Gantry crane rail potential safety hazard monitoring method based on machine vision

Abstract

The invention provides a gantry crane track potential safety hazard monitoring method based on machine vision. The gantry crane track potential safety hazard monitoring method comprises the following steps: step (1), acquiring a monitoring video image of a gantry crane track; (2) detecting the monitoring video image based on a target detection model, and identifying key components of the track; step (3), analyzing characteristic parameters of the identification area; and (4) judging whether potential safety hazards exist or not according to the characteristic parameters. By means of the machine vision technology, automatic, real-time and high-precision monitoring on potential safety hazards such as overlarge track gaps, pressing plate deviation and bolt missing of the gantry crane is achieved, the overturning risk of the gantry crane is effectively reduced, and operation safety is guaranteed. Through the target detection model and characteristic parameter analysis, the track state can be monitored in real time, early warning can be given out in time, the detection reliability and accuracy are improved, and the intelligent level of gantry crane track safety monitoring is remarkably enhanced.

Description

Technical Field

[0001] This invention relates to the field of gantry crane track inspection technology, specifically a method for monitoring safety hazards in gantry crane tracks based on machine vision. Background Technology

[0002] With the increasing scale and complexity of large-scale bridge construction, the safety of the track system of gantry cranes at high bridge pier construction sites is of paramount importance, as they are key lifting equipment. If problems such as excessive track gaps, pressure plate displacement, and missing bolts are not detected in time, they can easily lead to derailment or even overturning accidents. Currently, the main method relied upon is manual inspection, which suffers from low efficiency, poor real-time performance, and difficulty in quantifying detection, failing to achieve accurate and efficient safety monitoring. Therefore, there is an urgent need for an automated, high-precision monitoring method to achieve real-time perception and early warning of potential hazards in gantry crane track conditions. Summary of the Invention

[0003] The technical problem solved by this invention is to provide a machine vision-based method for monitoring safety hazards on gantry crane tracks, so as to solve the problems mentioned in the background art.

[0004] The technical problem solved by this invention is achieved by the following technical solution: a method for monitoring safety hazards on gantry crane tracks based on machine vision, comprising: Step (1). Obtain monitoring video images of the gantry crane track; Step (2). Detect the monitoring video image based on the target detection model to identify key track components; the target detection model is an improved YOLOv8 model, including: a Backbone layer, which extracts features from the monitoring video image based on convolutional modules, C2f modules, and SPPF modules; a Neck layer, which uses the features extracted from the Backbone layer to extract features from the monitoring video image based on upsampling, feature stitching, convolutional modules, C2f modules, and SPPF modules; and a Head layer, which uses multiple detection heads to detect key track components, including track gaps, pressure plates, and bolts, based on the fused features. Step (3). Analyze the characteristic parameters of the identification area. The characteristic parameters include: the actual size of the track gap, whether the pressure plate is displaced, and the number of bolts fixing the pressure plate. Step (4). Determine whether there is a safety hazard based on the feature parameters. Compare the feature parameters with a preset safety threshold. If the feature parameters exceed the safety threshold, it is determined that there is a safety hazard.

[0005] Furthermore, the acquisition of gantry crane track monitoring video images includes: welding an industrial camera above the gantry crane wheels, which moves with the gantry crane to collect images, enabling real-time detection of the track that the wheels will pass over, detecting the track gap width, track pressure plate, and bolts fixing the pressure plate; the video data collected by the industrial camera is transmitted in real-time to a server deployed in the electrical room or control center via a 5G network.

[0006] Furthermore, the training method for the target detection model in step (2) includes the following steps: (1) Collect a large number of images of gantry crane tracks, and annotate the track gaps, pressure plates, and bolts to construct a training dataset; (2) Divide the dataset into a training set and a test set in an 8:2 ratio; (3) Train the model using the training set and evaluate its performance using the test set, and adjust the hyperparameters to optimize detection accuracy.

[0007] Furthermore, the analysis of feature parameters of the identified region in step (3) includes: Based on the track gap detection box output by the target detection model, obtain the pixel positions of its left and right edges; The position of the pressure plate is measured based on the distance between the center line of the track and the center point of the pressure plate. Based on the bolt identification results of the target detection model, the number of bolts detected in each pressure plate area is counted.

[0008] Furthermore, in step (3), the pixel positions of the left and right edges of the track gap detection box output by the target detection model are obtained, and the pixel width of the track gap is calculated.

[0009] in, This represents the pixel position of the left edge of the track; This represents the pixel position of the right edge of the track; The pixel width of the track gap; The actual width of the track gap is calculated by obtaining the scale factor from the pixel to the actual distance through camera calibration. in, This is the actual width of the track gap. To obtain the scale factor from the pixel to the actual distance through camera calibration; The actual width is used to compare with a preset safety threshold to determine whether the gap is too large.

[0010] Furthermore, in step (3), the position of the pressure plate is measured based on the distance between the center line of the track and the center point of the pressure plate. First, calculate the pixel coordinates of the center line of the track gap. in, The location of the centerline point of the track. Secondly, obtain the pixel coordinates of the center point of the pressure plate detection frame. in, This refers to the center point of the track pressure plate; The left corner of the pressure plate detection frame; The right corner of the pressure plate detection frame. Calculate the horizontal pixel distance between the center point of the pressure plate and the center line of the track gap. in, The horizontal pixel distance between the center point of the pressure plate and the center line of the track gap. Convert pixel horizontal distance to actual horizontal distance. in, This is the actual horizontal distance between the center point of the pressure plate and the center line of the track gap. This displacement distance is used to determine whether there is any abnormal offset of the pressure plate.

[0011] Further, the step (4) of judging safety hazards based on feature parameters includes: setting a threshold for the width of the track gap and judging whether the actual width of the track gap detected exceeds the threshold; setting a threshold for the distance between the center point of the track pressure plate and the center line of the track and judging whether the pressure plate has a large offset; setting the number of bolts on the pressure plate and judging whether the pressure plate bolts have fallen off.

[0012] A system for monitoring safety hazards on gantry crane tracks using a machine vision-based method includes: an acquisition module for acquiring monitoring video images of the gantry crane tracks; a detection module for detecting the monitoring video images based on a target detection model and identifying key components of the tracks; and an analysis module for analyzing feature parameters of the identified areas and determining whether safety hazards exist based on the feature parameters.

[0013] A computer program product includes a computer program that uses a machine vision-based method for monitoring safety hazards on gantry crane tracks, wherein when the computer program is executed, it implements the steps of the method for monitoring safety hazards on gantry crane tracks.

[0014] A readable storage medium includes a computer program for using a machine vision-based method for monitoring safety hazards on gantry crane tracks. The computer program, when executed, implements the steps of the method for monitoring safety hazards on gantry crane tracks.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention utilizes machine vision technology to achieve automated, real-time, and high-precision monitoring of safety hazards such as excessive gaps in gantry crane tracks, offset pressure plates, and missing bolts, effectively reducing the risk of gantry crane overturning and ensuring operational safety. Through target detection models and feature parameter analysis, the track status can be monitored in real time, and timely warnings can be issued, improving the reliability and accuracy of detection and significantly enhancing the intelligence level of gantry crane track safety monitoring. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the method flow of the present invention.

[0017] Figure 2 This is a schematic diagram of the main view of the gantry crane structure of the present invention.

[0018] Figure 3 This is a schematic side view of the gantry crane structure of the present invention.

[0019] Figure 4 This is a schematic diagram of the gantry crane track inspection according to the present invention.

[0020] Figure 5 This is a flowchart illustrating the overall processing flow of the present invention.

[0021] Figure 6 This invention provides an improved YOLOv8 model architecture.

[0022] In the diagram: 1. Main beam of the gantry crane; 2. Outriggers; 3. Electric hoist; 4. Drive motor; 5. Trolley traveling mechanism; 6. Lower crossbeam; 7. Industrial camera. Detailed Implementation

[0023] To make the technical means, creative features, objectives and effects of the present invention easier to understand, the present invention will be further described below with reference to specific illustrations. In the description of the present invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation", "connection" and "connection" should be interpreted broadly. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection between the internal parts of two components.

[0024] Example 1 like Figures 1-6 As shown, a machine vision-based method for monitoring safety hazards on gantry crane tracks includes the following steps: S1: Acquire monitoring video images of the gantry crane track.

[0025] Specifically, step S1 includes: An industrial camera is installed on the traveling mechanism of the gantry crane, positioned above the crane wheels, to capture real-time images of the track as the crane moves. Figure 2 As shown. The industrial camera uses a high-definition lens and is installed at a top-down angle to ensure coverage of critical areas such as track gaps, pressure plates, and bolts.

[0026] Video data captured by industrial cameras is transmitted in real time to servers deployed in electrical rooms or control centers via 5G networks.

[0027] S2: Based on the target detection model, detect and identify key components of the track in the surveillance video images.

[0028] Specifically, step S2 includes: In practical applications, target detection models such as YOLO, YOLOv8, and other improved versions of YOLO can be used to detect the monitoring video images at the quay crane spreader, identify the spreader, the working container, and the connected container, and define the detection area.

[0029] For example, three YOLOv8 detection models can be built to detect track gaps, track pressure plates, and pressure plate bolts, respectively.

[0030] The improved YOLOv8 model includes: (1) Backbone layer: Features are extracted from the input image based on the convolution module, C2f module, and SPPF module; (2) Neck layer: With the help of upsampling, feature splicing and C2f module, the further fusion and scale adaptation of multi-scale features are completed; (3) Head layer: Based on the fusion features, detect and locate the area where the target is located.

[0031] The model training process includes: (1) Collect a large number of images of gantry crane tracks, and annotate the track gaps, pressure plates, and bolts to construct a training dataset; (2) Divide the dataset into a training set and a test set in an 8:2 ratio; (3) Train the model using the training set and evaluate its performance using the test set, and adjust the hyperparameters to optimize detection accuracy.

[0032] S3: Analyze the feature parameters of the identified region.

[0033] Specifically, step S3 includes: Track gap size calculation: Calculate the actual width of the track gap based on the coordinates of the left and right edges of the detection frame; Pressure plate displacement detection: Calculate the distance between the center line of the track gap and the center point of the pressure plate to determine whether displacement exists; Bolt missing detection: Count the number of bolts in the detection area to determine if any are missing.

[0034] Specifically, step S3 includes: S31: Based on the track gap detection box output by the object detection model, obtain the pixel positions of its left and right edges. Calculate the pixel width of the track gap.

[0035] in, This represents the pixel position of the left edge of the track; This represents the pixel position of the right edge of the track; This represents the pixel width of the track gap.

[0036] The actual width of the track gap is calculated by obtaining the scale factor from the pixel to the actual distance through camera calibration.

[0037] in, This is the actual width of the track gap. To obtain the scale factor from the pixel to the actual distance through camera calibration.

[0038] The actual width is used to compare with a preset safety threshold to determine whether the gap is too large.

[0039] S32: Measure the position of the pressure plate based on the distance between the center line of the track and the center point of the pressure plate.

[0040] First, calculate the pixel coordinates of the center line of the track gap.

[0041] in, The location of the centerline point of the track. Secondly, obtain the pixel coordinates of the center point of the pressure plate detection frame.

[0042] in, This refers to the center point of the track pressure plate; The left corner of the pressure plate detection frame; This is the right corner point of the pressure plate detection frame.

[0043] Calculate the horizontal pixel distance between the center point of the pressure plate and the center line of the track gap.

[0044] in, This represents the horizontal pixel distance between the center point of the pressure plate and the center line of the track gap.

[0045] Convert pixel horizontal distance to actual horizontal distance.

[0046] in, This is the actual horizontal distance between the center point of the pressure plate and the center line of the track gap. This displacement distance is used to determine whether the pressure plate has any abnormal offset.

[0047] S33: Based on the bolt identification results of the target detection model, count the number of bolts detected in each pressure plate area.

[0048] S4: Determine whether there are any safety hazards based on the characteristic parameters.

[0049] Specifically, step S4 includes: (1) Set a safety threshold for the width of the track gap. If the actual gap width exceeds the threshold, it is considered a potential hazard. (2) Set a threshold for the distance between the center point of the pressure plate and the center line of the track. If the distance is too large, the pressure plate displacement is determined to be abnormal. (3) Set the required number of bolts for each pressure plate. If the number of bolts is insufficient, it is determined that the bolts are missing.

[0050] Figure 4 The diagram shows the overall processing flow of this method. In practical applications, real-time image data of the gantry crane track can be acquired for detection, enabling timely identification and handling of any potential safety hazards.

[0051] The beneficial effects of this embodiment are as follows: This method is based on real-time acquired video images of the gantry crane track. It uses a target detection model to accurately identify key components such as track gaps, pressure plates, and bolts. Then, it analyzes the actual size, displacement status, and quantity of these components, and compares them with preset safety thresholds to determine whether there are safety hazards such as excessive track gaps, pressure plate displacement, or missing bolts.

[0052] This method enables automated and real-time monitoring of the gantry crane track status. Based on the diagnostic results, the system can issue timely safety warnings to prompt staff to intervene, effectively reducing the risk of derailment and overturning caused by track defects, improving the reliability and accuracy of safety monitoring, and ensuring the continuous and safe operation of the gantry crane.

[0053] Example 2 like Figure 1 As shown, a method for monitoring safety hazards on gantry crane tracks based on machine vision includes the following steps: S1: Acquire monitoring video images of the gantry crane track.

[0054] Specifically, step S1 includes: An industrial camera is installed on the traveling mechanism of the gantry crane, positioned above the crane wheels, to capture real-time images of the track as the crane moves. Figure 2 As shown. The industrial camera uses a high-definition lens and is installed at a top-down angle to ensure coverage of critical areas such as track gaps, pressure plates, and bolts.

[0055] Video data captured by industrial cameras is transmitted in real time to servers deployed in electrical rooms or control centers via 5G networks.

[0056] S2: Based on the target detection model, detect and identify key components of the track in the surveillance video images.

[0057] Specifically, step S2 includes: By utilizing a pre-trained object detection model, YOLOv8 is improved to perform real-time detection on received video frames, identifying track gaps, pressure plates, and bolts in the images, such as... Figure 3 , Figure 4 As shown.

[0058] The improved YOLOv8 model includes: (1) Backbone layer: Features are extracted from the input image based on the convolution module, C2f module, and SPPF module; (2) Neck layer: With the help of upsampling, feature splicing and C2f module, the further fusion and scale adaptation of multi-scale features are completed; (3) Head layer: The features are weighted and concatenated using the CBAM attention module to provide enhanced feature input for subsequent tasks.

[0059] The improved YOLOv8 model training process includes: (1) Collect a large number of images of gantry crane tracks, and annotate the track gaps, pressure plates, and bolts to construct a training dataset; (2) Divide the dataset into a training set and a test set in an 8:2 ratio; (3) Train the model using the training set and evaluate its performance using the test set, and adjust the hyperparameters to optimize detection accuracy.

[0060] S3: Analyze the feature parameters of the identified region.

[0061] Specifically, step S3 includes: Track gap size calculation: Calculate the actual width of the track gap based on the coordinates of the left and right edges of the detection frame; Pressure plate displacement detection: Calculate the distance between the center line of the track gap and the center point of the pressure plate to determine whether displacement exists; Bolt missing detection: Count the number of bolts in the detection area to determine if any are missing.

[0062] Specifically, step S3 includes: S31: Based on the track gap detection box output by the object detection model, obtain the pixel positions of its left and right edges. Calculate the pixel width of the track gap.

[0063] in, This represents the pixel position of the left edge of the track; This represents the pixel position of the right edge of the track; This represents the pixel width of the track gap.

[0064] The actual width of the track gap is calculated by obtaining the scale factor from the pixel to the actual distance through camera calibration.

[0065] in, This is the actual width of the track gap. To obtain the scale factor from the pixel to the actual distance through camera calibration.

[0066] The actual width is used to compare with a preset safety threshold to determine whether the gap is too large.

[0067] S32: Measure the position of the pressure plate based on the distance between the center line of the track and the center point of the pressure plate.

[0068] First, calculate the pixel coordinates of the center line of the track gap.

[0069] in, The location of the centerline point of the track. Secondly, obtain the pixel coordinates of the center point of the pressure plate detection frame.

[0070] in, This refers to the center point of the track pressure plate; The left corner of the pressure plate detection frame; This is the right corner point of the pressure plate detection frame.

[0071] Calculate the horizontal pixel distance between the center point of the pressure plate and the center line of the track gap.

[0072] in, This represents the horizontal pixel distance between the center point of the pressure plate and the center line of the track gap.

[0073] Convert pixel horizontal distance to actual horizontal distance.

[0074] in, This is the actual horizontal distance between the center point of the pressure plate and the center line of the track gap. This displacement distance is used to determine whether the pressure plate has any abnormal offset.

[0075] S33: Based on the bolt identification results of the target detection model, count the number of bolts detected in each pressure plate area.

[0076] S4: Determine whether there are any safety hazards based on the characteristic parameters.

[0077] Specifically, step S4 includes: (1) Set a safety threshold for the width of the track gap. If the actual gap width exceeds the threshold, it is considered a potential hazard. (2) Set a threshold for the distance between the center point of the pressure plate and the center line of the track. If the distance is too large, the pressure plate displacement is determined to be abnormal. (3) Set the required number of bolts for each pressure plate. If the number of bolts is insufficient, it is determined that the bolts are missing.

[0078] Figure 5 The diagram shows the overall processing flow of this method. In practical applications, real-time image data of the gantry crane track can be acquired for detection, enabling timely identification and handling of any potential safety hazards.

[0079] The improved YOLOv8 model used in this method significantly enhances the model's ability to focus on key features such as track gaps, pressure plates, and bolts by introducing an attention mechanism. This design effectively improves the accuracy and anti-interference capability of target detection in complex field environments, making the identification of safety hazards more accurate and reliable.

[0080] Example 3 A machine vision-based gantry crane track safety hazard monitoring system, based on the method described in any of the above embodiments, includes: Acquisition module: Used to acquire real-time monitoring video images of the gantry crane track; Detection module: Identifies key track components based on a target detection model; Analysis module: Calculates characteristic parameters such as track gap width, pressure plate displacement, and number of bolts; Judgment module: Based on the comparison results of feature parameters and safety thresholds, determine whether there is a safety hazard and trigger an alarm mechanism.

[0081] Example 4 A computer program product comprising a computer program that, when executed, implements the steps of the machine vision-based gantry crane track safety hazard monitoring method as described in Embodiment 1 or 2.

[0082] Example 5 A readable storage medium storing a computer program as described in Embodiment 4, wherein when the computer program is executed, it implements the steps of the machine vision-based gantry crane track safety hazard monitoring method as described in Embodiment 1 or 2.

[0083] This invention uses monitoring video images and target detection models of gantry crane tracks to identify key track components and analyze their characteristic parameters, thereby determining whether there are safety hazards such as excessive track gaps, pressure plate displacement, and missing bolts.

[0084] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A machine vision-based method for monitoring safety hazards on gantry crane tracks, comprising: Its features are: Step (1). Obtain monitoring video images of the gantry crane track; Step (2). Detect the surveillance video images based on the target detection model to identify key track components; The target detection model is an improved YOLOv8 model, comprising: a Backbone layer, which extracts features from surveillance video images based on convolutional, C2f, and SPPF modules; a Neck layer, which uses the features extracted from the Backbone layer to extract features from surveillance video images based on upsampling, feature concatenation, convolutional, C2f, and SPPF modules; and a Head layer, which uses multiple detectors to detect key track components, including track gaps, pressure plates, and bolts, based on fused features. Step (3). Analyze the characteristic parameters of the identification area. The characteristic parameters include: the actual size of the track gap, whether the pressure plate is displaced, and the number of bolts fixing the pressure plate. Step (4). Determine whether there is a safety hazard based on the feature parameters. Compare the feature parameters with a preset safety threshold. If the feature parameters exceed the safety threshold, it is determined that there is a safety hazard.

2. The method for monitoring safety hazards of gantry crane tracks based on machine vision according to claim 1, characterized in that: The acquisition of gantry crane track monitoring video images includes: welding an industrial camera above the gantry crane wheels, which moves with the gantry crane to collect images, enabling real-time detection of the track that the wheels will pass over, detecting the track gap width, track pressure plate, and bolts fixing the pressure plate; the video data collected by the industrial camera is transmitted in real-time to a server deployed in the electrical room or control center via a 5G network.

3. The method for monitoring safety hazards of gantry crane tracks based on machine vision according to claim 1, characterized in that: The training method for the target detection model in step (2) includes the following steps: (1) Collect a large number of images of gantry crane tracks, and annotate the track gaps, pressure plates, and bolts to construct a training dataset; The dataset was divided into a training set and a test set in an 8:2 ratio. (3) Train the model using the training set and evaluate its performance using the test set, and adjust the hyperparameters to optimize detection accuracy.

4. The method for monitoring safety hazards on gantry crane tracks based on machine vision according to claim 1, characterized in that: The analysis of feature parameters of the identified region in step (3) includes: Based on the track gap detection box output by the target detection model, obtain the pixel positions of its left and right edges; The position of the pressure plate is measured based on the distance between the center line of the track and the center point of the pressure plate. Based on the bolt identification results of the target detection model, the number of bolts detected in each pressure plate area is counted.

5. The method for monitoring safety hazards of gantry crane tracks based on machine vision according to claim 4, characterized in that: In step (3), the pixel positions of the left and right edges of the track gap detection box output by the target detection model are obtained, and the pixel width of the track gap is calculated. in, This represents the pixel position of the left edge of the track; This represents the pixel position of the right edge of the track; The pixel width of the track gap; The actual width of the track gap is calculated by obtaining the scale factor from the pixel to the actual distance through camera calibration. in, This is the actual width of the track gap. To obtain the scale factor from the pixel to the actual distance through camera calibration; The actual width is used to compare with a preset safety threshold to determine whether the gap is too large.

6. The method for monitoring safety hazards of gantry crane tracks based on machine vision according to claim 4, characterized in that: In step (3), the position of the pressure plate is measured based on the distance between the center line of the track and the center point of the pressure plate. First, the pixel coordinates of the center line of the track gap are calculated. in, The location of the centerline point of the track. Secondly, obtain the pixel coordinates of the center point of the pressure plate detection frame. in, This refers to the center point of the track pressure plate; The left corner point of the pressure plate detection frame; The right corner of the pressure plate detection frame. Calculate the horizontal pixel distance between the center point of the pressure plate and the center line of the track gap. in, The horizontal pixel distance between the center point of the pressure plate and the center line of the track gap. Convert pixel horizontal distance to actual horizontal distance. in, This is the actual horizontal distance between the center point of the pressure plate and the center line of the track gap. This displacement distance is used to determine whether there is any abnormal offset of the pressure plate.

7. The method for monitoring safety hazards of gantry crane tracks based on machine vision according to claim 1, characterized in that: The step (4) of judging safety hazards based on characteristic parameters includes: setting a threshold for the width of the track gap and judging whether the actual width of the track gap detected exceeds the threshold; setting a threshold for the distance between the center point of the track pressure plate and the center line of the track and judging whether the pressure plate has a large offset; setting the number of bolts on the pressure plate and judging whether the bolts on the pressure plate have fallen off.

8. The method for monitoring safety hazards of gantry crane tracks based on machine vision according to claim 1, characterized in that: A system for monitoring safety hazards on gantry crane tracks using a machine vision-based method includes: an acquisition module for acquiring monitoring video images of the gantry crane tracks; a detection module for detecting the monitoring video images based on a target detection model and identifying key components of the tracks; and an analysis module for analyzing feature parameters of the identified areas and determining whether safety hazards exist based on the feature parameters.

9. The method for monitoring safety hazards of gantry crane tracks based on machine vision according to claim 1, characterized in that: A computer program product includes a computer program that uses a machine vision-based method for monitoring safety hazards on gantry crane tracks, wherein when the computer program is executed, it implements the steps of the method for monitoring safety hazards on gantry crane tracks.

10. A method for monitoring safety hazards on gantry crane tracks based on machine vision according to claim 1, characterized in that: A readable storage medium includes a computer program for using a machine vision-based method for monitoring safety hazards on gantry crane tracks. The computer program, when executed, implements the steps of the method for monitoring safety hazards on gantry crane tracks.

Images