High-altitude operation monitoring method, device and system and computer readable storage medium

Abstract

The invention relates to a high-altitude operation monitoring method, device and system and a computer readable storage medium, and the method comprises the steps: receiving an image, obtained by camera equipment, of a monitoring region, carrying out the recognition of the image, obtaining a target bearing part which is separated from the ground in the image, and carrying out the recognition of the target bearing part; identifying the number of people on the target bearing part and wearable equipment information; when the number of the personnel meets the personnel early warning requirement, personnel potential safety hazard information is obtained; when the wearable equipment information meets the equipment early warning requirement, equipment potential safety hazard information is obtained; and generating a potential safety hazard result based on the personnel potential safety hazard information and the equipment potential safety hazard information, and sending the potential safety hazard result to a target client. According to the invention, the problem that a manager cannot timely discover potential safety hazards existing in high-altitude operation is solved.

Description

Technical Field

[0001] The present application relates to the field of high-altitude work monitoring, and in particular to a high-altitude work monitoring method, device, system, computer equipment and computer-readable storage medium. Background Art

[0002] Aerial work refers to various work activities performed at a certain height from the ground. Among them, a certain height from the ground usually refers to more than 2 meters from the ground. Due to the particularity of aerial work, workers who do aerial work often face some risks of accidents. In order to ensure the safety of aerial work, the sensor's hanging basket status monitoring system, the operator's safety equipment monitoring system and manual inspection are usually used to monitor the aerial work, thereby ensuring the safe operation of aerial work. However, the manual inspection method cannot detect the hidden dangers in aerial work in time. Therefore, how to timely warn of the safety hazards in aerial work has become an urgent problem to be solved. Summary of the invention

[0003] The embodiments of the present application provide a method, device, system and computer-readable storage medium for monitoring aerial work, so as to at least solve the problem in the related art of how to promptly warn of safety hazards existing in aerial work.

[0004] In a first aspect, an embodiment of the present application provides a method for monitoring aerial work, characterized in that the method is applied to an aerial work monitoring system, the monitoring system includes a video camera and a processor connected in communication, and the method is applied to the processor, specifically including:

[0005] Receive an image of the monitoring area acquired by a camera device, identify the image to acquire a target bearing component that is off the ground in the image, and identify the number of people on the target bearing component and the information of the wearable device;

[0006] When the number of personnel meets the personnel warning requirements, obtain personnel safety hazard information;

[0007] When the wearable device information meets the device warning requirements, the device safety hazard information is obtained;

[0008] Based on the personnel safety hazard information and equipment safety hazard information, a safety hazard result is generated and sent to the target client.

[0009] In one embodiment, when the number of personnel meets the personnel warning requirement, personnel safety hazard information is obtained, including:

[0010] If the number of personnel is greater than the upper limit of the working threshold, the safety hazard information of overcrowding in high-altitude operations is obtained;

[0011] If the number of personnel is less than the lower limit of the working threshold, the safety hazard information of insufficient personnel in high-altitude operations is obtained.

[0012] In one embodiment, the camera device includes a static camera device and a dynamic camera device, and acquires an image of the monitoring area, and identifies the target bearing component that is off the ground in the image, including:

[0013] According to the panoramic image acquired by the static camera device, the dynamic camera device is controlled to acquire an image of the monitoring area, wherein the panoramic image includes the image of the monitoring area;

[0014] Segment the monitoring area image to obtain a number of detection grids, and traverse all the detection grids to identify the bearing parts to be determined;

[0015] According to the relative position relationship between the bearing component to be determined and the ground in the panoramic image, the target bearing component that is separated from the ground is obtained.

[0016] In one embodiment, traversing all the detection grids to identify the bearing member to be determined includes:

[0017] For any one of the detection grids, extracting features of the detection grid, wherein the features include edge features of the load-bearing component to be determined and detail features of the load-bearing component to be determined;

[0018] The edge features and the detail features are processed to obtain the bearing component to be determined.

[0019] In one embodiment, after identifying the number of people on the target carrier, the method further comprises:

[0020] When the number of personnel is 0, the suspension information of the load-bearing component to be determined is obtained according to the relative position relationship, and the suspension information is sent to the target client to realize the monitoring of safety hazards.

[0021] In one embodiment, after obtaining the number of personnel, if the number of personnel meets the warning threshold, obtaining the personnel safety hazard information, it also includes:

[0022] If the number of personnel is within the upper and lower limits of the working threshold, the safety information of the aerial work is obtained.

[0023] In a second aspect, an embodiment of the present application provides a high-altitude work monitoring system, characterized in that it includes:

[0024] Camera equipment, including static camera equipment and dynamic camera equipment, used to obtain images of the monitoring area;

[0025] A processor is used to process the high-altitude work monitoring method of the first aspect.

[0026] In a third aspect, an embodiment of the present application provides a high-altitude operation monitoring device, characterized in that it includes:

[0027] An identification module is used to obtain an image of the monitoring area, identify the target bearing member that is off the ground in the image, and identify the number of people on the target bearing member and the information of the wearable devices;

[0028] Personnel safety hazard information module, used to obtain personnel safety hazard information when the number of personnel meets the personnel warning requirements;

[0029] The equipment safety hazard information module is used to obtain equipment safety hazard information when the wearable device information meets the equipment warning requirements;

[0030] The sending module is used to generate safety hazard results based on personnel safety hazard information and equipment safety hazard information, and send the safety hazard results to the target client to realize the monitoring of safety hazards.

[0031] In a fourth aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for monitoring aerial work according to the first aspect described above is implemented.

[0032] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aerial work monitoring method as described in the first aspect above.

[0033] The high-altitude work monitoring method, device, system and computer-readable storage medium provided in the embodiments of the present application have at least the following technical effects.

[0034] The aerial work monitoring system obtains an image of the monitoring area, identifies the target bearing member that has been detached from the ground in the image, and determines the personnel safety hazard information and equipment safety hazard information based on the personnel information and wearable device information on the target bearing member. The above safety hazard information is sent to the target client. Through the above method, the aerial work monitoring system can monitor the aerial work situation in the monitoring area through the camera equipment, and timely discover safety hazards through the recognition algorithm, so that the monitoring personnel can timely obtain the safety hazards existing in the aerial work, so that the monitoring personnel can timely discover the safety hazards and rectify the existing safety hazards, thereby solving the problem of not being able to timely warn of the safety hazards existing in the aerial work.

[0035] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0037] Figure 1 is a flow chart of a method for monitoring aerial work according to an exemplary embodiment;

[0038] Figure 2 is a flow chart of a method for monitoring aerial work according to another exemplary embodiment;

[0039] Figure 3 is a flow chart of a method for monitoring aerial work according to another exemplary embodiment;

[0040] Figure 4 is a block diagram showing a high-altitude work monitoring device according to an exemplary embodiment;

[0041] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated 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 intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0043] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0044] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0045] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0046] In a first aspect, the present application provides a method for monitoring aerial work. Figure 1 is a flow chart of a method for monitoring aerial work according to an exemplary embodiment. Figure 1 As shown, the aerial work monitoring methods include:

[0047] Step S101: receiving an image of a monitoring area acquired by a camera device, identifying the image to acquire a target bearing component that is off the ground in the image, and identifying the number of people on the target bearing component and information about the wearable devices.

[0048] The camera equipment includes a static camera equipment and a dynamic camera equipment. The static camera equipment has a fixed shooting angle device, and the dynamic camera equipment can change the shooting angle, shooting position and shooting direction. Through the camera equipment, the image of the monitoring area is obtained, and then the image is identified to obtain the target bearing part that is off the ground in the image, which specifically includes the following steps:

[0049] Step S100: According to the panoramic image acquired by the static camera device, the dynamic camera device is controlled to acquire an image of the monitoring area, wherein the panoramic image includes an image of the monitoring area;

[0050] The static camera device regularly acquires the panoramic video stream of the shooting area according to the preset time interval. The processor cuts the frame of the panoramic video stream to obtain each frame of the panoramic image. And pre-processes each frame of the panoramic image to improve the accuracy of subsequent recognition of the panoramic image. Optionally, the pre-processing includes image denoising, contrast enhancement, and image color correction.

[0051] The processor recognizes that there is a monitoring area in the panoramic area through the recognition model, and then controls the moving point camera device to move and zoom to scan the monitoring area and obtain several frames of images of the monitoring area.

[0052] Step S200: segment the monitoring area image to obtain a plurality of detection grids, and traverse all the detection grids to identify the bearing member to be determined.

[0053] For any frame of the image of the monitoring area, the image of the monitoring area is segmented according to a preset ratio to obtain a number of detection grids. Traverse all the detection grids to identify the bearing to be judged. It should be noted that the preset ratio is determined according to the size of the target object to be identified, and the area of ​​the detection grid is larger than the preset ratio of the panoramic image area to prevent inaccurate recognition during the recognition process. For example, the image of the monitoring area is segmented at a ratio of 2×2, and the area of ​​the detection grid obtained is larger than 2% of the panoramic image area.

[0054] In any detection grid, the recognition algorithm is used to identify the object. During the recognition process, there is a detection frame, which is used to provide boundary restrictions for the detection object so that the recognition algorithm can focus on the content in the area. If the detection frame in the detection grid is smaller than the preset area, it is determined that there is no load to be determined in the detection grid. If the detection frame is smaller than the preset area, it means that there are items similar to the load to be determined in the detection grid.

[0055] In one embodiment, for any detection grid, feature extraction is performed on the detection grid, wherein the extracted features include edge features of the carrier to be determined and detail features of the carrier to be determined, and the edge features and detail features are fused and pooled to obtain the target carrier to be determined.

[0056] By traversing all the detection grids, the load-bearing parts to be judged are identified in the detection grids. Since the area of ​​the detection grid is small, identification in the detection grid can reduce the calculation complexity and improve the processing speed, so that the load-bearing parts to be judged can be quickly identified.

[0057] Step S300: Acquire a target bearing component that is off the ground according to the relative position relationship between the bearing component to be determined and the ground in the panoramic image.

[0058] After the bearing member to be determined is identified in step S200, the PTZ value of the moving-point camera device is obtained, and the relative position relationship between the bearing member to be determined and the ground is determined according to the PTZ value, so as to obtain the target bearing member that is off the ground.

[0059] In one embodiment, in the panoramic image, an xy coordinate system is constructed with the horizontal direction of the ground as the x-axis and the vertical direction perpendicular to the ground as the y-axis. The coordinates of the target bearing part in the xy coordinate system are determined according to the PTZ value of the moving point camera device. It is determined whether the value of the y-axis coordinate of the coordinate is 0. If the value of the y-axis coordinate is 0, it means that the target bearing part is on the ground. If the value of the y-axis coordinate of the coordinate is greater than 0, it means that the target bearing part is off the ground.

[0060] In another embodiment, in the panoramic image, the pixels at the bottom of the support to be determined are compared with the pixels on the ground to determine whether there is overlap between the two pixels. If there is overlap, it means that the support to be determined is on the ground. If there is no overlap, it means that the support to be determined is off the ground.

[0061] Continuing to refer to the content of step S101, after obtaining the target bearing that is off the ground in the image, the target bearing is further identified to identify the number of people and wearable device information on the target bearing. The processor obtains the number of people on the target bearing through a human posture detection algorithm, and obtains the wearable device information on the target bearing through a recognition algorithm model.

[0062] Through the content of the above step S101, the target bearing member that has left the ground is identified in the image of the monitoring area, and the number of people and wearable device information on the target bearing member are obtained, which provides a basis for subsequent monitoring of safety hazards of high-altitude operations.

[0063] Step S102: When the number of personnel meets the personnel warning requirements, obtain personnel safety hazard information.

[0064] According to the requirements for protection of aerial work, aerial workers cannot perform aerial work alone. Therefore, the working threshold range of aerial work is determined according to the rated load limit of the target load-bearing component. The personnel warning requirement is that the number of aerial workers is outside the working threshold range of aerial work.

[0065] If the number of personnel is greater than the upper limit of the working threshold, the safety hazard information of overcrowding in high-altitude operations is obtained.

[0066] If the number of personnel is less than the lower limit of the working threshold, the safety hazard information of insufficient personnel in high-altitude operations is obtained.

[0067] If the number of personnel is within the upper and lower limits of the working threshold, the safety information of the aerial work is obtained.

[0068] In one embodiment, the upper limit of the working threshold is 3, the lower limit of the working threshold is 2, and if the number of personnel on the target carrier is 5, the safety hazard information of overcrowding in high-altitude operations is obtained. If the number of personnel on the target carrier is 1, the safety hazard information of undercrowding in high-altitude operations is obtained. If the number of personnel on the target carrier is 2, the safety information of high-altitude operations is obtained. Overcrowding and undercrowding in high-altitude operations are both safety hazards in the high-altitude operation process. If the number of personnel meets the working threshold range, it means that the high-altitude operation process is in a safe state.

[0069] In another embodiment, the rated load of the target bearing member is 2 persons. If the number of persons on the target bearing member is 3, the safety hazard information of overloading of high-altitude operation is obtained. If the number of persons on the target bearing member is 1, the safety hazard information of underloading of high-altitude operation is obtained. If the number of persons on the target bearing member is 2, the safety information of high-altitude operation is obtained.

[0070] Based on the number of personnel identified, the safety hazard information of personnel is preliminarily determined so as to obtain the safety hazard information about the number of personnel in high-altitude operations.

[0071] Step S103: When the wearable device information meets the device warning requirements, the device safety hazard information is obtained.

[0072] When the number of personnel on the target carrier is not 0, the equipment safety hazard information is obtained based on whether the equipment information worn by the personnel on the target carrier meets the equipment warning requirements. Optionally, the equipment warning requirements include not wearing safety equipment or not wearing safety equipment correctly. Wearing safety equipment includes safety belts and helmets.

[0073] In one embodiment, when the number of personnel on the target carrier is greater than 0, the wearable device information of each aerial worker is obtained. For any aerial worker, the recognition algorithm is used to identify whether the aerial worker is wearing a safety belt. If the aerial worker is not wearing a safety belt, the safety hazard information of not wearing a safety belt is obtained. If the aerial worker is wearing a safety belt, it is further identified whether the safety belt worn by the aerial worker is worn correctly, that is, whether the aerial worker fastens the safety belt according to the use requirements and whether the safety belt is hung in the appropriate position as required. If the aerial worker is not wearing it correctly, the safety hazard information of not wearing the safety belt correctly will be obtained.

[0074] When there are workers at high altitudes on the target load-bearing part, the wearable device information of each worker at high altitudes is obtained to ensure the safety of the workers at high altitudes. The safety hazard information of not wearing safety equipment or wearing equipment that is not used correctly is obtained, so that the high-altitude operations can be monitored based on the safety information of the wearable equipment.

[0075] Step S104: Generate a safety hazard result based on the personnel safety hazard information and the equipment safety hazard information, and send the safety hazard result to the target client.

[0076] Based on the obtained personnel safety hazard information and equipment safety hazard information, a safety hazard result is generated and sent to the target client. The manager can timely discover problems existing in high-altitude operations based on the safety hazard results in the target client and rectify the existing problems.

[0077] More specifically, based on the safety hazard information of personnel and equipment, safety hazard results are generated. The safety hazard results include the location, time, and existing safety hazard information of the safety hazard. The processor pushes the safety hazard results to the administrator's target client. The administrator finds safety anomalies of high-altitude operations based on the safety hazard results in the target client to monitor high-altitude operations. The administrator can also handle safety anomalies in a timely manner to avoid accidents at high altitudes.

[0078] The aerial work system is under real-time monitoring, so managers can obtain real-time safety hazard results and make timely corrections to safety anomalies. Based on the real-time safety hazard results every day, periodic safety hazard reports are obtained and sent to the target client, so that managers can improve management measures based on the overall safety hazard situation of aerial work to ensure the safety of subsequent aerial work.

[0079] The safety hazard results are generated through the safety hazard information of personnel and equipment. On the one hand, the management personnel can timely discover the safety hazard problems based on the safety hazard results, so as to realize the real-time monitoring of the aerial work. On the other hand, the safety hazard report is obtained based on the safety hazard results, which provides a scientific basis for improving management measures to improve the safety of aerial work.

[0080] In another embodiment, if there are no high-altitude workers in the target bearing member that has been lifted off the ground, there is a safety hazard of unauthorized personnel entering the target bearing member that has been lifted off the ground, and there is a safety hazard of damage or falling and injuring people due to natural weather and electrical influences. Therefore, when the number of personnel is 0, the suspension information of the bearing member to be judged is obtained based on the relative position relationship between the bearing member to be judged and the ground, and the suspension information is sent to the target client so that the management personnel can monitor the safety hazard of high-altitude operations based on the suspension information.

[0081] In another embodiment, the outer side of the building is used as the monitoring area, and the hanging basket for carrying high-altitude workers is used as the target bearing member. Figure 2 is a flow chart of a method for monitoring aerial work according to another exemplary embodiment. Figure 2As shown, a recognition algorithm is configured to perform recognition based on the image of the monitoring area obtained by the moving point camera device. It is identified whether there is a hanging basket in the detection grid. If no hanging basket is identified, another detection grid is continuously identified until all detection grids are traversed. If there is a hanging basket in the detection grid, the moving point camera is controlled to zoom to obtain a clearer outer side image. In the outer side image, it is identified whether the hanging basket is suspended in the air, that is, whether the hanging basket is off the ground. If the hanging basket is not suspended in the air, the image is stored and information without safety hazards is output. If the hanging basket is suspended in the air, it is identified whether there are high-altitude workers in the hanging basket. If there are no high-altitude workers, the floor where the hanging basket is suspended in the air and the safety hazard information that the hanging basket is in a non-working state and has not landed are obtained. If there are high-altitude workers in the hanging basket, the number of people in the hanging basket and whether the high-altitude workers are wearing safety belts are obtained. If the number of people in the hanging basket is 1, the information of the shortage of people in the hanging basket is obtained; if the number of people in the hanging basket is 2, the image is stored and the information of no safety hazard is output; if the number of people in the hanging basket is greater than 2, the information of overcrowding in the hanging basket is obtained. For any high-altitude operation in the hanging basket, it is identified whether the safety belt is worn. If the high-altitude operator does not wear a safety belt, the information of the operator not wearing a safety belt is obtained; if the high-altitude operator wears a safety belt, it is further determined whether the safety belt is used as required. If the high-altitude operator uses the belt as required, the image is stored and the information of no safety hazard is obtained; if the high-altitude operator does not use the safety belt as required, the information of improper use of the safety belt is obtained.

[0082] In another embodiment, Figure 3 FIG. 1 is a flow chart of a method for monitoring aerial work according to another exemplary embodiment. Figure 3As shown, the identification area is obtained, and the types of the identification area include the top surface of the floor, the side surface of the floor, the surface working surface, and the flammable area where materials are stacked. The identification area also includes the coordinate position of the area. The corresponding identification algorithm is obtained according to the type of the identification area. Optionally, the top surface area of ​​the floor identifies the external frame and the horizontal protection of the floor, the protective railing of the working layer, the horizontal protection of the adjustment port, and the safety belt; the side area of ​​the floor identifies the overcrowding of the hanging basket, the edge protection, and the safety belt. Through the panoramic camera calibration, the panoramic image is obtained through the static camera device. It is judged whether the obtained recognition algorithm is initialized. If it is not initialized, the task is reported to the system, where the task includes returning the cruise task type, the PTZ parameters of the point, the picture, and the recognition model. If the initialization is not completed, the original area of ​​the image is densely laid, and it is judged whether the task configured by the algorithm is completed. If it is completed, the task is reported to the system. If the task configured by the algorithm is not completed, the algorithm is configured with a cruise task, and it is judged that the area is divided into the smallest picture. If not required, it is re-judged whether the task configured by the algorithm is completed. If segmentation is required, it is performed according to the segmentation ratio, where the segmentation ratios include 1×1, 2×2, 3×3, 4×4, and 5×5. The smallest segmented screen is not less than 2% of the panoramic image area. Model recognition is performed on each segmented area. If the size of the recognition detection frame through model recognition is lower than the minimum threshold of model recognition, it is re-determined whether it is necessary to segment again; if the size of the recognition detection frame is higher than the minimum threshold of model recognition, the type of cruise mission is determined. The types of cruise missions include regional cruise missions, point cruise missions, and linear cruise missions.

[0083] If it is a regional cruise mission, obtain the regional PTZ parameters and generate a mission.

[0084] If it is a linear cruise task, obtain the outline of the linear area and identify the point coordinates of the outline, obtain the PTZ parameters of the three points (outer, middle and inner) for each point, and generate the task.

[0085] If it is a point cruise task, determine whether the configuration of the identification site is complete. If the configuration is complete, directly generate the task. If the configuration is not complete, control the movement of the moving point camera device according to the model recognition coordinates so that the model can be recognized. Through model recognition, determine whether the identification coordinate frame is close to the four sides of the picture, whether the area of ​​the identification coordinate frame is less than 25% of the picture area, and whether the offset between the center of the identification coordinate frame and the center of the picture reaches 25%. When all the judgment conditions mentioned are no, record the point PTZ parameters and store the image. Based on the point PTZ parameters and the stored image, determine again whether the configuration of the identification site is complete.

[0086] If the recognition coordinate frame is close to the four sides of the picture, the camera device is controlled to reduce the magnification and deflection direction, and the model recognition is performed again; if the area of ​​the recognition coordinate frame is less than 25% of the picture area, the camera device is controlled to increase the magnification; if the offset between the center of the coordinate frame and the center of the picture reaches 25%, the camera device is controlled to deflection direction.

[0087] Based on the tasks generated by the above-mentioned regional cruise tasks, linear cruise tasks and point cruise tasks, it is judged again whether the algorithm configuration is completed according to the generated tasks.

[0088] Optionally, in the above-mentioned high-altitude work monitoring method, the recognition model and recognition algorithm adopt the YOLOv5 algorithm model. The YOLOv5 algorithm model includes an input end, a Backbone layer, a Neck network and an output end. The YOLOv5 algorithm model can be used to identify the hanging basket on the outer side of the building. The steps of identifying the hanging basket specifically include:

[0089] At the input end, the Kmeans algorithm is used to cluster all the detection frames in the training set, and the genetic algorithm is used to mutate all the detection frames to obtain the detection frames that can fit the hanging basket. The letterbox technology is used to keep the detection frame at a certain aspect ratio. If there are detection frames that do not meet the aspect ratio, the missing parts are filled with gray edges to achieve a fixed size.

[0090] Backbone layer uses slicing operation to split the high-resolution image into several low-resolution images. Conv, C3, and SPPF are used to extract features for each low-resolution image. Conv is used to downsample the image; C3 is used to extract and fuse the edge features of the hanging basket; SPPF is used to pool and fuse the detailed features of the hanging basket to enrich the detailed features of the hanging basket.

[0091] The Neck network uses the FPN operation to map and fuse the edge features and detail features of the hanging basket obtained from the Backbone layer, thereby locating the hanging basket in the image.

[0092] At the output end, the output data obtained by processing includes the location and category confidence information of the detected target in each area. The processing content includes threshold filtering, calculating the confidence of each category and calculating non-maximum suppression to obtain the location, category and confidence of the final target. Among them, threshold filtering is to eliminate the confidence below the threshold; calculating non-maximum suppression is based on the overlap of two recognition detection frames. When the overlap rate of the two recognition detection frames is high, the recognition detection frame with relatively low confidence is eliminated.

[0093] After completing the above four steps, you can locate the hanging basket in the picture, obtain the information of the operator in the hanging basket and the wearing information of the safety belt.

[0094] To sum up, the high-altitude work monitoring method provided in the embodiment of the present application can identify the target load that is detached from the ground through the image recognition of the monitoring area, and obtain the number of personnel and wearable device information through the recognition algorithm, obtain safety hazard information based on the number of personnel and wearable device information, and send it to the target client of the manager in a timely manner, so as to timely discover the safety hazards that always exist in high-altitude work.

[0095] In a second aspect, an embodiment of the present application provides a high-altitude operation monitoring system. The high-altitude operation monitoring system includes:

[0096] Camera equipment, including static camera equipment and dynamic camera equipment, is used to obtain images of the monitoring area.

[0097] The camera equipment is set up at a high place where aerial work is performed. For example, at a construction site, the camera equipment is set up at a crane tower so that the entire construction site can be captured.

[0098] A processor is used to process any one of the aerial work monitoring methods in the above embodiments.

[0099] In a third aspect, an embodiment of the present application provides a high-altitude work monitoring device. Figure 4 FIG. 1 is a block diagram of a high-altitude operation monitoring device according to an exemplary embodiment. Figure 4 As shown, the aerial work monitoring device comprises:

[0100] An identification module, used to obtain an image of the monitoring area, identify a target bearing component that is off the ground in the image, and identify the number of people on the target bearing component and information about wearable devices;

[0101] A personnel safety hazard information module is used to obtain personnel safety hazard information when the number of personnel meets the personnel warning requirements;

[0102] The device safety hazard information module is used to obtain device safety hazard information when the wearable device information meets the device warning requirements;

[0103] The sending module is used to generate a safety hazard result based on the personnel safety hazard information and the equipment safety hazard information, and send the safety hazard result to a target client to realize monitoring of safety hazards.

[0104] In summary, the aerial work monitoring device provided by the present application obtains an image of the monitoring area through the aerial work monitoring system, and identifies the target carrier that is off the ground in the image, and determines the personnel safety hazard information and equipment safety hazard information based on the personnel information and wearable device information on the target carrier. The above safety hazard information is sent to the target client. Through the above method, the aerial work monitoring system can monitor the aerial work situation in the monitoring area through the camera equipment, and timely discover safety hazards through the recognition algorithm, so that the monitoring personnel can timely obtain the safety hazards existing in the aerial work, so that the monitoring personnel can timely discover the safety hazards and rectify the existing safety hazards, thereby solving the problem of not being able to timely warn of the safety hazards existing in the aerial work.

[0105] It should be noted that the aerial work monitoring device provided in this embodiment is used to implement the above-mentioned implementation mode, and the descriptions that have been made will not be repeated. As used above, the terms "module", "unit", "subunit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the above embodiment is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0106] In a fourth aspect, an embodiment of the present application provides an electronic device, Figure 5 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 5 As shown, the electronic device may include a processor 81 and a memory 82 storing computer program instructions.

[0107] Specifically, the processor 81 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0108] Among them, the memory 82 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 82 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 82 may be inside or outside the data processing device. In a specific embodiment, the memory 82 is a non-volatile memory. In a specific embodiment, the memory 82 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable Programmable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0109] The memory 82 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 81 .

[0110] The processor 81 implements any one of the aerial work monitoring methods in the above-mentioned embodiments by reading and executing computer program instructions stored in the memory 82 .

[0111] In one embodiment, the aerial work monitoring device may further include a communication interface 83 and a bus 80. Figure 5 As shown, the processor 81, the memory 82, and the communication interface 83 are connected via a bus 80 and communicate with each other.

[0112] The communication interface 83 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication port 83 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0113] The bus 80 includes hardware, software or both, and couples the components of the aerial work monitoring device to each other. The bus 80 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 80 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0114] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, the high-altitude work monitoring method provided in the first aspect is implemented.

[0115] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0116] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of the high-altitude work monitoring method provided in the first aspect.

[0117] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on a user device, partially on a user device, as an independent software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0118] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described 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 specification.

[0119] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. 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 patent of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring high-altitude operations, characterized in that: The method is applied to a high-altitude work monitoring system, the monitoring system includes a video camera and a processor connected in communication, and the method is applied to the processor, specifically including: Receiving an image of the monitoring area acquired by the camera device, identifying the image to acquire a target bearing component that is off the ground in the image, and identifying the number of people on the target bearing component and information about the wearable devices; When the number of personnel meets the personnel warning requirements, personnel safety hazard information is obtained; When the wearable device information meets the device warning requirements, the device safety hazard information is obtained; Based on the personnel safety hazard information and the equipment safety hazard information, a safety hazard result is generated, and the safety hazard result is sent to a target client.

2. The method for monitoring aerial work according to claim 1, characterized in that: When the number of personnel meets the personnel warning requirements, the personnel safety hazard information is obtained, including: If the number of personnel is greater than the upper limit of the working threshold, the safety hazard information of overcrowding in high-altitude operations is obtained; If the number of personnel is less than the lower limit of the working threshold, the safety hazard information of the small number of personnel working at heights is obtained.

3. The method for monitoring aerial work according to claim 1, characterized in that: The camera device includes a static camera device and a dynamic camera device, and the image is identified to obtain a target bearing component that is separated from the ground in the image, including: According to the panoramic image acquired by the static-point camera device, controlling the dynamic-point camera device to acquire an image of the monitoring area, wherein the panoramic image includes the image of the monitoring area; Segmenting the monitoring area image to obtain a plurality of detection grids, and traversing all of the detection grids to identify the bearing member to be determined; The target bearing component that is separated from the ground is acquired according to the relative position relationship between the bearing component to be determined and the ground in the panoramic image.

4. The method for monitoring aerial work according to claim 3, characterized in that: The traversing all the detection grids to identify the bearing member to be determined includes: For any one of the detection grids, extracting features of the detection grid, wherein the features include edge features of the load-bearing component to be determined and detail features of the load-bearing component to be determined; The edge features and the detail features are processed to obtain the bearing component to be determined.

5. The method for monitoring aerial work according to claim 3, characterized in that: After identifying the number of people on the target carrier, the method further includes: When the number of personnel is 0, the suspension information of the load-bearing component to be determined is obtained according to the relative position relationship, and the suspension information is sent to the target client to realize the monitoring of potential safety hazards.

6. The method for monitoring aerial work according to claim 2, characterized in that: In the step of obtaining the number of personnel, if the number of personnel meets the warning threshold, after obtaining the personnel safety hazard information, the method further includes: If the number of personnel is within the upper limit of the working threshold and the lower limit of the working threshold, high-altitude work safety information is obtained.

7. A high-altitude operation monitoring system, characterized in that: include: Camera equipment, including a static camera equipment and a dynamic camera equipment, for acquiring images of the monitoring area; A processor, used to process the aerial work monitoring method according to any one of claims 1 to 6.

8. A high-altitude operation monitoring device, characterized in that: include: An identification module, used to obtain an image of the monitoring area, identify a target bearing component that is off the ground in the image, and identify the number of people on the target bearing component and information about wearable devices; A personnel safety hazard information module is used to obtain personnel safety hazard information when the number of personnel meets the personnel warning requirements; The device safety hazard information module is used to obtain device safety hazard information when the wearable device information meets the device warning requirements; The sending module is used to generate a safety hazard result based on the personnel safety hazard information and the equipment safety hazard information, and send the safety hazard result to a target client to realize monitoring of safety hazards.

9. An electronic device, characterized in that: including memory, processor, and A computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for monitoring aerial work as claimed in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for monitoring aerial work as described in any one of claims 1 to 6 is implemented.

Images