A method and system for detecting defects in building exterior walls
By dividing the building exterior wall into sub-regions and using image recognition technology for detection, the problem of inefficiency of traditional methods is solved, efficient and accurate detection of the building exterior wall is achieved, cutting work is reduced, and detection efficiency is improved.
Patent Information
- Application Number
- CN202410340018.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-25
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-03-25
AI Technical Summary
Traditional building exterior wall defect detection methods are inefficient and rely on manual visual inspection. The detection accuracy is limited by professional level. The existing equipment needs to be cut and spliced after taking pictures during movement, which is a large workload and low processing efficiency.
The exterior wall of the building is divided into sub-regions, marked and numbered, and the detection integrity is determined using image recognition technology. The adjacent defect pictures are cut and spliced through the crack recognition algorithm to update the crack information.
It realizes complete and clear inspection of building exterior walls, reduces tailing work, improves inspection efficiency, and ensures inspection accuracy and efficiency.
Smart Images

Figure CN118134892B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of building exterior wall detection, and in particular to a method and system for detecting defects in building exterior walls. Background Art
[0002] With the acceleration of urbanization and the rapid development of the construction industry, the quality of building exterior walls has also received increasing attention. Exterior wall defects such as cracks, peeling, and shedding not only affect the beauty of the building, but more seriously affect the safety of the building. Therefore, how to accurately and efficiently detect defects in building exterior walls has become an urgent problem to be solved. The traditional method of detecting defects in the exterior of building exterior walls mainly relies on manual visual inspection, which is not only inefficient, but also the detection accuracy is limited by the professional level and experience of the inspectors. The existing acquisition equipment moves from the bottom to the top of the building's exterior wall, takes multiple pictures during the movement, then cuts and splices all the photos, and then analyzes all the pictures to determine whether the building has defects such as cracks. The workload is large and the processing efficiency is reduced. Summary of the invention
[0003] The purpose of the present invention is to provide a method and system for detecting defects in building exterior walls to solve the problems raised in the above-mentioned background technology.
[0004] To achieve the above object, the present invention provides the following technical solutions:
[0005] A method for detecting defects in building exterior walls, the method comprising the following steps:
[0006] Divide the building exterior wall into various sub-areas, and mark and number the preset positions of each sub-area to obtain a preset number set;
[0007] Based on the acquisition device, the captured pictures of each sub-area of the building exterior wall are collected, the number information in the captured pictures is obtained, and an identification number set is obtained, and it is determined whether the building exterior wall is completely detected according to the identification number set and the preset number set;
[0008] Crack identification is performed on the captured images to obtain a defect image set containing cracks and crack information, adjacent defect images in the sub-areas of the defect image set are trimmed and spliced to obtain a spliced image, and the crack information is updated according to the spliced image.
[0009] As a further technical solution of the present invention, the steps of dividing the building exterior wall into various sub-areas, marking and numbering the preset positions of the sub-areas, and obtaining the preset number set include:
[0010] Obtain building exterior wall information and preset area division information;
[0011] Divide the building exterior wall into various sub-areas according to the building exterior wall information and preset area division information;
[0012] and marking and numbering the preset positions of each sub-area to obtain a preset number set;
[0013] The coordinates of the center point of each sub-region are obtained according to the region division information.
[0014] As a further technical solution of the present invention, the step of collecting photographs of each sub-area of the building exterior wall based on the acquisition device, obtaining the number information in the photographs, obtaining an identification number set, and determining whether the building exterior wall is completely detected according to the identification number set and the preset number set includes:
[0015] Collecting pictures of each sub-area of the building's exterior wall based on a collection device to obtain a picture set;
[0016] Identify the number information in the photograph based on image recognition technology to obtain an identification number set;
[0017] Reading data from the identification number set in sequence, and traversing the preset number set according to the read data;
[0018] When the match is successful, the corresponding number in the preset number set is deleted;
[0019] When the data of the preset number set is empty, cutoff information is generated and determined to be normal, and it is determined that the building exterior wall is completely detected;
[0020] When each data in the identification number set is read and the preset number set is not empty, it is judged as an abnormality, and it is determined that the building exterior wall has not been completely detected, and a prompt message is sent to the management end, and the prompt message carries the remaining number information in the preset number set.
[0021] As a further technical solution of the present invention, the steps of performing crack recognition on the captured images to obtain a defect image set containing cracks and crack information, cutting and splicing adjacent defect images in sub-regions in the defect image set to obtain a spliced image, and updating the crack information according to the spliced image include:
[0022] Performing initial crack recognition analysis on the captured images based on the crack recognition algorithm to obtain crack information of each sub-area in the captured images;
[0023] Marking corresponding photographed pictures, and extracting a defect picture set containing cracks from the photographed picture set;
[0024] Obtain the coordinates of the center points of the sub-regions corresponding to each defect image in the defect image set to obtain a defect coordinate set;
[0025] Calculating the distance between each center point in the defect coordinate set;
[0026] When the distances between a certain center point and the other center points are all greater than the preset distances, it is determined that the sub-region corresponding to this center point is not adjacent to the sub-regions corresponding to the other center points, and there is no need to crop and splice the defect image corresponding to this center point;
[0027] When the distance between the two center points is less than the preset distance, it is determined that the sub-regions corresponding to the two center points are adjacent, and the clipping boundaries of the two sub-regions are determined according to the coordinates of the two center points and a preset boundary clipping table;
[0028] The defect images corresponding to the two center points are cut and spliced according to the cut boundary to obtain a spliced image;
[0029] The crack information is updated according to the spliced image.
[0030] As a further technical solution of the present invention, the step of updating the crack information according to the spliced image includes:
[0031] Performing secondary crack recognition on the spliced image based on a crack recognition algorithm;
[0032] The crack information identified for the first time is replaced by the crack information identified for the second time in the sub-region corresponding to the spliced image, and the other crack information remains unchanged, thereby obtaining updated crack information.
[0033] Another object of an embodiment of the present invention is to provide a building exterior wall defect detection system, the system comprising:
[0034] The area division and numbering module is used to divide the building exterior wall into various sub-areas, and mark and number the preset positions of each sub-area to obtain a preset number set;
[0035] The acquisition verification module is used to collect pictures of each sub-area of the building's exterior wall based on the acquisition device, obtain the number information in the pictures, obtain the identification number set, and determine whether the building's exterior wall has been completely detected according to the identification number set and the preset number set;
[0036] The crack recognition module is used to perform crack recognition on the captured images to obtain a defect image set containing cracks and crack information, trim and splice adjacent defect images in the sub-areas of the defect image set to obtain a spliced image, and update the crack information according to the spliced image.
[0037] As a further technical solution of the present invention, the area division numbering module includes:
[0038] An information acquisition unit, used to acquire building exterior wall information and preset area division information;
[0039] The exterior wall division unit is used to divide the exterior wall of the building into various sub-areas according to the exterior wall information of the building and the preset area division information;
[0040] A marking and numbering unit, used to mark and number the preset positions of each sub-region to obtain a preset number set;
[0041] The center point coordinate acquisition unit is used to acquire the center point coordinates of each sub-area according to the area division information.
[0042] As a further technical solution of the present invention, the acquisition verification module includes:
[0043] A picture acquisition unit, used to acquire pictures of each sub-area of the building's exterior wall based on an acquisition device to obtain a picture set;
[0044] A number recognition unit, used to recognize the number information in the photograph based on image recognition technology to obtain a set of identification numbers;
[0045] A number traversal unit, used to read data from the identification number set in sequence, and traverse the preset number set according to the read data;
[0046] A number matching unit, used for deleting the corresponding number in the preset number set when the matching is successful;
[0047] A normal detection determination unit, used for generating cutoff information and determining that it is normal when the data of the preset number set is empty, and determining that the building exterior wall is completely detected;
[0048] The abnormality detection and judgment unit is used to judge it as an abnormality when each data in the identification number set is read and the preset number set is not empty, determine that the building exterior wall has not been completely detected, and send a prompt message to the management end, wherein the prompt message carries the remaining number information in the preset number set.
[0049] As a further technical solution of the present invention, the crack identification module includes:
[0050] A crack initial recognition unit, used to perform initial crack recognition analysis on the captured image based on a crack recognition algorithm, and obtain crack information of each sub-area in the captured image;
[0051] A defect picture extraction unit, used for marking corresponding photographed pictures, and extracting a defect picture set containing cracks from the photographed picture set;
[0052] A defect coordinate acquisition unit, used to acquire the coordinates of the center points of the sub-regions corresponding to each defect image in the defect image set to obtain a defect coordinate set;
[0053] A center point distance calculation unit, used to calculate the distance between each center point in the defect coordinate set;
[0054] The sub-region non-adjacent determination unit is used to determine that the sub-region corresponding to a certain center point is not adjacent to the sub-regions corresponding to the other center points when the distances between the center point and the other center points are greater than a preset distance, and it is not necessary to crop and splice the defect image corresponding to the center point;
[0055] A sub-region adjacent determination unit, configured to determine that the sub-regions corresponding to the two center points are adjacent when the distance between the two center points is less than a preset distance, and determine the clipping boundaries of the two sub-regions according to the coordinates of the two center points and a preset boundary clipping table;
[0056] A picture cutting and splicing unit, used for cutting and splicing defect pictures corresponding to two center points according to the cutting boundary to obtain a spliced picture;
[0057] The crack information updating unit is used to update the crack information according to the spliced image.
[0058] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides a method and system for detecting defects in building exterior walls, in which the building exterior walls are divided into various sub-areas, and the preset positions of each sub-area are marked and numbered, and whether the photographed photo completely contains the part to be detected of the building exterior wall is determined according to the marked number. The present invention ensures the complete detection of the building exterior walls while also ensuring the clarity of the photographed photos, thereby realizing a complete and clear detection of the building exterior walls; in addition, in the present invention, firstly, the crack information of each sub-area in the photographed pictures is obtained by performing an initial crack recognition analysis on the photographed pictures, and then the information obtained by the initial recognition is used to realize targeted cropping and splicing of adjacent defective pictures, and the crack information is updated according to the obtained spliced pictures, so that the obtained crack information is accurate and complete, while reducing the cropping work and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention.
[0060] Figure 1 The flowchart of the building exterior wall defect detection method is shown in FIG.
[0061] Figure 2 The flowchart is a flowchart of the steps of dividing the building exterior wall into sub-areas in the building exterior wall defect detection method.
[0062] Figure 3 The present invention is a flowchart of the steps for determining the complete inspection of building exterior walls in the building exterior wall defect inspection method.
[0063] Figure 4 The flowchart is a flow chart of the crack identification step in the building exterior wall defect detection method.
[0064] Figure 5 This is the structural block diagram of the building exterior wall defect detection system. DETAILED DESCRIPTION
[0065] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0066] like Figure 1 As shown, an embodiment of the present invention provides a method for detecting defects in building exterior walls, the method comprising the following steps:
[0067] Step S100, dividing the building exterior wall into various sub-areas, and marking and numbering the preset positions of each sub-area to obtain a preset number set;
[0068] The building exterior wall information includes information such as the length, width and height of the wall, and the preset area division information is the size information and position information of each sub-area preset and determined according to the building exterior wall information. The marking number can be written on each sub-area in the form of a colored pen or a seal, and the number can be a combination of one or more of numbers, letters, and Chinese characters.
[0069] Step S200, based on the acquisition device, collects photographs of each sub-area of the building exterior wall, obtains the number information in the photographs, obtains an identification number set, and determines whether the building exterior wall is completely detected according to the identification number set and the preset number set;
[0070] The acquisition device is a wall-climbing robot or a drone equipped with a camera, and each photo acquired by the acquisition device corresponds to a sub-area;
[0071] Step S300, performing crack recognition on the captured images to obtain a defect image set containing cracks and crack information, trimming and splicing adjacent defect images in sub-regions in the defect image set to obtain a spliced image, and updating the crack information according to the spliced image.
[0072] In the present invention, the exterior wall of the building is divided into various sub-areas, and the preset positions of each sub-area are marked and numbered, and it is determined whether the photographed photo completely contains the part of the exterior wall of the building to be inspected according to the marked number. The present invention ensures the complete inspection of the exterior wall of the building while ensuring the clarity of the photographed photo, thereby realizing the complete and clear inspection of the exterior wall of the building. In addition, in the present invention, the crack information of each sub-area in the photographed photo is obtained by first performing an initial crack recognition analysis on the photographed photo, and then the information obtained by the initial recognition is used to realize the targeted cutting and splicing of adjacent defective photos, and the crack information is updated according to the obtained spliced photo, so that the obtained crack information is accurate and complete, while reducing the cutting work and improving the work efficiency.
[0073] like Figure 2 As shown, as a preferred embodiment of the present invention, the steps of dividing the building exterior wall into various sub-areas, marking and numbering the preset positions of each sub-area, and obtaining the preset number set include:
[0074] Step S101, obtaining building exterior wall information and preset area division information;
[0075] Step S102, dividing the building exterior wall into various sub-areas according to the building exterior wall information and preset area division information;
[0076] Step S103, marking and numbering the preset positions of each sub-area to obtain a preset number set;
[0077] The preset position may be the center point of each sub-area, the border of each sub-area, or other preset points;
[0078] Step S104, obtaining the coordinates of the center point of each sub-region according to the region division information; the coordinates of the center point of each sub-region can be calculated through the size information and position information of each sub-region in the region division information.
[0079] like Figure 3 As shown, as a preferred embodiment of the present invention, the step of collecting photographs of each sub-area of the building exterior wall based on the acquisition device, obtaining the number information in the photographs, obtaining the identification number set, and determining whether the building exterior wall is completely detected according to the identification number set and the preset number set includes:
[0080] Step S201, collecting pictures of each sub-area of the building exterior wall based on a collection device to obtain a collection of pictures;
[0081] Step S202, identifying the number information in the photograph based on image recognition technology to obtain an identification number set;
[0082] Among them, the identification of serial numbers in photographs based on image recognition technology mainly involves computer vision and deep learning. The identification of serial numbers in photographs based on image recognition technology is an existing technology. With the continuous development of computer vision and deep learning technology, the identification of serial numbers based on image recognition technology has been widely used. This technology can automatically identify and process serial numbers in photos.
[0083] Step S203, reading data from the identification number set in sequence, and traversing the preset number set according to the read data;
[0084] Step S204, when the match is successful, deleting the corresponding number in the preset number set;
[0085] Step S205, when the data of the preset number set is empty, generating cutoff information and judging it as normal, and determining that the building exterior wall is completely detected;
[0086] Step S206, when each data in the identification number set is read and the preset number set is not empty, it is judged as abnormal, it is determined that the building exterior wall has not been completely detected, and a prompt message is sent to the management end, and the prompt message carries the remaining number information in the preset number set.
[0087] This embodiment can ensure the complete detection of the building's exterior wall, avoid incomplete detection, and also ensure the clarity of the photographed photo, because if the clarity of the photographed photo does not meet the preset standard, the number information cannot be recognized. Therefore, this embodiment achieves a complete and clear detection of the building's exterior wall.
[0088] like Figure 4 As shown, as a preferred embodiment of the present invention, the steps of performing crack recognition on the captured images to obtain a defect image set containing cracks and crack information, trimming and splicing adjacent defect images in sub-regions in the defect image set to obtain a spliced image, and updating the crack information according to the spliced image include:
[0089] Step S301, performing initial crack recognition analysis on the captured image based on a crack recognition algorithm to obtain crack information of each sub-area in the captured image;
[0090] The crack information includes the position, length, width and shape of the crack, and the crack information also carries the number of the corresponding sub-region; the crack recognition algorithm includes the Sobel algorithm, the Canny algorithm, the Hough transform and the algorithm based on deep learning. In the embodiment of the present invention, the algorithm based on deep learning is selected to recognize the cracks in the picture, and a deep learning model suitable for crack recognition is selected, such as a convolutional neural network (CNN). The model is trained using labeled data. The labeled data refers to a training sample image containing annotations. The content of the annotations includes information such as the position, shape, length, width and the like of the crack. When the output result meets the preset accuracy, the training is completed;
[0091] Step S302, marking the corresponding photographs, and extracting a defective picture set containing cracks from the photographed picture set, wherein the marked ones are the photographs containing cracks;
[0092] Step S303, obtaining the coordinates of the center points of the sub-regions corresponding to each defect image in the defect image set to obtain a defect coordinate set;
[0093] Step S304, calculating the distance between each center point in the defect coordinate set;
[0094] Step S305, when the distances between a certain center point and the other center points are all greater than the preset distances, it is determined that the sub-region corresponding to the center point is not adjacent to the sub-regions corresponding to the other center points, and there is no need to crop and splice the defect image corresponding to the center point; which further indicates that the defect in the defect image corresponding to the center point exists only in the sub-region corresponding to the center point, and is a separate and complete defect crack;
[0095] Step S306, when the distance between the two center points is less than the preset distance, it is determined that the sub-regions corresponding to the two center points are adjacent, and the clipping boundaries of the two sub-regions are determined according to the coordinates of the two center points and a preset boundary clipping table;
[0096] Among them, the preset boundary cropping table clarifies the cropping boundary between two adjacent sub-areas according to the relative orientation between the two center points. The relative orientation between the first center point and the second center point includes east, south, west, north, southeast, northeast, southwest, and northwest. Specifically, when the first center point is directly north of the second center point, the southern boundary of the defect image corresponding to the first center point is cropped, and the northern boundary of the defect image corresponding to the second center point is cropped. When the first center point is northeast of the second center point, the western and southern boundaries of the defect image corresponding to the first center point are cropped, and the eastern and northern boundaries of the defect image corresponding to the second center point are cropped.
[0097] Step S307, cropping and splicing the defective images corresponding to the two center points according to the cropping boundary and the relative orientation to obtain a spliced image; wherein the images are of the same size, and the size required for cropping of each cropping boundary is preset and fixed. After targeted cropping, the cropped defective images are spliced according to the relative orientation between the centers, and there is no need to splice the uncropped defective images;
[0098] Step S308: updating the crack information according to the stitched image.
[0099] Specifically, the method includes: performing secondary crack recognition on the spliced image based on a crack recognition algorithm; replacing the initially recognized crack information with the secondary recognized crack information of the corresponding sub-region of the spliced image, and keeping the other crack information unchanged, thereby obtaining updated crack information.
[0100] The existing technology is to obtain a large number of pictures uniformly, cut and splice the pictures to obtain a complete wall picture, and then identify and analyze the complete wall picture to determine whether there are defects such as cracks, which requires a large number of cutting and comparison operations, and the workload is large. In the present invention, cracks in a single picture are first identified, and pictures containing adjacent cracks are targetedly cut and spliced according to the crack information to obtain a picture of a complete crack, thereby reducing cutting and comparison operations.
[0101] like Figure 5 As shown, another object of the embodiment of the present invention is to provide a building exterior wall defect detection system, the system comprising:
[0102] The area division and numbering module 100 is used to divide the building exterior wall into various sub-areas, and mark and number the preset positions of each sub-area to obtain a preset number set;
[0103] The acquisition verification module 200 is used to acquire photographs of each sub-area of the building exterior wall based on the acquisition device, obtain the number information in the photographs, obtain the identification number set, and determine whether the building exterior wall is completely detected according to the identification number set and the preset number set;
[0104] The crack identification module 300 is used to identify cracks in the captured images to obtain a defect image set containing cracks and crack information, trim and splice adjacent defect images in the sub-areas of the defect image set to obtain a spliced image, and update the crack information according to the spliced image.
[0105] As a preferred embodiment of the present invention, the area division numbering module 100 includes:
[0106] An information acquisition unit, used to acquire building exterior wall information and preset area division information, wherein the building exterior wall information includes information such as the length, width and height of the wall, and the preset area division information is size information and position information of each sub-area determined according to the building exterior wall information;
[0107] The exterior wall division unit is used to divide the exterior wall of the building into various sub-areas according to the exterior wall information of the building and the preset area division information;
[0108] A marking and numbering unit, used to mark and number the preset positions of each sub-region to obtain a preset number set;
[0109] The center point coordinate acquisition unit is used to acquire the center point coordinates of each sub-area according to the area division information.
[0110] As a preferred embodiment of the present invention, the acquisition verification module 200 includes:
[0111] A picture acquisition unit, used to acquire pictures of each sub-area of the building's exterior wall based on an acquisition device to obtain a set of pictures, wherein the acquisition device includes a wall-climbing robot equipped with a camera;
[0112] A number recognition unit, used to recognize the number information in the photograph based on image recognition technology to obtain a set of identification numbers;
[0113] A number traversal unit, used to read data from the identification number set in sequence, and traverse the preset number set according to the read data;
[0114] A number matching unit, used for deleting the corresponding number in the preset number set when the matching is successful;
[0115] A normal detection determination unit, used for generating cutoff information and determining that it is normal when the data of the preset number set is empty, and determining that the building exterior wall is completely detected;
[0116] The abnormality detection and judgment unit is used to judge it as an abnormality when each data in the identification number set is read and the preset number set is not empty, determine that the building exterior wall has not been completely detected, and send a prompt message to the management end, wherein the prompt message carries the remaining number information in the preset number set.
[0117] As a preferred embodiment of the present invention, the crack identification module 300 includes:
[0118] A crack initial recognition unit, used to perform initial crack recognition analysis on the captured image based on a crack recognition algorithm, and obtain crack information of each sub-area in the captured image;
[0119] A defect picture extraction unit, used for marking corresponding photographed pictures, and extracting a defect picture set containing cracks from the photographed picture set;
[0120] A defect coordinate acquisition unit, used to acquire the coordinates of the center points of the sub-regions corresponding to each defect image in the defect image set to obtain a defect coordinate set;
[0121] A center point distance calculation unit, used to calculate the distance between each center point in the defect coordinate set;
[0122] The sub-region non-adjacent determination unit is used to determine that the sub-region corresponding to a certain center point is not adjacent to the sub-regions corresponding to the other center points when the distances between the center point and the other center points are greater than a preset distance, and it is not necessary to crop and splice the defect image corresponding to the center point;
[0123] A sub-region adjacent determination unit, configured to determine that the sub-regions corresponding to the two center points are adjacent when the distance between the two center points is less than a preset distance, and determine the clipping boundaries of the two sub-regions according to the coordinates of the two center points and a preset boundary clipping table;
[0124] A picture cutting and splicing unit, used for cutting and splicing defect pictures corresponding to two center points according to the cutting boundary to obtain a spliced picture;
[0125] The crack information updating unit is used to update the crack information according to the spliced image.
[0126] The functions that can be achieved by the above-mentioned building exterior wall defect detection method are all completed by a computer device, and the computer device includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories. The program code is loaded and executed by the one or more processors to achieve the functions of the building exterior wall defect detection method.
[0127] The processor takes out instructions from the memory one by one, analyzes the instructions, and then completes the corresponding operations according to the instruction requirements, generating a series of control commands, so that the various parts of the computer can automatically, continuously and coordinately move to become an organic whole, realize the input of programs, the input of data, and the calculation and output of results. The arithmetic operations or logical operations generated in this process are all completed by the operator; the memory includes a read-only memory (ROM), which is used to store computer programs, and a protection device is provided outside the memory.
[0128] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.
[0129] Those skilled in the art will understand that the description of the above service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, etc.
[0130] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire user terminal.
[0131] The above-mentioned memory can be used to store computer programs and / or modules. The above-mentioned processor realizes various functions of the above-mentioned terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as an information collection template display function, a product information release function, etc.), etc.; the data storage area can store data created according to the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to release, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0132] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the modules / units in the above-mentioned embodiment system, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program can realize the functions of the above-mentioned various system embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media can include: any entity or device that can carry computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.
[0133] It should be noted that, in this article, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.
[0134] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A method for detecting defects in building exterior walls, It is characterized in that The method comprises the following steps: Divide the building exterior wall into various sub-areas, and mark and number the preset positions of each sub-area to obtain a preset number set; Based on the acquisition device, the captured pictures of each sub-area of the building exterior wall are collected, the number information in the captured pictures is obtained, and an identification number set is obtained, and it is determined whether the building exterior wall is completely detected according to the identification number set and the preset number set; Perform crack recognition on the captured images to obtain a defect image set containing cracks and crack information, trim and splice adjacent defect images in sub-regions in the defect image set to obtain a spliced image, and update the crack information according to the spliced image; The steps of collecting pictures of each sub-area of the building exterior wall based on the collection device, obtaining the number information in the pictures, obtaining the identification number set, and determining whether the building exterior wall is completely detected according to the identification number set and the preset number set include: Collecting pictures of each sub-area of the building's exterior wall based on a collection device to obtain a picture set; Identify the number information in the captured image based on image recognition technology to obtain an identification number set; Reading data from the identification number set in sequence, and traversing the preset number set according to the read data; When the match is successful, the corresponding number in the preset number set is deleted; When the data of the preset number set is empty, cutoff information is generated and determined to be normal, and it is determined that the building exterior wall is completely detected; When each data in the identification number set is read and the preset number set is not empty, it is determined to be abnormal, it is determined that the building exterior wall has not been completely detected, and a prompt message is sent to the management end; The steps of performing crack recognition on the captured images to obtain a defect image set containing cracks and crack information, cutting and splicing adjacent defect images in the sub-regions of the defect image set to obtain a spliced image, and updating the crack information according to the spliced image include: Performing initial crack recognition analysis on the captured images based on the crack recognition algorithm to obtain crack information of each sub-area in the captured images; Marking corresponding photographed pictures, and extracting a defect picture set containing cracks from the photographed picture set; Obtain the coordinates of the center points of the sub-regions corresponding to each defect image in the defect image set to obtain a defect coordinate set; Calculating the distance between each center point in the defect coordinate set; When the distances between a certain center point and the other center points are all greater than the preset distances, it is determined that the sub-region corresponding to this center point is not adjacent to the sub-regions corresponding to the other center points, and there is no need to crop and splice the defect image corresponding to this center point; When the distance between the two center points is less than the preset distance, it is determined that the sub-regions corresponding to the two center points are adjacent, and the clipping boundaries of the two sub-regions are determined according to the coordinates of the two center points and a preset boundary clipping table; The defect images corresponding to the two center points are cut and spliced according to the cut boundary to obtain a spliced image; The crack information is updated according to the spliced image.
2. A method for detecting building exterior wall defects according to claim 1, It is characterized in that The step of dividing the building exterior wall into various sub-areas and marking and numbering the preset positions of the sub-areas to obtain the preset number set includes: Obtain building exterior wall information and preset area division information; Divide the building exterior wall into various sub-areas according to the building exterior wall information and preset area division information; and marking and numbering the preset positions of each sub-area to obtain a preset number set; The coordinates of the center point of each sub-region are obtained according to the region division information.
3. A method for detecting building exterior wall defects according to claim 1, It is characterized in that The step of updating the crack information according to the spliced image comprises: Performing secondary crack recognition on the spliced image based on a crack recognition algorithm; The crack information identified for the first time is replaced by the crack information identified for the second time in the sub-region corresponding to the spliced image, and the other crack information remains unchanged, thereby obtaining updated crack information.
4. A building exterior wall defect detection system, It is characterized in that The system comprises: The area division and numbering module is used to divide the building exterior wall into various sub-areas, and mark and number the preset positions of each sub-area to obtain a preset number set; The acquisition verification module is used to collect pictures of each sub-area of the building's exterior wall based on the acquisition device, obtain the number information in the pictures, obtain the identification number set, and determine whether the building's exterior wall has been completely detected according to the identification number set and the preset number set; A crack identification module is used to identify cracks in the captured images to obtain a defect image set containing cracks and crack information, trim and splice adjacent defect images in sub-regions in the defect image set to obtain a spliced image, and update the crack information according to the spliced image; The acquisition verification module includes: A picture acquisition unit, used to acquire pictures of each sub-area of the building's exterior wall based on an acquisition device to obtain a picture set; A number recognition unit, used to recognize the number information in the photographed picture based on image recognition technology to obtain a recognition number set; A number traversal unit, used to read data from the identification number set in sequence, and traverse the preset number set according to the read data; A number matching unit, used for deleting the corresponding number in the preset number set when the matching is successful; A normal detection determination unit, used for generating cutoff information and determining that it is normal when the data of the preset number set is empty, and determining that the building exterior wall is completely detected; An abnormality detection and determination unit, configured to determine that when each data in the identification number set is read and the preset number set is not empty, it is abnormal, determines that the building exterior wall has not been completely detected, and sends a prompt message to the management terminal; The crack identification module comprises: A crack initial recognition unit, used to perform initial crack recognition analysis on the captured image based on a crack recognition algorithm, and obtain crack information of each sub-area in the captured image; A defect picture extraction unit, used for marking corresponding photographed pictures, and extracting a defect picture set containing cracks from the photographed picture set; A defect coordinate acquisition unit, used to acquire the coordinates of the center points of the sub-regions corresponding to each defect image in the defect image set to obtain a defect coordinate set; A center point distance calculation unit, used to calculate the distance between each center point in the defect coordinate set; The sub-region non-adjacent determination unit is used to determine that the sub-region corresponding to a certain center point is not adjacent to the sub-regions corresponding to the other center points when the distances between the center point and the other center points are greater than a preset distance, and it is not necessary to crop and splice the defect image corresponding to the center point; A sub-region adjacent determination unit, configured to determine that the sub-regions corresponding to the two center points are adjacent when the distance between the two center points is less than a preset distance, and determine the clipping boundaries of the two sub-regions according to the coordinates of the two center points and a preset boundary clipping table; A picture cutting and splicing unit, used for cutting and splicing defect pictures corresponding to two center points according to the cutting boundary to obtain a spliced picture; The crack information updating unit is used to update the crack information according to the spliced image.
5. A building exterior wall defect detection system according to claim 4, It is characterized in that The area division numbering module includes: An information acquisition unit, used to acquire building exterior wall information and preset area division information; The exterior wall division unit is used to divide the exterior wall of the building into various sub-areas according to the exterior wall information of the building and the preset area division information; A marking and numbering unit, used to mark and number the preset positions of each sub-region to obtain a preset number set; The center point coordinate acquisition unit is used to acquire the center point coordinates of each sub-area according to the area division information.
