CN114965487B - Calibration method and device of automatic monitoring equipment for tunnel typical damage - Google Patents
Calibration method and device of automatic monitoring equipment for tunnel typical damage Download PDFInfo
- Publication number
- CN114965487B CN114965487B CN202210655193.9A CN202210655193A CN114965487B CN 114965487 B CN114965487 B CN 114965487B CN 202210655193 A CN202210655193 A CN 202210655193A CN 114965487 B CN114965487 B CN 114965487B
- Authority
- CN
- China
- Prior art keywords
- tunnel
- tunnel defect
- image
- calibration
- detection area
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000001514 detection method Methods 0.000 claims abstract description 108
- 230000007547 defect Effects 0.000 claims description 167
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 34
- 230000004927 fusion Effects 0.000 claims description 22
- 201000010099 disease Diseases 0.000 claims description 13
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000011282 treatment Methods 0.000 claims description 9
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Theoretical Computer Science (AREA)
- Analytical Chemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
The invention provides a calibration method and a device for automatic monitoring equipment of tunnel typical faults, which are characterized in that before tunnel fault shooting is carried out, a detection area is set and processed, so that all shot images comprise all tunnel fault images, each sub image comprises tunnel faults, corresponding calibration is selected according to different tunnel fault types, preset points are set based on calibrated positions, and target detection areas are further divided based on the preset points, so that different tunnel fault types are divided into different target detection areas, and the fault identification rate and the identification precision are further improved.
Description
Technical Field
The invention relates to the technical field of automatic monitoring of tunnel defects, in particular to a calibration method and device of automatic monitoring equipment for typical defects of tunnels.
Background
With the improvement of social and economic level and the development of highway traffic industry, the scale and the number of the traffic and engineering construction in China generally show a continuous trend. The tunnel is an engineering building of an underground passage, has some other incomparable advantages, and thus has a very obvious growing trend. Because of the particularities of tunnels and underground engineering, a great number of problems in the field of monitoring the running state of tunnels are not well solved.
In recent years, an automatic monitoring method based on machine vision is continuously developed, and the method is widely applied to automatic monitoring of apparent diseases of an operation tunnel, so that the monitoring efficiency is improved. Since machine vision is based on computer deep learning to achieve the functions of recognition and positioning, the parameters of the model are numerous, and a large amount of picture data is needed to train the model. At present, in the automatic identification process of the system, the detection area and the range of the diseases to be detected are often not correctly segmented, so that the phenomenon of low disease identification rate and precision occurs. Therefore, an intelligent disease labeling method with higher accuracy is urgently needed to improve the labeling precision and efficiency of typical apparent disease images of tunnels.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a calibration method and a calibration device of automatic monitoring equipment for typical tunnel diseases, which are used for solving the technical problems that the detection area cannot be divided correctly and the range of the diseases to be detected in the prior art, so that the identification rate and the accuracy of the diseases are low.
The method for calibrating the automatic monitoring equipment for the typical tunnel defect is characterized by comprising the following steps of: setting a plurality of detection areas according to the positions of tunnel defects, wherein tunnel defects exist in each detection area; selecting corresponding calibration to be arranged in the detection area according to the tunnel defect type in the detection area; aiming a preset shooting device at the calibration in each detection area to carry out tunnel defect shooting to obtain a plurality of tunnel defect sub-images; a multiband fusion algorithm is adopted to fuse a plurality of tunnel defect sub-images, so that a tunnel defect image is obtained; based on the tunnel defect image, setting a preset point at the position where the calibration is positioned; and dividing the target detection area of the tunnel defect image by adopting a rectangular frame based on the preset points to obtain a plurality of target detection areas, wherein each target detection area comprises one preset point.
In one embodiment, the step of selecting the corresponding calibration to be set in the detection area according to the tunnel defect type in the detection area includes: dividing tunnel defects in the detection area into cracks and leakage water, and judging the types of the tunnel defects in the detection area; when the tunnel defect is a crack, selecting a single black mark as a target mark to be arranged in the detection area; and when the tunnel defect is water leakage, selecting a calibration plate with black and white intervals as a target for calibration and setting in the detection area.
In one embodiment, before the step of capturing the tunnel defect by aligning the preset capturing device with the calibration in each detection area to obtain the plurality of tunnel defect sub-images, the method further includes: and moving the shooting device according to the calibrated position, and keeping the vertical distance between the shooting device and the calibration as a preset value.
In one embodiment, the step of fusing the plurality of tunnel defect sub-images by using a multiband fusion algorithm further includes: and carrying out light intensity recognition on each tunnel defect sub-image, and carrying out light intensity contrast intensity increasing treatment on the tunnel defect sub-images with the light intensity recognition results lower than a light intensity threshold value.
In one embodiment, based on the preset points, dividing the target detection area of the tunnel defect image by adopting a rectangular frame to obtain a plurality of target detection areas, and after each target detection area includes one preset point, further including: carrying out graying treatment on each target detection area to obtain a gray image; and preprocessing the gray level image to obtain a parameter monitoring value of tunnel defect.
In one embodiment, the step of preprocessing the gray level image to obtain a parameter monitoring value of the tunnel defect includes: and when the tunnel defect is a crack, extracting the characteristic edge of the gray level image to obtain a width monitoring value of the crack.
In one embodiment, the step of preprocessing the gray level image to obtain a parameter monitoring value of the tunnel defect includes: and when the tunnel defect is water leakage, carrying out edge dynamic identification on the gray level image based on an intelligent algorithm to obtain an area monitoring value of the water leakage.
In one embodiment, before the step of obtaining the plurality of target detection areas, the method includes: receiving a manually selected reference area of one datum in the tunnel defect image; and calculating the actual length corresponding to the unit pixel in the tunnel defect image according to the reference area.
In one embodiment, after the step of preprocessing the gray-scale image to obtain the parameter monitoring value of the tunnel defect, the method further includes: and converting the parameter monitoring value into an actual value according to the actual length corresponding to the unit pixel in the tunnel defect image.
The utility model provides a calibration device of tunnel typical disease automatic monitoring equipment, includes detection zone setting module, marks and selects module, sub-image shooting module, image fusion module, preset point setting module and detection zone division module, wherein: the detection zone setting module is used for setting a plurality of detection zones according to the positions of tunnel defects, wherein tunnel defects exist in each detection zone; the calibration selection module is used for selecting corresponding calibration to be arranged in the detection area according to the tunnel defect type in the detection area; the sub-image shooting module is used for shooting tunnel defects by aiming a preset shooting device at the calibration in each detection area to obtain a plurality of tunnel defect sub-images; the image fusion module is used for fusing a plurality of tunnel defect sub-images by adopting a multiband fusion algorithm to obtain a tunnel defect image; the preset point setting module is used for setting preset points at the positions where the calibration is located based on the tunnel defect images; the detection region dividing module is used for dividing the target detection region of the tunnel defect image by adopting a rectangular frame based on the preset points to obtain a plurality of target detection regions, wherein each target detection region comprises one preset point.
According to the technical scheme, the beneficial technical effects of the invention are as follows:
1. Before tunnel defect shooting is carried out, the detection area is set, so that all shot images are guaranteed to contain all tunnel defect images, each sub image contains tunnel defects, corresponding calibration is selected according to different tunnel defect types, preset points are set based on the calibrated positions, and the target detection areas are further divided based on the preset points, so that different tunnel defect types are divided into different target detection areas, and defect recognition rate and recognition accuracy are further improved.
2. The single black calibration is adopted for the tunnel defect of the crack, so that the width parameter of the crack is convenient to measure and calculate, and the black-white alternate calibration plate is adopted for the tunnel defect of the leakage water, so that the area parameter of the leakage water is convenient to measure and calculate.
3. And the tunnel defect sub-images with the light intensity recognition result lower than the light intensity threshold value are subjected to light intensity contrast intensity increasing treatment, so that the recognition effect of tunnel defects in the tunnel defect sub-images is improved, and the recognition accuracy of the tunnel defects is further improved.
4. The actual length corresponding to the unit pixel in the tunnel defect image is calculated according to the reference area by receiving a manually selected reference area, so that the actual value corresponding to the parameter monitoring value of the tunnel defect can be calculated, and the tunnel defect can be monitored better.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
FIG. 1 is a schematic flow chart of a method for calibrating an automatic monitoring device for typical tunnel defects in an embodiment;
fig. 2 is an application scenario diagram of tunnel defect shooting in one embodiment;
FIG. 3 is a schematic diagram showing a positional relationship between a camera and a calibration in an embodiment;
FIG. 4 is a schematic diagram labeled in one embodiment;
Fig. 5 is a block diagram of a calibration device of an automatic monitoring apparatus for tunnel typical damage in one embodiment.
Detailed Description
Embodiments of the technical scheme of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and thus are merely examples, and are not intended to limit the scope of the present invention.
It is noted that unless otherwise indicated, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs.
In one embodiment, as shown in fig. 1, a calibration method of an automatic monitoring device for typical tunnel damage is provided, which includes the following steps:
s1, setting a plurality of detection areas according to the positions of tunnel defects, wherein tunnel defects exist in each detection area.
Specifically, as shown in fig. 2 and 3, the range covering all tunnel defects is a defect monitoring area in the figure, and in the defect monitoring area, the defect monitoring area can be artificially divided into a plurality of small areas with basically the same size, namely a detection area, according to the types, the trends and the distribution of the defects.
S2, selecting corresponding calibration to be arranged in the detection area according to the tunnel defect type in the detection area.
Specifically, a specific identifier (i.e., a calibration) is placed within each detection zone. In the view field range of the camera, the calibration can be randomly placed around the crack or the leakage water, and the back of the calibration is provided with a bonding material, so that the calibration can be directly stuck near the crack or the leakage water area when in use.
In one embodiment, step S2 includes: dividing tunnel defects in the detection area into cracks and leakage water, and judging the types of the tunnel defects in the detection area; when tunnel defect is a crack, selecting a single black mark as a target mark to be arranged in a detection area; when tunnel defect is water leakage, selecting a calibration plate with black and white intervals as a target for calibration and setting in a detection area.
Specifically, as shown in fig. 4, tunnel defects are commonly classified into two types, namely a crack and water leakage, and the area I in fig. 4 is marked for the crack, namely the crack is marked for independent black, and the width of the crack needs to be monitored, so that the crack is marked for single; the area II is a calibration plate with black and white phases aiming at the calibration of the water leakage, and the parameter to be monitored of the water leakage is the area, so that the calibration plate is more suitable. Corresponding calibration is selected according to different tunnel defect types, so that the recognition efficiency and recognition accuracy of tunnel defects in a detection area can be improved.
And S3, aiming a preset shooting device at the calibration in each detection area to perform tunnel defect shooting, so as to obtain a plurality of tunnel defect sub-images.
Specifically, the shooting device is any one of the existing rotatable cameras, and the position where the shooting device is calibrated is the direction against which the shooting device is used for shooting. A calibration corresponds to a patrol area, which is a field of view of the camera, i.e. the area is taken as a picture (tunnel defect sub-image). Taking one of the pictures as an example, the resolution is 300DPI, the corresponding pixel of the whole picture is 1920×1080= 2073600, wherein the area (the side length of the calibration itself) for calibration is square with the side length of 2cm, the corresponding pixel is 236×236= 55696, 55696/2073600= 0.02686, namely the pixel of the calibration area is 0.02686 times of the pixel of the whole picture, namely the length corresponding to 1 pixel is 0.2686mm. The calibration area (the area occupied by the calibration) acts like a reference.
In one embodiment, as shown in fig. 3, before step S3, moving the photographing device according to the calibrated position is further included, and keeping the vertical distance of the photographing device from the calibration at a preset value.
Specifically, as shown in fig. 4, the photographing device may maintain the vertical distance from the calibration to be 1 meter, 2 meters, 3 meters, 4 meters, 5 meters, 6 meters, etc. The method comprises the steps of firstly keeping the vertical distance from calibration to be 1m, carrying out alignment shooting on all calibration, then changing the vertical distance from calibration to be 2m, carrying out alignment shooting on all calibration again, carrying out corresponding repeated shooting operation once when changing the vertical distance, thus obtaining a plurality of groups of tunnel defect sub-images, carrying out subsequent S4-S6 on each group of tunnel defect sub-images, and carrying out the subsequent step operation after the step S6, thus obtaining a plurality of groups of crack identification rate, crack width test precision and water seepage area identification under different angle conditions with different distances, and carrying out a plurality of groups of comparison to reduce errors and realize the dynamic monitoring of tunnel defects.
And S4, fusing a plurality of tunnel defect sub-images by adopting a multiband fusion algorithm to obtain a tunnel defect image.
Specifically, after the shot tunnel defect sub-images are collected, the shot tunnel defect sub-images are spliced into a whole, the pose of the tunnel defect sub-images is acquired, and then the images are mapped to a spliced image plane through transformation, so that image splicing is realized. However, the photographed image is susceptible to factors such as illumination, so that the splicing transition is unnatural and obvious splicing marks appear, and therefore, the images need to be fused before the spliced image is generated. And a multiband fusion algorithm is adopted, namely, laplacian pyramids are respectively constructed on images to be fused, then the images on the same layer are fused according to a certain rule, and the most important fusion is that a fusion window with a proper size is selected, and the fusion effect of the images can be influenced by different fusion windows. The optimal fusion window should smooth the fused image and have no ghosts. The laplacian pyramid fusion procedure is as follows:
1) Respectively constructing a Laplara pyramid L A and a Laplara pyramid L B for any adjacent images A and B;
2) Constructing a Gaussian pyramid GM from the selected mask map;
3) With GM as a weight, a joint L S pyramid is constructed by adopting L A and L B, wherein the calculation formula of L S is as follows:
LS=GM×LA+(1-GM)×LB
4) Disassembling the L S pyramid to obtain a fused graph.
A complete tunnel defect image is convenient to view and analyze the development trend of tunnel defects, and is beneficial to the overall monitoring of tunnel defects.
In one embodiment, before step S4, the method further includes: and carrying out light intensity recognition on each tunnel defect sub-image, and carrying out light intensity contrast intensity increasing treatment on the tunnel defect sub-images with the light intensity recognition results lower than the light intensity threshold value.
In particular, good light is a prerequisite for monitoring equipment within a tunnel. However, for some areas in the hole, the phenomena of damage to lighting facilities, insufficient illumination and the like may exist, so that the detection precision of the equipment monitoring data is affected. Therefore, the tunnel defect sub-image with the light intensity recognition result lower than the light intensity threshold value needs to be subjected to light intensity contrast intensity increasing treatment, so that the recognition effect of tunnel defects in the tunnel defect sub-image is improved, and the recognition precision of the tunnel defects is further improved.
S5, setting a preset point at the position where the calibration is based on the tunnel defect image.
Specifically, the calibration position is set to be a preset point, so that when the target detection areas are divided later, each target detection area is provided with a preset point, and tunnel diseases in the target detection areas can be processed conveniently.
And S6, dividing the target detection areas of the tunnel defect image by adopting a rectangular frame based on preset points to obtain a plurality of target detection areas, wherein each target detection area comprises a preset point.
Specifically, the tunnel defect image is obtained by fusing and splicing the tunnel defect sub-images, although the integral image is more beneficial to researching the development trend of tunnel defect, in order to improve the monitoring precision, the object detection area of the tunnel defect image is divided, the division is based on the distribution of preset points and the distribution of tunnel defect, the preset points are essentially calibration positions, and the distribution of the preset points is considered during the division although the fusion jigsaw processing is performed according to the calibration positions during the shooting, so that the follow-up parameter monitoring is more beneficial. And the whole graph is larger, and the accuracy and the efficiency of the processing can be improved through the parallel processing after the region is divided.
In one embodiment, after step S6, further comprising: carrying out graying treatment on each target detection area to obtain a gray image; and preprocessing the gray level image to obtain a parameter monitoring value of tunnel defect.
Specifically, after the gray level image is obtained, different treatments are required according to preset points (namely the calibrated types) in the target detection area, and different parameters required to be monitored for tunnel diseases are different, so that the corresponding pretreatment is also different, the parameters required to be monitored for the cracks are the width of the cracks, and the parameters required to be monitored for the seepage are the area of seepage. When the tunnel lining is cracked and leaked, obvious color differences exist between the area of the cracked and leaked water and the surrounding area after the area is identified by the system (namely gray processing), and the width of the crack and the area of the leaked water are automatically converted according to the pixels of the area occupied by the cracked and the leaked water by taking the calibration area as a reference. For cracks and water leakage exceeding the allowable range (namely exceeding the corresponding crack width and water leakage area), an alarm threshold value can be set in advance, and real-time early warning can be performed according to monitoring data.
In one embodiment, the step of preprocessing the gray level image to obtain a parameter monitoring value of the tunnel defect includes: and when the tunnel defect is a crack, extracting the characteristic edge of the gray image to obtain a width monitoring value of the crack.
Specifically, after the image is collected, grayed and preprocessed, if the gray value of the image around the crack is changed, the characteristic edge is extracted by threshold segmentation, so that the purpose of dynamically monitoring the width change is achieved. And the single black mark is adopted for calibrating tunnel defects of the cracks, so that the width parameters of the cracks can be conveniently measured and calculated.
In one embodiment, the step of preprocessing the gray level image to obtain a parameter monitoring value of the tunnel defect includes: when the tunnel defect is water leakage, carrying out edge dynamic identification on the gray level image based on an intelligent algorithm to obtain an area monitoring value of the water leakage.
Specifically, when water seepage occurs or develops, the gray value of the image around the water seepage can change, and the edge of the water seepage is dynamically identified through an intelligent algorithm (namely, the pixel area occupied by the area corresponding to the water seepage is measured), so that the purpose of dynamically monitoring the change of the water seepage area is achieved. And the tunnel defect of the leakage water is calibrated by adopting a calibration plate with black and white phases, so that the area parameter of the leakage water can be conveniently measured and calculated.
In one embodiment, before the step of obtaining the plurality of target detection areas, the method further includes: receiving a reference area of a datum in the manually selected tunnel defect image; and calculating the actual length corresponding to the unit pixel in the tunnel defect image according to the reference area.
Specifically, the reference area of the reference is the area where the calibration in the step S2 is located, and since the actual side length and the shape of the calibration are known, the actual length corresponding to a unit pixel in the tunnel defect image can be correspondingly calculated through the ratio of the area to the pixel.
In one embodiment, after the step of preprocessing the gray level image to obtain the parameter monitoring value of the tunnel defect, the method further includes: and converting the parameter monitoring value into an actual value according to the actual length corresponding to the unit pixel in the tunnel defect image.
Specifically, according to the actual length corresponding to one unit pixel in the tunnel defect image obtained by the steps in one embodiment, the parameter monitoring value is converted, the actual value corresponding to the parameter monitoring value is obtained, the actual parameter of the tunnel defect is conveniently and accurately calculated in a calibration and conversion mode, and the monitoring accuracy is improved.
In one embodiment, as shown in fig. 5, a calibration device of an automatic monitoring device for typical tunnel diseases is provided, which includes a detection area setting module 210, a calibration selecting module 220, a sub-image shooting module 230, an image fusion module 240, a preset point setting module 250, and a detection area dividing module 260, wherein: the detection area setting module 210 is configured to set a plurality of detection areas according to positions of tunnel defects, where each detection area has a tunnel defect; the calibration selection module 220 is configured to select a corresponding calibration to be set in the detection area according to the type of tunnel defect in the detection area; the sub-image shooting module 230 is configured to perform tunnel defect shooting by aiming a preset shooting device at calibration in each detection area, so as to obtain a plurality of tunnel defect sub-images; the image fusion module 240 is configured to fuse the multiple tunnel defect sub-images by using a multiband fusion algorithm to obtain a tunnel defect image; the preset point setting module 250 is configured to set a preset point at the location of the calibration based on the tunnel defect image; the detection region dividing module 260 is configured to divide the target detection region of the tunnel defect image by using a rectangular frame based on the preset points, so as to obtain a plurality of target detection regions, where each target detection region includes a preset point.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device, or distributed across a network of computing devices, or they may alternatively be implemented in program code executable by computing devices, such that they may be stored on a computer storage medium (ROM/RAM, magnetic or optical disk) for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than what is shown or described herein, or they may be individually manufactured as individual integrated circuit modules, or a plurality of modules or steps in them may be manufactured as a single integrated circuit module. Therefore, the present invention is not limited to any specific combination of hardware and software.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (9)
1. The method for calibrating the automatic monitoring equipment for the typical tunnel defect is characterized by comprising the following steps of:
setting a plurality of detection areas according to the positions of tunnel defects, wherein tunnel defects exist in each detection area;
Selecting corresponding calibration to be arranged in the detection area according to the tunnel defect type in the detection area, including: dividing tunnel defects in the detection area into cracks and leakage water, and judging the types of the tunnel defects in the detection area; when the tunnel defect is a crack, selecting a single black mark as a target mark to be arranged in the detection area; when the tunnel defect is water leakage, selecting a calibration plate with black and white intervals as a target for calibration and setting in the detection area;
Aiming a preset shooting device at the calibration in each detection area to carry out tunnel defect shooting to obtain a plurality of tunnel defect sub-images;
A multiband fusion algorithm is adopted to fuse a plurality of tunnel defect sub-images, so that a tunnel defect image is obtained;
based on the tunnel defect image, setting a preset point at the position where the calibration is positioned;
and dividing the target detection area of the tunnel defect image by adopting a rectangular frame based on the preset points to obtain a plurality of target detection areas, wherein each target detection area comprises one preset point.
2. The method according to claim 1, wherein before the step of capturing the tunnel defect with the predetermined capturing device aligned with the calibration in each detection area to obtain the plurality of tunnel defect sub-images, the method further comprises:
and moving the shooting device according to the calibrated position, and keeping the vertical distance between the shooting device and the calibration as a preset value.
3. The method of claim 1, wherein the step of fusing the plurality of tunnel defect sub-images using a multi-band fusion algorithm, before the step of obtaining the tunnel defect image, further comprises:
and carrying out light intensity recognition on each tunnel defect sub-image, and carrying out light intensity contrast intensity increasing treatment on the tunnel defect sub-images with the light intensity recognition results lower than a light intensity threshold value.
4. The method according to claim 1, wherein the step of dividing the tunnel defect image into a plurality of target detection areas by using a rectangular frame based on the preset points, and each of the target detection areas includes one of the preset points, further includes:
carrying out graying treatment on each target detection area to obtain a gray image;
and preprocessing the gray level image to obtain a parameter monitoring value of tunnel defect.
5. The method of claim 4, wherein the step of preprocessing the gray scale image to obtain the parameter monitoring value of the tunnel defect comprises:
And when the tunnel defect is a crack, extracting the characteristic edge of the gray level image to obtain a width monitoring value of the crack.
6. The method of claim 4, wherein the step of preprocessing the gray scale image to obtain the parameter monitoring value of the tunnel defect comprises:
And when the tunnel defect is water leakage, carrying out edge dynamic identification on the gray level image based on an intelligent algorithm to obtain an area monitoring value of the water leakage.
7. The method of claim 4, further comprising, prior to the step of obtaining the plurality of target detection zones:
receiving a manually selected reference area of one datum in the tunnel defect image;
And calculating the actual length corresponding to the unit pixel in the tunnel defect image according to the reference area.
8. The method of claim 7, wherein after the step of preprocessing the gray scale image to obtain the parameter monitoring value of the tunnel defect, further comprising:
And converting the parameter monitoring value into an actual value according to the actual length corresponding to the unit pixel in the tunnel defect image.
9. The utility model provides a calibration device of tunnel typical disease automatic monitoring equipment which characterized in that, including detection zone setting up module, mark and select module, sub-image shooting module, image fusion module, preset point setting up module and detection zone division module, wherein:
The detection zone setting module is used for setting a plurality of detection zones according to the positions of tunnel defects, wherein tunnel defects exist in each detection zone;
The calibration selecting module is used for selecting corresponding calibration setting in the detection area according to the tunnel defect type in the detection area, and comprises the following steps: dividing tunnel defects in the detection area into cracks and leakage water, and judging the types of the tunnel defects in the detection area; when the tunnel defect is a crack, selecting a single black mark as a target mark to be arranged in the detection area; when the tunnel defect is water leakage, selecting a calibration plate with black and white intervals as a target for calibration and setting in the detection area;
the sub-image shooting module is used for shooting tunnel defects by aiming a preset shooting device at the calibration in each detection area to obtain a plurality of tunnel defect sub-images;
The image fusion module is used for fusing a plurality of tunnel defect sub-images by adopting a multiband fusion algorithm to obtain a tunnel defect image;
The preset point setting module is used for setting preset points at the positions where the calibration is located based on the tunnel defect images;
the detection region dividing module is used for dividing the target detection region of the tunnel defect image by adopting a rectangular frame based on the preset points to obtain a plurality of target detection regions, wherein each target detection region comprises one preset point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210655193.9A CN114965487B (en) | 2022-06-10 | 2022-06-10 | Calibration method and device of automatic monitoring equipment for tunnel typical damage |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210655193.9A CN114965487B (en) | 2022-06-10 | 2022-06-10 | Calibration method and device of automatic monitoring equipment for tunnel typical damage |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114965487A CN114965487A (en) | 2022-08-30 |
CN114965487B true CN114965487B (en) | 2024-06-14 |
Family
ID=82962290
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210655193.9A Active CN114965487B (en) | 2022-06-10 | 2022-06-10 | Calibration method and device of automatic monitoring equipment for tunnel typical damage |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114965487B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110111322A (en) * | 2019-05-13 | 2019-08-09 | 招商局重庆交通科研设计院有限公司 | A kind of tunnel defect identifying system based on image |
CN111812065A (en) * | 2020-06-28 | 2020-10-23 | 上海识湛智能科技有限公司 | Method for detecting material light transmittance in plastic laser welding |
Family Cites Families (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4080514B2 (en) * | 2006-07-27 | 2008-04-23 | シャープ株式会社 | Inspection device, inspection method, inspection program, and computer-readable recording medium |
CZ305330B6 (en) * | 2010-11-19 | 2015-08-05 | tarman Stanislav Ĺ | Test equipment for detection of defects in rotary metal bodies by a magnetic powder method |
CN102679914B (en) * | 2012-05-14 | 2014-08-13 | 同济大学 | Method and device for measuring percolating water area of shield tunnel lining segment |
JP6627389B2 (en) * | 2015-10-06 | 2020-01-08 | 大同特殊鋼株式会社 | Flaw detection method and flaw detection device |
CN109087291B (en) * | 2018-07-26 | 2021-08-27 | 杭州国翌科技有限公司 | Tunnel position information base establishing method and tunnel defect positioning method |
CN109615649A (en) * | 2018-10-31 | 2019-04-12 | 阿里巴巴集团控股有限公司 | A kind of image labeling method, apparatus and system |
CN109827833B (en) * | 2019-03-21 | 2021-03-16 | 招商局重庆交通科研设计院有限公司 | Preparation method of experimental test piece for water seepage characteristic of cracked tunnel lining structure |
CN110033407B (en) * | 2019-03-29 | 2020-10-30 | 华中科技大学 | Shield tunnel surface image calibration method, splicing method and splicing system |
CN110334727B (en) * | 2019-04-30 | 2021-04-27 | 国家电网有限公司 | Intelligent matching detection method for tunnel cracks |
CN110455821A (en) * | 2019-07-03 | 2019-11-15 | 南京理工大学 | Vcehicular tunnel and the apparent disease automatic checkout system device and method of subway tunnel |
CN111160301B (en) * | 2019-12-31 | 2023-04-18 | 同济大学 | Tunnel disease target intelligent identification and extraction method based on machine vision |
CN111415344B (en) * | 2020-03-19 | 2023-06-20 | 北京城建勘测设计研究院有限责任公司 | Disease detection method and device for horseshoe-shaped tunnel |
CN111507971A (en) * | 2020-04-20 | 2020-08-07 | 南京航空航天大学 | Tunnel surface defect detection method |
CN111562220A (en) * | 2020-06-02 | 2020-08-21 | 吉林大学 | Rapid and intelligent detection method for bridge diseases |
CN112215203A (en) * | 2020-11-02 | 2021-01-12 | 坝道工程医院(平舆) | Pavement disease detection method and device based on deep learning |
CN112964724B (en) * | 2021-02-01 | 2024-02-20 | 苏州百迈半导体技术有限公司 | Multi-target multi-region visual detection method and detection system |
CN113063795B (en) * | 2021-03-31 | 2024-02-02 | 辽宁省交通规划设计院有限责任公司 | Expressway tunnel defect position determining method and system |
CN113538385B (en) * | 2021-07-21 | 2022-10-25 | 上海勘察设计研究院(集团)有限公司 | Tunnel apparent disease type and grade discrimination method based on deep learning |
CN113820328A (en) * | 2021-09-23 | 2021-12-21 | 广州利科科技有限公司 | Tunnel disease detection method and tunnel disease detection device based on laser detection |
CN114018932B (en) * | 2021-11-02 | 2023-05-30 | 西安电子科技大学 | Pavement disease index measurement method based on rectangular calibration object |
CN114113118B (en) * | 2021-12-01 | 2023-10-13 | 同济大学 | Rapid detection device and detection method for subway tunnel lining crack leakage water disease |
CN114109072B (en) * | 2022-01-27 | 2022-05-24 | 山东建筑大学 | Comprehensive quantitative detection and repair process for surface cracks of underground structure |
-
2022
- 2022-06-10 CN CN202210655193.9A patent/CN114965487B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110111322A (en) * | 2019-05-13 | 2019-08-09 | 招商局重庆交通科研设计院有限公司 | A kind of tunnel defect identifying system based on image |
CN111812065A (en) * | 2020-06-28 | 2020-10-23 | 上海识湛智能科技有限公司 | Method for detecting material light transmittance in plastic laser welding |
Also Published As
Publication number | Publication date |
---|---|
CN114965487A (en) | 2022-08-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108918542B (en) | Optical cable surface defect detection device and method | |
JP7262614B2 (en) | POSITIONING METHOD, POSITIONING DEVICE, AND STORAGE MEDIUM | |
CN111383429A (en) | Method, system, device and storage medium for detecting dress of workers in construction site | |
CN103051872B (en) | Based on the belt deflection detection method of Edge extraction | |
CN102673106A (en) | Silk screen print positioning equipment and method for photovoltaic solar silicon chip | |
CN111899288A (en) | Tunnel leakage water area detection and identification method based on infrared and visible light image fusion | |
CN103345755A (en) | Chessboard angular point sub-pixel extraction method based on Harris operator | |
CN112801947A (en) | Visual detection method for dead pixel of LED display terminal | |
CN112526391A (en) | Electrolytic cell fault detection system and method | |
CN110646434A (en) | Device and method for automatically monitoring dam damage deformation in real time through video | |
CN110910372A (en) | Deep convolutional neural network-based uniform light plate defect detection method | |
CN113763484A (en) | Ship target positioning and speed estimation method based on video image analysis technology | |
Kargah-Ostadi et al. | Evaluation framework for automated pavement distress identification and quantification applications | |
CN109544513A (en) | A kind of steel pipe end surface defect extraction knowledge method for distinguishing | |
CN111476785A (en) | Night infrared light-reflecting water gauge detection method based on position recording | |
CN114965487B (en) | Calibration method and device of automatic monitoring equipment for tunnel typical damage | |
CN204718967U (en) | The accurate disposal system of image in a kind of chemical fiber paper tube outward appearance testing process | |
CN116883433B (en) | Photovoltaic module surface temperature distribution real-time monitoring system | |
CN112461845A (en) | Solar cell panel rainbow texture detection method based on double-light integration | |
CN111161264B (en) | Method for segmenting TFT circuit image with defects | |
CN111307267A (en) | Conductor galloping monitoring method based on concentric circle detection | |
CN112257514B (en) | Infrared vision intelligent detection shooting method for equipment fault inspection | |
CN116934852A (en) | Lattice type slope protection monitoring system and method based on deep learning | |
CN116344378A (en) | Intelligent detection system for photovoltaic panel production and detection method thereof | |
CN110216082A (en) | The recognition methods of fluorescent marker seed dynamics and system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |