A field monitoring method based on engineering informatization

Abstract

The present invention discloses a on-site monitoring method based on engineering informatization, including: real-time collecting the data of the tightness degree of the rope through the tension sensor integrated on the safety rope, and transmitting the data to the on-site monitoring system; obtaining the working pictures of workers taken by the video monitoring equipment deployed at the construction site, and extracting the posture features such as the body tilt angle and the arm extension length of the workers in the pictures; determining the real-time position coordinates of the workers according to the positioning tag information worn by the workers, and judging whether the coordinates are within the preset dangerous area electronic fence; according to the distance relationship between the connection points of the workers and the safety rope, analyzing the swinging trajectory of the safety rope and the movement trajectory calculated from the change of the worker position coordinates, and judging whether the worker has committed the violation of detaching from the safety rope; if it is judged that the worker has detached from the safety rope, according to the material characteristics and color characteristics of the safety rope, the position of the suspected detached connection point of the safety rope is marked in the monitoring picture.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a field monitoring method based on engineering informatization. Background Art

[0002] In the engineering safety monitoring system, there is a key technical problem: how to accurately identify whether workers have detached from the protective rope in a complex construction environment. At present, the system collects rope data through tension sensors and analyzes it in combination with video monitoring and positioning tag information. However, due to factors such as noise interference, light changes and obstructions at the construction site, it is difficult to make accurate judgments based solely on these data. Especially when workers move quickly or work in a small space, the data collected by the sensor may fluctuate instantaneously, resulting in false alarms or missed alarms. At the same time, changes in the worker's posture will also affect the rope tension, making it difficult for the system to distinguish between normal operation and detachment from protection. Relying solely on the vibration frequency and motion trajectory of the rope, it is difficult to fully reflect the actual working status of the workers and the potential dangers of the surrounding environment. How to establish a dynamic and accurate protective rope detachment model is a technical challenge that needs to be solved urgently. Summary of the invention

[0003] The purpose of the present invention is to solve the problems in the prior art and to propose a field monitoring method based on engineering informationization.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] A field monitoring method based on engineering informationization, S1, collects rope tightness data in real time through a tension sensor integrated on the protection rope, and transmits the data to a field monitoring system;

[0006] S2, obtaining the worker working picture taken by the video surveillance equipment deployed at the construction site, and extracting the posture features of the worker's body tilt angle and arm extension length in the picture;

[0007] S3, determining the real-time location coordinates of the worker according to the positioning tag information worn by the worker, and judging whether the coordinates are within the preset dangerous area electronic fence;

[0008] S4, if the worker is in the danger zone, the body tilt angle, arm extension length posture characteristics and the tightness data of the safety rope are correlated and analyzed to obtain the distance relationship between the worker and the connection point of the safety rope;

[0009] S5, according to the distance relationship between the worker and the connection point of the protection rope, analyzing the swing trajectory of the protection rope and the motion trajectory calculated by the change of the worker's position coordinates, to determine whether the worker has violated the rules by leaving the protection rope;

[0010] S6. If it is determined that the worker has detached from the safety rope, based on the material characteristics and color features of the safety rope, mark the position of the suspected detachment connection point of the safety rope on the monitoring screen.

[0011] S7. According to the body swing frequency of the worker and the vibration frequency of the safety rope, combined with the position of the safety rope connection point, evaluate whether the amplitude of the worker's operation exceeds the protection range of the safety rope, calculate the center of gravity offset distance of the worker, and determine whether there is detachment. If there is detachment, give a warning reminder.

[0012] The present invention has the following advantages compared with the prior art:

[0013] First, the present invention monitors whether the worker has detached from the safety rope in real time by integrating a tension sensor on the safety rope, analyzing the worker's posture in the video monitoring screen, and positioning the worker's position, etc. It comprehensively utilizes multi-source information such as tension sensor data, video monitoring data, and positioning tag data, improving the accuracy and comprehensiveness of judgment; at the same time, it correlates and analyzes the tightness of the safety rope, the worker's posture characteristics, and position information, judges the distance relationship between the worker and the safety rope connection point, and combines the swing trajectory of the safety rope and the movement trajectory of the worker to evaluate whether the operation amplitude exceeds the protection range. When it is found that the worker has detached from the safety rope, a warning can be issued in a timely manner, realizing intelligent analysis and judgment of complex situations, effectively preventing high-altitude falling accidents, and improving operation safety. Brief Description of the Drawings

[0014] Figure 1 It is a flowchart of a field monitoring method based on engineering informatization proposed by the present invention;

[0015] Figure 2 It is a schematic diagram of a field monitoring method based on engineering informatization proposed by the present invention;

[0016] Figure 3 It is another schematic diagram of a field monitoring method based on engineering informatization proposed by the present invention. Detailed Embodiment

[0017] 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.

[0018] Refer to Figures 1-3 , a field monitoring method based on engineering informatization in this embodiment specifically includes the following steps:

[0019] S1. Real-time collect the data of the tightness of the rope through the tension sensor integrated on the safety rope, and transmit this data to the on-site monitoring system.

[0020] More specifically, obtain the original data of the tightness degree of the rope collected by the tension sensor integrated on the safety rope; according to the on-site environmental temperature value measured by the temperature sensor, use the preset temperature compensation curve to correct the original data of the tightness degree of the rope to obtain the corrected tension data; perform median filtering on the corrected tension data, use median filtering with a window size of 5 to remove outliers, obtain the tension data with outliers removed, and according to the set transmission priority, use the ZigBee protocol for data transmission to transmit the tension data with outliers removed to the on-site monitoring system. The on-site monitoring system receives and analyzes the transmitted data through special software and displays the tension data of each safety rope in real time.

[0021] Exemplarily, install a tension sensor of model XL-100 on the safety rope, set the acquisition frequency to 10 Hz, and collect the data of the tightness degree of the rope in real time. At the same time, use a PT100 temperature sensor to measure the on-site environmental temperature, and use the preset temperature compensation curve y = ax^2 + bx + c, where a, b, and c are constants determined according to the rope material, to correct the original tension data. The corrected tension data is processed by a median filtering algorithm with a window size of 5 to remove outliers. For example, remove 150 from [100, 102, 150, 103, 105]. Use the ZigBee protocol for data transmission and transmit it to the on-site monitoring system. The on-site monitoring system receives and analyzes the transmitted data through special software and displays the tightness degree data of each safety rope on the graphical interface in real time.

[0022] S2. Obtain the worker operation images captured by the video monitoring equipment deployed at the construction site, and extract the body tilt angle and the gesture features of the arm extension length of the workers in the images.

[0023] Obtain the original video frames collected by the video surveillance equipment at the construction site, preprocess the original video frames, perform image denoising using Gaussian filtering, adjust the brightness and enhance the contrast through histogram equalization to obtain the preprocessed images. Perform human detection based on the preprocessed images, use the YOLOv5s object detection algorithm to locate the positions of the workers in the frame, set the confidence threshold and non-maximum suppression threshold, such as the confidence threshold is 0.6 and the non-maximum suppression threshold is 0.5, and output the bounding box coordinates of each detected worker. For the multi-person scenario, retain all detected human bounding boxes. Crop out individual worker images from the preprocessed images according to the bounding box coordinates, and use the BODY_25 human pose estimation algorithm to extract the skeletal key points of the workers, including the two-dimensional coordinates of at least 25 key points such as the head, torso, and limbs, and set the key point detection confidence threshold to 0.5. If some key point detections fail, use the linear interpolation method to estimate the positions of the missing key points. Based on the skeletal key point coordinates, calculate the body tilt angle and arm extension length of the worker. The body tilt angle is calculated through three key points: the top of the head, the neck, and the ankle, considering the three-dimensional space projection. The arm extension length is calculated from the spatial position relationship of three key points: the shoulder, the elbow, and the wrist. For occlusion situations, use temporal information to predict the key point positions. For light changes, adjust the detection parameters using an adaptive threshold.

[0024] Exemplarily, a high-definition camera deployed at the construction site captures video frames at a frame rate of 30fps with a resolution of 1920x1080. Each frame of the image is filtered and denoised using a 3x3 Gaussian kernel, and then the pixel intensity distribution is extended from the original range concentrated in 100 - 150 to the full range of 0 - 255 through histogram equalization to enhance the image contrast. The preprocessed image is input into the YOLOv5s model, which is pre-trained on the COCO dataset and fine-tuned on the construction scene dataset. The detection confidence threshold is set to 0.6, and the non-maximum suppression threshold is 0.5, and the bounding box coordinates of each worker are output. For a multi-person scenario, if 5 workers are detected, 5 sets of bounding box coordinates are retained. The individual worker images are cropped according to the bounding boxes and fed into the BODY_25 model, which is based on the OpenPose architecture and can detect 25 human key points, including 5 facial points, 6 torso points, and 14 limb points. The key point detection confidence threshold is set to 0.5. If the confidence of a certain point is lower than the threshold, the position of this point in the adjacent two frames is used for linear interpolation estimation. After obtaining the key point coordinates, the body tilt angle is calculated using the four points of the top of the head, the neck, and the left and right ankles. Considering that the camera installation height is 5 meters and the viewing angle pitch angle is about 30 degrees, the two-dimensional coordinates are converted into three-dimensional space coordinates for calculation. The arm extension length is obtained by summing the Euclidean distances of the three points of the shoulder, elbow, and wrist. For the case of being blocked by other objects, the Kalman filter is used to predict the key point trajectory of the previous 3 frames before occlusion to estimate the current frame position. When the light changes, the detection threshold of YOLOv5s is dynamically adjusted by calculating the average image brightness in real time, reduced to 0.5 in the shadow area and increased to 0.7 in the strong light area to adapt to different lighting conditions.

[0025] S3. Determine the real-time position coordinates of the worker according to the positioning tag information worn by the worker, and judge whether the coordinates are within the preset dangerous area electronic fence.

[0026] Obtain the wireless signals emitted by the positioning tags worn by workers per second, and the wireless signals are received by signal receivers distributed at the construction site; Parse the worker ID and initial position data from the wireless signals; Select the three receivers with the strongest signals, and calculate the real-time two-dimensional coordinates of the worker using the known positions of the receivers and the time difference of signal arrival; Combine the signal strengths of multiple receivers and the known height information, and estimate the height value through triangulation to obtain the three-dimensional space coordinates of the worker; Perform Kalman filtering on the three-dimensional space coordinates. The Kalman filtering includes setting the state vector to contain position and velocity, the observation vector to be position, and the process noise covariance matrix and the observation noise covariance matrix are determined according to the actual measurement error; Eliminate the coordinate jitter caused by signal interference and multipath effects through Kalman filtering to obtain a smoothed sequence of worker position coordinates; Transform the latest coordinate point in the smoothed sequence of worker position coordinates to the local coordinate system with a fixed point at the construction site as the origin through affine transformation; Use the ray method to determine whether the latest coordinate point is within the polygon of the preset dangerous area electronic fence. The ray method includes making a ray in any direction from the judgment point and calculating the number of intersection points with the polygon boundary to determine whether the point is within the polygon.

[0027] Exemplarily, 20 signal receivers are deployed at the construction site. The positioning tags worn by workers send 2.4 GHz wireless signals containing the worker ID and the initial position once per second. After receiving the signals, the three receivers with the highest signal strength are selected. Assuming their coordinates are (0,0,0), (10,0,0), and (0,10,0) respectively, the two-dimensional coordinates of the worker are calculated through the time difference of arrival of the signals, such as Δt1 = 0.00000005 seconds and Δt2 = 0.00000008 seconds. Combining the signal strengths of all receivers, such as -60 dBm, -62 dBm, -65 dBm, etc., and the known height information, the height value is estimated using the triangulation method, and finally the three-dimensional space coordinates of the worker (5.2, 4.8, 1.7) are obtained. Applying the Kalman filter to these original coordinate data, the state vector is set as [x, y, z, vx, vy, vz], the observation vector is [x, y, z], and the process noise covariance matrix Q and the observation noise covariance matrix R are set according to the actual measurement error, such as Q = diag(0.1, 0.1, 0.1, 0.01, 0.01, 0.01) and R = diag(0.2, 0.2, 0.2). After filtering, a smooth position coordinate sequence is obtained. The latest smooth coordinates (5.3, 4.9, 1.8) are transformed into the local coordinate system with the southwest corner of the construction site as the origin through an affine transformation matrix, resulting in (105.3, 94.9, 1.8). The preset electronic fence for the dangerous area is a polygon with vertex coordinates [(100, 90, 0), (110, 90, 0), (110, 100, 0), (100, 100, 0)]. The ray method is used to determine whether the point is inside the polygon. A ray is drawn from the point (105.3, 94.9, 1.8) in the positive x-axis direction, and the number of intersections with the polygon boundary is calculated to be an odd number 1, determining that the point is inside the polygon.

[0028] S4. If the worker is in the dangerous area, then the body tilt angle, the gesture features of the arm extension length, and the data of the tightness of the safety rope are correlated and analyzed to obtain the distance relationship between the connection point of the worker and the safety rope.

[0029] Obtain the worker data located inside the dangerous polygon from the real-time monitoring database. The worker data includes the identity identifier, position coordinates, body tilt angle, and arm extension length. The body tilt angle includes the torso tilt angle, the arm extension angle, the angle of standing or squatting of the legs, and the head orientation; calculate the center of gravity position of the worker according to the worker data, including determining the joint point positions using a 15-node simplified human bone model and obtaining the center of gravity offset by combining the body tilt angle and the arm extension length; obtain the data of the tightness of the safety rope, establish a mapping function according to the tightness data, and determine the actual length and shape of the safety rope through the mapping function.

[0030] Exemplarily, at the construction site, the real-time monitoring database uses the R-tree spatial indexing technology to define the dangerous area as a polygon [(0,0),(10,0),(10,10),(0,10)]. It quickly queries worker A located in this area, whose identity identifier is worker_001, with a position coordinate of (5,5,2) and a body tilt angle of 30 degrees and an arm extension length of 0.8 meters. At the same time, the tightness data of the worker's safety rope is obtained from the safety rope monitoring subsystem, and the tension value is 200N.

[0031] S401, analyze the body posture of the worker, including the torso tilt angle, the extension length and angle of both arms, the angle of the legs in a standing or squatting position, and the head orientation. Analyze the state of the safety rope, calculate the bending degree and slackness of the rope through the tension sensor data, and estimate the relative position of the connection point between the worker and the safety rope.

[0032] Obtain the body posture characteristic parameters of the worker from the real-time monitoring database. And obtain the real-time data of multiple tension sensors on the safety rope, and use the cubic spline interpolation method to fit the tension sensor data points to obtain a continuous tension distribution curve. According to the body posture characteristic parameters of the worker and the tension distribution curve, establish a three-dimensional spatial relationship model of the worker-safety rope, and estimate the relative position of the connection point between the worker and the safety rope.

[0033] Exemplarily, obtain the real-time data of multiple tension sensors on the safety rope, use the cubic spline interpolation method to fit the tension sensor data points to obtain a continuous tension distribution curve, and calculate the bending degree of the rope. Combine the stress-strain characteristic curve of the rope material measured in advance in the laboratory to estimate the actual length and slackness of the rope. According to the worker posture characteristic parameters and the safety rope state data, establish a three-dimensional spatial relationship model of the worker-safety rope, use the least squares method to fit the three-dimensional curve of the safety rope, and combine the worker's position to calculate the nearest point as the connection point to obtain the relative position coordinates of the connection point between the safety rope and the worker. A tension sensor is installed every 0.5m on the safety rope, with a total of 10, and the real-time tension data [100N, 105N, 110N, 108N, 106N, 104N, 102N, 101N, 100N, 99N] is collected. Use the cubic spline interpolation method to fit these data points to obtain a continuous tension distribution curve f(x)=ax^3+bx^2+cx+d, where a, b, c, d are fitting coefficients. According to the pre-measured stress-strain curve ε = 0.001σ + 0.0001σ^2, where ε is the strain and σ is the stress, estimate that the actual length of the rope is 5.2m and the slackness is 4%. Use the least squares method to fit the three-dimensional curve g(t)=(x(t), y(t), z(t)) of the safety rope, and combine the worker's position (2,3,1.5) to calculate the connection point coordinates (2.1,3.2,1.6).

[0034] S402. Establish an association model between the worker's posture and the state of the safety rope. Pair the spatial coordinates of each part of the worker's body with the coordinates of the connection points of the safety rope, calculate the offset distance of the worker's center of gravity position relative to the connection points of the safety rope, and obtain the distance between the worker and the connection points of the safety rope.

[0035] Obtain the three-dimensional spatial coordinates of each part of the worker's body collected by the depth camera and the real-time coordinates of the connection points of the safety rope obtained by the inertial measurement unit. Use the rigid body transformation matrix to convert the coordinates of the inertial measurement unit to the depth camera coordinate system, and unify the two sets of coordinate data into the same coordinate system. According to the spatial coordinates of each part of the worker's body, use a 15-node simplified human body model to calculate the worker's center of gravity position according to the mass ratio of each part. At the same time, based on the data of the tension sensor of the safety rope, use the finite element method to solve the elastic catenary model, and estimate the spatial shape of the safety rope according to the data of the tension sensor of the safety rope. Establish an association model between the worker's posture and the state of the safety rope, construct a weight function based on distance and angle, quantify the influence of the worker's posture on the state of the safety rope, and use the KD-tree structure to optimize the nearest neighbor search process. Pair the spatial coordinates of each part of the worker's body with the discrete points on the safety rope to form a worker-safety rope spatial correspondence. Calculate the three-dimensional offset vector of the worker's center of gravity position relative to the connection points of the safety rope, use the Euclidean distance formula to calculate the absolute value of the offset distance, and combine the offset direction to obtain the distance relationship between the worker and the connection points of the safety rope. Use the Kalman filter to predict the worker's movement trajectory, update the distance relationship in real time, and fuse the multi-source data of the depth camera, inertial measurement unit, and tension sensor through the Bayesian estimation method to improve the accuracy of the distance relationship calculation.

[0036] Exemplarily, deploy an Intel RealSense D455 depth camera at the construction site to collect depth images with a resolution of 1280x720 at a frequency of 30 frames per second. At the same time, install an Xsens MTi-300 AHRS inertial measurement unit at the connection point of the safety rope, with a sampling rate of 100 Hz. Adopt a 15-node simplified human body model, where the head accounts for 7%, the torso accounts for 43%, each upper arm accounts for 3%, each forearm accounts for 2%, each thigh accounts for 12%, each calf accounts for 5%, and each foot accounts for 1.5% of the mass ratio. The calculated center of gravity position of the worker is (2.1, 1.5, 0.9) meters. Install a tension sensor every 0.5 meters on the safety rope, and the measured tension data is [120N, 115N, 110N, 105N, 100N]. Use the fourth-order Runge-Kutta method to solve the elastic catenary equation y = a cosh(x / a), and obtain the spatial shape curve of the safety rope y = 2.5 cosh(x / 2.5). Construct a distance weight function w_d = 1 / (1 + d^2) and an angle weight function w_θ = cos(θ), where d is the Euclidean distance and θ is the included angle. The comprehensive weight w of the influence of the worker's posture on the state of the safety rope is w = 0.6w_d + 0.4w_θ. Use a KD tree to perform nearest neighbor matching between the 15 nodes of the worker and 50 discrete points of the safety rope, and the average search time is 0.5 milliseconds. Calculate the offset vector of the worker's center of gravity (2.1, 1.5, 0.9) relative to the connection point of the safety rope (0, 0, 3) as (2.1, 1.5, -2.1), and the Euclidean distance is 3.4 meters. Use a Kalman filter, with the state vector [x, y, z, vx, vy, vz] and the observation vector [x, y, z], and predict the position of the worker 0.1 seconds later as (2.15, 1.52, 0.91). Finally, through the Bayesian estimation method, fuse the depth image, inertial data, and tension data to obtain the posterior probability distribution of the distance relationship between the worker and the connection point of the safety rope, with a mean of 3.38 meters and a standard deviation of 0.05 meters.

[0037] S5. According to the distance relationship between the worker and the connection point of the safety rope, analyze the swinging trajectory of the safety rope and the movement trajectory calculated from the change of the worker's position coordinates, and judge whether the worker has committed a violation of detaching from the safety rope.

[0038] The acceleration and angular velocity data of the connection point of the safety rope are collected in real time by using an inertial measurement unit. The swing trajectory of the safety rope is obtained by numerical integration of the acceleration and angular velocity data through the fourth-order Runge-Kutta method, and the cumulative error is corrected by using a Kalman filter. At the same time, the three-dimensional position coordinate sequence of the worker is obtained by using a depth camera, and the movement trajectory of the worker is obtained by calculating the position difference between adjacent moments according to the three-dimensional position coordinate sequence; the swing trajectory of the safety rope and the movement trajectory of the worker are aligned in time series, and the dynamic time warping algorithm is used to calculate the similarity score between the swing trajectory of the safety rope and the movement trajectory of the worker. The window size is set to 50 frames, the step size is 10 frames, the Euclidean distance is used as the cost function, and the similarity threshold is set to judge whether the worker follows the swing of the safety rope. The change rate of the Euclidean distance between the worker's position and the connection point of the safety rope over time is calculated, and the mutation point of the change rate is detected by the sliding window method. The window size is set to 1 second (30 frames), the step size is 0.1 second (3 frames), and if the change rate exceeds the preset threshold, it is marked as a potential detachment event; according to the similarity score and the change rate, a support vector machine classifier is used to classify the worker's behavior. The SVM model is trained by historical annotation data, the RBF kernel function is used, and the hyperparameters C and gamma are optimized by grid search to output the judgment result of whether there is a violation of detaching from the safety rope. When the distance between the worker and the connection point of the safety rope exceeds 2 meters and the duration exceeds 3 seconds, it is determined as a violation of detaching from the safety rope.

[0039] Exemplarily, an Xsens MTi-G-710 inertial measurement unit is deployed at the construction site, the sampling rate is set to 100 Hz, and the acceleration and angular velocity data of the connection point of the safety rope are collected. The fourth-order Runge-Kutta method is used for numerical integration, the step size is set to 0.01 seconds, and the swinging trajectory of the safety rope is calculated. The Kalman filter is applied, the state vector includes position and velocity, the process noise covariance matrix Q = diag(0.01, 0.01, 0.01, 0.1, 0.1, 0.1), and the observation noise covariance matrix R = diag(0.1, 0.1, 0.1) to correct the cumulative error. At the same time, an Intel RealSense D455 depth camera with a frame rate of 30 fps and a resolution of 1280x720 is used to obtain the three-dimensional coordinate sequence of the worker. Dynamic time warping is performed on the two trajectories with a window size of 50 frames and a step size of 10 frames. Using the Euclidean distance as the cost function, the similarity score of 0.85 is calculated, with a full score of 1. A similarity threshold of 0.7 is set to determine whether the worker follows the swinging of the safety rope. Using a sliding window of 1 second in size and a step size of 0.1 second, the rate of change of the distance between the worker and the connection point is calculated, and the preset threshold is 0.5 m / s. The LibSVM library is used to train a support vector machine classifier, using the RBF kernel function, and the best parameters C = 10 and gamma = 0.1 are obtained through five-fold cross-validation and grid search. The input feature vector includes the trajectory similarity score and the rate of change of distance, and the probability of violation behavior is output as 0.92. According to the preset rules, when the distance exceeds 2 meters and lasts for more than 3 seconds, the system determines that the worker has committed the violation of detaching from the safety rope. When an abnormal signal is detected, such as no valid data within 3 seconds, linear interpolation is used to estimate the missing data to ensure the continuous operation of the system.

[0040] S5 further includes calculating the real-time deviation between the worker's movement trajectory and the swinging trajectory of the safety rope according to the distance relationship between the worker and the connection point of the safety rope, setting a safety distance threshold between the worker and the connection point of the safety rope, and continuously monitoring whether the actual distance exceeds this threshold.

[0041] Collect the three-dimensional coordinate data of the connection point of the safety rope through an inertial measurement unit. At the same time, use a depth camera to obtain the real-time three-dimensional coordinates of the worker. Use a rigid body transformation matrix to convert the coordinates of the inertial measurement unit to the camera coordinate system. Calculate the Euclidean distance between the worker and the connection point of the safety rope every 100 milliseconds based on the two sets of coordinate data to obtain the coordinates of the connection point of the safety rope and the coordinates of the worker in the unified coordinate system. Use a Kalman filter to predict and smooth the coordinates of the connection point of the safety rope and the coordinates of the worker. The state vector of the Kalman filter includes position and velocity. The process noise covariance matrix and the observation noise covariance matrix are set according to the actual measurement error to reduce the influence of measurement noise and obtain a more accurate motion trajectory and swing trajectory. Calculate the real-time deviation between the worker's motion trajectory and the swing trajectory of the safety rope through the dynamic time warping algorithm. The window size of the dynamic time warping algorithm is set to a preset duration, and the step size is set to a preset value. If the real-time deviation exceeds the preset safety distance threshold, trigger the safety warning mechanism. The safety distance threshold is dynamically adjusted by a fuzzy logic controller according to the working environment and task type. For example, set the window size to 2 seconds and the step size to 0.5 seconds, compare the deviation value with the preset safety distance threshold to determine whether there is a potential danger. Dynamically adjust the safety distance threshold according to the working environment and task type using a fuzzy logic controller. The initial threshold is set to 2 meters, and a sliding time window is set to continuously monitor the relationship between the actual distance and the threshold. When the distance of 5 consecutive sampling points exceeds the threshold, trigger the safety warning mechanism.

[0042] Exemplarily, deploy an Xsens MTi-G-710 inertial measurement unit at the construction site to collect the data of the connection point of the safety rope, with a sampling rate of 100 Hz. At the same time, use an Intel RealSense D455 depth camera with a frame rate of 30 fps and a resolution of 1280x720 to obtain the real-time three-dimensional coordinates of the worker. Calculate the Euclidean distance every 100 ms, d = sqrt((x1 - x2)^2+(y1 - y2)^2+(z1 - z2)^2). Apply the Kalman filter, with the state vector X = [x, y, z, vx, vy, vz], the observation vector Z = [x, y, z], the process noise covariance Q = diag(0.01, 0.01, 0.01, 0.1, 0.1, 0.1), and the observation noise covariance R = diag(0.1, 0.1, 0.1) to smooth the coordinates. Use the dynamic time warping algorithm with a window size of 60 frames, 2 seconds, and a step size of 15 frames, 0.5 seconds to calculate the trajectory deviation. Use a Mamdani-type fuzzy logic controller to dynamically adjust the safety threshold. The input variables are the work difficulty from 1 to 10 and the environmental complexity from 1 to 10, and the output is the threshold adjustment amount from -0.5 m to +0.5 m, with an initial threshold of 2 m. Set a sliding window of 0.5 seconds and 5 sampling points. If the distance of 5 consecutive points exceeds the current threshold, such as [2.1, 2.2, 2.15, 2.3, 2.25] m, then trigger an alarm.

[0043] S5 further includes analyzing the acceleration and direction changes of the worker's movement trajectory, identifying abnormal movements that cause sudden detachment from the safety rope, evaluating the correlation between the safety rope tension change and the worker's position change, and detecting whether there is an abnormal situation of sudden tension reduction.

[0044] Obtain the worker's movement data, which is collected by an inertial measurement unit with a sampling frequency of 100 Hz; calculate the three-dimensional acceleration and angular velocity according to the worker's movement data; use the Kalman filter algorithm to smooth the three-dimensional acceleration and angular velocity. The state vector includes position, velocity, and acceleration, and the observation vector is position and acceleration, to obtain the acceleration and direction change sequence of the worker's movement trajectory; for the acceleration and direction change sequence, segment it by the sliding window method, with the window size set to 1 second and 100 samples, and the step size set to 0.1 second and 10 samples. Select the acceleration peak, direction change rate, and attitude angle from the segmented sequence as features; use the support vector machine algorithm to train the abnormal movement recognition model, which is used to detect in real time whether the worker has abnormal movements that cause sudden detachment from the safety rope; obtain the safety rope tension data, which is collected by a tension sensor with a sampling frequency of 50 Hz; calculate the tension change rate and position change rate according to the safety rope tension data and the worker's position coordinates; use the Pearson correlation coefficient to evaluate the correlation between the tension change rate and the position change rate; if the tension change rate exceeds the preset threshold and the correlation is lower than the preset correlation coefficient threshold, it is determined that there is an abnormal situation. For example, according to the abnormal movement recognition result and correlation analysis, using the statistical analysis of historical data, set the tension change threshold to 3 times the standard deviation of the mean, and the correlation coefficient threshold to 0.5. When the tension suddenly decreases and the correlation with the position change is significantly reduced, it is determined that there is an abnormal situation, trigger the alarm mechanism and record the abnormal event.

[0045] Exemplarily, at the construction site, workers wear Xsens MTi-G-710 inertial measurement units, with the sampling frequency set to 100 Hz, to collect three-axis acceleration and angular velocity data. The Kalman filter is used for data smoothing. The state vector X = [x, y, z, vx, vy, vz, ax, ay, az], the observation vector Z = [x, y, z, ax, ay, az], the process noise covariance Q = diag(0.01, 0.01, 0.01, 0.1, 0.1, 0.1, 1, 1, 1), and the observation noise covariance R = diag(0.1, 0.1, 0.1, 0.5, 0.5, 0.5). The sliding window size is set to 100 samples, 1 second, and the step size is 10 samples, 0.1 second, to extract characteristic acceleration peaks, direction change rates, and attitude angles. The LibSVM is used to train a support vector machine model, with the RBF kernel function selected, the parameter C = 10, gamma = 0.1, and optimized through 5-fold cross-validation. An S-type tension sensor HBMS9M with a sampling frequency of 50 Hz is installed on the safety rope, with a range of 0 - 5 kN. Calculate the tension change rate ΔT / Δt and the position change rate Δs / Δt for 50 samples within 1 second, and use the Pearson correlation coefficient r = cov(ΔT / Δt, Δs / Δt) / (σ(ΔT / Δt)σ(Δs / Δt)) to evaluate the correlation. Based on historical data, the tension change threshold is set to μ + 3σ = 500 N / s, and the correlation coefficient threshold is 0.5. When an abnormal action is detected (the SVM output is 1), and the tension change rate > 500 N / s, and the correlation coefficient < 0.5, the system determines it as a sudden detachment situation and sends an alarm to the monitoring center through the MQTT protocol, including the worker ID, timestamp, and abnormal type.

[0046] S6. If it is determined that the worker has detached from the safety rope, then based on the material characteristics and color features of the safety rope, mark the position of the suspected detached safety rope connection point on the monitoring screen.

[0047] After determining that the worker has detached from the safety rope, obtain the real-time image of the high-definition surveillance camera, preprocess the real-time image to obtain the preprocessed image, including denoising using Gaussian filtering, performing illumination equalization and contrast enhancement using adaptive histogram equalization to improve the recognizability of the safety rope in the frame; establish a texture descriptor based on the gray-level co-occurrence matrix from the preprocessed image, convert the preprocessed image from the RGB color space to the HSV color space to obtain the HSV image; use the threshold segmentation algorithm to process the HSV image, extract the area that conforms to the characteristics of the safety rope to obtain the preliminary contour image of the safety rope; perform morphological operations such as using opening operation to remove noise and closing operation to fill small holes, and use the Canny edge detection algorithm to refine and optimize the preliminary contour image, extract the precise edges and endpoints of the safety rope to obtain the edge endpoint image, which is used as the candidate area for the suspected detached connection point; use the extracted edge and endpoint information as input, and use the YOLOv5 object detection algorithm trained based on the self-built safety rope connection point dataset to identify and locate the suspected detached safety rope connection point in the candidate area, and mark it with a specific color and shape in the surveillance frame to obtain the marked surveillance frame.

[0048] Exemplarily, deploy a high-definition camera with a 4K resolution at the construction site, and the frame rate is 30fps. When the system determines that the worker has detached from the safety rope, immediately trigger the image processing process. First, apply a Gaussian filter kernel with a size of 5x5 to the captured image for denoising, and then use 8x8 block adaptive histogram equalization to enhance the image contrast. Next, calculate the gray-level co-occurrence matrix of the image, and extract four features: contrast, energy, homogeneity, and correlation as the texture descriptor of the safety rope material. Convert the image from RGB to the HSV color space, and according to the preset color range of the safety rope, for example, hue H 20 - 40, saturation S 0.6 - 1.0, brightness V 0.4 - 0.8, use threshold segmentation to extract the suspected safety rope area. Apply opening and closing operations to the segmentation result using a structuring element of 3x3 to remove noise less than 50 pixels and fill holes less than 30 pixels. Then use the Canny edge detection algorithm with a low threshold of 50 and a high threshold of 150 to extract the safety rope contour. Input the processed edge image into the pre-trained YOLOv5s model, trained based on 1000 annotated safety rope connection point images, with mAP@0.5 being 0.92, to detect possible connection point positions. Finally, mark the detected connection points on the original image with a red rectangular box line width of 5 pixels, and mark the confidence score in the upper left corner of the box.

[0049] S7. According to the body swing frequency of the worker and the vibration frequency of the safety rope, combined with the position of the safety rope connection point, evaluate whether the amplitude of the worker's operation exceeds the protection range of the safety rope, calculate the center of gravity offset distance of the worker, determine whether there is detachment, and if there is detachment, give a warning reminder.

[0050] Accelerometer data is collected through an inertial measurement unit worn on the worker. According to the accelerometer data, a 1024-point fast Fourier transform algorithm is used to perform spectral analysis on the data of a 2-second sliding window to obtain the main frequency components of the worker's body swing; the vibration data of the tension sensor on the safety rope is obtained, and the vibration frequency of the safety rope is calculated according to the vibration data to obtain the ratio of the worker's body swing frequency to the safety rope vibration frequency, and a safe frequency ratio range is set; according to the worker's movement trajectory captured by the camera and the pre-calibrated position of the safety rope connection point, a cubic spline function is used to fit the worker's movement trajectory curve, and the maximum amplitude and average amplitude of the operation action are calculated according to the movement trajectory curve, and compared with the preset safety rope protection range, a spherical space centered on the connection point with a radius of 80% of the safety rope length, to determine whether the operation action amplitude exceeds the preset safety rope protection range; using a 15-node simplified human body model and inertial measurement unit data, the mass ratio of each part is set according to human anatomy data, the mass distribution and spatial position of each part of the worker's body are estimated, the center of gravity position is calculated, and the Kalman filter algorithm is used to smooth the center of gravity trajectory, with the state variables being the three-dimensional coordinates and velocity of the center of gravity, and the observation variable being the estimated center of gravity position, to obtain the offset distance of the worker's center of gravity relative to the safety rope connection point; the calculated frequency ratio, operation action amplitude, and center of gravity offset distance are compared with the dynamic safety thresholds set based on historical data statistical analysis and expert experience. If the threshold is exceeded, it is determined as a detached state, triggering a warning mechanism, sending a warning message to the intelligent device worn by the worker through the wireless communication module, and at the same time marking the position and detached state of the worker on the monitoring center display screen.

[0051] Exemplarily, at the construction site, workers wear Xsens MTi-G-710 inertial measurement units with a sampling rate set to 100 Hz to collect three-axis acceleration data. The 1024-point FFT is used to perform spectral analysis on the data of 200 samples in a 2-second sliding window, and the frequency with the largest amplitude in the range of 0.5 - 5 Hz is extracted as the body swing frequency of the worker. At the same time, an HBMS9M tension sensor is installed on the safety rope with a sampling rate of 50 Hz, and the vibration frequency of the safety rope is calculated by the same FFT method. The frequency ratio is calculated, and the safety range is set to 0.8 - 1.2. An Intel RealSense D455 depth camera is used to collect the movement trajectory of the worker at 30 fps. The scipy.interpolate.splrep function is used to fit a cubic spline curve to calculate the maximum amplitude. Assuming the length of the safety rope is 5 meters, the protection range is a spherical space with a radius of 4 meters. A 15-node simplified human model is used, with the mass ratios of the head accounting for 7%, the torso for 43%, the upper arms for 3% each, the forearms for 2% each, the thighs for 12% each, the calves for 5% each, and the feet for 1.5% each to estimate the position of the center of gravity. The Kalman filter is applied, with the state vector X = [x, y, z, vx, vy, vz], the observation vector Z = [x, y, z], the process noise covariance Q = diag(0.01, 0.01, 0.01, 0.1, 0.1, 0.1), and the observation noise covariance R = diag(0.1, 0.1, 0.1) to calculate the deviation of the center of gravity. Based on 1000 historical data, a dynamic threshold is set. If the frequency ratio exceeds ±20%, the action amplitude exceeds 3.5 meters, or the center of gravity deviation exceeds 3 meters, it is determined as a detachment. If triggered, a warning is sent to the worker's smart bracelet through the LoRaWAN network, and the position of the worker is marked with a red icon on the 55-inch display screen in the monitoring center.

[0052] As described above, it is only the preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, makes equivalent substitutions or changes, and all should be covered within the protection scope of the present invention.

Claims

1. A field monitoring method based on engineering informationization, characterized in that: The following steps are involved: S1, collects rope tightness data in real time through the tension sensor integrated on the protection rope, and transmits the data to the on-site monitoring system; S2, obtaining the worker working picture taken by the video surveillance equipment deployed at the construction site, and extracting the posture features of the worker's body tilt angle and arm extension length in the picture; S3, determining the real-time location coordinates of the worker according to the positioning tag information worn by the worker, and judging whether the coordinates are within the preset dangerous area electronic fence; S4, if the worker is in the danger zone, the body tilt angle, arm extension length posture characteristics and the tightness data of the safety rope are correlated and analyzed to obtain the distance relationship between the worker and the connection point of the safety rope; S5, according to the distance relationship between the worker and the connection point of the protection rope, analyzing the swing trajectory of the protection rope and the motion trajectory calculated by the change of the worker's position coordinates, to determine whether the worker has violated the rules by leaving the protection rope; S6, if it is determined that the worker has detached from the safety rope, the location of the connection point of the safety rope suspected to have detached is marked in the monitoring image according to the material characteristics and color characteristics of the safety rope; S7, based on the worker's body swing frequency and the vibration frequency of the safety rope, combined with the location of the safety rope connection point, evaluates whether the worker's working movement range exceeds the protection range of the safety rope, calculates the worker's center of gravity offset distance, determines whether he is out of the rope, and issues a warning if so.

2. The on-site monitoring method based on engineering informationization according to claim 1 is characterized in that: The S1 includes: Obtaining raw data on the tightness of the rope collected by a tension sensor integrated on the protective rope; According to the on-site ambient temperature value measured by the temperature sensor, the original data of the tightness of the rope is corrected using a preset temperature compensation curve to obtain corrected tension data; The corrected tension data is subjected to median filtering, and a filter window size is preset to obtain tension data with outliers removed.

3. The on-site monitoring method based on engineering informationization according to claim 1 is characterized in that: The S2 includes: Obtaining original video frames captured by video surveillance equipment at the construction site, preprocessing the original video frames, performing image denoising using Gaussian filtering, and performing brightness adjustment and contrast enhancement through histogram equalization to obtain a preprocessed image; Performing human body detection according to the preprocessed image, locating the position of the worker in the picture, setting a confidence threshold and a non-maximum suppression threshold, and outputting the bounding box coordinates of each detected worker; cropping a single worker image from the preprocessed image according to the bounding box coordinates, and extracting the worker's skeletal key points; If some key points fail to be detected, the positions of the missing key points are estimated; Based on the coordinates of the skeleton key points, the worker's body inclination angle and arm extension length are calculated.

4. The on-site monitoring method based on engineering informationization according to claim 1 is characterized in that: The S3 includes: Acquire a wireless signal emitted every second by the positioning tag worn by the worker, wherein the wireless signal is received by a signal receiver distributed at the construction site; Obtaining worker ID and initial location data according to the wireless signal analysis; Selecting three receivers with the strongest signals and calculating the real-time two-dimensional coordinates of the workers using the known positions of the receivers and the time difference of arrival of the signals; Combining the signal strength of multiple receivers with known height information, the height value is estimated to obtain the three-dimensional spatial coordinates of the worker; Processing the three-dimensional space coordinates to eliminate coordinate jitter caused by signal interference and multipath effects, and obtaining a smoothed worker position coordinate sequence; Converting the latest coordinate point in the smoothed worker position coordinate sequence into a local coordinate system with a fixed point at the construction site as the origin through affine transformation; Determine whether the latest coordinate point is within the preset dangerous area electronic fence polygon.

5. The on-site monitoring method based on engineering informationization according to claim 1 is characterized in that: The S4 includes: firstly, obtaining worker data located within the danger polygon from the real-time monitoring database, wherein the worker data includes identity identification, location coordinates, body inclination angle, and arm extension length, wherein the body inclination angle includes the trunk inclination angle, the arm extension angle, the angle of the legs standing or squatting, and the head orientation; Calculating the center of gravity position of the worker according to the worker data, including using a 15-node simplified human body model to determine the position of the joint points, and combining the body tilt angle and the arm extension length to obtain the center of gravity offset; The tightness data of the protective rope is obtained, a mapping function is established according to the tightness data, and the actual length and shape of the protective rope are determined by the mapping function.

6. The on-site monitoring method based on engineering informationization according to claim 5 is characterized in that: The S4 specifically comprises the following steps: S401, analyzing the body posture of the worker, including the inclination angle of the torso, the length and angle of the arms, the angle of the legs when standing or squatting, and the head orientation, analyzing the state of the safety rope, calculating the bending degree and slackness of the rope through the tension sensor data, and estimating the relative position of the connection point between the worker and the safety rope; S402, establish an association model between the worker's posture and the state of the protective rope, match the spatial coordinates of various parts of the worker's body with the coordinates of the protective rope connection point, calculate the offset distance of the worker's center of gravity position relative to the protective rope connection point, and obtain the distance between the worker and the protective rope connection point.

7. The on-site monitoring method based on engineering informationization according to claim 6 is characterized in that: The S401 specifically includes: Obtaining the worker's body posture characteristic parameters from the real-time monitoring database; And obtain real-time data of multiple tension sensors on the protection rope, fit the data points of the tension sensors, and obtain a continuous tension distribution curve; According to the body posture characteristic parameters of the worker and the tension distribution curve, a three-dimensional spatial relationship model of the worker and the protection rope is established to estimate the relative position of the connection point between the worker and the protection rope; The S402 specifically includes: Obtain the three-dimensional spatial coordinates of various parts of the worker's body collected by the depth camera and the real-time coordinates of the connection points of the protective rope obtained by the inertial measurement unit, and use the rigid body transformation matrix to transform the inertial measurement unit coordinates into the depth camera coordinate system; According to the spatial coordinates of each part of the worker's body, a 15-node simplified human body model is used to calculate the center of gravity of the worker, and the center of gravity is determined by the mass ratio of each part; estimating the spatial shape of the protective rope according to the protective rope tension sensor data; Establishing a model for associating worker posture with the state of the protective rope, constructing a weight function based on distance and angle, and quantifying the influence of the worker posture on the state of the protective rope; Calculate the three-dimensional offset vector of the worker's center of gravity relative to the connection point of the protective rope, calculate the absolute value of the offset distance, and obtain the distance relationship between the worker and the connection point of the protective rope; The worker's movement trajectory is predicted, and the distance relationship is updated in real time.

8. The on-site monitoring method based on engineering informationization according to claim 1 is characterized in that: The S5 includes: Acquire the acceleration and angular velocity data of the connection point of the protection rope collected in real time by the inertial measurement unit, and obtain the swing trajectory of the protection rope by numerical integration according to the acceleration and angular velocity data; The worker's three-dimensional position coordinate sequence is obtained through a depth camera, and the position difference at adjacent moments is calculated according to the three-dimensional position coordinate sequence to obtain the worker's movement trajectory; Performing time series alignment on the swing trajectory of the protection rope and the movement trajectory of the worker, and calculating a similarity score between the swing trajectory of the protection rope and the movement trajectory of the worker; Calculate the rate of change of the Euclidean distance between the worker's position and the connection point of the protective rope over time, and detect the mutation point of the change rate; According to the similarity score and the change rate, a support vector machine classifier is used to classify the worker's behavior, and if the worker's behavior is classified as being out of the safety rope, it is determined to be a violation; It also includes: calculating the real-time deviation between the worker's movement trajectory and the protection rope's swing trajectory based on the distance relationship between the worker and the protection rope's connection point, setting a safety distance threshold between the worker and the protection rope's connection point, and continuously monitoring whether the actual distance exceeds this threshold; Analyze the acceleration and direction changes of the worker's movement trajectory, identify abnormal movements that lead to sudden detachment from the safety rope, evaluate the correlation between the change in the safety rope tension and the change in the worker's position, and detect whether there is an abnormal situation of sudden tension reduction; The method calculates the real-time deviation between the worker's motion trajectory and the swing trajectory of the protective rope according to the distance relationship between the worker and the connection point of the protective rope, sets a safety distance threshold between the worker and the connection point of the protective rope, and continuously monitors whether the actual distance exceeds the threshold, specifically including: Obtaining the three-dimensional coordinate data of the protective rope connection point and the real-time three-dimensional coordinates of the worker, wherein the three-dimensional coordinate data is collected by an inertial measurement unit and the real-time three-dimensional coordinates are obtained by a depth camera; The inertial measurement unit coordinates are converted into the depth camera coordinate system according to the rigid body transformation matrix to obtain the protective rope connection point coordinates and the worker coordinates in the unified coordinate system; A Kalman filter is used to predict and smooth the coordinates of the protective rope connection point and the worker coordinates, wherein the state vector of the Kalman filter includes position and velocity, and the process noise covariance matrix and the observation noise covariance matrix are set according to actual measurement errors; Calculating the real-time deviation between the worker's motion trajectory and the protection rope's swing trajectory; If the real-time deviation exceeds the preset safety distance threshold, a safety warning mechanism is triggered; The analysis of the acceleration and direction changes of the worker's motion trajectory, identification of abnormal movements that lead to sudden separation from the safety rope, evaluation of the correlation between the change in the safety rope tension and the change in the worker's position, and detection of whether there is an abnormal situation of a sudden decrease in tension specifically includes: Acquiring worker movement data, where the worker movement data is collected by an inertial measurement unit with a sampling frequency of 100 Hz; Calculating three-dimensional acceleration and angular velocity based on the worker movement data; Smoothing the three-dimensional acceleration and angular velocity to obtain a sequence of acceleration and direction changes of the worker's motion trajectory; For the acceleration and direction change sequence, segmenting is performed by a sliding window method; The acceleration peak, direction change rate and attitude angle are selected as features from the segmented sequence obtained by segmenting using the sliding window method; Training an abnormal action recognition model, wherein the abnormal action recognition model is used to detect in real time whether a worker has made an abnormal action that causes a sudden break away from the safety rope; Acquire the tension data of the protective rope, wherein the tension data of the protective rope is collected by a tension sensor with a sampling frequency of 50 Hz; Calculate the tension change rate and the position change rate according to the protection rope tension data and the worker position coordinates; evaluating a correlation between the rate of change of tension and the rate of change of position; If the tension change rate exceeds a preset threshold and the correlation is lower than a preset correlation coefficient threshold, it is determined that an abnormal situation exists.

9. The on-site monitoring method based on engineering informationization according to claim 1 is characterized in that: The S6 includes: Obtaining a real-time image from a high-definition surveillance camera, and preprocessing the real-time image to obtain a preprocessed image; Establishing a texture descriptor based on a gray-level co-occurrence matrix according to the preprocessed image, converting the preprocessed image from an RGB color space to an HSV color space to obtain an HSV image; Processing the HSV image, extracting the area that meets the characteristics of the protection rope, and obtaining a preliminary contour image of the protection rope; Processing the preliminary contour image, extracting the precise edge and endpoints of the protection rope, and obtaining an edge endpoint image; If there is a suspected detached protection rope connection point in the edge endpoint image, the edge endpoint image is processed to identify and locate the suspected detached protection rope connection point to obtain a marked monitoring picture.

10. The on-site monitoring method based on engineering informationization according to claim 1 is characterized in that: The S7 includes: Acquire acceleration data collected by the inertial measurement unit, perform spectrum analysis based on the acceleration data, and obtain the main frequency components of the worker's body swing; Acquire vibration data of a tension sensor on the protection rope, calculate the vibration frequency of the protection rope according to the vibration data, and obtain a ratio of the worker's body swing frequency to the protection rope vibration frequency; Fitting the worker's motion trajectory curve, calculating the maximum amplitude and average amplitude of the working action according to the motion trajectory curve, and judging whether the working action amplitude exceeds the preset protection range of the safety rope; The mass distribution and spatial position of each part of the worker's body are estimated based on the 15-node simplified human body model and inertial measurement unit data, and the center of gravity trajectory is smoothed to obtain the offset distance of the worker's center of gravity relative to the connection point of the protective rope; Determine whether the frequency ratio, operating motion amplitude and center of gravity offset distance exceed the preset dynamic safety threshold. If so, it is determined to be a disengaged state, and a warning message is sent to the smart device worn by the worker through the wireless communication module; the frequency ratio is the ratio of the worker's body swinging frequency to the safety rope vibration frequency.

Images