, and face replacement. Based on this, the problem of information leakage caused by untimely occlusion of the occluded target is avoided. Figure 4 Schematic diagram of the edge area where the occluded target pre-enters in this embodiment, as shown in Figure 4 As shown, when the camera device B finds that the real-time position information of the occluding target T meets the preset pre-occluding condition (about to enter Figure 4), then according to the size of the blocked target, pre-blocking is performed at the edge of the monitoring screen corresponding to the monitoring range, such as pre-coding, and the square area in the figure is set as the pre-blocking area. When the blocked target enters the edge area, it can be blocked, and information leakage will not occur due to untimely blocking.

[0054] In step S230, the image features extracted from the edge area are matched with the target image features of the occluded target acquired in advance. When the matching result indicates that the occluded target has entered the edge area, the occluded target is occluded in real time based on the detection frame of the occluded target, and the pre-occlusion of the edge area is canceled.

[0055] In this step, it is necessary to further verify whether the occluded target has entered the pre-occluded edge area. Specifically, it can be verified by image feature comparison. The image features of the above edge area are extracted and matched with the target image features of the occluded target acquired in advance to calculate the similarity of the features of both parties. When the similarity calculation result meets the preset similarity threshold, it is confirmed that the features of both parties are matched successfully, and it is confirmed that the occluded target has entered the edge area; if the match is not successful, it is confirmed that the occluded target may have changed its direction of movement or stagnated. At this time, the pre-occlusion is terminated after the duration of the pre-occlusion operation on the above edge area reaches the preset duration threshold.

[0056] Figure 5a This is a schematic diagram of an obstruction target entering an edge area according to this embodiment; Figure 5b FIG. 1 is a schematic diagram of an embodiment of the present invention in which an obstruction target does not enter an edge region. Figure 5a As shown, at this time, the occluded target has moved to the edge area of ​​the pre-occluded area (such as Figure 5a In the figure, the occluded target T has overlapped with the square, and the arrow is the moving direction of the occluded target), then the image features extracted from the edge area can be successfully matched with the target image features of the occluded target obtained in advance. In the case where the occluded target has entered the edge area, the Figure 5a The pre-occlusion operation of the square area (edge ​​area) in is replaced by using the detection box of the occluded target itself to perform formal real-time occlusion. Figure 5b As shown in FIG. 1 , when the blocking target T changes its moving direction, it does not enter the monitoring range of the camera device B. Figure 5b The image features extracted from the square area (edge ​​area) will not be matched successfully with the target image features of the occluded target obtained in advance. In view of this situation, the pre-occlusion operation can be stopped after the pre-occlusion time of the edge area reaches a preset time threshold.

[0057] It is understandable that the above image features can be set according to the target that needs to be occluded in the actual application scenario. For example, when the target occlusion method of this embodiment is applied to the scene of face detection and occlusion, the above image features can be any features that can characterize the face; when the target occlusion method of this embodiment is applied to the scene of license plate detection and occlusion, the above image features can be any features that can characterize the license plate. This embodiment does not specifically limit this.

[0058] In some related technologies, the occluded target is often occluded after it appears on the screen. When the target just appears in the picture, it may be impossible to detect the complete occluded target or detect and identify it, and it may not be possible to perform occlusion protection in time, resulting in information leakage. In some other related technologies, a forward supplementary coding method is also introduced, that is, based on the position of the new privacy target in the current frame image and the preset frame image, the new privacy target in a predetermined number of frame images before the current frame image is occluded. This remedial coding measure cannot guarantee the real-time performance of the video display because it needs to process the previous video frames, which will cause delays in video display.

[0059] In view of the problems existing in the existing related technologies, this embodiment, through the above steps S210 to S230, for a monitoring system with multiple camera devices, makes full use of the positional relationship between adjacent camera devices, predicts the monitoring range that the occluded target will enter based on the movement of the occluded target within the monitoring range of different camera devices, and then performs pre-occlusion in the corresponding monitoring screen to avoid missed occlusion, thereby reducing the information leakage problem caused by untimely occlusion when the occluded target just enters the screen; in addition, this embodiment adopts an advance occlusion method, and there is no need to supplement the occlusion of the previous video frame, so that real-time display of video data can also be achieved. In addition, this embodiment also verifies whether the occluded target enters the edge area based on feature matching, and then appropriately ends the pre-occlusion operation, and uses the detection frame to perform real-time occlusion in time for the target that has entered the edge area.

[0060] Through the above steps S210 to S230, when it is determined that the front adjacent device detects the occluding target, the real-time position information of the occluding target is calculated according to the detection result of the front adjacent device for the occluding target; the front adjacent device is the adjacent camera device that has detected the occluding target; when the real-time position information meets the preset pre-occlusion condition, the edge area that the occluding target is about to enter is pre-occluded within the monitoring range; the image features extracted from the edge area are matched with the target image features of the occluding target obtained in advance, and when the matching result indicates that the occluding target has entered the edge area, the occluding target is occluded in real time based on the detection frame of the occluding target, and the pre-occlusion of the edge area is cancelled. It can estimate the monitoring screen area that the occluding target is about to enter based on the information between multiple camera devices, thereby realizing the pre-occlusion of the occluding target in the monitoring screen.

[0061] In one embodiment, when it is determined that the front adjacent device detects the occluding target, calculating the real-time position information of the occluding target according to the detection result of the front adjacent device for the occluding target may specifically include:

[0062] The real-time position information of the occluding target is calculated based on the movement speed of the occluding target detected by the front adjacent device and the distance of the occluding target relative to the preset reference object when the occluding target is detected in the front adjacent device.

[0063] When the preceding adjacent device (e.g., camera device A) detects an obstructing target, it determines the distance of the obstructing target relative to a preset reference object, such as a reference point set within the monitoring range, and calculates the movement speed within a preset time period. Afterwards, the current camera device (e.g., camera device B) determines the distance between the obstructing target when it is detected by the preceding adjacent device and a reference point within its own monitoring range based on the above information detected by the preceding adjacent device and the distance between the preceding adjacent device, and then predicts the real-time position of the obstructing target based on the above movement speed.

[0064] This embodiment can achieve accurate prediction of the movement state of the occluded target within the monitoring range of different camera devices based on the detection of the front adjacent device and the information interaction between the front adjacent device and the current camera device.

[0065] Additionally, in one embodiment, the target shielding method may further include:

[0066] When the real-time position information is within a preset pre-blocking range, it is confirmed that the real-time position information meets the pre-blocking condition.

[0067] In one embodiment, the target shielding method may further include:

[0068] When the matching result indicates that the occluding target has not entered the edge region and the duration of pre-occluding the edge region reaches a preset duration threshold, the pre-occluding of the edge region is cancelled.

[0069] If the matching result indicates that the occluded target has not entered the edge area, there is no need to continue pre-occluding the edge area. Therefore, the pre-occlusion of the edge area can be ended after the pre-occlusion duration exceeds the preset duration threshold to avoid invalid occlusion of the video screen.

[0070] Additionally, in one embodiment, the target shielding method may further include:

[0071] When the real-time position information of the occluded target meets the preset pre-leaving condition, the detection result for the occluded target is sent to the rear adjacent device to trigger the rear adjacent device to pre-occlude the occluded target; the rear adjacent device is an adjacent camera device that predicts that the occluded target will be detected.

[0072] Optionally, if the current camera device detects that the occluding target moves toward the edge of the monitoring range, or detects that the distance between the occluding target and the center point set in the monitoring range is getting farther and farther, it can be determined that the real-time position of the occluding target meets the pre-leaving condition. At this time, the detection result related to the occluding target can be sent to the subsequent adjacent device that will detect the occluding target, so as to trigger the subsequent adjacent device to start pre-occluding the occluding target.

[0073] This embodiment can continuously trigger different camera devices to perform pre-blocking according to the movement of the occluding target among multiple camera devices, so that the occluding target can be blocked in time when it moves into the monitoring range of different camera devices, thereby avoiding missed occlusion and information leakage.

[0074] In particular, in one embodiment, when the real-time position information of the blocking target meets the preset pre-leaving condition, the detection result for the blocking target is sent to the rear adjacent device to trigger the rear adjacent device to pre-block the blocking target, which may specifically include:

[0075] When the real-time position information of the occluded target meets the preset pre-exit condition, the rear adjacent device that will detect the occluded target is predicted from multiple adjacent camera devices based on the real-time position information and moving direction of the occluded target, and the detection result for the occluded target is sent to the rear adjacent device.

[0076] Among them, when the camera device determines that the occluded target is about to leave the current monitoring range, the monitoring range of another camera device that the occluded target is about to enter is determined based on the real-time position information and moving direction of the occluded target, so as to predict the next subsequent adjacent device that can detect the occluded target.

[0077] For example, camera device A is the first camera device to detect an occluding target. When camera device A determines that the occluding target moves toward the monitoring range of the adjacent camera device B, the detection result of the occluding target is sent to camera device B to trigger the pre-occluding operation of camera device B. At this time, camera device A is the front adjacent device of camera device B. After camera device B confirms that the occluding target has moved to the monitoring range of camera device B, the pre-occluding operation can be ended and the real-time occlusion of the occluding target's own detection frame can be used instead. Afterwards, if camera device B detects that the occluding target moves toward the adjacent camera device C, camera device B sends the detection result of the occluding target to camera device C to trigger the pre-occluding operation of camera device C. At this time, camera device C is the rear adjacent device of camera device B. In this way, the early occluding operation of the occluding target by different cameras can be accurately and continuously triggered.

[0078] In addition, in one embodiment, the distances between different camera devices are determined in advance based on reference points within the monitoring range corresponding to each camera device. Specifically, the distances between different camera devices can be calibrated after all camera devices are installed. Reference points can be set within the monitoring range of each camera device, and the distances between the reference points of each camera device are used as the distances between the camera devices. Figure 6 FIG. 1 is a schematic diagram of distance calibration of a camera device according to the present embodiment. Figure 6 As shown, the monitoring range of the camera device A is Figure 6 The circular area on the left is the monitoring range of camera device B. Figure 6 For the circular area on the right, the center points of the two circular areas can be used as the reference points of the two camera devices, and the distance dis_ab between the two center points can be used as the distance between camera device A and camera device B. By calibrating this distance, the distance of the occluded target relative to the camera device reference point can be more accurately detected in the subsequent occluded target detection.

[0079] Figure 7 is a flow chart of a target occlusion method in some of the embodiments, such as Figure 7 As shown, the target occlusion method includes the following steps:

[0080] Step S701, determining the distances between different camera devices in the monitoring system.

[0081] Step S702: The camera device that detects the obstructing target determines the moving speed of the obstructing target within the monitoring range.

[0082] Step S703: The camera device that detects the occluded target sends the motion speed and target image features of the occluded target to an adjacent rear camera device to trigger a pre-occlusion operation.

[0083] Step S704: The camera device that has triggered the pre-blocking operation performs pre-blocking in the edge area where the blocked target is to enter; wherein, the real-time position information of the blocked target is predicted based on the distance determined in step S701 and the moving speed of the blocked target. When it is determined that the blocked target is about to enter its own monitoring range based on the real-time position information, pre-blocking is performed in the edge area where the blocked target is to enter.

[0084] Step S705: After the camera device that has triggered the pre-occlusion operation determines that the occluded target has entered the pre-occluded edge area, it stops pre-occlusion and performs real-time occlusion on the occluded target based on the detection frame of the occluded target; wherein, the image features of the pre-occluded edge area are extracted and matched with the target image features of the occluded target, and it is determined whether the occluded target has entered the above edge area according to the matching result. If the occluded target has not entered the above edge area, the pre-occlusion ends after the duration of the pre-occlusion exceeds the preset duration threshold.

[0085] The above steps S701 to S705 can estimate the monitoring screen area that the occluding target will enter based on the information between the multiple camera devices, thereby achieving pre-occlusion of the occluding target in the monitoring screen.

[0086] In this embodiment, a target shielding device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0087] Figure 8 is a structural block diagram of a target shielding device 80 of this embodiment, wherein the target shielding device 80 is used in a monitoring system, and the monitoring system includes at least two camera devices such as Figure 8 As shown, the target shielding device 80 includes: a position calculation module 82, a first shielding module 84 and a second shielding module 86; wherein:

[0088] The position calculation module 82 is used to calculate the real-time position information of the occluded target according to the detection result of the front adjacent device for the occluded target when it is determined that the front adjacent device has detected the occluded target; the front adjacent device is the adjacent camera device that has detected the occluded target; the first occlusion module 84 is used to pre-occlude the edge area that the occluded target is about to enter within the monitoring range when the real-time position information meets the preset pre-occlusion condition; the second occlusion module 86 is used to match the image features extracted from the edge area with the target image features of the occluded target acquired in advance, and when the matching result indicates that the occluded target has entered the edge area, the occluded target is occluded in real time based on the detection frame of the occluded target, and the pre-occlusion of the edge area is canceled.

[0089] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0090] In this embodiment, a monitoring system is provided, which includes at least two camera devices; the camera devices are used to perform target detection; wherein: among all the camera devices, at least one camera device is also used to execute the target shielding method provided in any of the above embodiments.

[0091] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0092] In addition, in combination with the target shielding method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the target shielding method. The storage medium stores a computer program, and when the computer program is executed by a processor, any target shielding method in the above embodiments is implemented.

[0093] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0094] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0095] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0096] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0097] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A target occlusion method, characterized in that: Used in a monitoring system, the monitoring system comprising at least two camera devices, the method being run on a camera device having a front adjacent device among the at least two camera devices, or being run on a server or electronic device associated with the camera device having the front adjacent device, the method comprising: When it is determined that the preceding adjacent device has detected an occluding target, calculating the real-time position information of the occluding target according to the detection result of the preceding adjacent device for the occluding target; the preceding adjacent device is an adjacent camera device that has detected the occluding target; When the real-time position information meets the preset pre-blocking condition, pre-blocking is performed on the edge area into which the blocking target is expected to enter within the monitoring range; the edge area is the edge area of ​​the current camera device itself; the current camera device is the camera device with the front adjacent device; The image features extracted from the edge area are matched with the target image features of the occluded target acquired in advance. When the matching result indicates that the occluded target has entered the edge area, the occluded target is occluded in real time based on the detection frame of the occluded target, and the pre-occlusion of the edge area is canceled.

2. The target shielding method according to claim 1, characterized in that: When it is determined that the preceding adjacent device detects the obstructing target, calculating the real-time position information of the obstructing target according to the detection result of the preceding adjacent device for the obstructing target, including: The real-time position information of the occluding target is calculated according to the movement speed of the occluding target detected by the front adjacent device and the distance of the occluding target relative to a preset reference object when the occluding target is detected in the front adjacent device.

3. The target shielding method according to claim 1, characterized in that: The method further comprises: When the real-time position information is within a preset pre-blocking range, it is confirmed that the real-time position information meets the pre-blocking condition.

4. The target shielding method according to claim 1, characterized in that: The method further comprises: When the matching result indicates that the occluding target has not entered the edge region and the duration of pre-occluding the edge region reaches a preset duration threshold, the pre-occluding of the edge region is cancelled.

5. The target shielding method according to claim 1, characterized in that: The method further comprises: When the real-time position information of the occluding target meets the preset pre-leaving condition, the detection result for the occluding target is sent to the rear adjacent device to trigger the rear adjacent device to pre-occlude the occluding target; the rear adjacent device is an adjacent camera device that predicts that the occluding target will be detected.

6. The target shielding method according to claim 5, characterized in that: When the real-time position information of the blocking target meets the preset pre-leaving condition, a detection result for the blocking target is sent to a rear adjacent device to trigger the rear adjacent device to pre-block the blocking target, including: When the real-time position information of the obstructing target meets the preset pre-exit condition, the rear adjacent device that will detect the obstructing target is predicted from multiple adjacent camera devices based on the real-time position information and moving direction of the obstructing target, and the detection result for the obstructing target is sent to the rear adjacent device.

7. The target shielding method according to any one of claims 1 to 6, characterized in that: The distances between different camera devices are determined in advance based on reference points within the monitoring range corresponding to each camera device.

8. A target shielding device, characterized in that: Used in a monitoring system, the monitoring system comprising at least two camera devices, the apparatus running on the camera device having a front adjacent device among the at least two camera devices, or running on a server or electronic device associated with the camera device having a front adjacent device; The target shielding device comprises: a position calculation module, a first shielding module and a second shielding module; wherein: The position calculation module is used to calculate the real-time position information of the occluding target according to the detection result of the preceding adjacent device for the occluding target when it is determined that the preceding adjacent device has detected the occluding target; the preceding adjacent device is an adjacent camera device that has detected the occluding target; The first blocking module is used to pre-block the edge area that the blocking target is expected to enter within the monitoring range when the real-time position information meets the preset pre-blocking condition; the edge area is the edge area of ​​the current camera device itself; the current camera device is the camera device with the front adjacent device; The second occlusion module is used to match the image features extracted from the edge area with the target image features of the occlusion target acquired in advance. When the matching result indicates that the occlusion target has entered the edge area, the occlusion target is occluded in real time based on the detection frame of the occlusion target, and the pre-occlusion of the edge area is canceled.

9. A monitoring system, characterized in that: including at least two camera devices; The camera device is used for target detection; wherein: Among all the camera devices, at least one of the camera devices is also used to execute the target occlusion 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, the steps of the target occlusion method according to any one of claims 1 to 7 are implemented.

Images