A building basket compliance judgment method and system based on AI recognition technology

Abstract

This invention provides a method and system for judging the compliance of suspended scaffolding in construction based on AI recognition technology, belonging to the field of suspended scaffolding monitoring technology at construction sites. The method includes the following steps: performing target recognition and detection on keyframe images to determine the boundary area of ​​the suspended scaffolding; creating a warning area based on the boundary area; determining whether human figures exist within the warning area; if so, proceeding to the next step; determining whether the human figures meet the permitted load capacity and whether protective equipment is being worn to obtain a first judgment result or a second judgment result; outputting an alarm based on the first or second judgment result; and forcing workers to comply with regulations through warnings, preventing danger from the source and creating a good construction environment at the construction site.

Description

Technical Field

[0001] This invention belongs to the field of construction site suspended platform monitoring technology, specifically, it relates to a method and system for judging the compliance of construction suspended platforms based on AI recognition technology. Background Technology

[0002] Artificial Intelligence (AI) is a new technological science that studies and develops theories, methods, technologies, and application systems to simulate, extend, and expand human intelligence.

[0003] Artificial intelligence (AI) is a branch of computer science that attempts to understand the essence of intelligence and produce new intelligent machines that can react in a way similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. Since its inception, AI has matured in both theory and technology, and its applications have expanded continuously. It is conceivable that future AI-driven technological products will serve as "containers" of human wisdom. AI can simulate the information processes of human consciousness and thought. While AI is not human intelligence, it can think like a human and may even surpass human intelligence.

[0004] As people's demands for safety continue to rise, more effective control measures are needed at construction sites. Artificial intelligence technology is developing rapidly and deeply integrating with various technological fields, already generating numerous innovative solutions in areas such as speech recognition and computer vision.

[0005] Currently, most construction sites lack monitoring systems for the use of suspended platforms, leading to workers neglecting to wear safety protective equipment and ignoring the load limits for suspended platforms, thus creating numerous safety hazards. Summary of the Invention

[0006] This invention provides a method and system for judging the compliance of construction suspended platforms based on AI recognition technology. Its purpose is to solve the problem that existing construction sites do not have monitoring systems for the use of suspended platforms, which leads to workers neglecting to wear safety protective equipment and ignoring the load-bearing regulations of suspended platforms.

[0007] In view of the above problems, the technical solution proposed by the present invention is as follows:

[0008] A method for determining the compliance of suspended scaffolding in construction based on AI recognition technology includes:

[0009] Target recognition and detection are performed on keyframe images to determine the boundary region of the suspended platform;

[0010] Create a warning area based on the boundary area;

[0011] Determine whether there are human-shaped features within the warning area; if so, proceed to the next step.

[0012] The first judgment result or the second judgment result is obtained by determining whether the human characteristics meet the required carrying capacity and whether protective equipment is worn;

[0013] An alarm is output based on either the first or the second judgment result.

[0014] As a preferred embodiment of the present invention, before determining the boundary region of the suspended basket by performing target recognition and detection on the keyframe image, the method further includes:

[0015] The first monitoring video image of the suspended basket area is acquired through the first acquisition device;

[0016] The first surveillance video image is preprocessed to obtain multiple single-frame images;

[0017] Multiple keyframe images are obtained by deleting from multiple single-frame images.

[0018] As a preferred embodiment of the present invention, the step of performing target recognition and detection on keyframe images to determine the boundary region of the suspended basket specifically includes:

[0019] Extract the initial pixel values ​​from multiple keyframe images;

[0020] Read the coordinates of the initial pixel value, and filter the initial pixel value according to the coordinates to obtain candidate pixel values;

[0021] Determine whether the candidate pixel value meets the preset pixel threshold and process it to obtain the boundary pixel value;

[0022] The boundary region of the hanging basket is determined based on the boundary pixel values.

[0023] As a preferred embodiment of the present invention, the step of creating a warning area based on the boundary area specifically includes:

[0024] The boundary pixel values ​​of the boundary region are binarized to obtain grayscale pixel values.

[0025] Extract the coordinate values ​​of the grayscale pixel values, and determine the neighborhood of the boundary region based on the coordinate values;

[0026] The warning area is created by filling the neighborhood with highlight pixel values.

[0027] As a preferred embodiment of the present invention, determining whether human-shaped features exist within the warning area specifically includes:

[0028] The warning area is scanned to obtain the outline region;

[0029] Calculate the curvature value at each point in the contour region;

[0030] Establish a curvature space matrix based on the curvature values;

[0031] The curvature space matrix is ​​matched with the curvature target threshold to determine whether the curvature space matrix has humanoid features.

[0032] As a preferred embodiment of the present invention, the step of determining whether the humanoid features meet the required carrying capacity and whether protective gear is being worn to obtain a first determination result or a second determination result specifically includes:

[0033] The number of humanoid features is determined, and it is determined whether the number of humanoid features meets the maximum allowed quantity to obtain the first determination result;

[0034] The second monitoring video image of the suspended basket area is acquired through the second acquisition device;

[0035] Extract key feature images of the human-shaped features from the second surveillance video image;

[0036] Identify the key regions of the key feature image and crop out the key region image;

[0037] A second judgment result is obtained by scanning the image of the key area using a recognition model.

[0038] As a preferred technical solution of the present invention, the first judgment result is that the humanoid feature meets the maximum number or the humanoid feature does not meet the maximum number.

[0039] As a preferred technical solution of the present invention, the second judgment result is that the human figure is wearing protective equipment or the human figure is not wearing protective equipment.

[0040] As a preferred embodiment of the present invention, the recognition model is obtained by training a sampling convolutional neural network.

[0041] On the other hand, embodiments of the present invention also provide a compliance judgment system for suspended scaffolding based on AI recognition technology, including:

[0042] The determination module is used to perform target recognition and detection on keyframe images to determine the boundary region of the suspended platform;

[0043] A module is created to generate a warning area based on the boundary area;

[0044] The first judgment module is used to determine whether there are human-shaped features within the warning area; if so, the next step is executed.

[0045] The second judgment module is used to determine whether the human features meet the required number of vehicles and whether protective gear is being worn, and to obtain a first judgment result or a second judgment result.

[0046] An alarm module is used to output an alarm based on the first judgment result or the second judgment result.

[0047] The beneficial effects of the above-mentioned technical solution provided by the embodiments of the present invention include at least the following: by determining whether there are human features in the warning area and whether the human features meet the load capacity and whether protective equipment is worn, a first judgment result or a second judgment result is obtained, and it is identified whether there is a person riding in the basket or whether the load capacity is exceeded. If there is a person riding in the basket, it is identified whether the person is wearing protective equipment. By warning, workers are forced to comply with regulations, the occurrence of danger is prevented from the source, and a good construction environment is created for the construction site.

[0048] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0049] Figure 1 This is a flowchart of a method for judging the compliance of building suspended platforms based on AI recognition technology disclosed in this invention;

[0050] Figure 2 This is a schematic diagram of the results of a building suspended platform compliance judgment system based on AI recognition technology disclosed in this invention.

[0051] Explanation of reference numerals in the attached diagram: 100, Determine module; 200, Create module; 300, First judgment module; 400, Second judgment module; 500, Alarm module. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0054] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0055] Example 1

[0056] See attached document Figure 1 As shown, the present invention provides a technical solution: a method for judging the compliance of building suspended platforms based on AI recognition technology, comprising the following steps;

[0057] S1, perform target recognition and detection on the keyframe image to determine the boundary region of the suspended platform.

[0058] Specifically, the step of performing target recognition and detection on keyframe images to determine the boundary region of the suspended platform includes:

[0059] S11, extract the initial pixel values ​​of multiple keyframe images.

[0060] S12, read the coordinate values ​​of the initial pixel value, and filter the initial pixel value according to the coordinate values ​​to obtain candidate pixel values.

[0061] S13, determine whether the candidate pixel value meets the preset pixel threshold and process it to obtain the boundary pixel value.

[0062] S14, determine the boundary region of the hanging basket based on the boundary pixel values.

[0063] To make keyframe images easier to identify, the edges of the basket can be painted with a bright color or covered with other brightly colored materials, such as red or blue; at the same time, a sign should be added indicating that the edges should not be obscured.

[0064] S2, Create a warning area based on the boundary area.

[0065] Specifically, creating a warning area based on the boundary area includes:

[0066] S21, the boundary pixel values ​​of the boundary region are binarized to obtain grayscale pixel values;

[0067] S22, extract the coordinate values ​​of the grayscale pixel values, and determine the neighborhood of the boundary region based on the coordinate values;

[0068] S23, fill the neighborhood with highlight pixel values ​​to create the warning area.

[0069] S3, determine whether there are human-shaped features within the warning area; if so, proceed to the next step.

[0070] Specifically, determining whether human-shaped features exist within the warning area includes:

[0071] S31, the warning area is scanned to obtain the outline area;

[0072] S32, Calculate the curvature value of each point in the contour region;

[0073] S33, Establish a curvature space matrix based on the curvature value;

[0074] S34, Match the curvature space matrix with the curvature target threshold to determine whether the curvature space matrix has humanoid features.

[0075] S4, determine whether the humanoid features meet the required carrying capacity and whether protective gear is being worn to obtain a first judgment result or a second judgment result.

[0076] Specifically, determining whether the humanoid features meet the permitted carrying capacity and whether protective gear is being worn to obtain a first or second determination result includes:

[0077] S41, determine the number of humanoid features, and determine whether the number of humanoid features meets the required quantity to obtain the first determination result;

[0078] S42, acquire the second monitoring video image of the suspended platform area through the second acquisition device;

[0079] S43, extract key feature images of the human-shaped features from the second surveillance video image;

[0080] S44, identify the key region of the key feature image and crop the key region image;

[0081] S45, the key area image is scanned using a recognition model to obtain a second judgment result.

[0082] It should be noted that the recognition model is obtained by training a sampling convolutional neural network.

[0083] The second acquisition device is a pan-tilt camera mounted on the basket via a pole, which is mainly responsible for capturing second monitoring video images of whether the personnel on the basket are wearing protective equipment.

[0084] S5, output an alarm based on the first judgment result or the second judgment result.

[0085] The first judgment result is that the human figure meets the permitted carrying capacity or the human figure does not meet the permitted carrying capacity; the second judgment result is that the human figure is wearing protective equipment or the human figure is not wearing protective equipment.

[0086] In particular, an alarm will be issued if the first judgment result is that the number of human figures exceeds the limit or that the human figures are not wearing protective equipment.

[0087] For safety reasons, it is best not to use the suspended platform for more than two people at a time; and the protective equipment specifically refers to safety helmets, safety ropes and safety locks.

[0088] In a preferred embodiment of the present invention, before performing target recognition and detection on the keyframe image to determine the boundary region of the suspended basket, the method further includes:

[0089] The first monitoring video image of the suspended basket area is acquired through the first acquisition device;

[0090] The first surveillance video image is preprocessed to obtain multiple single-frame images;

[0091] Multiple keyframe images are obtained by deleting from multiple single-frame images.

[0092] It should be noted that the first acquisition device is a pan-tilt camera installed on the opposite side of the suspended platform, which can record the first monitoring video image of the suspended platform in real time.

[0093] Example 2

[0094] This invention also discloses a compliance judgment system for suspended scaffolding based on AI recognition technology, as shown in the attached figure. Figure 2 As shown;

[0095] The determination module 100 is used to perform target recognition and detection on keyframe images to determine the boundary region of the suspended basket;

[0096] A creation module 200 is used to create a warning area based on the boundary area;

[0097] The first judgment module 300 is used to determine whether there are human-shaped features within the warning area; if so, the next step is executed.

[0098] The second judgment module 400 is used to determine whether the human features meet the required number of loads and whether protective gear is worn to obtain a first judgment result or a second judgment result.

[0099] Alarm module 500 is used to output an alarm based on the first judgment result or the second judgment result.

[0100] In the detailed description above, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features in a single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, with each claim representing a separate preferred embodiment of the invention.

[0101] Those skilled in the art will also understand that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments herein can be implemented as electronic hardware, computer software, or a combination thereof. To clearly illustrate the interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps described above are generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in alternative ways for each specific application; however, such implementation decisions should not be construed as departing from the scope of this disclosure.

[0102] The steps of the methods or algorithms described in conjunction with the embodiments herein can be directly embodied in hardware, software modules executed by a processor, or a combination thereof. The software modules can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in a user terminal. Alternatively, the processor and storage medium can exist as discrete components in the user terminal.

[0103] For software implementation, the techniques described in this application can be implemented using modules (e.g., procedures, functions, etc.) that perform the functions described in this application. This software code can be stored in memory units and executed by a processor. The memory units can be implemented within the processor or outside the processor; in the latter case, they are communicatively coupled to the processor via various means, as is well known in the art.

[0104] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

Claims

1. A method for judging the compliance of construction suspended scaffolds based on AI recognition technology, characterized in that, include: The first monitoring video image of the suspended basket area is acquired through the first acquisition device; The first surveillance video image is preprocessed to obtain multiple single-frame images; Multiple keyframe images are obtained by deleting from multiple single-frame images; The edges of the suspended platform are painted with a high-gloss color, either red or blue, and there are signs indicating that the edges should not be obscured. Target recognition and detection are performed on keyframe images to determine the boundary region of the suspended platform, specifically including: Extract the initial pixel values ​​from multiple keyframe images; Read the coordinates of the initial pixel value, and filter the initial pixel value according to the coordinates to obtain candidate pixel values; Determine whether the candidate pixel value meets the preset pixel threshold and process it to obtain the boundary pixel value; The boundary region of the suspended basket is determined based on the boundary pixel values; a warning region is created based on the boundary region. Determine whether there are human-shaped features within the warning area; if so, proceed to the next step. Determining whether the humanoid features meet the permitted carrying capacity and whether protective gear is being worn yields a first or second determination result, specifically including: The number of humanoid features is determined, and it is determined whether the number of humanoid features meets the maximum allowed quantity to obtain the first determination result; The second monitoring video image of the suspended basket area is acquired through the second acquisition device; Extract key feature images of the human-shaped features from the second surveillance video image; Identify the key regions of the key feature image and crop out the key region image; A second judgment result is obtained by scanning the image of the key area using a recognition model; The second determination result is that the human figure is wearing protective equipment or the human figure is not wearing protective equipment; The first determination result is that the humanoid feature meets the maximum allowed quantity or the humanoid feature does not meet the maximum allowed quantity; An alarm is output based on either the first or the second judgment result.

2. The method for judging the compliance of building suspended platforms based on AI recognition technology according to claim 1, characterized in that, The step of creating a warning area based on the boundary area specifically includes: The boundary pixel values ​​of the boundary region are binarized to obtain grayscale pixel values. Extract the coordinate values ​​of the grayscale pixel values, and determine the neighborhood of the boundary region based on the coordinate values; The warning area is created by filling the neighborhood with highlight pixel values.

3. The method for judging the compliance of building suspended platforms based on AI recognition technology according to claim 1, characterized in that, The determination of whether human-shaped features exist within the warning area specifically includes: The warning area is scanned to obtain the outline region; Calculate the curvature value at each point in the contour region; Establish a curvature space matrix based on the curvature values; The curvature space matrix is ​​matched with the curvature target threshold to determine whether the curvature space matrix has humanoid features.

4. The method for judging the compliance of building suspended platforms based on AI recognition technology according to claim 1, characterized in that, The recognition model is obtained by training a sampling convolutional neural network.

5. A compliance judgment system for suspended scaffolding based on AI recognition technology, applied to the compliance judgment method for suspended scaffolding based on AI recognition technology as described in any one of claims 1 to 4, comprising: The determination module is used to perform target recognition and detection on keyframe images to determine the boundary region of the suspended platform; A module is created to generate a warning area based on the boundary area; The first judgment module is used to determine whether there are human-shaped features within the warning area; if so, the next step is executed. The second judgment module is used to determine whether the human features meet the required number of vehicles and whether protective gear is being worn, and to obtain a first judgment result or a second judgment result. An alarm module is used to output an alarm based on the first judgment result or the second judgment result.

Images