A Monitoring Method and Application of Safety Hooks for Aerial Workers

Abstract

The present invention discloses a monitoring method and application for safety hooks of high-altitude workers, which relates to the technical field of high-altitude operation safety equipment, including spatial calibration of camera equipment, identification of high-altitude workers, monitoring of the altitude of workers, and real-time monitoring of safety belt hooks. Specifically, it relates to a monitoring method and application for safety hooks of high-altitude workers; it solves the technical problem that once there are situations such as missed buckling of the lock or incorrect hanging position of the safety hook of high-altitude workers, it will seriously affect the life safety of personnel: by monitoring the altitude of high-altitude workers and the position of safety hooks in real time, normal high-altitude workers and abnormal high-altitude workers are marked, so as to achieve the purpose of monitoring the safety of high-altitude workers during high-altitude operations.

Description

Technical Field

[0001] The present invention relates to the technical field of high-altitude operation safety equipment, and particularly relates to a method and application for monitoring the safety hooks of high-altitude operation personnel. Background Art

[0002] With the development of the construction industry and the increase in population density, high-rise buildings have emerged in an endless stream. In a city with high-rise buildings standing tall, various types of personnel are required to perform high-altitude operations. How to ensure the safety of high-altitude operation personnel has become a key issue. Usually, when construction workers are working at heights, they wear safety belts with safety hooks on their bodies to ensure their safety.

[0003] The patent with the publication number CN112933456A discloses a safety monitoring system and method for the hanging state of a construction safety belt. By adopting a safety belt hook monitoring system and a background management system, the safety belt hook monitoring system is communicatively connected to the background management system. The safety belt hook monitoring system is installed on the hook, and the hook is connected to the safety belt. The safety belt hook monitoring system can judge whether the construction worker wearing the safety belt has hooked the hook on a fixed part, so as to be able to monitor in real time whether the construction worker has hooked the hook of the safety belt on the fixed part, and solve the problems of low automation degree of construction worker safety belt wearing control, low management efficiency, and potential safety hazards. In addition, by setting an opening and closing recognition device, the reliability of the safety belt hanging can be improved; by setting a high-altitude operation monitoring system, it can be judged whether the construction worker is in a high-altitude operation state and whether the distance of the construction worker from the edge of the platform is greater than or equal to the safety distance.

[0004] However, during the process of high-altitude operation personnel wearing safety equipment, the safety hook is a very crucial link. The safety hook is not only the external rope of the personnel, but also the internal life of the personnel. Ground supervisors usually need to constantly look up at the high-altitude workers or rely on active altimeters, hook lockers and other equipment to monitor the safety hook to ensure the safety of the safety hook. However, due to problems such as sunlight irradiation, building shadows, and ground perspectives during this process, it is difficult to ensure the accuracy of the ground supervisor's judgment on the state of the safety hook, and relying on active altimeters, hook lockers and other equipment is not conducive to the economy of high-altitude operations. Once there are situations such as missed buckling or incorrect hanging positions of the safety hooks of high-altitude operation personnel, it will seriously affect the life safety of the personnel. Therefore, a method and application for monitoring the safety hooks of high-altitude operation personnel are proposed. Summary of the Invention

[0005] The object of the present invention is to provide a monitoring method and application for safety hooks of high-altitude operators, which solves the technical problem that once there are situations such as missed buckling of the lock or wrong hanging position of the safety hook of high-altitude operators, it will seriously affect the life safety of the personnel.

[0006] The object of the present invention can be achieved by the following technical solutions:

[0007] A monitoring method for safety hooks of high-altitude operators includes the following steps:

[0008] Step 1: Through spatial calibration of the camera device, construct the calibration relationship between the image main body collected by the camera device and the distant building main body, and obtain the altitude of the high-altitude operator main body through the calibration relationship.

[0009] Step 2: Identify the high-altitude operator main body by the camera device in the way of a three-layer neural network.

[0010] Step 3: During the process of the high-altitude operator main body performing high-altitude operations, if the camera device cannot collect the panoramic view of the building, adopt the rolling time-domain dynamic calibration method to monitor the altitude of the high-altitude operator main body.

[0011] Step 4: Perform real-time detection of the safety belt hook through the identification of the end of the safety rope. At the same time, mark the normal high-altitude operator main body and the abnormal high-altitude operator main body according to the monitoring results of the safety hook body. The specific method for performing real-time detection of the safety hook body is as follows:

[0012] S01: First, identify the high-altitude operator main body through Step 2 and use it as the target person.

[0013] S02: Perform connected domain processing on the real-time video image collected by the camera device, that is, calculate the dynamic strip-shaped rope that changes with the operator as the personnel follow-up connected domain, and identify the dynamic strip-shaped rope as the safety rope for protecting safety.

[0014] S03: Identify the intersection point between the safety rope and the high-altitude operator main body as the safety hook body, and perform real-time detection and position identification on the safety hook body. Since the safety rope and the high-altitude operator main body need to be always connected, it is processed as a connected domain.

[0015] S04: Through image recognition, the position of the safety hook body can be obtained by using Step 3 and the head vertex position of the high-altitude operator main body and the foot bottom point position , when the height position of the safety hook body satisfies If so, it is considered that the position of the safety hook body is accurate and the monitoring is normal, and the corresponding high-altitude operation personnel body is marked as a normal high-altitude operation personnel body. If not, it is considered that the position of the safety hook body is inaccurate and the monitoring is abnormal, and the corresponding high-altitude operation personnel body is marked as an abnormal high-altitude operation personnel body. At the same time, the altitude position information corresponding to the abnormal high-altitude operation personnel body is sent to the display terminal for display. The altitude position information corresponding to the high-altitude operation personnel body includes the head vertex position and the foot bottom position of the high-altitude operation personnel body.

[0016] As a further solution of the present invention: The specific construction method of the calibration relationship is as follows:

[0017] S1: First, artificially measure the length of the building foundation and its corresponding foundation height on the building ground and mark them as and h0 respectively, mark the altitude of the high-altitude operation personnel body to be measured as h, and mark the actual height of the high-altitude operation personnel body as , where . The actual height of the high-altitude operation personnel body refers to the height difference between the altitude of the high-altitude operation personnel body and the foundation height of the building.

[0018] S2: Mark the length of the building foundation in the image body collected by the camera device as , and mark the imaging height of the actual height of the high-altitude operation personnel body in the image body as ;

[0019] S3: According to the similarity triangle determination rule, the altitude h of the high-altitude operation personnel body to be measured can be obtained. Here .

[0020] As a further solution of the present invention: The specific method for the three-layer neural network to specifically identify the high-altitude operation personnel body is as follows:

[0021] Take the camera device as the video input layer for real-time video acquisition, extract the static buildings in the real-time video, form an image feature extraction layer with the feature information and dynamic operator information, and then obtain the output layer of the operator through the difference between the real-time video image frames collected by the camera device and the processing and recognition of the local dynamic images.

[0022] As a further solution of the present invention: The specific method of the rolling horizon dynamic calibration method is as follows: Taking the high-altitude operation personnel body as the focus, when the high-altitude operation personnel body is performing high-altitude operations on the building surface and needs to gradually rise from the foundation height of the building, that is, when the high-altitude operation personnel body needs to rise from the first area to the second area and then rise to the third area, when the artificially measured length of the building foundation is , when the height of the building base is h0, the length of the building base and the actual height of the main body of the aerial worker are spatially calibrated through the imaging device, that is, their imaging lengths and imaging heights in the image are respectively marked as and , at the same time, the fourth area of the building and its imaging length are also imaged in the imaging device. The altitude h1 corresponding to the fourth area of the building is calculated through the law of similar triangle determination.

[0023] As a further solution of the present invention: The specific method for calculating the altitude h1 corresponding to the fourth area through the law of similar triangle determination is: through the formula , the altitude h1 corresponding to the fourth area and the length of a partial area of the building can be calculated. Here ;

[0024] During the ascent of the worker, the tracking part of the imaging device follows the main body of the aerial worker in a partial area, and the image is continuously calibrated as time goes by, so that the altitude information of the position of the main body of the aerial worker and the calibration information of the length of a partial area of the building can be obtained.

[0025] The application of a safety hook monitoring method for aerial workers is used to implement the safety hook monitoring method for aerial workers. The method is deployed on the server side to support the application of the safety hook monitoring method for aerial workers.

[0026] Beneficial effects of the present invention:

[0027] In the present invention, by monitoring the altitude of the aerial worker and the position of the safety hook in real time, normal aerial workers and abnormal aerial workers are marked, so as to achieve the purpose of monitoring the safety of aerial workers during high-altitude operations. Moreover, there is no need to carry too many sensors on the aerial workers, and there is no need to rely on active altimeters, hook lockers and other devices. The safety hook of the aerial worker can be monitored in real time through a remote imaging device, reducing the safety risks of aerial workers while ensuring the operation safety of aerial workers, and at the same time reducing the wearing equipment of aerial workers, improving the economy of high-altitude operations. Description of the Drawings

[0028] The present invention will be further described below with reference to the drawings.

[0029] Figure 1 is a schematic diagram of the framework structure of the present invention;

[0030] Figure 2 is a schematic diagram of the calibration relationship of the imaging device of the present invention;

[0031] Figure 3 This is a schematic diagram of the principle of the present invention for identifying high-altitude workers through a three-layer neural network;

[0032] Figure 4 This is a schematic diagram of the principle for monitoring the altitude of high-altitude workers in the present invention;

[0033] Figure 5 This is a schematic diagram of a high-altitude worker, a safety rope, and a safety hook in the present invention;

[0034] In the figure: 101, image main body; 103, imaging device; 104, distant building main body; 301, building surface; 302, first area; 303, second area; 304, third area; 305, building base; 306, fourth area; 307, fifth area; 308, sixth area; 309, seventh area; 2-1, video input layer; 2-2, image feature extraction layer; 2-3, output layer; 2-4, feature information; 2-5, worker information; 401, high-altitude worker main body; 402, safety rope; 403, safety hook main body. Detailed implementation manners

[0035] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0036] Please refer to Figure 1 - Figure 5 As shown, the present invention is a method and application for monitoring a safety hook of a high-altitude worker, including the following steps:

[0037] Step 1: Through spatial calibration of the imaging device 103, a calibration relationship between the image main body 101 collected by the imaging device 103 and the distant building main body 104 is constructed, and the altitude of the high-altitude worker main body 401 is obtained through the calibration relationship. The specific construction method of the calibration relationship is as follows:

[0038] S1: First, the length of the building base 305 and its corresponding base height are measured artificially on the building ground and marked as and h0 respectively, the altitude of the high-altitude worker main body 401 to be measured is marked as h, and the actual height of the high-altitude worker main body 401 is marked as , where , the actual height of the high-altitude worker main body 401 refers to the height difference between the altitude of the high-altitude worker main body 401 and the building base height;

[0039] S2: Mark the length of the building base 305 in the image main body 101 collected by the imaging device 103 as , and mark the imaging height of the actual height of the aerial working personnel main body 401 in the image main body 101 as ;

[0040] S3: According to the determination rule of similar triangles, the altitude h of the aerial working personnel main body 401 to be measured can be obtained. Here ;

[0041] Step 2: Identify the aerial working personnel main body 401 through the imaging device 103. Here, the imaging device 103 uses a three-layer neural network to identify the aerial working personnel main body 401. The specific method for the three-layer neural network to identify the aerial working personnel main body 401 is as follows:

[0042] Take the imaging device 103 as the video input layer 2-1 for real-time video acquisition, extract the static buildings in the real-time video, form the image feature extraction layer 2-2 with the feature information 2-4 and the dynamic worker information 2-5, and then obtain the output layer 2-3 of the workers through the difference between the real-time video image frames collected by the imaging device 103 and the processing and recognition of the local dynamic images, thereby completing the identification of the aerial working personnel main body 401. It should be noted that the static building here refers to a building that has not changed much for a long time in the real-time video image;

[0043] Step 3: During the process of the aerial working personnel main body 401 performing aerial work, if the imaging device 103 cannot collect the panoramic view of the building, that is, when the imaging device 103 cannot simultaneously capture the base height of the building and the actual height of the aerial working personnel main body 401, a rolling horizon dynamic calibration method is used to monitor the altitude of the aerial working personnel main body 401. The specific method of the rolling horizon dynamic calibration method is as follows:

[0044] Taking the aerial working personnel main body 401 as the focus, when the aerial working personnel main body 401 performs aerial work on the building surface 301 and needs to gradually rise from the base height of the building, that is, when the aerial working personnel main body 401 needs to rise from the first area 302 to the second area 303 and then rise to the third area 304, when the manually measured length of the building base 305 is , and the height of the building base 305 is h0, spatially calibrate the length of the building base 305 and the actual height of the aerial working personnel main body 401 through the imaging device 103, that is, mark their imaging lengths and imaging heights in the image as and , at the same time, the fourth area 306 of the building and its imaging length are also imaged in the imaging device 103 , and then calculate the altitude h1 corresponding to the fourth area 306 of the building through the determination rule of similar triangles. The specific method for calculating the altitude h1 is as follows:

[0045] Through the formula , the altitude h1 corresponding to the fourth area 306 and the length of a partial area of the building can be calculated , where ;

[0046] During the ascent of the operator, the tracking part of the imaging device 103 follows the main body 401 of the operator working at height in a partial area, and the image is continuously calibrated as time goes by, and the altitude information of the position of the main body 401 of the operator working at height and the calibration information of the length of a partial area of the building can be obtained:

[0047] For example: ;

[0048] During the dynamic lifting and lowering of the main body 401 of the operator working at height, the method of rolling horizon dynamic calibration is continuously used. It can not only monitor the altitude of the main body 401 of the operator working at height in the case of losing the view of the building base 305, but also roll and update the building calibration of a partial area of the building to make the data more accurate;

[0049] Step 4: Real-time monitor the end of the safety rope 402 connected to the safety hook body 403, and at the same time mark the normal main body 401 of the operator working at height and the abnormal main body 401 of the operator working at height according to the monitoring results of the safety hook body 403. When the safety hook body 403 is monitored in real time, since the safety hook body 403 is small in size and is generally hung on the waist and abdomen of the main body 401 of the operator working at height and is not easy to observe, the safety rope 402 connected to the safety hook body 403 is collected for identification, and the safety hook body 403 is detected in real time through the identification of the end of the safety rope 402. The specific method for detecting the safety hook body 403 in real time is as follows:

[0050] S01: First, identify the main body 401 of the operator working at height through Step 2 and use it as the target person;

[0051] S02: Perform image connected component processing on the real-time video image collected by the imaging device 103, that is, calculate the dynamic strip-shaped rope that changes with the operator as the personnel follow-up connected component, and identify the dynamic strip-shaped rope as the safety rope 402 for protecting safety;

[0052] S03: Identify the intersection point between the safety rope 402 and the main body 401 of the aerial worker as the safety hook body 403, and perform real-time detection and position identification on the safety hook body 403. The safety hook body 403 should be ensured to be always mounted on the main body 401 of the aerial worker during the operation of the main body 401 of the aerial worker, and at the same time, the position of the safety hook body 403 should be at the waist and abdomen to meet the requirements of safe operation. Since the safety rope 402 and the main body 401 of the aerial worker need to be always connected, it is processed as a connected domain;

[0053] S04: During the process of performing connected domain processing on the real-time video image, if it is identified that there is always a strip-shaped follow-up area in the connected area of the main body 401 of the aerial worker, it is determined as the safety rope 402, and the safety rope 402 is connected to the main body 401 of the aerial worker through the safety hook body 403. The connection point between the safety rope 402 and the main body 401 of the aerial worker is the safety hook body 403. The position of the safety hook body 403 can be obtained through image recognition using Step 3 and the vertex position of the head of the main body 401 of the aerial worker and the bottom point position of the feet , due to the differences in personal body types and the dragging of the safety hook body 403, set the position accuracy weight of the safety hook body 403 to . When the height position of the safety hook body 403 satisfies: , it is considered that the position of the safety hook body 403 is accurate and the monitoring is normal, and the corresponding main body 401 of the aerial worker is marked as a normal main body 401 of the aerial worker. If not satisfied, it is considered that the position of the safety hook body 403 is inaccurate and the monitoring is abnormal, and the corresponding main body 401 of the aerial worker is marked as an abnormal main body 401 of the aerial worker. At the same time, the altitude position information corresponding to the abnormal main body 401 of the aerial worker is sent to the display terminal for display. The altitude position information corresponding to the main body 401 of the aerial worker includes the vertex position of the head and the bottom point position of the feet of the main body 401 of the aerial worker, which is convenient for relevant personnel to view and conduct timely supervision and management.

[0054] The application of a safety hook monitoring method for aerial workers is used to implement the safety hook monitoring method for aerial workers. The method is deployed on the server side to support the application of the safety hook monitoring method for aerial workers.

[0055] Working principle of the present invention: First, through the spatial calibration of the imaging device 103, the dynamic personnel information of high-altitude operations in the real-time video collected by the imaging device 103 is identified by using a three-layer neural network of the real-time video input layer 2-1, the image feature extraction layer 2-2, and the output layer 2-3 of the operator. Then, the rolling horizon dynamic calibration method is used to monitor the altitude of the high-altitude operation personnel main body 401. During the dynamic lifting and lowering process of the high-altitude operation personnel main body 401, the rolling horizon dynamic calibration method is continuously used, which can not only obtain the altitude of the high-altitude operation personnel main body 401 for monitoring in the case of losing the view of the building base 305, but also can roll and update the building calibration of some areas of the building to make the data more accurate. It also includes the spatial calibration of the imaging device 103, the identification of the high-altitude operation personnel main body 401, the monitoring of the altitude of the high-altitude operation personnel main body 401, the real-time monitoring of the end of the safety rope 402 connected to the safety hook body 403. At the same time, according to the monitoring results of the safety hook body 403, the normal high-altitude operation personnel main body 401 and the abnormal high-altitude operation personnel main body 401 are marked, and the altitude position information corresponding to the abnormal high-altitude operation personnel main body 401 is sent to the display terminal for display, which is convenient for relevant personnel to view and timely supervise and manage, solving the problem of high-altitude operation safety guarantee without the need for personnel to wear additional safety monitoring equipment.

[0056] The above formulas are all dimensionless and take their numerical calculations. The formula is a formula obtained by collecting a large amount of data for software simulation to get the closest real situation. The preset parameters and threshold selection in the formula are set by those skilled in the art according to the actual situation.

[0057] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A monitoring method for the safety hook of high-altitude operators, characterized in that Including the following steps: Step 1: Through spatial calibration of the camera device (103), construct the calibration relationship between the image main body (101) collected by the camera device (103) and the distant building main body (104), and obtain the altitude of the high-altitude operation personnel main body (401) through the calibration relationship; Step 2: Use a three-layer neural network method through the camera device (103) to identify the high-altitude operation personnel main body (401); Step 3: During the process of the high-altitude operation personnel main body (401) performing high-altitude operations, if the camera device (103) cannot collect the panoramic view of the building, use the rolling horizon dynamic calibration method to monitor the altitude of the high-altitude operation personnel main body (401); Step 4: Through the end recognition of the safety rope (402), perform real-time detection on the safety belt hook, and at the same time mark the normal high-altitude operation personnel main body and the abnormal high-altitude operation personnel main body according to the monitoring results of the safety hook main body (403). The specific method for performing real-time detection on the safety hook main body (403) is as follows: S01: First, identify the high-altitude operation personnel main body (401) through Step 2 and use it as the target person; S02: Perform connected component processing on the real-time video image collected by the camera device (103), that is, calculate the dynamic strip-shaped rope that changes with the operator as the personnel follow-up connected component, and identify the strip-shaped rope as the safety rope (402) for protecting safety; S03: Identify the intersection point between the safety rope (402) and the high-altitude operation personnel main body (401) as the safety hook main body (403), and perform real-time detection and position recognition on the safety hook main body (403). Since the safety rope (402) and the high-altitude operation personnel main body (401) need to be continuously connected, it is processed as a connected component; S04: The position of the safety hook body (403) can be obtained through image recognition using Step 3 and the head vertex position of the high-altitude worker body (401) and the bottom point position of the feet , when the height position of the safety hook body (403) meets , it is considered that the position of the safety hook body (403) is accurate and the monitoring is normal, and the corresponding high-altitude worker body (401) is marked as a normal high-altitude worker body. If it does not meet the requirement, it is considered that the position of the safety hook body (403) is inaccurate and the monitoring is abnormal, and the corresponding high-altitude worker body (401) is marked as an abnormal high-altitude worker body. At the same time, the altitude position information corresponding to the abnormal high-altitude worker body is sent to the display terminal for display. The altitude position information corresponding to the high-altitude worker body (401) includes the head vertex position and the bottom point position of the feet of the high-altitude worker body (401).

2. The safety hook monitoring method for aerial work personnel according to claim 1, characterized in that, The specific construction method of the calibration relationship is: S1: First, artificially measure the length of the building foundation (305) on the building ground and its corresponding foundation height, which are respectively marked as and h0, mark the altitude of the main body of the high-altitude operator (401) to be measured as h, and mark the actual height of the main body of the high-altitude operator (401) as , where , the actual height of the main body of the high-altitude operator (401) refers to the height difference between the altitude of the main body of the high-altitude operator (401) and the foundation height of the building; S2: Mark the length of the building base (305) in the image main body (101) collected by the imaging device (103) as , and mark the imaging height of the actual height of the aerial working personnel main body (401) in the image main body (101) as ; S3: The altitude h of the main body (401) of the aerial work personnel to be measured can be obtained through the determination rule of similar triangles. Here .

3. The safety hook monitoring method for high-altitude workers according to claim 1, characterized in that, The specific identification method of the three-layer neural network for the high-altitude operation personnel main body (401) is: Take the camera device (103) as the video input layer (2-1) for real-time video acquisition, extract the static building in the real-time video, form the image feature extraction layer (2-2) with the feature information (2-4) and the dynamic operator information (2-5), and then obtain the output layer (2-3) of the operator through the difference between the real-time video image frames collected by the camera device (103) and the processing and recognition of the local dynamic image.

4. A safety hook monitoring method for high-altitude workers according to claim 1, characterized in that The specific method of the rolling horizon dynamic calibration method is as follows: Taking the main body of the aerial worker (401) as the focus, when the main body of the aerial worker (401) performs aerial work on the building surface (301) and needs to gradually rise from the base height of the building, that is, when the main body of the aerial worker (401) needs to rise from the first area (302) to the second area (303) and then rise to the third area (304), when the length of the building base (305) measured manually is , and the height of the building base (305) is h0, the spatial calibration of the length of the building base (305) and the actual height of the main body of the aerial worker (401) is carried out through the imaging device (103), that is, the imaging length and imaging height in the image are respectively marked as and . At the same time, the fourth area (306) of the building and its imaging length are also imaged in the imaging device (103). The altitude h1 corresponding to the fourth area (306) of the building is calculated by the similarity triangle determination rule.

5. The safety hook monitoring method for high-altitude operators according to claim 4, wherein The specific method for calculating the altitude h1 corresponding to the fourth region (306) by the determination rule of similar triangles is as follows: Through the formula the altitude h1 corresponding to the fourth region (306) and the length of the building partial region can be calculated , where ; During the process of the operator ascending, the camera device (103) follows and tracks a partial area of the high-altitude operation personnel main body (401), and the image is continuously calibrated in a rolling manner over time, so as to obtain the altitude information of the position of the high-altitude operation personnel main body (401) and the calibration information of the length of a partial area of the building.

Images