Edge protection position detection method, device, equipment and medium

Abstract

The invention discloses a limb protection position detection method and device, equipment and a medium, and the method comprises the steps: recognizing a dangerous region and limb protection in a monitoring video frame through a trained limb protection detection model; respectively extracting the contour of the dangerous area and the contour of the limb protection, and determining the shortest distance between the contour of the dangerous area and the contour of the limb protection; and determining whether the edge protection placement position is qualified or not according to the shortest distance. According to the method, accurate segmentation and classification of the edge protection and dangerous areas in the construction site are realized, the accuracy of safety monitoring is greatly improved, and meanwhile, the introduced contour analysis and distance calculation effectively assess whether the edge protection setting reaches the standard or not, so that the safety management level of the construction site is comprehensively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of edge protection, and particularly relates to an edge protection position detection method, device, equipment and medium. BACKGROUND

[0002] In the construction scene, edge protection is a key measure to protect the safety of workers and equipment. At present, the detection technology for edge protection mainly includes the following aspects: first, existence detection, such as detecting whether there is a guardrail around the hole through a sensor or image recognition technology; second, edge protection state monitoring, such as monitoring the physical state of the guardrail itself, such as voltage fluctuation, to ensure that the guardrail is in a normal working state; third, dangerous behavior identification, such as detecting whether a person leans against the guardrail or climbs the guardrail.

[0003] However, the existing technical solutions have certain limitations in actual application. The existing solutions usually default that the edge protection facilities have been correctly set around the dangerous area according to the regulations, but in the actual construction process, there may be cases where the guardrail has been installed but not placed around the dangerous area, or the guardrail is too far away from the edge of the dangerous area or even completely deviates from the dangerous area. In this case, although the existing technology detects the existence of the edge protection, since the guardrail is not in the effective protection position, its protection function cannot function normally, and the safety hazard still exists, and even may be ignored, thereby leading to the occurrence of accidents. SUMMARY

[0004] The present application provides an edge protection position detection method, device, equipment and medium, which can effectively detect whether the edge protection setting position meets the standard, thereby improving the safety management level of the construction site.

[0005] In a first aspect, the present application provides an edge protection position detection method, which comprises: identifying a dangerous area and an edge protection in a monitoring video frame through a trained edge protection detection model; extracting the contours of the dangerous area and the edge protection respectively, and determining the shortest distance between the dangerous area contour and the edge protection contour; determining whether the edge protection placement position is qualified according to the shortest distance.

[0006] In combination with the first aspect, in an implementation manner, identifying a dangerous area and an edge protection in a monitoring video frame through a trained edge protection detection model comprises: identifying a dangerous area and an edge protection in a monitoring video frame through a trained edge protection detection model to obtain a dangerous area mask and an edge protection mask.

[0007] In combination with the first aspect, in an implementation, before identifying the dangerous area and the edge protection in the monitoring video frame by using the trained edge protection detection model, the method further comprises: collecting site scene pictures under various visual angles, different illuminations and different weather conditions; annotating the dangerous area and the edge protection in the site scene pictures; training the edge protection detection model using the annotated site scene pictures to obtain the trained edge protection detection model.

[0008] In combination with the first aspect, in an implementation, the contour of the dangerous area and the contour of the edge protection are extracted respectively, and the shortest distance between the contour of the dangerous area and the contour of the edge protection is determined, comprising: extracting a dangerous area contour point set according to the dangerous area mask and extracting an edge protection contour point set according to the edge protection mask; calculating the Euclidean distance between each edge protection contour point in the edge protection contour point set and each dangerous area contour point in the dangerous area contour point set, and taking the minimum value of all the Euclidean distances as the shortest distance.

[0009] In combination with the first aspect, in an implementation, the calculation of the Euclidean distance between each edge protection contour point in the edge protection contour point set and each dangerous area contour point in the dangerous area contour point set, and the taking of the minimum value of all the Euclidean distances as the shortest distance, comprises: selecting any one of the edge protection contour point set or the dangerous area contour point set as a target contour point set; constructing a KD tree according to the target contour point set; for each contour point in the non-target contour point set, performing a nearest neighbor search using the KD tree to obtain the Euclidean distance from the contour point to the nearest neighbor point in the target contour point set; traversing the Euclidean distances from all non-target contour points to their corresponding nearest neighbor points, and taking the minimum Euclidean distance as the shortest distance.

[0010] In combination with the first aspect, in an implementation, determining whether the placement position of the edge protection is qualified according to the shortest distance, comprising: if the shortest distance is greater than the distance threshold, determining that the placement position of the edge protection is unqualified; if the shortest distance is less than or equal to a preset distance threshold, determining that the placement position of the edge protection is qualified.

[0011] In combination with the first aspect, in an implementation, the method further comprises: After determining that the edge protection placement position is unqualified, a pre-warning signal indicating that the edge protection is placed too far is sent out.

[0012] In a second aspect, an embodiment of the present application provides an edge protection position detection device, which comprises: The identification module is configured to identify a dangerous area and an edge protection in a monitoring video frame by using the trained edge protection detection model. The first determination module is configured to extract the contours of the dangerous area and the edge protection respectively, and determine the shortest distance between the dangerous area contour and the edge protection contour. The second determination module is configured to determine whether the edge protection placement position is qualified according to the shortest distance.

[0013] In a third aspect, an embodiment of the present application provides an edge protection position detection device, which comprises a processor, a memory, and an edge protection position detection program stored in the memory and executable by the processor, wherein when the edge protection position detection program is executed by the processor, the steps of the edge protection position detection method according to any one of the above embodiments are implemented. In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores an edge protection position detection program, wherein when the edge protection position detection program is executed by a processor, the steps of the edge protection position detection method according to any one of the above embodiments are implemented.

[0014] The edge protection position detection method, device, equipment and medium provided by the embodiments of the present application can identify a dangerous area and an edge protection in a monitoring video frame by using a trained edge protection detection model, extract the contours of the dangerous area and the edge protection respectively, and determine the shortest distance between the dangerous area contour and the edge protection contour, and determine whether the edge protection placement position is qualified according to the shortest distance. The embodiments of the present application can realize accurate segmentation and classification of the edge protection and the dangerous area in a construction site, greatly improve the accuracy of safety monitoring, and effectively evaluate whether the edge protection setting meets the standard by introducing contour analysis and distance calculation, thereby improving the safety management level of the construction site. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 FIG. 1 is a flowchart of an embodiment of the edge protection position detection method of the present application; Figure 2 FIG. 2 is a flowchart of another embodiment of the edge protection position detection method of the present application; Figure 3 FIG. 3 is a schematic diagram of the functional modules of an embodiment of the edge protection position detection device of the present application; Figure 4 The hardware structure diagram of the edge protection position detection device involved in the embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] In order to enable personnel in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0017] First, some technical terms in the present application are explained and described in order to facilitate the understanding of the present application by those skilled in the art.

[0018] KD tree (K-dimensional tree): a tree-shaped data structure for storing instance points in k-dimensional space for fast retrieval, mainly applied to the search of multi-dimensional space key data.

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the embodiments of the present application will be described in further detail below with reference to the drawings.

[0020] In a first aspect, the embodiments of the present application provide an edge protection position detection method.

[0021] In an embodiment, with reference to Figure 1 , Figure 1 The flowchart of the first embodiment of the edge protection position detection method of the present application is shown. As shown in Figure 1 , the edge protection position detection method comprises: Step S101, identifying the dangerous area and edge protection in the monitoring video frame by using the trained edge protection detection model.

[0022] It is worth noting that the types of dangerous areas and edge protection in the present embodiment can be set according to actual needs. For example, the dangerous area can include areas such as trenches, foundation pits and openings of construction sites, and can also include electrical equipment areas and road construction areas, etc. The edge protection can include protective fences, protective cover plates, safety warning signs and other protective facilities.

[0023] In an embodiment, before step S101, it further comprises: collecting construction site pictures under different light and weather conditions through multiple perspectives; labeling the dangerous area and edge protection in the construction site pictures; training the edge protection detection model using the labeled construction site pictures to obtain the trained edge protection detection model.

[0024] Exemplary, such as Figure 2 As shown, on the training side, drone oblique photography and multi-angle ground-based camera capture can be used to obtain multiple construction site images covering different lighting and weather conditions. These images include the hazardous areas and edge protection types to be identified. Using data annotation tools such as Labelme, each type of hazardous area and edge protection in the captured construction site images is labeled to complete training data processing. Next, the labeled construction site images are divided into training and test sets to complete the dataset construction.

[0025] In this embodiment, the edge protection detection model can be trained by an instance segmentation algorithm, that is, the core of the edge protection detection model includes an instance segmentation model, such as yolov12. The training set is input into the instance segmentation model for training. During the training process, the instance segmentation model will learn how to identify dangerous scenes and edge protection from the input image and generate corresponding segmentation masks. And the parameters of the instance segmentation model are continuously adjusted during the training process to minimize the error between the dangerous scenes and edge protection output by the instance segmentation model and the dangerous scenes and edge protection of the real annotations. And the instance segmentation model is tested by the test set until the error between the output of the instance segmentation model and the real annotation is within the preset error range, and the training of the instance segmentation model is completed, thereby obtaining a trained edge protection detection model that can accurately segment and classify dangerous areas and edge protection.

[0026] Optionally, the training of the edge protection detection model can be completed offline on the training side, and the edge protection position can be detected online on the inference side. When detecting the edge protection position, the on-site image data such as the surveillance video frame can be directly input into the trained edge protection detection model. The edge protection detection model can identify the dangerous area and edge protection in the surveillance video frame to obtain the dangerous area mask and the edge protection mask. Then, contour analysis and distance calculation are performed based on the dangerous area mask and the edge protection mask to finally determine whether the edge protection placement position is qualified, so as to output the warning result. The dangerous area mask and the edge protection mask can be pixel-level masks.

[0027] Step S102 : extract the contours of the dangerous area and the edge protection respectively, and determine the shortest distance between the contour of the dangerous area and the contour of the edge protection.

[0028] In one embodiment, step S102 specifically includes: extracting a dangerous area contour point set according to the dangerous area mask, and extracting an edge protection contour point set according to the edge protection mask; calculating the Euclidean distance between each edge protection contour point in the edge protection contour point set and each dangerous area contour point in the dangerous area contour point set, and taking the smallest value of all Euclidean distances as the shortest distance.

[0029] Exemplary, such as Figure 2 As shown, OpenCV can be used for contour analysis to extract the dangerous area contour from the dangerous area mask and the edge protection contour from the edge protection mask. Then, cv2.findContours is used to generate the dangerous area contour point set based on the dangerous area contour and the edge protection contour point set based on the edge protection contour. For each dangerous area and edge protection in the surveillance video frame, the corresponding contour point set can be expressed as , where P is the contour point set, each point Represents the position coordinates of a point on the contour, such as , Contour points The horizontal axis, Contour points The coordinate system takes the upper left corner of the image as the origin (0,0), the x-axis is in the right direction, and the y-axis is in the downward direction.

[0030] Furthermore, the Euclidean distance between each edge protection contour point in the edge protection contour point set and each dangerous area contour point in the dangerous area contour point set is calculated, and the smallest value of all Euclidean distances is used as the shortest distance, including: selecting any one of the edge protection contour point set or the dangerous area contour point set as the target contour point set; constructing a KD tree based on the target contour point set; for each contour point in the non-target contour point set, using the KD tree to perform a nearest neighbor search to obtain the Euclidean distance from the contour point to the nearest neighbor point in the target contour point set; traversing the Euclidean distances of all non-target contour points and their corresponding nearest neighbor points, and taking the smallest Euclidean distance as the shortest distance.

[0031] For example, when performing distance calculation, taking a groove contour point set as the target contour point set as an example, the remaining contour point sets are non-target contour point sets. Every contour point , use KD tree to query its groove contour point set The nearest neighbor of The nearest neighbor point can be found by a nearest neighbor search function of the KD tree, which returns the nearest neighbor point with the smallest Euclidean distance.

[0032] wherein given two points and their Euclidean distance D is calculated by the following formula:

[0033] wherein D is the Euclidean distance between and is the x-coordinate of is the x-coordinate of is the y-coordinate of is the y-coordinate of

[0034] The Euclidean distance between each edge protection contour point and the nearest neighbor point in the trench contour point set is calculated according to the above method. The minimum value of all the calculated Euclidean distances is taken as the shortest distance between the edge protection and the dangerous area (trench):

[0035] wherein is the shortest distance, M is the number of edge protection contour points, represents the Euclidean distance between the ith edge protection contour point and the nearest neighbor point in the trench contour point set.

[0036] The nearest neighbor search by the KD tree can improve the search efficiency and calculation speed of the nearest neighbor point, so as to obtain the shortest distance between the dangerous area and the edge protection more quickly.

[0037] Step S103: determining whether the edge protection placement position is qualified according to the shortest distance.

[0038] Specifically, if the shortest distance is greater than the distance threshold , i.e. , it is determined that the edge protection placement position is unqualified; if the shortest distance is less than or equal to the preset distance threshold, i.e. , it is determined that the edge protection placement position is qualified. The distance threshold can be set according to actual safety requirements.

[0039] ​​​​Further, after determining that the placement position of the edge protection is unqualified, a warning signal indicating that the edge protection is placed too far away is sent. The warning signal includes: sending a field sound alarm to remind field personnel to pay attention to the dangerous area, sending a warning message to the manager through a short message or an email to instruct the manager to adjust the position of the edge protection and set the edge protection at a proper distance from the dangerous area, and the edge protection is too far away from the dangerous area and cannot play a safety protection role, thereby improving the safety management level of the construction site.

[0040] In an optional embodiment, when the edge protection detection model identifies that there is a dangerous area but no edge protection in the monitoring video frame, a warning signal indicating that there is no edge protection near the dangerous area is sent.

[0041] The edge protection position detection method provided by the embodiments of the present application realizes accurate segmentation and classification of the edge protection and the dangerous area related type target in the construction site through the deep learning technology, and significantly improves the accuracy of safety monitoring. In addition, the method introduces the contour analysis technology and combines the KD tree to perform minimum distance calculation, so that whether the edge protection setting meets the safety standard can be quickly and effectively evaluated, and a danger warning can be sent in time, and the safety management level of the construction site is comprehensively enhanced.

[0042] In a second aspect, the embodiments of the present application also provide an edge protection position detection device.

[0043] In an embodiment, the edge protection position detection device comprises: Figure 3 , Figure 3 FIG. 1 is a schematic diagram of the function modules of an embodiment of the edge protection position detection device of the present application. As shown in FIG. 1, the edge protection position detection device comprises: Figure 3 an identification module, configured to identify a dangerous area and edge protection in a monitoring video frame through a trained edge protection detection model; a first determination module, configured to extract contours of the dangerous area and the edge protection respectively, and determine a shortest distance between the dangerous area contour and the edge protection contour; a second determination module, configured to determine whether the placement position of the edge protection is qualified according to the shortest distance.

[0044] Further, in an embodiment, the identification module is further configured to: identify a dangerous area and edge protection in a monitoring video frame through a trained edge protection detection model to obtain a dangerous area mask and an edge protection mask.

[0045] Further, in an embodiment, the device further comprises a training module, configured to: ​Collecting site scene pictures under various visual angles, different illuminations and different weather conditions; Labeling dangerous areas and edge protection in the site scene pictures; Training an edge protection detection model using the labeled site scene pictures to obtain a trained edge protection detection model.

[0046] Further, in an embodiment, the first determining module is further configured to: Extract a dangerous area contour point set according to the dangerous area mask and an edge protection contour point set according to the edge protection mask; Calculate the Euclidean distance between each edge protection contour point in the edge protection contour point set and each dangerous area contour point in the dangerous area contour point set, and take the minimum value among all the Euclidean distances as the shortest distance.

[0047] Further, in an embodiment, the first determining module is further configured to: Select any one of the edge protection contour point set or the dangerous area contour point set as a target contour point set; Construct a KD tree according to the target contour point set; For each contour point in the non-target contour point set, perform a nearest neighbor search using the KD tree to obtain the Euclidean distance between the contour point and the nearest neighbor point in the target contour point set; Iterate through the Euclidean distances between all non-target contour points and their corresponding nearest neighbor points, and take the minimum Euclidean distance as the shortest distance.

[0048] Further, in an embodiment, the second determining module is further configured to: If the shortest distance is greater than the distance threshold, determine that the edge protection placement position is unqualified; If the shortest distance is less than or equal to a preset distance threshold, determine that the edge protection placement position is qualified.

[0049] Further, in an embodiment, the edge protection position detection apparatus further comprises: A warning module configured to issue a warning signal indicating that the edge protection is placed too far away after determining that the edge protection placement position is unqualified.

[0050] The functions of each module in the above edge protection position detection apparatus correspond to the steps in the above edge protection position detection method embodiments, and the functions and implementation processes will not be repeated here.

[0051] In a third aspect, an embodiment of the present application provides a side-protection position detection device. The side-protection position detection device can be a personal computer (PC), a notebook computer, a server, or any other device with a data processing function.

[0052] Reference is made to Figure 4 , Figure 4 FIG. 1 is a schematic diagram of a hardware structure of a side-protection position detection device according to an embodiment of the present application. In the embodiment, the side-protection position detection device can include a processor, a memory, a communication interface, and a communication bus.

[0053] The communication bus can be of any type and used to interconnect the processor, the memory, and the communication interface.

[0054] The communication interface includes an input / output (I / O) interface, a physical interface, and a logical interface, which are used to interconnect devices inside the side-protection position detection device, and interfaces used to interconnect the side-protection position detection device with other devices (e.g., other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber interface, an ATM interface, or the like. The user device can be a display, a keyboard, or the like.

[0055] The memory can be of various types, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), or the like.

[0056] The processor can be a general-purpose processor, which can invoke a side-protection position detection program stored in the memory and execute the side-protection position detection method provided by the embodiment. For example, the general-purpose processor can be a central processing unit (CPU). The method executed by the side-protection position detection program when invoked can refer to the embodiments of the side-protection position detection method of the present application, which will not be described herein.

[0057] Those skilled in the art can understand that Figure 4The hardware structure shown in the figures is not a limitation on the present application, and can include more or fewer components, or combine certain components, or arrange different components.

[0058] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium.

[0059] The computer readable storage medium of the present application stores a position detection program of a parapet, wherein the position detection program of the parapet is executed by a processor to implement the steps of the position detection method of the parapet.

[0060] The method implemented by the position detection program of the parapet when executed can refer to each embodiment of the position detection method of the parapet of the present application, which will not be described here.

[0061] It should be noted that the serial numbers of the embodiments of the present application described above are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0062] The terms "include" and "have" and any variations thereof in the specification and claims of the present application and the above-described figures are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device. The terms "first", "second" and "third" and the like descriptions are used to distinguish different objects, and do not represent the order or limit the types of "first", "second" and "third".

[0063] In the description of the embodiments of the present application, "exemplary", "for example" or "for instance" is used to represent an example, illustration or description. Any embodiment or design scheme described as "exemplary", "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. In fact, the words "exemplary", "for example" or "for instance" are intended to present the relevant concept in a specific manner.

[0064] In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B; "and / or" in the text only represents the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0065] In some of the processes described in this specification, the order of operations or steps can be modified. Specifically, the serial order of any two consecutive steps carried out according to the processes described in this specification can be changed so that these two steps can be carried out in parallel or simultaneously, or the order of these two steps can be reversed.

[0066] Those skilled in the art can clearly understand the above-mentioned embodiment method from the description of the above embodiments, which can be realized by software and a necessary general hardware platform, of course, can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disc) as described above, and includes a plurality of instructions for causing a terminal device to execute the methods described in the various embodiments of the present application.

[0067] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the content of the specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method of detecting an edge protection position, characterized by, The edge protection position detection method comprises: The dangerous area and the edge protection in the monitoring video frame are identified by using the trained edge protection detection model; The contours of the dangerous area and the edge protection are extracted respectively, and the shortest distance between the dangerous area contour and the edge protection contour is determined; It is determined whether the edge protection placement position is qualified according to the shortest distance.

2. The edge guard position detection method according to claim 1, wherein The dangerous area and the edge protection in the monitoring video frame are identified by using the trained edge protection detection model, including: The dangerous area and the edge protection in the monitoring video frame are identified by using the trained edge protection detection model, and a dangerous area mask and an edge protection mask are obtained.

3. The edge guard position detection method according to claim 2, wherein Before the dangerous area and the edge protection in the monitoring video frame are identified by using the trained edge protection detection model, the method further comprises: Collecting construction site scene pictures under multiple visual angles, different illuminations and different weather conditions; Labeling the dangerous area and the edge protection in the construction site scene pictures; The edge protection detection model is trained using the labeled construction site scene pictures to obtain the trained edge protection detection model.

4. The edge guard position detection method according to claim 2, wherein The contours of the dangerous area and the edge protection are extracted respectively, and the shortest distance between the dangerous area contour and the edge protection contour is determined, including: The dangerous area contour point set is extracted according to the dangerous area mask, and the edge protection contour point set is extracted according to the edge protection mask; The Euclidean distances between each edge protection contour point in the edge protection contour point set and each dangerous area contour point in the dangerous area contour point set are calculated, and the minimum value among all the Euclidean distances is taken as the shortest distance.

5. The edge guard position detection method according to claim 4, wherein The Euclidean distances between each edge protection contour point in the edge protection contour point set and each dangerous area contour point in the dangerous area contour point set are calculated, and the minimum value among all the Euclidean distances is taken as the shortest distance, including: Any one of the edge protection contour point set or the dangerous area contour point set is selected as a target contour point set; The KD tree is constructed according to the target contour point set; For each contour point in the non-target contour point set, the KD tree is used for nearest neighbor search to obtain the Euclidean distance from the contour point to the nearest neighbor point in the target contour point set; All the Euclidean distances between the non-target contour points and their corresponding nearest neighbor points are traversed, and the minimum Euclidean distance is taken as the shortest distance.

6. The hemline position detection method according to claim 1, wherein It is determined whether the edge protection placement position is qualified according to the shortest distance, including: If the shortest distance is greater than the distance threshold, it is determined that the edge protection placement position is unqualified; If the shortest distance is less than or equal to the preset distance threshold, it is determined that the edge protection placement position is qualified.

7. The hemline position detection method according to claim 1, wherein The method further comprises: After it is determined that the edge protection placement position is unqualified, a warning signal indicating that the edge protection is placed too far is sent out.

8. A fall-protection position detection device, characterized by The edge protection position detection device comprises: The identification module is configured to identify the dangerous area and the edge protection in the monitoring video frame by using the trained edge protection detection model; a first determining module configured to extract the contour of the dangerous area and the contour of the edge protection respectively, and determine the shortest distance between the dangerous area contour and the edge protection contour; a second determining module configured to determine whether the edge protection placement position is qualified according to the shortest distance.

9. A fall-protection position-detecting device, characterized by The edge protection position detection device comprises a processor, a memory, and an edge protection position detection program stored in the memory and executable by the processor, wherein the edge protection position detection program, when executed by the processor, implements the steps of the edge protection position detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores an edge protection position detection program, wherein the edge protection position detection program, when executed by the processor, implements the steps of the edge protection position detection method according to any one of claims 1 to 7.

Images