Regional intrusion detection method, system and device and computer equipment

Abstract

The invention relates to a region intrusion detection method, system and device and computer equipment. The method comprises the following steps: acquiring a static background video containing a target area in a transformer substation, and modeling according to a video frame image in the static background video to obtain a background detection model; acquiring a real-time monitoring video containing a target area, processing a video frame image in the real-time monitoring video by adopting the background detection model, and identifying a monitored to-be-processed moving object; when the to-be-processed moving object meets the intrusion detection condition, determining a regional spatial position where the to-be-processed moving object is located according to a target position in a current video frame image of the real-time monitoring video; and when the regional spatial position is within the target regional range, triggering a regional intrusion alarm operation for the to-be-processed moving object. By adopting the method, whether the moving object enters the set alarm area or not can be accurately and timely detected, and the accuracy of area intrusion detection is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of regional detection technology, and in particular to a regional intrusion detection method, system, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] With the continuous development of intelligent monitoring technology and the increasing maturity of image processing technology, the original use of manpower to monitor suspicious targets can no longer meet actual needs. Intelligent security systems based on technologies such as artificial intelligence and video analysis can make up for the problem of insufficient manpower to a large extent.

[0003] In the related art, the monitoring system for suspicious targets is easily affected by factors such as lighting changes, shadows, and occlusions when facing complex dynamic scenes. It is difficult to accurately extract moving targets for effective identification, and usually relies on simple area division to determine the location of suspicious targets to determine whether to issue an intrusion alarm, and the detection effect is poor. Summary of the invention

[0004] Based on this, it is necessary to provide an area intrusion detection method, system, device, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of area intrusion detection in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for detecting an area intrusion, comprising:

[0006] Obtain a static background video containing a target area in the substation, and obtain a background detection model based on video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area;

[0007] Acquire a real-time monitoring video containing the target area, use the background detection model to process the video frame images in the real-time monitoring video, and identify the monitored moving objects to be processed;

[0008] When the mobile object to be processed meets the intrusion detection condition, the spatial position of the region where the mobile object to be processed is located is determined according to the target position in the current video frame image of the real-time monitoring video; the target position is determined based on the target object part in the mobile object to be processed;

[0009] When the regional spatial position is within the target area, a regional intrusion alarm operation for the mobile object to be processed is triggered.

[0010] In one embodiment, the step of modeling a background detection model based on video frame images in the static background video includes:

[0011] Based on a static background image sequence constructed from a plurality of video frame images in the static background video, characteristic data of each pixel point corresponding to the target area that changes over time is calculated, and background modeling is performed on each pixel point;

[0012] The background detection model is obtained according to the background modeling result of each pixel.

[0013] In one embodiment, the method further comprises:

[0014] Acquire a newly added static background image including the target area;

[0015] According to the difference in background parameters for the target area between the newly added static background image and the background detection model, the background parameters of the background detection model are updated.

[0016] In one embodiment, the step of using the background detection model to process the video frame images in the real-time monitoring video and identifying the monitored moving objects to be processed includes:

[0017] Using the background detection model, the dynamic situation of the video frame image in the real-time monitoring video is detected to extract the foreground image;

[0018] By distinguishing the human feature information and the background feature information in the foreground image, a human outline is identified from the foreground image as the moving object to be processed.

[0019] In one of the embodiments, when the mobile object to be processed meets the intrusion detection condition, determining the regional spatial position of the mobile object to be processed according to the target position in the current video frame image of the real-time monitoring video includes:

[0020] When it is detected that the residence time of the mobile object to be processed exceeds a preset threshold, determining that the mobile object to be processed meets the intrusion detection condition;

[0021] In the current video frame image, a human body posture estimation algorithm is used to determine a target position of a target object part in the moving object to be processed;

[0022] Based on the mapping relationship between the video frame image and the actual space coordinates, the target position is mapped into the actual space coordinate system to obtain the regional spatial position of the moving object to be processed.

[0023] In a second aspect, the present application also provides a regional intrusion detection system, comprising:

[0024] A collection device is used to obtain a static background video containing a target area in the substation, and to obtain a real-time monitoring video containing the target area; the target area includes a non-working area in the substation; the static background video is a background video containing no moving objects in the target area;

[0025] A control system, for obtaining a background detection model based on the video frame images in the static background video, using the background detection model to process the video frame images in the real-time monitoring video, identifying the monitored moving object to be processed, and when the moving object to be processed meets the intrusion detection condition, determining the regional spatial position of the moving object to be processed according to the target position in the current video frame image of the real-time monitoring video, and triggering a regional intrusion alarm operation for the moving object to be processed when the regional spatial position is within the target area; the target position is determined based on the target object part in the moving object to be processed;

[0026] The alarm device is used to execute the area intrusion alarm operation for the mobile object to be processed.

[0027] In a third aspect, the present application also provides a regional intrusion detection device, including:

[0028] A model building module is used to obtain a static background video containing a target area in the substation, and to obtain a background detection model based on video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area;

[0029] A mobile object recognition module is used to obtain a real-time monitoring video containing the target area, use the background detection model to process the video frame images in the real-time monitoring video, and identify the monitored mobile objects to be processed;

[0030] A regional spatial position determination module, used to determine the regional spatial position of the mobile object to be processed according to the target position in the current video frame image of the real-time monitoring video when the mobile object to be processed meets the intrusion detection condition; the target position is determined based on the target object part in the mobile object to be processed;

[0031] The area intrusion alarm triggering module is used to trigger an area intrusion alarm operation for the mobile object to be processed when the spatial position of the area is within the range of the target area.

[0032] In a fourth aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Obtain a static background video containing a target area in the substation, and obtain a background detection model based on video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area;

[0034] Acquire a real-time monitoring video containing the target area, use the background detection model to process the video frame images in the real-time monitoring video, and identify the monitored moving objects to be processed;

[0035] When the mobile object to be processed meets the intrusion detection condition, the spatial position of the region where the mobile object to be processed is located is determined according to the target position in the current video frame image of the real-time monitoring video; the target position is determined based on the target object part in the mobile object to be processed;

[0036] When the regional spatial position is within the target area, a regional intrusion alarm operation for the mobile object to be processed is triggered.

[0037] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0038] Obtain a static background video containing a target area in the substation, and obtain a background detection model based on video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area;

[0039] Acquire a real-time monitoring video containing the target area, use the background detection model to process the video frame images in the real-time monitoring video, and identify the monitored moving objects to be processed;

[0040] When the mobile object to be processed meets the intrusion detection condition, the spatial position of the region where the mobile object to be processed is located is determined according to the target position in the current video frame image of the real-time monitoring video; the target position is determined based on the target object part in the mobile object to be processed;

[0041] When the regional spatial position is within the target area, a regional intrusion alarm operation for the mobile object to be processed is triggered.

[0042] In a sixth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0043] Obtain a static background video containing a target area in the substation, and obtain a background detection model based on video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area;

[0044] Acquire a real-time monitoring video containing the target area, use the background detection model to process the video frame images in the real-time monitoring video, and identify the monitored moving objects to be processed;

[0045] When the mobile object to be processed meets the intrusion detection condition, the spatial position of the region where the mobile object to be processed is located is determined according to the target position in the current video frame image of the real-time monitoring video; the target position is determined based on the target object part in the mobile object to be processed;

[0046] When the regional spatial position is within the target area, a regional intrusion alarm operation for the mobile object to be processed is triggered.

[0047] The above-mentioned regional intrusion detection method, system, device, computer equipment, computer-readable storage medium and computer program product obtain a static background video containing a target area in a substation, and obtain a background detection model based on the video frame image in the static background video. The target area includes a non-working area in the substation. The static background video is a background video that does not contain a moving object in the target area. Then, a real-time monitoring video containing the target area is obtained, and the video frame image in the real-time monitoring video is processed using the background detection model to identify the monitored moving object to be processed. Then, when the moving object to be processed meets the intrusion detection condition, the regional spatial position of the moving object to be processed is determined according to the target position in the current video frame image of the real-time monitoring video. The target position is determined based on the target object part in the moving object to be processed. When the regional spatial position is within the target area, the regional intrusion alarm operation for the moving object to be processed is triggered, thereby realizing dynamic real-time detection of the foreground and background motion conditions and accurate judgment of the spatial position of the human body area. It can accurately and timely detect whether the moving object enters the set alarm area, effectively improving the accuracy of regional intrusion detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0049] FIG1 is a schematic diagram of a flow chart of a method for detecting regional intrusion in an embodiment;

[0050] FIG2 is a schematic diagram of a system monitoring interface in one embodiment;

[0051] FIG3 is a schematic diagram of a flow chart of a method for detecting regional intrusion in another embodiment;

[0052] FIG4 is a schematic diagram of the architecture of a regional intrusion detection system in one embodiment;

[0053] FIG5 is a structural block diagram of a regional intrusion detection device in one embodiment;

[0054] FIG. 6 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] In an exemplary embodiment, as shown in FIG1 , a method for detecting an area intrusion is provided. This embodiment uses the method applied to a terminal as an example for explanation. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps 101 to 104. Among them:

[0057] Step 101, obtaining a static background video containing a target area in a substation, and obtaining a background detection model based on modeling of video frame images in the static background video.

[0058] As an example, the target area may include a non-working area in the substation, such as an operation-hazardous area in the substation.

[0059] The static background video may be a background video that does not include a moving object in the target area. For example, the video may be captured when there is no dynamic moving object (such as a worker) in the target area.

[0060] In actual applications, for application scenarios such as substations, since work activities have designated work areas, there are great safety hazards in activities in non-working areas. The safety protection system (i.e., regional intrusion detection system) needs to have the function of detecting workers entering dangerous areas. The system can set some dangerous areas as non-working areas (i.e., target areas), and obtain static background videos of the non-working areas for foreground and background modeling to obtain a background detection model for regional intrusion detection in non-working areas, so as to monitor the regional intrusion situation of non-working areas in real time based on the background detection model.

[0061] Step 102: acquiring a real-time monitoring video including the target area, using the background detection model to process the video frame images in the real-time monitoring video, and identifying the monitored moving objects to be processed.

[0062] In a specific implementation, by capturing video streams or continuous image frames in real time, a real-time monitoring video containing the target area can be obtained, and then a background detection model can be used to process the video frame images in the real-time monitoring video to realize dynamic real-time detection of background motion. When the operator enters a non-working area, the system will track the operator, that is, identify the monitored moving objects to be processed.

[0063] Optionally, the system can provide an interface for setting an intrusion alarm area (i.e., a target area) to detect foreground objects (i.e., moving objects to be processed) that intrude into the set alarm area. For example, the system can provide a graphical user interface GUI for users to customize the intrusion alarm area, thereby providing a flexible alarm area setting function to meet security needs in different scenarios.

[0064] Step 103, when the mobile object to be processed meets the intrusion detection condition, the spatial position of the region where the mobile object to be processed is located is determined according to the target position in the current video frame image of the real-time monitoring video.

[0065] The target position may be determined based on the target object part in the moving object to be processed, for example, the target position may be determined based on the foot of a human body.

[0066] In one example, when a worker is detected staying in a non-working area under monitoring, that is, the moving object to be processed meets the intrusion detection conditions, the system can lock the worker, identify the human body outline through the human body detection algorithm, and determine the position of the feet in the human body outline (that is, the target position), and then accurately determine the spatial position of the human body area, that is, the spatial position of the area where the moving object to be processed is located.

[0067] Step 104 : when the regional spatial position is within the target area, triggering a regional intrusion alarm operation for the mobile object to be processed.

[0068] Specifically, when the system detects that the operator is staying in the monitored non-working area, it will lock the system and determine that the operator has invaded the non-working area, that is, the spatial position of the area is within the target area, and the regional intrusion alarm operation can be triggered, such as a voice broadcast to remind the on-site personnel that the location is a non-working area. Therefore, through foreground and background modeling, the system can dynamically detect the movement of the foreground and background in real time. By accurately identifying the human body contour and judging the position of the feet, it can achieve accurate judgment of the spatial position of the human body area, overcome the shortcomings of the traditional method that is easily disturbed by the environment, and improve the accuracy and reliability of detection.

[0069] For example, when it is detected that a human body area in a video frame image enters a preset alarm area, the system can automatically trigger an alarm signal, including but not limited to a sound alarm, a text message notification, an email alarm, etc.

[0070] In an optional embodiment, as shown in FIG2 , the system may display a real-time monitoring interface, which may display a monitoring video screen including the target area, and may provide feedback on relevant monitoring information (such as equipment information in the target area, monitored operator information, etc.).

[0071] In the above-mentioned regional intrusion detection method, a static background video containing a target area in the substation is obtained, and a background detection model is obtained according to the video frame images in the static background video. Then, a real-time monitoring video containing the target area is obtained, and the background detection model is used to process the video frame images in the real-time monitoring video to identify the monitored moving object to be processed. Then, when the moving object to be processed meets the intrusion detection conditions, the regional spatial position of the moving object to be processed is determined according to the target position in the current video frame image of the real-time monitoring video. When the regional spatial position is within the target area, the regional intrusion alarm operation for the moving object to be processed is triggered, thereby realizing dynamic real-time detection of the foreground and background motion conditions and accurate judgment of the regional spatial position of the human body. It can accurately and timely detect whether the moving object has entered the set alarm area, effectively improving the accuracy of regional intrusion detection.

[0072] In an exemplary embodiment, the step of obtaining a background detection model based on the video frame images in the static background video may include the following steps:

[0073] Based on a static background image sequence constructed from multiple video frame images in the static background video, the feature data of each pixel point corresponding to the target area that changes with time is calculated, and background modeling is performed on each pixel point; based on the background modeling result of each pixel point, the background detection model is obtained.

[0074] In practical applications, for background modeling, an image sequence of a static background video (i.e., a static background image sequence) can be selected as the initial data to establish a background detection model. By calculating the characteristic data of each pixel that changes over time, such as the mean value, variance and other statistical characteristic data, the optical flow information and deep learning algorithm can be combined to perform background modeling based on the video frame image sequence. By continuously learning and updating the background model, it can adapt to the dynamic changes of the scene and effectively overcome the influence of factors such as illumination changes, shadows, and occlusions.

[0075] For example, a Gaussian mixture model algorithm can be used to perform background modeling on each pixel in a video frame image sequence, and the model parameters can be updated in real time to improve the adaptability and accuracy of the background detection model.

[0076] In an exemplary embodiment, the following steps may also be included:

[0077] Acquire a newly added static background image including the target area; and update the background parameters of the background detection model according to the difference in background parameters for the target area between the newly added static background image and the background detection model.

[0078] In the background modeling process, the model can be updated based on the difference between the newly added video frame image (i.e., the newly added static background image containing the target area) and the current background detection model. For example, the Gaussian mixture model algorithm, median filtering, frame difference method, etc. can be used to determine the difference to update the background detection model. This allows the model to be flexibly adjusted based on background changes, effectively improving the adaptability of the background detection model.

[0079] In an exemplary embodiment, the step of using the background detection model to process the video frame images in the real-time monitoring video and identifying the monitored moving objects to be processed may include the following steps:

[0080] The background detection model is used to detect the dynamic situation of the video frame image in the real-time monitoring video and extract the foreground image; by distinguishing the human feature information and the background feature information in the foreground image, the human body contour is identified from the foreground image as the moving object to be processed.

[0081] In one example, for real-time detection of dynamic situations, the video frame image in the real-time monitoring video can be differentially processed with the background detection model to extract the foreground image from the video frame image. Then, based on the result of foreground segmentation (i.e., foreground image), the changes in the foreground area in continuous video frame images can be analyzed. For example, the pixel change rate of the foreground area and the connected area analysis can be calculated to achieve dynamic real-time detection of foreground and background motion situations.

[0082] For example, by adopting background modeling techniques such as background difference method, such as Gaussian mixture model algorithm, each frame image in the monitoring video stream can be analyzed in real time to distinguish the foreground and background, and then the segmented foreground image can be further processed, such as using human body detection algorithm to identify human body contours and determine the moving object to be processed.

[0083] For example, through feature extraction, human feature information such as shape, color, texture, etc. can be extracted from the segmented foreground image, and then the extracted human feature information and background feature information can be classified using machine learning or deep learning models to obtain human body detection results in the foreground image. Then, using edge detection algorithms or image segmentation-based methods, human body contours can be extracted from the human body detection results, and morphological operations (such as corrosion, dilation, opening operations, and closing operations) can be performed on the human body contours to smooth the contours and remove noise, thereby achieving more refined segmentation.

[0084] In another example, the foreground image can be a binary foreground image. By using the target detection algorithm in deep learning, the moving target in the binary foreground image can be accurately identified, with special attention paid to the human body area. Then, based on the difference between the background detection model and the binary foreground image, the foreground (such as a moving object) can be segmented from the background through threshold processing and other methods to identify the moving object to be processed, thereby accurately detecting the moving object based on the dynamic real-time detection of the foreground and background motion.

[0085] In an exemplary embodiment, when the mobile object to be processed meets the intrusion detection condition, determining the spatial position of the region where the mobile object to be processed is located according to the target position in the current video frame image of the real-time monitoring video may include the following steps:

[0086] When it is detected that the residence time of the moving object to be processed exceeds a preset threshold, it is determined that the moving object to be processed meets the intrusion detection condition; in the current video frame image, a human body posture estimation algorithm is used to determine the target position of the target object part in the moving object to be processed; based on the mapping relationship between the video frame image and the actual space coordinates, the target position is mapped to the actual space coordinate system to obtain the regional spatial position of the moving object to be processed.

[0087] In a specific implementation, by further analyzing the identified human body contour, the specific position of the foot in the human body contour (ie, the target position) can be determined as a basis for judging whether the moving object to be processed enters the set alarm area (ie, the target area).

[0088] In one example, a human body detection algorithm can be used to identify the human body contour in a video frame image, and a human body posture estimation algorithm can be used to further analyze the specific position of the feet. Then, the human body contour and the position of its feet can be mapped to the actual space coordinate system in combination with the pixel coordinate system of the video frame, thereby enabling accurate judgment of the spatial position of the area where the moving object to be processed is located.

[0089] For example, based on specific pattern recognition algorithms such as human body proportions and posture analysis, the position of the feet can be located in the human body outline, and then the position of the feet in the image coordinate system can be converted into coordinates in the actual space, such as by performing perspective transformation or camera calibration based on parameters such as the camera's viewing angle, focal length, and position, and then the position information of the moving object to be processed in the actual space (i.e., the regional spatial position) can be output.

[0090] In an exemplary embodiment, as shown in FIG3 , a flow chart of another method for detecting regional intrusion is provided. In this embodiment, the method includes the following steps:

[0091] In step 301, a static background video containing a target area in a substation is obtained, and a background detection model is obtained based on the video frame image model in the static background video. In step 302, a real-time monitoring video containing a target area is obtained, and the background detection model is used to detect the dynamic situation of the video frame image in the real-time monitoring video, and a foreground image is extracted. In step 303, by distinguishing the human feature information and the background feature information in the foreground image, a human body contour is identified from the foreground image as a mobile object to be processed. In step 304, when it is detected that the residence time of the mobile object to be processed exceeds a preset threshold, it is determined that the mobile object to be processed meets the intrusion detection condition. In step 305, in the current video frame image, a human posture estimation algorithm is used to determine the target position of the target object part in the mobile object to be processed. In step 306, based on the mapping relationship between the video frame image and the actual space coordinates, the target position is mapped to the actual space coordinate system to obtain the regional spatial position of the mobile object to be processed. In step 307, when the regional spatial position is within the target area, a regional intrusion alarm operation for the mobile object to be processed is triggered. It should be noted that the specific definitions of the above steps can be found in the specific definitions of a regional intrusion detection method above, which will not be repeated here.

[0092] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0093] Based on the same inventive concept, the embodiment of the present application also provides a regional intrusion detection system for implementing the regional intrusion detection method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more regional intrusion detection system embodiments provided below can refer to the limitations on the regional intrusion detection method above, and will not be repeated here.

[0094] In an exemplary embodiment, as shown in FIG4 , a regional intrusion detection system is provided, the system comprising:

[0095] A collection device is used to obtain a static background video containing a target area in the substation, and to obtain a real-time monitoring video containing the target area; the target area includes a non-working area in the substation; the static background video is a background video containing no moving objects in the target area;

[0096] A control system, for obtaining a background detection model based on the video frame images in the static background video, using the background detection model to process the video frame images in the real-time monitoring video, identifying the monitored moving object to be processed, and when the moving object to be processed meets the intrusion detection condition, determining the regional spatial position of the moving object to be processed according to the target position in the current video frame image of the real-time monitoring video, and triggering a regional intrusion alarm operation for the moving object to be processed when the regional spatial position is within the target area; the target position is determined based on the target object part in the moving object to be processed;

[0097] The alarm device is used to execute the area intrusion alarm operation for the mobile object to be processed.

[0098] Based on the same inventive concept, the embodiment of the present application also provides a regional intrusion detection device for implementing the regional intrusion detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more regional intrusion detection device embodiments provided below can refer to the limitations of the regional intrusion detection method above, and will not be repeated here.

[0099] In an exemplary embodiment, as shown in FIG5 , a regional intrusion detection device is provided, comprising:

[0100] The model building module 501 is used to obtain a static background video containing a target area in the substation, and to obtain a background detection model based on the video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area;

[0101] A moving object recognition module 502 is used to obtain a real-time monitoring video containing the target area, process the video frame images in the real-time monitoring video using the background detection model, and identify the monitored moving objects to be processed;

[0102] The regional spatial position determination module 503 is used to determine the regional spatial position of the mobile object to be processed according to the target position in the current video frame image of the real-time monitoring video when the mobile object to be processed meets the intrusion detection condition; the target position is determined based on the target object part in the mobile object to be processed;

[0103] The area intrusion alarm triggering module 504 is used to trigger an area intrusion alarm operation for the mobile object to be processed when the area spatial position is within the range of the target area.

[0104] In one embodiment, the model building module 501 includes:

[0105] A background modeling submodule, for calculating the time-varying feature data of each pixel point corresponding to the target area based on a static background image sequence constructed from a plurality of video frame images in the static background video, and performing background modeling on each pixel point;

[0106] The background detection model obtaining submodule is used to obtain the background detection model according to the background modeling result of each pixel point.

[0107] In one embodiment, the apparatus further comprises:

[0108] A new background image acquisition module is added, which is used to acquire a new static background image including the target area;

[0109] The model updating module is used to update the background parameters of the background detection model according to the background parameter difference between the newly added static background image and the background detection model for the target area.

[0110] In one embodiment, the mobile object identification module 502 includes:

[0111] A foreground image extraction submodule is used to detect the dynamic situation of the video frame image in the real-time monitoring video using the background detection model to extract the foreground image;

[0112] The submodule for determining the moving object to be processed is used to identify the human body contour from the foreground image as the moving object to be processed by distinguishing the human body feature information and the background feature information in the foreground image.

[0113] In one embodiment, the regional spatial position determination module 503 includes:

[0114] An intrusion detection determination submodule, configured to determine that the mobile object to be processed meets the intrusion detection condition when it is detected that the residence time of the mobile object to be processed exceeds a preset threshold;

[0115] A target position acquisition submodule is used to determine the target position of the target object part in the moving object to be processed in the current video frame image by using a human posture estimation algorithm;

[0116] The coordinate mapping submodule is used to map the target position into the actual space coordinate system based on the mapping relationship between the video frame image and the actual space coordinates, so as to obtain the regional spatial position of the moving object to be processed.

[0117] Each module in the above-mentioned regional intrusion detection device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0118] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG6. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for detecting an area intrusion is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0119] Those skilled in the art will understand that the structure shown in FIG. 6 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0120] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0121] Obtain a static background video containing a target area in the substation, and obtain a background detection model based on video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area;

[0122] Acquire a real-time monitoring video containing the target area, use the background detection model to process the video frame images in the real-time monitoring video, and identify the monitored moving objects to be processed;

[0123] When the mobile object to be processed meets the intrusion detection condition, the spatial position of the region where the mobile object to be processed is located is determined according to the target position in the current video frame image of the real-time monitoring video; the target position is determined based on the target object part in the mobile object to be processed;

[0124] When the regional spatial position is within the target area, a regional intrusion alarm operation for the mobile object to be processed is triggered.

[0125] In one embodiment, when the processor executes the computer program, it also implements the steps of the area intrusion detection method in other embodiments described above.

[0126] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0127] Obtain a static background video containing a target area in the substation, and obtain a background detection model based on video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area;

[0128] Acquire a real-time monitoring video containing the target area, use the background detection model to process the video frame images in the real-time monitoring video, and identify the monitored moving objects to be processed;

[0129] When the mobile object to be processed meets the intrusion detection condition, the spatial position of the region where the mobile object to be processed is located is determined according to the target position in the current video frame image of the real-time monitoring video; the target position is determined based on the target object part in the mobile object to be processed;

[0130] When the regional spatial position is within the target area, a regional intrusion alarm operation for the mobile object to be processed is triggered.

[0131] In one embodiment, when the computer program is executed by a processor, the steps of the area intrusion detection method in other embodiments described above are also implemented.

[0132] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0133] Obtain a static background video containing a target area in the substation, and obtain a background detection model based on video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area;

[0134] Acquire a real-time monitoring video containing the target area, use the background detection model to process the video frame images in the real-time monitoring video, and identify the monitored moving objects to be processed;

[0135] When the mobile object to be processed meets the intrusion detection condition, the spatial position of the region where the mobile object to be processed is located is determined according to the target position in the current video frame image of the real-time monitoring video; the target position is determined based on the target object part in the mobile object to be processed;

[0136] When the regional spatial position is within the target area, a regional intrusion alarm operation for the mobile object to be processed is triggered.

[0137] In one embodiment, when the computer program is executed by a processor, the steps of the area intrusion detection method in other embodiments described above are also implemented.

[0138] 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, and the collection, use and processing of relevant data must comply with relevant regulations.

[0139] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0140] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0141] The above-described 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 the present application. 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 protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A regional intrusion detection method, characterized in that: The method comprises: Obtain a static background video containing a target area in the substation, and obtain a background detection model based on video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area; Acquire a real-time monitoring video containing the target area, use the background detection model to process the video frame images in the real-time monitoring video, and identify the monitored moving objects to be processed; When the mobile object to be processed meets the intrusion detection condition, the spatial position of the region where the mobile object to be processed is located is determined according to the target position in the current video frame image of the real-time monitoring video; the target position is determined based on the target object part in the mobile object to be processed; When the regional spatial position is within the target area, a regional intrusion alarm operation for the mobile object to be processed is triggered.

2. The method according to claim 1, characterized in that The step of modeling the background detection model based on the video frame images in the static background video includes: Based on a static background image sequence constructed from a plurality of video frame images in the static background video, characteristic data of each pixel point corresponding to the target area that changes over time is calculated, and background modeling is performed on each pixel point; The background detection model is obtained according to the background modeling result of each pixel.

3. The method according to claim 2, characterized in that The method further comprises: Acquire a newly added static background image including the target area; According to the difference in background parameters for the target area between the newly added static background image and the background detection model, the background parameters of the background detection model are updated.

4. The method according to claim 1, characterized in that: The using the background detection model to process the video frame images in the real-time monitoring video to identify the monitored moving objects to be processed includes: Using the background detection model, the dynamic situation of the video frame image in the real-time monitoring video is detected to extract the foreground image; By distinguishing the human feature information and the background feature information in the foreground image, a human outline is identified from the foreground image as the moving object to be processed.

5. The method according to claim 1, characterized in that When the mobile object to be processed meets the intrusion detection condition, determining the regional spatial position of the mobile object to be processed according to the target position in the current video frame image of the real-time monitoring video includes: When it is detected that the residence time of the mobile object to be processed exceeds a preset threshold, determining that the mobile object to be processed meets the intrusion detection condition; In the current video frame image, a human body posture estimation algorithm is used to determine a target position of a target object part in the moving object to be processed; Based on the mapping relationship between the video frame image and the actual space coordinates, the target position is mapped into the actual space coordinate system to obtain the regional spatial position of the moving object to be processed.

6. A regional intrusion detection system, characterized in that: The system comprises: A collection device is used to obtain a static background video containing a target area in the substation, and to obtain a real-time monitoring video containing the target area; the target area includes a non-working area in the substation; the static background video is a background video containing no moving objects in the target area; A control system, for obtaining a background detection model based on the video frame images in the static background video, using the background detection model to process the video frame images in the real-time monitoring video, identifying the monitored moving object to be processed, and when the moving object to be processed meets the intrusion detection condition, determining the regional spatial position of the moving object to be processed according to the target position in the current video frame image of the real-time monitoring video, and triggering a regional intrusion alarm operation for the moving object to be processed when the regional spatial position is within the target area; the target position is determined based on the target object part in the moving object to be processed; The alarm device is used to execute the area intrusion alarm operation for the mobile object to be processed.

7. A regional intrusion detection device, characterized in that: The device comprises: A model building module is used to obtain a static background video containing a target area in the substation, and to obtain a background detection model based on video frame images in the static background video; the target area includes a non-working area in the substation; the static background video is a background video that does not contain a moving object in the target area; A mobile object recognition module is used to obtain a real-time monitoring video containing the target area, use the background detection model to process the video frame images in the real-time monitoring video, and identify the monitored mobile objects to be processed; A regional spatial position determination module, used to determine the regional spatial position of the mobile object to be processed according to the target position in the current video frame image of the real-time monitoring video when the mobile object to be processed meets the intrusion detection condition; the target position is determined based on the target object part in the mobile object to be processed; The area intrusion alarm triggering module is used to trigger an area intrusion alarm operation for the mobile object to be processed when the spatial position of the area is within the range of the target area.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images