Abnormality detection method and device, electronic equipment and storage medium

Abstract

The invention provides an anomaly detection method and device, electronic equipment and a storage medium, and relates to the technical field of monitoring, and the method comprises the steps: receiving a target image obtained through the shooting of a target monitoring point by a target pan-tilt camera; when it is judged that the target monitoring point is preliminarily abnormal based on the target image, all pan-tilt cameras in the pan-tilt camera set are scheduled to shoot the target monitoring point to obtain a set of images, and all the pan-tilt cameras in the pan-tilt camera set are located at different angle positions of the target monitoring point; performing image recognition on each image in the group of images to obtain a group of recognition results; and determining whether the target monitoring point is abnormal or not according to the group of identification results. By implementing the technical scheme provided by the invention, the effect of improving the anomaly detection efficiency is achieved.

Description

Technical Field

[0001] The present application relates to the field of monitoring technology, and in particular to an anomaly detection method, device, electronic device and storage medium. Background Art

[0002] In the field of power system automation monitoring technology, substation inspections mainly rely on periodic scanning of fixed cameras or single pan-tilt cameras, complete image acquisition through preset programs or manual remote control, and then perform anomaly recognition on single-view images to determine whether there is an anomaly in the substation (such as a certain power equipment or component). The methods in related technologies have the problem of single-view limitations, which may lead to false detection due to occlusion, lighting changes or small target size. In related technologies, there are also methods that use manual intervention to adjust the angles of other cameras to obtain images from multiple angles. This method cannot obtain multi-view data in real time, delaying the anomaly confirmation time. It can be seen that the anomaly detection methods in related technologies have the technical problem of low efficiency. Summary of the Invention

[0003] In order to solve the above technical problems, the present application provides an anomaly detection method, device, electronic device and storage medium.

[0004] In a first aspect, the present application provides an anomaly detection method, comprising: receiving a target image uploaded by a target pan-tilt camera, wherein the target image is obtained by photographing a target monitoring point by the target pan-tilt camera; when the target monitoring point is judged to be preliminarily abnormal based on the target image, scheduling each pan-tilt camera in the pan-tilt camera group to photograph the target monitoring point respectively to obtain a group of images, wherein a group of images includes images obtained by photographing the target monitoring point by each pan-tilt camera in the pan-tilt camera group, and each pan-tilt camera in the pan-tilt camera group is located at a different angular position of the target monitoring point; performing image recognition on each image in a group of images to obtain a group of recognition results, wherein each recognition result in a group of recognition results corresponds to an image in a group of images; and determining whether there is an abnormality at the target monitoring point based on a group of recognition results.

[0005] By adopting the above technical solution, the target image uploaded by the target gimbal camera is first received and it is determined whether the target monitoring point has a preliminary abnormality. If it is a preliminary abnormality, the gimbal camera group at different angles is dispatched to take a group of images, and the group of images is recognized separately to obtain a group of recognition results. Finally, it is determined whether the target monitoring point has an abnormality based on the recognition results. This avoids the limitation of a single perspective, can obtain multi-perspective data in real time, improves the efficiency of anomaly detection, and reduces false detections.

[0006] Optionally, each pan-tilt camera in the pan-tilt camera group is scheduled to shoot the target monitoring point separately to obtain a group of images, including: determining a pan-tilt camera group that meets preset conditions; scheduling each pan-tilt camera in the pan-tilt camera group to synchronously shoot the target monitoring point separately and upload the shot images; obtaining the images uploaded by each pan-tilt camera in the pan-tilt camera group to obtain a group of images.

[0007] By adopting the above technical solution, the target image uploaded by the target PTZ camera is first received. Based on this, when the target monitoring point is judged to have a preliminary abnormality, the PTZ camera group that meets the preset conditions can accurately select the appropriate camera to assist in shooting. These cameras are dispatched to synchronously shoot and upload images of the target monitoring point, which can obtain multi-view data in real time, avoiding delays in abnormality confirmation time due to manual intervention and adjustment. Finally, the images uploaded by each camera are obtained as a group of images, providing a multi-angle and more comprehensive data foundation for subsequent image recognition and accurate judgment of whether the target monitoring point has an abnormality, thereby improving the accuracy and efficiency of anomaly detection. Through automated scheduling and synchronous shooting, the full automation of multi-view image acquisition is achieved, reducing manual intervention and improving the operating efficiency and intelligence level of the system. The synchronously shot multi-view images can more comprehensively reflect the status of the target monitoring point, providing richer information for subsequent image recognition and anomaly judgment, thereby improving the accuracy of anomaly detection.

[0008] Optionally, determining a gimbal camera group that meets preset conditions includes one of the following: forming a gimbal camera group with each gimbal camera in the gimbal camera group whose distance to the target gimbal camera is less than a preset distance threshold, wherein the gimbal camera group includes the target gimbal camera; determining candidate gimbal cameras from the gimbal camera group according to a preset gimbal configuration table, and forming the candidate gimbal cameras into a gimbal camera group, wherein the gimbal configuration table records the monitoring points covered by each gimbal camera in the gimbal camera group, and the monitoring range of each gimbal camera in the candidate gimbal cameras covers the target monitoring point.

[0009] By adopting the above technical solution, a pan-tilt camera group that meets the preset conditions can be determined from the pan-tilt camera group. The pan-tilt camera group can be flexibly formed according to the distance of the target pan-tilt camera or the pan-tilt configuration table, so that the pan-tilt camera group can shoot the target monitoring point from different angles, avoiding the limitations of a single perspective, reducing false detection or missed detection due to occlusion, lighting changes or small target size, improving the accuracy and efficiency of anomaly detection, and realizing real-time acquisition of multi-perspective data and timely confirmation of anomalies.

[0010] Optionally, each pan-tilt camera in the pan-tilt camera group is scheduled to shoot the target monitoring point respectively to obtain a group of images, including: determining the target information of the target monitoring point based on the target image, wherein the target information includes the target space coordinate information and the target size information; sending the target information to each pan-tilt camera in the pan-tilt camera group, so that each pan-tilt camera in the pan-tilt camera group can adjust the posture and focal length based on the target information, and synchronously shoot the target monitoring point and upload the shot images; receiving the images uploaded by each pan-tilt camera in the pan-tilt camera group to obtain a group of images.

[0011] By adopting the above technical solution, after receiving the target image uploaded by the target gimbal camera and judging that the target monitoring point is preliminarily abnormal, the target space coordinate information and target size information of the target monitoring point are determined according to the target image, and this information is sent to each gimbal camera in the gimbal camera group. Based on this information, each camera can adjust its posture and focal length, synchronously shoot the target monitoring point and upload the image, which can improve the accuracy and pertinence of the shot image, and avoid image blur or failure to cover the target monitoring point due to inappropriate camera posture and focal length; finally, the images uploaded by each gimbal camera are received to obtain a group of images for subsequent recognition, which helps to comprehensively and accurately identify whether the target monitoring point has an abnormality from multiple angles, and solve the problem of low efficiency of the abnormality detection method in the related art.

[0012] Optionally, the target information of the target monitoring point is determined according to the target image, including: determining the pixel coordinates and abnormal pixel size of the target monitoring point according to the target image; obtaining the target spatial coordinate information based on the target pose data, target field of view angle data and pixel coordinates of the target pan-tilt camera, and obtaining the target size information based on the target pose data, target field of view angle data and abnormal pixel size of the target pan-tilt camera.

[0013] By adopting the above technical solution, the pixel coordinates and abnormal pixel size of the target monitoring point can be determined using the target image, and then the target spatial coordinate information and target size information of the target monitoring point can be accurately obtained in combination with the target posture data and target field of view angle data of the target gimbal camera. This provides an accurate basis for each gimbal camera in the subsequent gimbal camera group to adjust the posture and focal length based on the target information and to synchronously shoot the target monitoring point, thereby avoiding the problem of poor shooting effects due to inaccurate target information, improving the accuracy of image recognition, and more efficiently determining whether there is an abnormality at the target monitoring point.

[0014] Optionally, determining whether there is an abnormality at the target monitoring point based on a set of recognition results includes: determining that there is an abnormality at the target monitoring point when the proportion of abnormal recognition results contained in a set of recognition results is greater than or equal to a preset proportion threshold.

[0015] By adopting the above technical solution, image recognition is performed on a group of images to obtain a group of recognition results. The presence of an abnormality at the target monitoring point is determined based on the comparison between the proportion of abnormal recognition results in the group of recognition results and a preset proportion threshold. This can overcome the limitations of a single perspective, avoid false detection or missed detection due to occlusion, lighting changes or small target size, and improve the accuracy and efficiency of abnormality detection.

[0016] Optionally, determining whether there is an abnormality at the target monitoring point based on a set of recognition results includes: performing weighted sum calculation on the confidence values corresponding to each recognition result in a set of recognition results to obtain a comprehensive score; when the comprehensive score is greater than a preset score threshold, determining that there is an abnormality at the target monitoring point.

[0017] By adopting the above technical solution, a weighted summation is performed on the confidence values corresponding to each recognition result in a set of recognition results to obtain a comprehensive score, which can more scientifically and accurately evaluate the abnormal situation of the target monitoring point. When the comprehensive score is greater than the preset score threshold, it is determined that the target monitoring point has an abnormality, which can improve the accuracy and reliability of anomaly detection, avoid false detection or missed detection caused by single-view detection, and improve the efficiency of anomaly detection.

[0018] Optionally, after determining that an abnormality exists at the target monitoring point, the method further includes: issuing an alarm message.

[0019] By adopting the above technical solution, when it is determined that there is indeed an abnormality at the target monitoring point, the system will trigger the alarm mechanism and send alarm information to designated objects (such as maintenance personnel, central control system, etc.). These alarm information can be conveyed through various channels, such as SMS, email, in-application notification or directly display warnings in the monitoring center.

[0020] In the second aspect of the present application, an abnormality detection device is also provided, including: a receiving module for receiving a target image uploaded by a target pan-tilt camera, wherein the target image is obtained by shooting the target monitoring point by the target pan-tilt camera; a scheduling module for scheduling each pan-tilt camera in the pan-tilt camera group to shoot the target monitoring point respectively when the target monitoring point is judged to be preliminarily abnormal based on the target image, to obtain a group of images, wherein the group of images includes images obtained by each pan-tilt camera in the pan-tilt camera group shooting the target monitoring point, and each pan-tilt camera in the pan-tilt camera group is located at a different angular position of the target monitoring point; an identification module for performing image recognition on each image in a group of images respectively to obtain a group of recognition results, wherein each recognition result in a group of recognition results corresponds to an image in a group of images; a determination module for determining whether there is an abnormality at the target monitoring point based on a group of recognition results.

[0021] In a third aspect of the present application, an electronic device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor implements any one of the above method steps when executing the program.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is further provided. The computer-readable storage medium stores instructions. When the instructions are executed, any one of the above method steps is performed.

[0023] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: 1. It avoids the limitation of single perspective and can obtain multi-perspective data in real time, thus improving the efficiency of anomaly detection and reducing false detection; 2. Through automated scheduling and synchronous shooting, full automation of multi-view image acquisition is achieved, reducing manual intervention and improving the system's operating efficiency and intelligence level. The synchronously shot multi-view images can more comprehensively reflect the status of the target monitoring point, providing richer information for subsequent image recognition and anomaly judgment, thereby improving the accuracy of anomaly detection. 3. The target spatial coordinate information and target size information of the target monitoring point are determined based on the target image, and this information is sent to each pan-tilt camera in the pan-tilt camera group. Each camera can adjust its posture and focal length based on this information, synchronously shoot the target monitoring point and upload the image, which can improve the accuracy and pertinence of the captured image and avoid image blur or failure to cover the target monitoring point due to inappropriate camera posture and focal length. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flowchart of an anomaly detection method provided by an embodiment of the present application; Figure 2 This is an architecture diagram of a multi-device collaborative active monitoring and decision-making system provided by an embodiment of the present application; Figure 3 is a schematic diagram of a spatial coordinate conversion algorithm provided in an embodiment of the present application; Figure 4 This is a schematic diagram of the multi-perspective decision-making process provided by an embodiment of the present application; Figure 5 This is a structural block diagram of an anomaly detection device provided in an embodiment of the present application; Figure 6 It is a structural diagram of an electronic device disclosed in an embodiment of the present application.

[0025] Description of reference numerals: 600 - electronic device; 601 - processor; 602 - communication bus; 603 - user interface; 604 - network interface; 605 - memory. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0027] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0028] In the description of the embodiments of the present application, the term "plurality" means two or more. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of such features. The terms "include," "comprise," "have" and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0029] This application provides an anomaly detection method, referring to Figure 1 , Figure 1 : is a flowchart of an anomaly detection method provided in an embodiment of the present application, the method comprising: Step S101: receiving a target image uploaded by a target PTZ camera, wherein the target image is obtained by photographing a target monitoring point by the target PTZ camera; Step S102: When the target monitoring point is determined to be preliminarily abnormal based on the target image, each pan-tilt camera in the pan-tilt camera group is dispatched to photograph the target monitoring point to obtain a set of images, wherein the set of images includes images obtained by each pan-tilt camera in the pan-tilt camera group photographing the target monitoring point, and each pan-tilt camera in the pan-tilt camera group is located at a different angular position of the target monitoring point. Step S103, performing image recognition on each image in the set of images to obtain a set of recognition results, wherein each recognition result in the set of recognition results corresponds to one image in the set of images; Step S104: determining whether there is any abnormality at the target monitoring point based on a set of recognition results.

[0030] Through the above steps, the target image uploaded by the target PTZ camera is first received and it is determined whether the target monitoring point has a preliminary abnormality. If it is a preliminary abnormality, the PTZ camera group at different angles is dispatched to take a group of images, and the group of images is recognized separately to obtain a group of recognition results. Finally, it is determined whether the target monitoring point has an abnormality based on the recognition results. This avoids the limitation of a single perspective, can obtain multi-perspective data in real time, improves the efficiency of anomaly detection, and reduces false detections.

[0031] The execution subject of the above steps can be a server, a cloud, or a central processing node. This embodiment provides an anomaly detection method for automated monitoring of power systems such as substations. First, a target PTZ camera receives a target image captured at a target monitoring point and performs a preliminary judgment on the target image. For example, based on the received target image, a preliminary judgment is made on whether the target monitoring point may have an abnormality. If the preliminary judgment is that an abnormality exists, a group (or multiple) of PTZ cameras are further dispatched. These cameras are located at different angles of the target monitoring point to capture the same target monitoring point, obtaining a group of images. The group of images is a group of images from different perspectives of the target monitoring point. Image recognition processing is performed on each group of images to obtain a group of recognition results. The group of recognition results are combined to finally determine whether the target monitoring point actually has an abnormality. That is, a single PTZ camera (target PTZ camera) performs regular photography of the monitoring point, and image recognition technology is used to determine whether a preliminary abnormality exists. When a preliminary abnormality is found, a group of PTZ cameras (PTZ camera group) pre-deployed at different spatial angles are automatically dispatched to simultaneously capture the target monitoring point to obtain a multi-perspective image dataset. After each group of perspective images is independently analyzed, a joint decision is made based on the recognition results of the multiple perspectives to ultimately determine whether an abnormality exists. The aforementioned PTZ camera group may or may not include the aforementioned target PTZ camera. In related technologies, due to the angular limitations of a single camera or a fixed camera, false detections are easily caused by factors such as occlusion and lighting changes. Alternatively, manual adjustment of the camera angle is required, making it impossible to acquire multi-view data in real time, resulting in low detection efficiency. This embodiment utilizes a PTZ camera group to capture target monitoring points from different angles, enabling more comprehensive capture of target feature information. Even when some angles are blocked or lighting conditions are poor, images from other angles may still provide sufficient information for anomaly determination, effectively reducing the probability of false detections. Upon detecting a preliminary anomaly, the PTZ camera group can be rapidly dispatched for multi-angle capture, and image recognition and analysis can be performed in real time, eliminating the need for manual adjustment of camera angles. This significantly shortens the time required to confirm anomalies and improves the system's response speed. This embodiment reduces manual intervention and improves the system's intelligence through automated scheduling and multi-view collaborative analysis. The system can automatically determine preliminary anomalies and trigger further multi-view detection, implementing an automated anomaly detection process and enhancing the intelligence level of automated monitoring of power systems. Taking abnormality detection of power equipment in a substation as an example, a pan-tilt camera cluster is deployed throughout the substation. The pan-tilt camera cluster includes the above-mentioned target pan-tilt camera and pan-tilt camera group. The above-mentioned target monitoring points can be power equipment in the substation, or local areas of power equipment, or components in the equipment, etc.

[0032] In an optional embodiment, each pan-tilt camera in the pan-tilt camera group is scheduled to shoot the target monitoring point respectively to obtain a group of images, including: determining a pan-tilt camera group that meets preset conditions; scheduling each pan-tilt camera in the pan-tilt camera group to synchronously shoot the target monitoring point respectively and upload the shot images; obtaining the images uploaded by each pan-tilt camera in the pan-tilt camera group to obtain a group of images.

[0033] In the above embodiment, the target image uploaded by the target PTZ camera is first received. Based on this, when the target monitoring point is judged to be initially abnormal, the PTZ camera group that meets the preset conditions can accurately select the appropriate camera to assist in shooting. These cameras are scheduled to synchronously shoot and upload images of the target monitoring point, which can obtain multi-view data in real time, avoiding delays in abnormality confirmation time due to manual intervention and adjustment. Finally, the images uploaded by each camera are obtained to obtain a group of images, which provides a multi-angle and more comprehensive data foundation for subsequent image recognition and accurate judgment of whether there is an abnormality at the target monitoring point, thereby improving the accuracy and efficiency of abnormality detection. Through automated scheduling and synchronous shooting, the full automation of multi-view image acquisition is achieved, reducing manual intervention and improving the operating efficiency and intelligence level of the system. The synchronously shot multi-view images can more comprehensively reflect the status of the target monitoring point, providing richer information for subsequent image recognition and abnormality judgment, thereby improving the accuracy of abnormality detection.

[0034] PTZ cameras that meet preset conditions are selected to form a PTZ camera group. The preset conditions can be determined based on the geographical location, equipment layout, and abnormality type of the monitoring point. For example, the preset condition can be that the above-mentioned target monitoring point is within the viewing angle coverage range, or the distance from the target monitoring point is less than a preset distance threshold, that is, the PTZ camera group that is most suitable for multi-angle shooting of the target monitoring point is screened out. The above-mentioned preset conditions can be flexibly set according to the actual application scenario to ensure that the selected PTZ camera group can cover the target monitoring point from different angles; each PTZ camera in the PTZ camera group is scheduled to shoot the target monitoring point at the same time, and upload the captured images to the server. Synchronous shooting ensures the temporal consistency of multi-view images and avoids information mismatch due to shooting time differences. In this way, the server can obtain a group of images, which includes a set of images from different perspectives of the target monitoring point. Not all available PTZ cameras are suitable for capturing images of a specific target monitoring point. By selecting cameras that meet preset conditions, resources can be used more efficiently, avoiding unnecessary energy consumption and data redundancy. Synchronous capture ensures that images are captured at the same time, reducing data inconsistencies caused by environmental changes (such as changes in lighting), and helping to improve the accuracy of subsequent analysis. Synchronous operation speeds up the image acquisition process, shortening the time from initial anomaly detection to completion of a comprehensive assessment, and improving the system's response speed. By dynamically selecting a group of PTZ cameras that meet preset conditions, this embodiment allows the system to flexibly adjust the combination of PTZ cameras involved in the capture process based on different monitoring needs and scenarios, thereby improving the system's adaptability and flexibility.

[0035] In an optional embodiment, determining a gimbal camera group that meets preset conditions includes one of the following: forming a gimbal camera group from each gimbal camera in the gimbal camera group whose distance from the target gimbal camera is less than a preset distance threshold, wherein the gimbal camera group includes the target gimbal camera; determining candidate gimbal cameras from the gimbal camera group according to a preset gimbal configuration table, and forming the candidate gimbal cameras into a gimbal camera group, wherein the gimbal configuration table records the monitoring points covered by each gimbal camera in the gimbal camera group, and the monitoring range of each gimbal camera in the candidate gimbal cameras covers the target monitoring point.

[0036] In the above embodiment, a pan-tilt camera group that meets the preset conditions can be determined from the pan-tilt camera group, and the pan-tilt camera group can be flexibly formed according to the distance of the target pan-tilt camera or the pan-tilt configuration table, so that the pan-tilt camera group can shoot the target monitoring point from different angles, avoiding the limitations of a single perspective, reducing false detection or missed detection due to occlusion, lighting changes or small target size, improving the accuracy and efficiency of anomaly detection, and at the same time realizing real-time acquisition of multi-perspective data and timely confirmation of anomalies.

[0037] This embodiment provides two different methods for determining the PTZ camera group. The first is a distance-based method, which selects all PTZ cameras whose distance from the target PTZ camera is less than a preset threshold to form a PTZ camera group. This method utilizes the spatial distribution relationship of PTZ cameras and screens out PTZ cameras that can effectively cover the target monitoring point by distance, ensuring that the same target monitoring point can be photographed from different angles. For example, all PTZ cameras within a radius of 50 meters (or other distance) can be used. This method is suitable for scenarios with compact physical space. The second is a configuration table-based method. According to a pre-set PTZ configuration table, candidate PTZ cameras whose monitoring range covers the target monitoring point are selected to form a PTZ camera group. That is, the selected cameras must be able to effectively cover the target monitoring point. The mapping relationship between each camera and the monitoring point is recorded in the PTZ configuration table. This method is suitable for scenarios with complex logical associations, such as multi-view coverage of distributed devices. Whether the selection method is based on distance or configuration table, both allow the system to be flexibly adjusted according to actual conditions, improving the ability to cope with different scenarios; this embodiment uses one of the above two methods to determine the pan-tilt camera group, which can ensure that data of the target monitoring point is obtained from multiple advantageous positions, reducing detection errors caused by viewing angle limitations; by reasonably selecting the pan-tilt camera group, unnecessary pan-tilt cameras are avoided from participating in shooting, resource utilization is optimized, and system operating costs are reduced.

[0038] In an optional embodiment, each pan-tilt camera in the pan-tilt camera group is scheduled to shoot the target monitoring point respectively to obtain a group of images, including: determining the target information of the target monitoring point based on the target image, wherein the target information includes target space coordinate information and target size information; sending the target information to each pan-tilt camera in the pan-tilt camera group, so that each pan-tilt camera in the pan-tilt camera group can adjust the posture and focal length based on the target information, and synchronously shoot the target monitoring point and upload the shot images; receiving the images uploaded by each pan-tilt camera in the pan-tilt camera group to obtain a group of images.

[0039] In the above embodiment, after receiving the target image uploaded by the target pan-tilt camera and judging that the target monitoring point is preliminarily abnormal, the target space coordinate information and target size information of the target monitoring point are determined according to the target image, and this information is sent to each pan-tilt camera in the pan-tilt camera group, so that each camera can adjust its posture and focal length based on this, synchronously shoot the target monitoring point and upload the image, which can improve the accuracy and pertinence of the captured image, and avoid image blur or non-coverage of the target monitoring point due to inappropriate camera posture and focal length; finally, the images uploaded by each pan-tilt camera are received to obtain a group of images for subsequent recognition, which helps to comprehensively and accurately identify whether there is an abnormality in the target monitoring point from multiple angles, and solve the problem of low efficiency of the abnormality detection method in the related art.

[0040] First, the target image uploaded by the target gimbal camera is analyzed to extract the target spatial coordinate information and target size information of the target monitoring point. The target spatial coordinate information is used to clarify the specific position of the target monitoring point in space, and the target size information reflects the size specifications of the target monitoring point. This information is the basis for subsequent operations. The acquired target information is sent to each gimbal camera in the gimbal camera group. Based on this information, each gimbal camera accurately adjusts its own posture (such as angle, direction) and focal length. Through posture adjustment, it is ensured that the camera can be aimed at the target monitoring point from an appropriate perspective. Through focal length adjustment, it is ensured that the captured image clearly and completely presents the details of the target monitoring point. Then, each gimbal camera synchronously shoots the target monitoring point and uploads the captured images. The server receives the images uploaded by each gimbal camera in the gimbal camera group and obtains a group of images for subsequent image recognition and anomaly judgment. This embodiment analyzes the target image and determines target information, enabling each PTZ camera in the PTZ camera group to accurately adjust its posture and focus based on the target's spatial coordinate information and size information, ensuring clear and complete captured images and improving image quality. Related art methods require manual adjustment of camera angle and focus (e.g., remote PTZ parameter control), which is time-consuming and error-prone. This embodiment's method automatically distributes target information, achieving millisecond-level adaptive parameter adjustment. Fixed-focus cameras struggle to capture small targets at long distances (e.g., insulator defects). This embodiment uses dynamic focus adjustment to automatically optimize magnification based on target size information, improving resolution. Through this embodiment, each PTZ camera in the PTZ camera group adjusts its posture and focus based on target information before capturing images. This allows for clearer images with a more appropriate viewing angle, more complete details of the target monitoring point, and provides high-quality data for subsequent image recognition, thereby improving the accuracy of anomaly detection. The PTZ camera group's shooting parameters can be flexibly adjusted based on the spatial coordinates and size information of different target monitoring points, making it suitable for a variety of complex monitoring scenarios and different types of target monitoring points, enhancing the adaptability and versatility of the entire anomaly detection system.

[0041] In an optional embodiment, the target information of the target monitoring point is determined according to the target image, including: determining the pixel coordinates and abnormal pixel size of the target monitoring point according to the target image; obtaining the target spatial coordinate information based on the target pose data, target field of view angle data and pixel coordinates of the target pan-tilt camera, and obtaining the target size information based on the target pose data, target field of view angle data and abnormal pixel size of the target pan-tilt camera.

[0042] In the above embodiment, the target image can be used to determine the pixel coordinates and abnormal pixel size of the target monitoring point, and then combined with the target posture data and target field of view angle data of the target pan-tilt camera to accurately obtain the target space coordinate information and target size information of the target monitoring point, so as to provide an accurate basis for each pan-tilt camera in the subsequent pan-tilt camera group to adjust the posture and focal length based on the target information and to synchronously shoot the target monitoring point, thereby avoiding the problem of poor shooting effect due to inaccurate target information, improving the accuracy of image recognition, and more efficiently determining whether there is an abnormality in the target monitoring point.

[0043] The target image taken by the target PTZ camera is analyzed and processed, and the pixel coordinates of the target monitoring point in the image, that is, the position of the target monitoring point on the image plane, are determined through image recognition and analysis algorithms; at the same time, the abnormal pixel size occupied by the target monitoring point in the image is calculated. These pixel-level data are the basis for subsequent calculations; then, combined with the target pose data of the target PTZ camera (including the position and pose information of the camera in space), the target field of view angle data (the spatial range angle that the camera can observe) and the determined pixel coordinates, the pixel coordinates on the image plane are converted to the actual space coordinate system using the principles of geometric optics and spatial coordinate transformation, thereby obtaining the target space coordinate information of the target monitoring point and determining its position in the real space. The specific position in real space; based on the target pose data, target field of view angle data and abnormal pixel size of the target gimbal camera, by establishing a correspondence model between image pixels and actual size, the pixel size of the target monitoring point in the image is converted into the actual physical size, and then the target size information is obtained, and the actual size specifications of the target monitoring point are clarified; in actual applications, when calculating the target space coordinates and target size information, it is also necessary to combine depth information, such as the z value of the target image in the camera coordinate system, that is, the world coordinate system position of the target monitoring point is calculated through the pixel coordinates, depth information, target gimbal camera pose data and field of view angle data of the target monitoring point; the physical size information of the target can be converted according to the size of the abnormal pixel area and the camera magnification. This embodiment combines the pixel information of the target image with the posture and field of view data of the gimbal camera to accurately calculate the spatial coordinates and size information of the target, providing more accurate input for subsequent anomaly detection, realizing automatic extraction and calculation of target information, reducing manual intervention, and improving the operating efficiency and intelligence level of the system. The accurate target information can guide the gimbal camera to adjust its posture and focal length, ensuring that multi-view images that are more in line with the actual situation of the target monitoring point are captured, improving the effectiveness and quality of the image, enhancing the reliability of anomaly detection, and improving the accuracy of anomaly detection.

[0044] In an optional embodiment, determining whether there is an abnormality at a target monitoring point based on a set of recognition results includes: determining that there is an abnormality at the target monitoring point when the proportion of abnormal recognition results contained in a set of recognition results is greater than or equal to a preset proportion threshold.

[0045] In the above embodiment, image recognition is performed on a group of images to obtain a group of recognition results. Whether there is an abnormality in the target monitoring point is determined based on the comparison between the proportion of abnormal recognition results in the group of recognition results and a preset proportion threshold. This can overcome the limitations of a single perspective, avoid false detection or missed detection due to occlusion, lighting changes or small target size, and improve the accuracy and efficiency of abnormality detection.

[0046] After performing image recognition on a set of images captured by the pan-tilt camera group, a set of recognition results is obtained. By counting the number of recognition results determined to be abnormal in this set of recognition results and calculating their proportion in the set of recognition results, when this proportion is greater than or equal to a pre-set ratio threshold, it is determined based on the majority judgment principle that the target monitoring point is abnormal; otherwise, it is considered that the target monitoring point is not abnormal. This method quantitatively analyzes the recognition results of multi-view images and determines the status of the target monitoring point using a unified standard. By integrating the recognition results of multi-view images and using a preset ratio threshold as the judgment basis, this embodiment can more comprehensively and objectively evaluate the status of the target monitoring point, reduce errors caused by single-view misjudgment or subjective judgment, and improve the accuracy of abnormality judgment. The preset ratio threshold can be flexibly adjusted according to different application scenarios to adapt to various specific needs and conditions, thereby improving the flexibility and adaptability of the system. For example, the preset ratio threshold is 50% (or 60%, or other).

[0047] In an optional embodiment, determining whether there is an abnormality at a target monitoring point based on a set of recognition results includes: performing weighted sum calculation on the confidence values corresponding to each recognition result in a set of recognition results to obtain a comprehensive score; when the comprehensive score is greater than a preset score threshold, determining that there is an abnormality at the target monitoring point.

[0048] In the above embodiment, a weighted summation is performed on the confidence values corresponding to each recognition result in a set of recognition results to obtain a comprehensive score, which can more scientifically and accurately evaluate the abnormal situation of the target monitoring point. When the comprehensive score is greater than the preset score threshold, it is determined that there is an abnormality in the target monitoring point, which can improve the accuracy and reliability of anomaly detection, avoid false detection or missed detection caused by single-view detection, and improve the efficiency of anomaly detection.

[0049] After performing image recognition on a set of images captured by the gimbal camera group, each recognition result corresponds to a confidence value, which reflects the reliability of the recognition result. The confidence of the image recognition results captured by different gimbal cameras may vary due to factors such as shooting angle and shooting quality. This embodiment assigns different weights to the confidence values of each recognition result, takes into account the differences in the importance of each recognition result, and then sums these weighted confidence values to obtain a comprehensive score. When the comprehensive score is greater than the pre-set score threshold, it is determined that the target monitoring point is abnormal; otherwise, it is considered that the target monitoring point is not abnormal. This method quantifies and integrates the reliability of multi-view image recognition results to form a unified judgment basis. Assume that the PTZ camera group includes 3 (or other numbers) PTZ cameras, with confidence values C1, C2, and C3, and corresponding weight coefficients K1, K2, and K3, respectively. In practical applications, the weight coefficient of each PTZ camera can be set according to the distance between each PTZ camera and the target monitoring point. The corresponding weight coefficient can also be set according to the proportion of the target monitoring point in the image taken by each PTZ camera. The larger the proportion of the target monitoring point in the image, the larger the corresponding weight coefficient. For example, K1=0.45, K2=0.35, K3=0.2. A comprehensive score is obtained by weighted summing up the confidence values. For example, the preset score threshold is 0.5 (or other value). When the comprehensive score is greater than the preset score threshold, it is considered that the target monitoring point is abnormal. In the related art, anomalies are judged based only on some simple rules, which cannot fully reflect the comprehensive situation of the multi-view image recognition results. However, this embodiment fully considers the reliability differences of the image recognition results of each view by weighted summation of the recognition result confidence values, making the judgment results more in line with the actual situation, reducing misjudgments, greatly improving the accuracy of anomaly judgment, and overcoming the limitations of a single judgment standard.

[0050] In an optional embodiment, after determining that an abnormality exists at the target monitoring point, the method further includes: issuing an alarm message.

[0051] In the above embodiment, when it is determined that there is indeed an abnormality at the target monitoring point, the system will trigger the alarm mechanism and send an alarm message to the designated object (such as maintenance personnel, central control system, etc.). These alarm messages can be conveyed through various channels, such as SMS, email, in-application notification or directly displaying warnings in the monitoring center.

[0052] Upon identifying an anomaly at a target monitoring point, the system triggers an alert mechanism, sending a warning message to relevant personnel or systems. This alert can take the form of sound, light, text message, pop-up window, and other notifications. Its purpose is to promptly notify relevant personnel of an anomaly at the target monitoring point, enabling them to quickly respond and take appropriate action. Automatically issuing an alert upon detecting an anomaly further enhances the system's automation, reduces manual intervention, and improves operational efficiency. Automatically issuing an alert ensures that anomalies are promptly identified, allowing relevant personnel or systems to take swift action and mitigate their impact on system operations.

[0053] Obviously, the embodiments described above are only a part of the embodiments of the present application, rather than all the embodiments. The present application will be described in detail below with reference to specific embodiments.

[0054] The present invention provides a multi-device collaborative active monitoring and decision-making method and system. Figure 2 This is an architecture diagram of a multi-device collaborative active monitoring and decision-making system provided in an embodiment of the present application. The system is described below.

[0055] 1. Collaborative architecture (the PTZ groups in the substation act as masters and slaves to each other) Target gimbal (e.g., gimbal A with an abnormality): Generates the target's 3D coordinates (through pixel coordinate and depth information conversion) and target size (through the abnormal pixel size and the field of view (FOV) at the camera's current magnification) when an abnormality is triggered. Other gimbals (such as gimbals B / C / D...): Receive the target's 3D spatial coordinates and size information from the server and automatically adjust the gimbal's attitude and focal length using a spatial coordinate system conversion algorithm (such as homogeneous matrix transformation). Multi-view synchronous acquisition module: Each of the other PTZs captures the target based on a unified timestamp and uploads it to the edge computing node (or server) via a network protocol (such as RTSP / ONVIF); Distributed voting decision module: adopts majority decision strategy (e.g. alarm is triggered when ≥50% of devices are identified as abnormal) and combines confidence weighted algorithm to optimize voting results.

[0056] 2. Working Principle Abnormal triggering phase: gimbal A detects a suspected abnormality (such as device heating or component detachment) and calculates the target's 3D coordinates and size based on the camera's pose and field of view (FOV). Collaborative scheduling phase: The system calls the spatial location database of neighboring gimbals, plans the shortest turning path, and sends the target coordinates and size to the slave gimbal; Multi-view data fusion: Each gimbal simultaneously shoots and performs local recognition, uploading the results to a central decision node (or server) for voting; Alarm decision stage: If the voting result meets the preset threshold, a graded alarm is triggered (for example, a level 1 alarm requires manual review, and a level 2 alarm is directly pushed to the operation and maintenance platform).

[0057] The above-mentioned edge computing nodes and central decision nodes can be located in the same server. Figure 2 The image recognition algorithm, spatial coordinate conversion algorithm and pan-tilt scheduling control can be executed by one server.

[0058] Figure 3 is a schematic diagram of the spatial coordinate conversion algorithm provided by the embodiment of the present application, wherein: Ow-XwYwZw: World coordinate system (World coordinate system), unit: m; Oc-XcYcZc: Camera coordinate system, with the optical center as the origin, unit: m; o-xy: image coordinate system, the optical center is the midpoint of the image, unit: mm; uv: pixel coordinate system, unit pixel; P: a point in the world coordinate system; p: projection in the image coordinate system; f: camera focal length, equal to the distance between o and Oc; In addition, the world coordinate system is moved up by a height of h along the Z axis and rotated by θ around the X axis to be transformed into the camera coordinate system.

[0059] The coordinate transformation is explained below: (1) Camera matrix calculation 1) Internal parameter matrix K: Where W and H are the image width and height, (c x ,c y )=(W / 2,H / 2),(c x ,c y ) represents the center point of the image, f x 、f y Respectively represent the horizontal focal length and vertical focal length of the camera, θ h ,θ v Represents horizontal and vertical viewing angles respectively; 2) External parameter matrix [R|t]: The rotation matrix R is determined by the three-degree-of-freedom rotation quantity (such as Euler angle or rotation vector); Translation vector t = -R·C, where C is the three-dimensional coordinate of the camera in the world coordinate system; 3) Projection matrix P: P = K[R|t]; (2) Calculation of three-dimensional coordinates and radius 1) Center point back projection: Take the pixel coordinates (u, v) at the center of the rectangle, and the corresponding depth value is z depth (z value in camera coordinate system).

[0060] Back-project the 3D point to the camera coordinate system: 2) World coordinate system conversion: Radius calculation: Calculate the ratio of pixels to space: horizontal ratio, vertical ratio; Horizontal scale: z depth / f x , vertical scale: z depth / f y ; Take the maximum value of the width and height (pixels) of the rectangular frame max(w,h), where w and h refer to the width and height of the detected defect or abnormal point, and calculate the spatial radius based on the ratio: The spatial radius corresponds to the aforementioned target size information. 3. Specific implementation methods (1) Hardware deployment: 1) Install multiple cameras supporting PTZ (pan-tilt-zoom) in the substation; 2) Edge servers deploy target detection models (such as YOLO) and spatial coordinate conversion services.

[0062] (2) Workflow: Figure 4 This is a schematic diagram of the multi-perspective decision-making process provided by an embodiment of the present application, which includes the following steps: Step 1: During a routine inspection, pan / tilt A detects a crack on the surface of an insulator (with a 65% confidence level), triggering an abnormal event. Step 2: The system calculates the insulator's three-dimensional coordinates and size based on pan / tilt A's position parameters (pitch angle, azimuth angle, and focal length) and broadcasts them to pan / tilts B, C, and D. Step 3: Gimbal B / C / D adjusts its posture through inverse kinematics and completes focus shooting within 3 seconds. Step 4: Each gimbal performs local recognition (B / C is identified as a crack with confidence levels of 72% and 68%; D fails recognition due to an angle problem). The decision module executes the decision logic and ultimately determines whether there is an abnormality. For example, if the decision module determines that the number of valid votes is 3 / 4, an alarm is triggered.

[0063] Spatial coordinate mapping: Use Zhang Zhengyou calibration method (or simplify it to ignore distortion based on the camera field of view) to establish the camera internal and external parameter matrix, and combine the PTZ data and depth estimation algorithm to realize the conversion from pixel coordinates to world coordinates.

[0064] Voting weight design: Dynamically adjust the confidence weight according to the distance between the gimbal and the target and the lighting conditions (such as the weight of close-range devices +20%).

[0065] The embodiments of the present application solve the following technical problems in the related art: solving the problem of misjudgment caused by environmental interference in single-view detection; eliminating the problem of collaborative response delay when multiple devices run independently; and improving the confidence and robustness of anomaly recognition through multi-view data fusion.

[0066] Compared with the prior art, the embodiments of the present application have at least the following technical effects: Improved accuracy: Multi-view cross-validation reduces false positive rates by ≥30% (simulated experimental data), especially for complex occlusion scenarios. Efficiency optimization: Collaborative response time is ≤ 2 seconds (measured value), which is 80% more efficient than manual scheduling. Resource saving: Reduce redundant shooting times through dynamic scheduling and extend the life of the gimbal mechanism; Strong scalability: supports elastic expansion of the PTZ group size and is compatible with devices of different brands (through a standardized protocol adaptation layer).

[0067] This application also provides an abnormality detection device, such as Figure 5 As shown, Figure 5 This is a structural block diagram of an anomaly detection device provided in an embodiment of the present application, which includes: A receiving module 51 is configured to receive a target image uploaded by a target PTZ camera, wherein the target image is obtained by photographing a target monitoring point by the target PTZ camera; The scheduling module 52 is configured to, when the target monitoring point is determined to be preliminarily abnormal based on the target image, schedule each pan-tilt camera in the pan-tilt camera group to photograph the target monitoring point to obtain a set of images, wherein the set of images includes images obtained by each pan-tilt camera in the pan-tilt camera group photographing the target monitoring point, and each pan-tilt camera in the pan-tilt camera group is located at a different angular position of the target monitoring point; a recognition module 53 configured to perform image recognition on each image in the set of images to obtain a set of recognition results, wherein each recognition result in the set of recognition results corresponds to one image in the set of images; The determination module 54 is configured to determine whether there is an abnormality at the target monitoring point based on a set of recognition results.

[0068] In an optional embodiment, the above-mentioned scheduling module 52 includes: a first determination unit, used to determine a pan-tilt camera group that meets preset conditions; a scheduling unit, used to schedule each pan-tilt camera in the pan-tilt camera group to synchronously shoot the target monitoring point and upload the shot images; an acquisition unit, used to acquire the images uploaded by each pan-tilt camera in the pan-tilt camera group to obtain a group of images.

[0069] In an optional embodiment, the above-mentioned first determination unit includes one of the following: a first composition subunit, used to form a gimbal camera group from each gimbal camera in the gimbal camera group whose distance from the target gimbal camera is less than a preset distance threshold, wherein the gimbal camera group includes the target gimbal camera; a second composition subunit, used to determine candidate gimbal cameras from the gimbal camera group according to a preset gimbal configuration table, and form the candidate gimbal cameras into a gimbal camera group, wherein the gimbal configuration table records the monitoring points covered by each gimbal camera in the gimbal camera group, and the monitoring range of each gimbal camera in the candidate gimbal cameras covers the target monitoring point.

[0070] In an optional embodiment, the scheduling module 52 includes: a second determination unit, used to determine the target information of the target monitoring point based on the target image, wherein the target information includes target space coordinate information and target size information; a sending unit, used to send the target information to each gimbal camera in the gimbal camera group, so that each gimbal camera in the gimbal camera group can adjust the posture and focal length based on the target information, and synchronously shoot the target monitoring point and upload the shot images; a receiving unit, used to receive the images uploaded by each gimbal camera in the gimbal camera group to obtain a group of images.

[0071] In an optional embodiment, the above-mentioned second determination unit includes: a determination subunit, used to determine the pixel coordinates and abnormal pixel size of the target monitoring point based on the target image; an acquisition subunit, used to obtain target spatial coordinate information based on the target pose data, target field of view angle data and pixel coordinates of the target pan-tilt camera, and to obtain target size information based on the target pose data, target field of view angle data and abnormal pixel size of the target pan-tilt camera.

[0072] In an optional embodiment, the above-mentioned determination module 54 includes: a third determination unit, which is used to determine that there is an abnormality in the target monitoring point when the proportion of abnormal recognition results included in a group of recognition results is greater than or equal to a preset proportion threshold.

[0073] In an optional embodiment, the above-mentioned determination module 54 includes: a calculation unit, which is used to perform weighted sum calculation on the confidence values corresponding to each recognition result in a set of recognition results to obtain a comprehensive score; and a fourth determination unit, which is used to determine that there is an abnormality in the target monitoring point when the comprehensive score is greater than a preset score threshold.

[0074] In an optional embodiment, the above-mentioned device further includes: an alarm module, which is used to issue an alarm message after determining that an abnormality exists at the target monitoring point.

[0075] It should be noted that the above embodiments provide devices that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0076] The present application also provides a computer-readable storage medium, which stores instructions. When the instructions are executed, any one of the above-mentioned method steps is executed.

[0077] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0078] This application also discloses an electronic device. Figure 6 As shown, Figure 6 6. This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. The electronic device 600 may include: at least one processor 601, at least one communication bus 602, a user interface 603, at least one network interface 604, and a memory 605.

[0079] The communication bus 602 is used to implement the connection and communication between these components.

[0080] The user interface 603 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 603 may also include a standard wired interface and a wireless interface.

[0081] The network interface 604 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0082] The processor 601 may include one or more processing cores. The processor 601 utilizes various interfaces and lines to connect the various parts of the entire electronic device (such as a server), and executes various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 605, and calling data stored in the memory 605. Optionally, the processor 601 may be implemented in the form of at least one hardware of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 601 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display; and the modem is used to handle wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 601 and may be implemented separately through a single chip.

[0083] Among them, the memory 605 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 605 includes a non-transitory computer-readable storage medium. The memory 605 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 605 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 605 may also be optionally at least one storage device located away from the aforementioned processor 601. Reference Figure 6 , the memory 605 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of an anomaly detection method.

[0084] exist Figure 6In the electronic device 600 shown, the user interface 603 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 601 can be used to call an application program of an anomaly detection method stored in the memory 605. When executed by one or more processors 601, the electronic device 600 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited to the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0085] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed device or system can be implemented in other ways. For example, the device or system embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0087] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0088] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0090] The foregoing is merely an exemplary embodiment of the present disclosure and is not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure herein.

[0091] This application is intended to cover any modifications, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field not described in the present disclosure.

Claims

1. A method for detecting anomalies, characterized in that: include: Receiving a target image uploaded by a target PTZ camera, wherein the target image is obtained by photographing a target monitoring point by the target PTZ camera; In a case where the target monitoring point is determined to be preliminarily abnormal based on the target image, each pan-tilt camera in the pan-tilt camera group is dispatched to photograph the target monitoring point respectively to obtain a group of images, wherein the group of images includes images obtained by each pan-tilt camera in the pan-tilt camera group photographing the target monitoring point, and each pan-tilt camera in the pan-tilt camera group is located at a different angular position of the target monitoring point; performing image recognition on each image in the set of images to obtain a set of recognition results, wherein each recognition result in the set of recognition results corresponds to an image in the set of images; Determine whether the target monitoring point has an abnormality based on the set of recognition results.

2. The method according to claim 1, characterized in that Each pan-tilt camera in the pan-tilt camera group is dispatched to shoot the target monitoring point respectively to obtain a set of images, including: Determining the pan-tilt camera group that meets preset conditions; Dispatching each pan-tilt camera in the pan-tilt camera group to synchronously shoot the target monitoring point and upload the shot images; The image uploaded by each pan-tilt camera in the pan-tilt camera group is obtained to obtain the group of images.

3. The method according to claim 2, characterized in that Determining the pan-tilt camera group that meets the preset conditions includes one of the following: Forming the pan-tilt camera group with pan-tilt cameras in the pan-tilt camera group whose distances to the target pan-tilt camera are less than a preset distance threshold, wherein the pan-tilt camera group includes the target pan-tilt camera; According to a preset gimbal configuration table, candidate gimbal cameras are determined from the gimbal camera group, and the candidate gimbal cameras are formed into the gimbal camera group, wherein the gimbal configuration table records the monitoring points covered by each gimbal camera in the gimbal camera group, and the monitoring range of each gimbal camera in the candidate gimbal cameras covers the target monitoring point.

4. The method according to claim 1, wherein Each pan-tilt camera in the pan-tilt camera group is dispatched to shoot the target monitoring point respectively to obtain a set of images, including: Determining target information of the target monitoring point according to the target image, wherein the target information includes target space coordinate information and target size information; Sending the target information to each pan-tilt camera in the pan-tilt camera group, so that each pan-tilt camera in the pan-tilt camera group adjusts its posture and focal length based on the target information, and synchronously shoots the target monitoring point and uploads the shot image; Receive the image uploaded by each pan-tilt camera in the pan-tilt camera group to obtain the group of images.

5. The method according to claim 4, characterized in that Determining target information of the target monitoring point according to the target image includes: Determining the pixel coordinates and abnormal pixel size of the target monitoring point according to the target image; The target space coordinate information is obtained based on the target pose data, target field angle data and the pixel coordinates of the target gimbal camera, and the target size information is obtained based on the target pose data, target field angle data and the abnormal pixel size of the target gimbal camera.

6. The method according to claim 1, wherein Determining whether the target monitoring point has an abnormality according to the set of recognition results includes: When the proportion of abnormal recognition results included in the group of recognition results is greater than or equal to a preset proportion threshold, it is determined that an abnormality exists at the target monitoring point.

7. The method according to claim 1, characterized in that Determining whether the target monitoring point has an abnormality according to the set of recognition results includes: Performing weighted sum calculation on the confidence values corresponding to each recognition result in the set of recognition results to obtain a comprehensive score; When the comprehensive score is greater than a preset score threshold, it is determined that an abnormality exists at the target monitoring point.

8. An abnormality detection device, characterized in that: include: A receiving module is used to receive a target image uploaded by a target PTZ camera, wherein the target image is obtained by photographing a target monitoring point by the target PTZ camera; a scheduling module, configured to, when it is determined based on the target image that the target monitoring point is preliminarily abnormal, schedule each pan-tilt camera in the pan-tilt camera group to respectively photograph the target monitoring point to obtain a group of images, wherein the group of images includes images obtained by each pan-tilt camera in the pan-tilt camera group photographing the target monitoring point, and each pan-tilt camera in the pan-tilt camera group is respectively located at a different angular position of the target monitoring point; a recognition module, configured to perform image recognition on each image in the set of images to obtain a set of recognition results, wherein each recognition result in the set of recognition results corresponds to an image in the set of images; A determination module is used to determine whether there is an abnormality in the target monitoring point based on the set of recognition results.

9. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images