CN115760825A - Rammed earth wall apparent crack intelligent detection system - Google Patents
Rammed earth wall apparent crack intelligent detection system Download PDFInfo
- Publication number
- CN115760825A CN115760825A CN202211508701.7A CN202211508701A CN115760825A CN 115760825 A CN115760825 A CN 115760825A CN 202211508701 A CN202211508701 A CN 202211508701A CN 115760825 A CN115760825 A CN 115760825A
- Authority
- CN
- China
- Prior art keywords
- image
- earth wall
- rammed earth
- module
- crack
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention provides an intelligent detection system for apparent cracks of a rammed earth wall, which takes a rammed earth wall which is commonly used in a traditional village as a main implementation object, completes the apparent crack detection work of the rammed earth wall through a series of operations of filling item information, uploading an image of the rammed earth wall to be detected, editing the image of the rammed earth wall to be detected, intelligently detecting cracks, automatically generating a detection report and the like, and simultaneously can inquire historical detection items to establish a quick, intelligent and accurate traditional village building apparent crack detection system, thereby realizing the automatic intelligent detection of the apparent cracks of the traditional rammed earth wall in the village and the inquiry and tracing of multi-source, detailed and accurate traditional rammed earth wall apparent crack intelligent detection information of the rammed earth wall in the village.
Description
Technical Field
The invention relates to an intelligent detection system for apparent cracks of a rammed earth wall.
Background
At the present stage, the traditional village construction and the village revivification become one of the important work of the social development of China. Among them, the traditional village often has a large amount of old houses due to a lot of problems such as low construction level and poor construction capability, and relates to hidden dangers such as building structure safety and building function loss, and needs to carry out building survey work urgently. At present, the adopted manual survey mode has the problems of inconsistent subjective experience, untimely information recording, difficult survey result tracing and the like, and the working efficiency of the traditional village building damage survey and the normal development of subsequent construction are seriously influenced.
Disclosure of Invention
The invention aims to provide an intelligent detection system for apparent cracks of a rammed earth wall.
In order to solve the above problems, the present invention provides an intelligent detection system for apparent cracks of a rammed earth wall, comprising:
the rammed earth wall apparent crack detection pretreatment system is used for acquiring, inputting and editing rammed earth wall images;
the rammed earth wall apparent crack intelligent detection system is used for obtaining an image to be reconstructed based on the edited rammed earth wall image;
and the rammed earth wall apparent crack detection post-processing system is used for automatically generating a detection report according to the original image of the rammed earth wall and the reconstructed image.
Further, in the above system, the soil wall apparent crack detection pretreatment system includes:
the image acquisition module is used for carrying out system acquisition on the image of the rammed earth wall by utilizing image acquisition equipment such as an unmanned aerial vehicle and a single lens reflex camera and inputting the acquired image into the image input module;
the image input module is used for inputting the acquired image to the image editing module;
and the image editing module is used for processing the acquired image to obtain a processed image of the rammed earth wall, and inputting the processed image of the rammed earth wall into the image reading module in the intelligent detection system for the apparent cracks of the rammed earth wall and the automatic generation module for the detection report in the post-processing system for the apparent cracks of the rammed earth wall respectively.
Further, in the above system, the processing the acquired image includes: and carrying out editing operations of rotation, turning over, cutting, amplification and reduction on the acquired image.
Further, in the above system, the rammed earth wall apparent crack intelligent detection system includes:
the image reading module is used for reading the processed rammed earth wall image and inputting the processed rammed earth wall image into the self-adaptive local equalization module;
the self-adaptive local equalization module is used for carrying out self-adaptive local equalization processing on the processed rammed earth wall image to obtain an equalized image;
the brightness non-uniform correction module is used for carrying out non-uniform correction on the brightness of the equalized image by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold to obtain a brightness corrected image;
the contrast non-uniform correction module is used for carrying out non-uniform correction on the contrast of the image brightness correction image by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold to obtain a corrected image;
the crack extraction module is used for converting the corrected image into a binary image with only two colors by using a threshold transformation method so as to display the trend and the distribution area of crack lines, form a crack characteristic image under an image mask, finish crack extraction and input the crack characteristic image into the crack reconstruction module;
the fracture reconstruction module is used for obtaining a reconstructed image by utilizing a fracture characteristic image under an image mask and inputting the reconstructed image to the image output module;
and the image output module is used for outputting the reconstructed image.
Further, in the system, the adaptive local equalization module is configured to automatically divide the processed image data of the rammed earth wall into a plurality of image separation areas by using an image histogram algorithm of the adaptive local equalization, and perform image histogram equalization on each image separation area to obtain an equalized image.
Further, in the above system, the image histogram equalization process for each image separation region is to convert the image histogram distribution into an approximately uniform distribution function by an accumulative distribution function.
Further, in the above system, the image histogram equalization process for each image separation region includes:
(1) Sequentially collecting gray level images of the original images, and calculating gray level histograms of the original images;
(2) Calculating a cumulative distribution function of the gray level histogram of the original image;
(3) According to the result of the cumulative distribution function, a mapping relation function is obtained as shown in formula (1):
wherein S is k Is the value of the current gray level after the cumulative distribution function mapping;
n is the sum of the pixels in the image;
n j is the number of pixels of the current gray level;
l is the total number of gray levels in the image;
(4) And finishing image histogram transformation according to the mapping relation function.
Further, in the system, the fracture reconstruction module is configured to perform fusion reconstruction on fracture feature labels in the fracture feature image under the image mask by using the fracture feature image under the image mask and referring to an imrecornstruct function and using a morphological reconstruction principle to obtain a reconstructed image, and input the reconstructed image to the image output module.
Further, in the above system, the system for post-treatment of apparent crack detection of rammed earth wall comprises:
the detection report automatic generation module is used for automatically generating a detection report, importing a rammed earth wall image processed by the image editing module in the rammed earth wall apparent crack detection pretreatment system and an image output by the crack reconstruction module in the rammed earth wall apparent crack detection system into the module, and automatically generating a detection report in a PDF format;
the automatic detection information recording module is used for recording historical detection information and facilitating the inquiry of historical detection items
And the detection information intelligent tracing module is used for tracing the detection information record, and is convenient for comprehensively checking project detection workload and detection results.
Compared with the prior art, the invention provides an intelligent detection system for apparent cracks of a rammed earth wall, which takes a rammed earth wall which is commonly used in the traditional village as a main implementation object, completes the apparent crack detection work of the rammed earth wall through a series of operations of filling project information, uploading an image of the rammed earth wall to be detected, editing the image of the rammed earth wall to be detected, intelligently detecting cracks, automatically generating a detection report and the like, and can simultaneously inquire historical detection projects to establish a quick, intelligent and accurate detection system for apparent cracks of the traditional village building, thereby realizing the automatic intelligent detection of the apparent cracks of the rammed earth wall of the traditional village and the multi-source, detailed and accurate intelligent detection information of the apparent cracks of the rammed earth wall of the traditional village.
The invention improves and solves the problems of non-uniform subjective experience, untimely information recording, difficult survey result tracing and the like of the traditional manual survey mode at present, establishes a rapid, intelligent and accurate traditional village building apparent crack detection system, and realizes the automatic intelligent detection of the apparent cracks of the traditional village rammed earth wall and the inquiry and tracing of the intelligent detection information of the apparent cracks of the traditional village rammed earth wall with multiple sources, detail and accuracy.
Drawings
FIG. 1 is an overall architecture diagram of a rammed earth wall apparent crack intelligent detection system according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, the present invention provides an intelligent detection system for apparent cracks of rammed earth wall, comprising:
the rammed earth wall apparent crack detection pretreatment system is used for acquiring, inputting and editing rammed earth wall images;
the rammed earth wall apparent crack intelligent detection system is used for obtaining an image to be reconstructed based on the edited rammed earth wall image;
and the rammed earth wall apparent crack detection post-processing system is used for automatically generating a detection report according to the original image of the rammed earth wall and the reconstructed image.
In an embodiment of the present invention, a tamper wall apparent crack intelligent detection system comprises:
the image acquisition module is used for performing system acquisition on the image of the rammed earth wall by using image acquisition equipment such as an unmanned aerial vehicle and a single lens reflex, and inputting the acquired image to the image input module;
the image input module is used for inputting the acquired image to the image editing module;
and the image editing module is used for carrying out editing operations of rotation, turning, cutting, amplification and reduction on the acquired image to obtain a processed rammed earth wall image, and respectively inputting the processed rammed earth wall image into the image reading module in the intelligent rammed earth wall apparent crack detection system and the detection report (PDF format) automatic generation module in the post-processing system for rammed earth wall apparent crack detection.
In an embodiment of the present invention, the system for intelligently detecting apparent cracks of a rammed earth wall comprises:
the image reading module is used for reading the processed rammed earth wall image and inputting the processed rammed earth wall image into the self-adaptive local equalization module;
the self-adaptive local equalization module is used for automatically dividing the processed image data of the rammed earth wall into a plurality of image separation areas by adopting a self-adaptive local equalization image histogram algorithm, performing image histogram equalization processing on each image separation area respectively, and combining the plurality of separation areas by utilizing a bilinear interpolation method to eliminate the image boundary effect, effectively limiting the contrast of an even brightness area (setting a contrast enhancement limiting parameter to be 0.0025 as a default value in the algorithm), and simultaneously reducing the influence of image noise on the crack identification effect, thereby obtaining an equalized image.
The image histogram equalization processing of each image separation area is to convert the image histogram distribution into an approximately uniform distribution function through an accumulative distribution function so as to enhance the image contrast, improve the feature definition of the crack image and provide conditions for subsequent crack extraction and reconstruction. The specific operation steps are the following 4 steps in sequence:
(1) Sequentially collecting gray level images of the original image, and calculating a gray level histogram of the original image;
(2) Calculating the cumulative distribution function of the gray level histogram of the original image;
(3) Obtaining a mapping relation function (as shown in formula (1)) according to the result of the cumulative distribution function;
(4) And finishing image histogram transformation according to the mapping relation function.
Wherein S is k Is the value of the current gray level after the cumulative distribution function mapping;
n is the sum of the pixels in the image;
n j is the number of pixels of the current gray level;
l is the total number of gray levels in the image.
The brightness non-uniformity correction module is used for carrying out non-uniformity correction on the brightness of the equalized image by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold to obtain a brightness correction image;
the contrast non-uniform correction module is used for carrying out non-uniform correction on the contrast of the image brightness correction image by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold to obtain a corrected image;
the brightness non-uniform correction module and the contrast non-uniform module are used for solving the problem that the traditional village rammed earth wall image has multiple possible illumination conditions, and further, the brightness and the contrast of the image are non-uniformly corrected by utilizing two means of segmenting a threshold vector and adjusting a threshold of image gray level on the basis of image self-adaptive local equalization.
Specifically, a stretchlim function and an imadjust function can be referred to solve the problems of image self-adaptive gray scale stretching and the like, and then, the morphological bottom-cap filtering and Gaussian denoising are utilized to perform image filtering. Wherein, the general syntax call format of the imadjust function is shown in formula (2), and the function is to transform the image f to the new image f 1 In the process of (3), the pixel point with the gray value lower than low _ in f is in f 1 The middle gray value is assigned as low _ out, and similarly, the pixel points with the middle gray value higher than high _ in are converted to f 1 The gray value is also assigned as high _ out; and for the parameter gamma, when the gamma is less than 1, the gray level image is close to the gray level of low _ inThe gray value of the pixel point with a lower value becomes higher, the gray variation range is stretched, the gray variation range of one end of the gray value close to high _ in is compressed, and the whole image becomes bright. Similarly, when gamma > 1, the gray value of the lower gray pixel point near low _ in of the gray image becomes lower, the gray variation range is compressed, and the gray variation range of the end near high _ in of the gray value is stretched. And calling a stretchlim function to calculate the optimal input interval of the gray image, automatically determining a threshold value by combining the stretchlim function and the imadjust function (as shown in a formula (3)), finishing contrast stretching, and inputting the corrected image to a crack extraction module after finishing the contrast stretching.
f 1 ＝imadjust(f,[low_in；high_in],[low_out；high_out],gamma) (2)
f 1 ＝imadjust(f,strechlin(f),[]) (3)
Wherein: [ low _ in; high _ in is the gray scale range to be converted in the original image f;
[low_out；high_out]for the transformed image f 1 The gray scale range of (a);
gamma is the mapping mode, the default value is 1, namely linear mapping, and when gamma ≠ 1, nonlinear mapping is performed.
The crack extraction module is used for converting the corrected image into a binary image (usually black and white) with only two colors by using a threshold transformation method so as to display the trend and the distribution area of crack lines, form a crack characteristic image under an image mask, complete crack extraction and input the crack characteristic image into the crack reconstruction module;
and the fracture reconstruction module is used for performing fusion reconstruction on the fracture characteristic marks in the fracture characteristic image under the image mask by using the fracture characteristic image under the image mask and referring to the Imeconstruct function (as shown in a formula (4)) and by using a morphological reconstruction principle to obtain a reconstructed image, and inputting the reconstructed image into the image output module.
Wherein the morphological reconstruction is a morphological transformation involving two images and a structuring element, one of the images being a marker (marker) which is the starting point of the transformation, the other image being a mask (mask) which is used to constrain the transformation process, the structuring element being used to define the connectivity.
IM＝imreconstruct(MARKER,MASK) (4)
Wherein: MARKER is a mark and represents an initial mark point matrix, and element 1 represents a mark point;
MASK is a MASK, represents an original image, and requires that the corresponding position of an element 1 in MARKER in X is also 1;
the mark and the mask are two grayscale images or two binary images and have the same size, and the return value IM of the function is also a grayscale image or a binary image of the same size.
And the image output module is used for outputting the reconstructed image.
In an embodiment of the intelligent detection system for apparent cracks of a rammed earth wall, the post-treatment system for apparent crack detection of the rammed earth wall specifically comprises:
a detection report (PDF format) automatic generation module for automatically generating a detection report, and leading the image of the rammed earth wall processed by the image editing module in the rammed earth wall apparent crack detection pre-processing system and the image output by the crack reconstruction module in the rammed earth wall apparent crack detection system into the module to automatically generate the detection report in the PDF format;
the automatic detection information recording module is used for recording historical detection information and facilitating the inquiry of historical detection items
And the detection information intelligent tracing module is used for tracing the detection information record, and is convenient for comprehensively checking project detection workload and detection results.
The invention provides an intelligent detection system for apparent cracks of a rammed earth wall, which takes a rammed earth wall which is commonly used in a traditional village as a main implementation object, completes the apparent crack detection work of the rammed earth wall through a series of operations of filling item information, uploading an image of the rammed earth wall to be detected, editing the image of the rammed earth wall to be detected, intelligently detecting cracks, automatically generating a detection report and the like, and can simultaneously inquire historical detection items to establish a quick, intelligent and accurate traditional village building apparent crack detection system so as to realize the automatic intelligent detection of the apparent cracks of the traditional rammed earth wall in the village and the multi-source, detailed and accurate inquiry and tracing of the traditional rammed earth wall apparent crack intelligent detection information of the rammed earth wall in the village.
The invention improves and solves the problems of non-uniform subjective experience, untimely information recording, difficult survey result tracing and the like of the traditional manual survey mode at present, establishes a rapid, intelligent and accurate traditional village building apparent crack detection system, and realizes the automatic intelligent detection of the apparent cracks of the traditional village rammed earth wall and the inquiry and tracing of the intelligent detection information of the apparent cracks of the traditional village rammed earth wall with multiple sources, detail and accuracy.
In summary, the rammed earth wall apparent crack intelligent detection system provided by the invention firstly inputs the image of the rammed earth wall acquired by image acquisition equipment such as an unmanned aerial vehicle and a single lens reflex into a rammed earth wall apparent crack detection pretreatment system to perform editing operations such as rotation, turning, cutting, amplification, reduction and the like; then, automatically dividing the read and edited image data of the rammed earth wall into a plurality of separation areas, respectively carrying out image histogram equalization processing on each image separation area, and combining the plurality of separation areas by using a bilinear interpolation method to eliminate the image boundary effect, effectively limiting the contrast of uniform brightness areas, and reducing the influence of image noise on crack identification effect; secondly, on the basis of image self-adaptive local equalization, uneven correction is carried out on the image brightness and the contrast by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold; further, displaying the trend and the distribution area of the crack lines by using a threshold transformation method, forming a crack characteristic image under an image mask, completing crack extraction, and performing fusion reconstruction on crack characteristic marks under the image mask based on a morphological reconstruction principle; further, automatically generating a detection report (PDF format) according to the original image of the rammed earth wall and the reconstructed image, and completing the apparent crack detection work of the rammed earth wall; and finally, the detection information is automatically recorded and intelligently traced, so that historical detection items, detection workload and detection results can be conveniently inquired.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. The utility model provides a rammed earth wall apparent crack intelligent detection system which characterized in that includes:
the rammed earth wall apparent crack detection pretreatment system is used for acquiring, inputting and editing rammed earth wall images;
the rammed earth wall apparent crack intelligent detection system is used for obtaining an image to be reconstructed based on the edited rammed earth wall image;
and the rammed earth wall apparent crack detection post-processing system is used for automatically generating a detection report according to the original image of the rammed earth wall and the reconstructed image.
2. The rammed earth wall apparent crack intelligent detection system of claim 1, wherein the treatment system before the detection of the apparent crack of the earth wall comprises:
the image acquisition module is used for carrying out system acquisition on the image of the rammed earth wall by utilizing image acquisition equipment such as an unmanned aerial vehicle and a single lens reflex camera and inputting the acquired image into the image input module;
the image input module is used for inputting the acquired image to the image editing module;
and the image editing module is used for processing the acquired image to obtain a processed image of the rammed earth wall, and inputting the processed image of the rammed earth wall into the image reading module in the intelligent detection system for the apparent cracks of the rammed earth wall and the automatic generation module for the detection report in the post-processing system for the apparent cracks of the rammed earth wall respectively.
3. The intelligent detection system for apparent cracks of rammed earth wall according to claim 1, wherein the processing of the acquired images comprises: and carrying out editing operations of rotation, turning over, cutting, amplification and reduction on the acquired image.
4. The rammed earth wall apparent crack intelligent detection system of claim 1, wherein the rammed earth wall apparent crack intelligent detection system comprises:
the image reading module is used for reading the processed image of the rammed earth wall and inputting the processed image of the rammed earth wall to the self-adaptive local equalization module;
the self-adaptive local equalization module is used for carrying out self-adaptive local equalization processing on the processed rammed earth wall image so as to obtain an equalized image;
the brightness non-uniform correction module is used for carrying out non-uniform correction on the brightness of the equalized image by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold to obtain a brightness corrected image;
the contrast non-uniform correction module is used for carrying out non-uniform correction on the contrast of the image brightness correction image by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold to obtain a corrected image;
the crack extraction module is used for converting the corrected image into a binary image with only two colors by using a threshold transformation method so as to display the trend and the distribution area of crack lines, form a crack characteristic image under an image mask, finish crack extraction and input the crack characteristic image into the crack reconstruction module;
the fracture reconstruction module is used for obtaining a reconstructed image by utilizing the fracture characteristic image under the image mask and inputting the reconstructed image to the image output module;
and the image output module is used for outputting the reconstructed image.
5. The intelligent detection system for apparent cracks of the rammed earth wall according to claim 4, wherein the adaptive local equalization module is configured to automatically divide the processed image data of the rammed earth wall into a plurality of image separation areas by using an image histogram algorithm of the adaptive local equalization, and perform image histogram equalization on each image separation area to obtain an equalized image.
6. The intelligent rammed earth wall apparent crack detection system of claim 5, wherein the image histogram equalization process for each image separation region is to convert the image histogram distribution through a cumulative distribution function to an approximately uniform distribution function.
7. The intelligent detection system for apparent cracks of rammed earth wall according to claim 6, wherein the image histogram equalization process for each image separation region comprises:
(1) Sequentially collecting gray level images of the original image, and calculating a gray level histogram of the original image;
(2) Calculating the cumulative distribution function of the gray level histogram of the original image;
(3) According to the result of the cumulative distribution function, a mapping relation function is obtained as shown in formula (1):
wherein S is k Is the value of the current gray level after the cumulative distribution function mapping;
n is the sum of the pixels in the image;
n j the number of pixels of the current gray level;
l is the total number of gray levels in the image;
(4) And finishing image histogram transformation according to the mapping relation function.
8. The intelligent detection system for apparent cracks of the rammed earth wall according to claim 4, wherein the crack reconstruction module is configured to perform fusion reconstruction on crack feature labels in the crack feature images under the image mask by using the crack feature images under the image mask and referring to an Imrechstruct function and using a morphological reconstruction principle to obtain reconstructed images, and input the reconstructed images to the image output module.
9. The rammed earth wall apparent crack intelligent detection system of claim 1, wherein the rammed earth wall apparent crack detection post-processing system comprises:
and the detection report automatic generation module is used for automatically generating a detection report, importing the image of the rammed earth wall processed by the image editing module in the rammed earth wall apparent crack detection pretreatment system and the image output by the crack reconstruction module in the rammed earth wall apparent crack detection system into the module, and automatically generating the detection report in a PDF format.
10. The rammed earth wall apparent crack intelligent detection system of claim 1, wherein the rammed earth wall apparent crack detection post-processing system further comprises:
the automatic detection information recording module is used for recording historical detection information and facilitating the inquiry of historical detection items
And the detection information intelligent tracing module is used for tracing the detection information record, and is convenient for comprehensively checking project detection workload and detection results.
Rammed earth wall apparent crack intelligent detection system
Technical Field
The invention relates to an intelligent detection system for apparent cracks of a rammed earth wall.
Background
At the present stage, the traditional village construction and the village revivification become one of the important work of the social development of China. Among them, the traditional village often has a large amount of old houses due to a lot of problems such as low construction level and poor construction capability, and relates to hidden dangers such as building structure safety and building function loss, and needs to carry out building investigation work urgently. At present, the adopted manual survey mode has the problems of inconsistent subjective experience, untimely information recording, difficult survey result tracing and the like, and the working efficiency of the traditional village building damage survey and the normal development of subsequent construction are seriously influenced.
Disclosure of Invention
The invention aims to provide an intelligent detection system for apparent cracks of a rammed earth wall.
In order to solve the above problems, the present invention provides an intelligent detection system for apparent cracks of a rammed earth wall, comprising:
the rammed earth wall apparent crack detection pretreatment system is used for acquiring, inputting and editing rammed earth wall images;
the rammed earth wall apparent crack intelligent detection system is used for obtaining an image to be reconstructed based on the edited rammed earth wall image;
and the rammed earth wall apparent crack detection post-processing system is used for automatically generating a detection report according to the rammed earth wall original image and the reconstructed image.
Further, in the above system, a treatment system before detection of apparent cracks of the earth wall includes:
the image acquisition module is used for carrying out system acquisition on the image of the rammed earth wall by utilizing image acquisition equipment such as an unmanned aerial vehicle and a single lens reflex camera and inputting the acquired image into the image input module;
the image input module is used for inputting the acquired image to the image editing module;
and the image editing module is used for processing the acquired image to obtain a processed image of the rammed earth wall, and inputting the processed image of the rammed earth wall into the image reading module in the intelligent detection system for the apparent cracks of the rammed earth wall and the automatic generation module for the detection report in the post-processing system for the apparent cracks of the rammed earth wall respectively.
Further, in the above system, the processing the acquired image includes: and carrying out editing operations of rotation, turning over, cutting, amplification and reduction on the acquired image.
Further, in the above system, the rammed earth wall apparent crack intelligent detection system includes:
the image reading module is used for reading the processed image of the rammed earth wall and inputting the processed image of the rammed earth wall to the self-adaptive local equalization module;
the self-adaptive local equalization module is used for carrying out self-adaptive local equalization processing on the processed rammed earth wall image so as to obtain an equalized image;
the brightness non-uniformity correction module is used for carrying out non-uniformity correction on the brightness of the equalized image by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold to obtain a brightness correction image;
the contrast non-uniform correction module is used for carrying out non-uniform correction on the contrast of the image brightness correction image by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold to obtain a corrected image;
the crack extraction module is used for converting the corrected image into a binary image with only two colors by using a threshold transformation method so as to display the trend and the distribution area of crack lines, form a crack characteristic image under an image mask, finish crack extraction and input the crack characteristic image into the crack reconstruction module;
the fracture reconstruction module is used for obtaining a reconstructed image by utilizing the fracture characteristic image under the image mask and inputting the reconstructed image to the image output module;
and the image output module is used for outputting the reconstructed image.
Further, in the system, the adaptive local equalization module is configured to automatically divide the processed image data of the rammed earth wall into a plurality of image separation regions by using an image histogram algorithm of the adaptive local equalization, and perform image histogram equalization on each image separation region respectively to obtain an equalized image.
Further, in the above system, the image histogram equalization process for each image separation region is to convert the image histogram distribution into an approximately uniform distribution function by an accumulative distribution function.
Further, in the above system, the image histogram equalization process for each image separation region includes:
(1) Sequentially collecting gray level images of the original image, and calculating a gray level histogram of the original image;
(2) Calculating the cumulative distribution function of the gray level histogram of the original image;
(3) According to the result of the cumulative distribution function, a mapping relation function is obtained as shown in formula (1):
wherein S is k Is the value of the current gray level after the cumulative distribution function mapping;
n is the sum of the pixels in the image;
n j the number of pixels of the current gray level;
l is the total number of gray levels in the image;
(4) And finishing image histogram transformation according to the mapping relation function.
Further, in the system, the fracture reconstruction module is configured to perform fusion reconstruction on fracture feature labels in the fracture feature image under the image mask by using the fracture feature image under the image mask and referring to an imrecornstruct function and using a morphological reconstruction principle to obtain a reconstructed image, and input the reconstructed image to the image output module.
Further, in the above system, the system for post-treatment of apparent crack detection of rammed earth wall comprises:
the detection report automatic generation module is used for automatically generating a detection report, importing a rammed earth wall image processed by the image editing module in the rammed earth wall apparent crack detection pretreatment system and an image output by the crack reconstruction module in the rammed earth wall apparent crack detection system into the module, and automatically generating a detection report in a PDF format;
the automatic detection information recording module is used for recording historical detection information and facilitating the inquiry of historical detection items
And the intelligent detection information tracing module is used for tracing the detection information record, so that the project detection workload and the detection result can be conveniently and comprehensively checked.
Compared with the prior art, the invention provides an intelligent detection system for apparent cracks of a rammed earth wall, which takes a rammed earth wall which is commonly used in the traditional village as a main implementation object, completes the apparent crack detection work of the rammed earth wall through a series of operations of filling project information, uploading an image of the rammed earth wall to be detected, editing the image of the rammed earth wall to be detected, intelligently detecting cracks, automatically generating a detection report and the like, and can simultaneously inquire historical detection projects to establish a quick, intelligent and accurate detection system for apparent cracks of the traditional village building, thereby realizing the automatic intelligent detection of the apparent cracks of the rammed earth wall of the traditional village and the multi-source, detailed and accurate intelligent detection information of the apparent cracks of the rammed earth wall of the traditional village.
The invention improves and solves the problems of non-uniform subjective experience, untimely information recording, difficult survey result tracing and the like of the traditional manual survey mode at present, establishes a rapid, intelligent and accurate traditional village building apparent crack detection system, and realizes the automatic intelligent detection of the apparent cracks of the traditional village rammed earth wall and the inquiry and tracing of the intelligent detection information of the apparent cracks of the traditional village rammed earth wall with multiple sources, detail and accuracy.
Drawings
FIG. 1 is an overall architecture diagram of a rammed earth wall apparent crack intelligent detection system according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, the present invention is described in detail with reference to the accompanying drawings and the detailed description thereof.
As shown in FIG. 1, the invention provides an intelligent detection system for apparent cracks of a rammed earth wall, which comprises:
the rammed earth wall apparent crack detection pretreatment system is used for acquiring, inputting and editing rammed earth wall images;
the rammed earth wall apparent crack intelligent detection system is used for obtaining an image to be reconstructed based on the edited rammed earth wall image;
and the rammed earth wall apparent crack detection post-processing system is used for automatically generating a detection report according to the original image of the rammed earth wall and the reconstructed image.
In an embodiment of the present invention, a tamper wall apparent crack intelligent detection system comprises:
the image acquisition module is used for carrying out system acquisition on the image of the rammed earth wall by utilizing image acquisition equipment such as an unmanned aerial vehicle and a single lens reflex camera and inputting the acquired image into the image input module;
the image input module is used for inputting the acquired image to the image editing module;
and the image editing module is used for carrying out editing operations of rotation, turning, cutting, amplification and reduction on the acquired image to obtain a processed rammed earth wall image, and respectively inputting the processed rammed earth wall image into the image reading module in the intelligent rammed earth wall apparent crack detection system and the detection report (PDF format) automatic generation module in the post-processing system for rammed earth wall apparent crack detection.
In an embodiment of the present invention, the system for intelligently detecting apparent cracks of a rammed earth wall comprises:
the image reading module is used for reading the processed rammed earth wall image and inputting the processed rammed earth wall image into the self-adaptive local equalization module;
the self-adaptive local equalization module is used for automatically dividing the processed image data of the rammed earth wall into a plurality of image separation areas by adopting a self-adaptive local equalization image histogram algorithm, performing image histogram equalization processing on each image separation area respectively, and combining the plurality of separation areas by utilizing a bilinear interpolation method to eliminate the image boundary effect, effectively limiting the contrast of an even brightness area (setting a contrast enhancement limiting parameter to be 0.0025 as a default value in the algorithm), and simultaneously reducing the influence of image noise on the crack identification effect, thereby obtaining an equalized image.
The image histogram equalization processing of each image separation area is to convert image histogram distribution into an approximately uniform distribution function through an accumulative distribution function so as to enhance image contrast, improve crack image feature definition and provide conditions for subsequent crack extraction and reconstruction. The specific operation steps are the following 4 steps in sequence:
(1) Sequentially collecting gray level images of the original images, and calculating gray level histograms of the original images;
(2) Calculating a cumulative distribution function of the gray level histogram of the original image;
(3) Obtaining a mapping relation function (as shown in formula (1)) according to the result of the cumulative distribution function;
(4) And finishing image histogram transformation according to the mapping relation function.
Wherein S is k Is the value of the current gray level after the cumulative distribution function mapping;
n is the sum of the pixels in the image;
n j is the number of pixels of the current gray level;
l is the total number of gray levels in the image.
The brightness non-uniform correction module is used for carrying out non-uniform correction on the brightness of the equalized image by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold to obtain a brightness corrected image;
the contrast non-uniform correction module is used for carrying out non-uniform correction on the contrast of the image brightness correction image by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold to obtain a corrected image;
the brightness non-uniform correction module and the contrast non-uniform module are used for solving the problem that the traditional village rammed earth wall image has multiple possible illumination conditions, and further, the brightness and the contrast of the image are non-uniformly corrected by utilizing two means of segmenting a threshold vector and adjusting a threshold of image gray level on the basis of image self-adaptive local equalization.
Specifically, a stretchlim function and an imadjust function can be referred to solve the problems of image self-adaptive gray scale stretching and the like, and then, the morphological bottom-cap filtering and Gaussian denoising are utilized to perform image filtering. Wherein, the general syntax call format of the imadjust function is shown in formula (2), and the function is to transform the image f to the new image f 1 In the process of (3), the pixel point with the gray value lower than low _ in f is in f 1 The middle gray value is assigned as low _ out, and similarly, the pixel points with the middle gray value higher than high _ in are converted to f 1 The gray value is also assigned as high _ out; and for the parameter gamma, when the gamma is less than 1, the gray value of the pixel point with lower gray value of the gray image close to low _ in is higher, the gray variation range is stretched, the gray variation range of one end of the gray image close to high _ in is compressed, and the whole image is brighter. Similarly, when gamma > 1, the gray value of the lower gray pixel point near low _ in of the gray image becomes lower, the gray variation range is compressed, and the gray variation range of the end near high _ in of the gray value is stretched. And calling a stretchlim function to calculate the optimal input interval of the gray image, combining the stretchlim function and the imadjust function (shown as a formula (3)), automatically determining a threshold, finishing contrast stretching, and inputting the corrected image to a crack extraction module.
f1＝imadjust(f,[low_in；high_in],[low_out；high_out],gamma) (2)
f 1 ＝imadjust(f,strechlin(f),[]) (3)
Wherein: [ low _ in; high _ in is the gray scale range to be transformed in the original image f;
[low_out；high_out]for the transformed image f 1 The gray scale range of (a);
gamma is the mapping mode, the default value is 1, namely linear mapping, and when gamma ≠ 1, nonlinear mapping is performed.
The crack extraction module is used for converting the corrected image into a binary image (usually black and white) with only two colors by using a threshold transformation method so as to display the trend and the distribution area of crack lines, form a crack characteristic image under an image mask, complete crack extraction and input the crack characteristic image into the crack reconstruction module;
and the fracture reconstruction module is used for performing fusion reconstruction on fracture characteristic marks in the fracture characteristic images under the image masks by using the fracture characteristic images under the image masks and referring to an Imrecornstruct function (as shown in a formula (4)), by using a morphological reconstruction principle, so as to obtain reconstructed images, and inputting the reconstructed images to the image output module.
Wherein the morphological reconstruction is a morphological transformation involving two images and a structuring element, one of the images being a marker (marker) which is the starting point of the transformation, the other image being a mask (mask) which is used to constrain the transformation process, the structuring element being used to define the connectivity.
IM＝imreconstruct(MARKER,MASK) (4)
Wherein: MARKER is a mark and represents an initial mark point matrix, and element 1 represents a mark point;
MASK is a MASK, represents an original image, and requires that the corresponding position of an element 1 in MARKER in X is also 1;
the marks and masks are two grayscale images or two binary images and have the same size, and the return IM of the function is also a grayscale image or a binary image of the same size.
And the image output module is used for outputting the reconstructed image.
In an embodiment of the intelligent detection system for apparent cracks of a rammed earth wall, the post-treatment system for apparent crack detection of the rammed earth wall specifically comprises:
a detection report (PDF format) automatic generation module for automatically generating a detection report, and leading the image of the rammed earth wall processed by the image editing module in the rammed earth wall apparent crack detection pre-processing system and the image output by the crack reconstruction module in the rammed earth wall apparent crack detection system into the module to automatically generate the detection report in the PDF format;
the automatic detection information recording module is used for recording historical detection information and facilitating the inquiry of historical detection items
And the detection information intelligent tracing module is used for tracing the detection information record, and is convenient for comprehensively checking project detection workload and detection results.
The invention provides an intelligent detection system for apparent cracks of a rammed earth wall, which takes a rammed earth wall which is commonly used in a traditional village as a main implementation object, completes the apparent crack detection work of the rammed earth wall through a series of operations of filling item information, uploading an image of the rammed earth wall to be detected, editing the image of the rammed earth wall to be detected, intelligently detecting cracks, automatically generating a detection report and the like, and can simultaneously inquire historical detection items to establish a quick, intelligent and accurate traditional village building apparent crack detection system so as to realize the automatic intelligent detection of the apparent cracks of the traditional rammed earth wall in the village and the multi-source, detailed and accurate inquiry and tracing of the traditional rammed earth wall apparent crack intelligent detection information of the rammed earth wall in the village.
The invention improves and solves the problems of non-uniform subjective experience, untimely information recording, difficult survey result tracing and the like of the traditional manual survey mode at present, establishes a rapid, intelligent and accurate traditional village building apparent crack detection system, and realizes the automatic intelligent detection of the apparent cracks of the traditional village rammed earth wall and the inquiry and tracing of the intelligent detection information of the apparent cracks of the traditional village rammed earth wall with multiple sources, detail and accuracy.
In summary, the rammed earth wall apparent crack intelligent detection system provided by the invention firstly inputs the image of the rammed earth wall acquired by image acquisition equipment such as an unmanned aerial vehicle and a single lens reflex into a rammed earth wall apparent crack detection pretreatment system to perform editing operations such as rotation, turning, cutting, amplification, reduction and the like; then, automatically dividing the read and edited image data of the rammed earth wall into a plurality of separation areas, respectively carrying out image histogram equalization processing on each image separation area, and combining the plurality of separation areas by using a bilinear interpolation method to eliminate the image boundary effect, effectively limiting the contrast of an area with uniform brightness, and reducing the influence of image noise on the crack identification effect; secondly, on the basis of image self-adaptive local equalization, uneven correction is carried out on the image brightness and the contrast by utilizing two means of a segmentation threshold vector and an image gray level adjustment threshold; further, displaying the trend and the distribution area of the crack lines by using a threshold transformation method, forming a crack characteristic image under an image mask, completing crack extraction, and performing fusion reconstruction on crack characteristic marks under the image mask based on a morphological reconstruction principle; further, automatically generating a detection report (PDF format) according to the original image of the rammed earth wall and the reconstructed image, and completing the apparent crack detection work of the rammed earth wall; and finally, the detection information is automatically recorded and intelligently traced, so that historical detection items, detection workload and detection results can be conveniently inquired.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211508701.7A CN115760825A (en) | 2022-11-29 | 2022-11-29 | Rammed earth wall apparent crack intelligent detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211508701.7A CN115760825A (en) | 2022-11-29 | 2022-11-29 | Rammed earth wall apparent crack intelligent detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115760825A true CN115760825A (en) | 2023-03-07 |
Family
ID=85340744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211508701.7A Pending CN115760825A (en) | 2022-11-29 | 2022-11-29 | Rammed earth wall apparent crack intelligent detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115760825A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117934407A (en) * | 2024-01-22 | 2024-04-26 | 广东筠诚建筑科技有限公司 | Apparent quality detection method and system for realizing light partition wall based on deep learning |
-
2022
- 2022-11-29 CN CN202211508701.7A patent/CN115760825A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117934407A (en) * | 2024-01-22 | 2024-04-26 | 广东筠诚建筑科技有限公司 | Apparent quality detection method and system for realizing light partition wall based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110675346B (en) | Image acquisition and depth map enhancement method and device suitable for Kinect | |
| Oakley et al. | Correction of simple contrast loss in color images | |
| CN109242791B (en) | Batch repair method for damaged plant leaves | |
| JP2021531571A (en) | Certificate image extraction method and terminal equipment | |
| CN114331869B (en) | Dam face crack semantic segmentation method | |
| CN114022383A (en) | Moire pattern removing method and device for character image and electronic equipment | |
| CN111696065B (en) | Precious stone image highlight removing method based on image processing | |
| JP2013105245A (en) | Image processing method, device and program | |
| CN114022732A (en) | Extremely dark light object detection method based on RAW image | |
| CN115760825A (en) | Rammed earth wall apparent crack intelligent detection system | |
| CN113971669A (en) | Three-dimensional detection system applied to pipeline damage identification | |
| CN114332081B (en) | Textile surface abnormity determination method based on image processing | |
| CN112348018A (en) | Digital display type instrument reading identification method based on inspection robot | |
| CN111275687B (en) | Fine-grained image stitching detection method based on connected region marks | |
| CN110349129B (en) | Appearance defect detection method for high-density flexible IC substrate | |
| CN110751690B (en) | Visual positioning method for milling machine tool bit | |
| CN116681879A (en) | Intelligent interpretation method for transition position of optical image boundary layer | |
| CN104463898A (en) | Image identification counting system for logistics platform | |
| Yuhan et al. | Detection of road surface crack based on PYNQ | |
| CN114820718A (en) | Visual dynamic positioning and tracking algorithm | |
| CN115187788A (en) | Crop seed automatic counting method based on machine vision | |
| CN113505622A (en) | Test system and method for automatically identifying multiple bar codes and LED lamps | |
| CN109272462B (en) | Image self-correction method, device and storage device suitable for metal workpiece identification | |
| Zhang et al. | Application of Machine Vision Technology in 3D Printing Quality Inspection System | |
| CN112232390A (en) | Method and system for identifying high-pixel large image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |