CN111507971A - Tunnel surface defect detection method - Google Patents
Tunnel surface defect detection method Download PDFInfo
- Publication number
- CN111507971A CN111507971A CN202010311648.6A CN202010311648A CN111507971A CN 111507971 A CN111507971 A CN 111507971A CN 202010311648 A CN202010311648 A CN 202010311648A CN 111507971 A CN111507971 A CN 111507971A
- Authority
- CN
- China
- Prior art keywords
- image
- cta
- tunnel
- area
- value
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Abstract
The invention discloses a tunnel surface defect detection method, which comprises the following steps: reading in an apparent image of the tunnel, and performing image preprocessing; accurately identifying the cracks through combination of a CTA (computed tomography angiography) measurement algorithm and edge detection based on the crack image characteristics; according to the characteristics of the water leakage image, an improved CTA algorithm is adopted, and a morphological processing method is combined to realize the identification and the positioning of the water leakage of the tunnel structure; and outputting the recognition effect image. The method can effectively identify the apparent tunnel diseases, simultaneously weaken cable interference and influence caused by illumination change, effectively make up for the defects of time consumption, labor consumption and strong subjectivity of manual detection of the tunnel surface, simultaneously improve the detection accuracy, improve the engineering efficiency and provide an effective means for tunnel quality safety detection.
Description
Technical Field
The invention relates to a detection method, in particular to a tunnel surface defect detection method, and belongs to the technical field of tunnel apparent disease detection.
Background
In recent years, with the increasing of the country to the investment of infrastructure, the traffic construction business of China has been developed rapidly, wherein the underground traffic construction business is particularly prominent, and the construction of subway tunnels plays a vital role therein. At present, China becomes the country with the most tunnel projects, the most complex tunnel projects and the fastest development in the world. The tunnel is a semi-hidden project built in underground geotechnical media, and many diseases have appeared after years of operation of the tunnel built in different periods and under different technical conditions, and common tunnel diseases comprise: deformation, cracks, water leakage, slab staggering, block dropping, collapse, base grout turning, mud pumping, sinking, bottom bulging, lining back cavity and the like, which bring great potential safety hazards to the operation of the tunnel, wherein the cracks and the water leakage are the two most common and serious defects of the tunnel.
At present, the detection of cracks and water leakage diseases of subway tunnels in China is mainly manually carried out on-site recording and disease marking. Finally, a disease development diagram of the tunnel vault is drawn by workers, a traffic road needs to be closed during detection, efficiency is low, the detection method needs a large amount of manpower and physics, the danger degree is high, special lifting equipment is needed for tunnel vault detection, the detection result subjectivity is high, different detection personnel can obtain different results, and most of safety evaluation on a tunnel lining structure is qualitative description. Foreign research institutions have developed different types of tunnel disease detection vehicles, but the monitoring index is single, the precision is lower, the requirements of tunnel disease detection on light are higher, the existing equipment cannot well meet the illumination requirements, and the shadow has great influence on the detection precision.
Therefore, the invention is needed to invent a detection method capable of simultaneously detecting the tunnel cracks and the water leakage diseases, and the requirements of illumination and detection precision can be met.
Disclosure of Invention
The invention aims to provide a tunnel surface defect detection method, which improves the efficiency of tunnel surface detection.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a tunnel surface defect detection method is characterized by comprising the following steps:
the method comprises the following steps: reading in an apparent image of the tunnel, and performing image preprocessing;
step two: accurately identifying the cracks through combination of a CTA (computed tomography angiography) measurement algorithm and edge detection based on the crack image characteristics;
step three: according to the characteristics of the water leakage image, an improved CTA algorithm is adopted, and a morphological processing method is combined to realize the identification and the positioning of the water leakage of the tunnel structure;
step four: and outputting the recognition effect image.
Further, the step one is specifically
1.1, preprocessing an image by adopting Gaussian low-pass filtering to reduce the influence of particles, dust and the like of a tunnel lining fireproof layer on a subsequent recognition effect; wherein the original Image is recorded as ImageOrg, and the preprocessed Image is recorded as Image;
1.2, the preprocessed image is processed in a blocking mode, and the size of the area is set.
Further, the second step is specifically
2.1 selecting an ROI area, calculating a CTA value of the image, setting the cumulative distribution value larger than th as 1 by using a CTA value probability density distribution function, and otherwise, setting the cumulative distribution value as 0 and marking as CTA _ ROI;
2.2, acquiring the edge of the image in the ROI area by using a Sobel edge detection method; performing morphological expansion on the edge detection result, wherein the size of a morphological structural element can be obtained by calculating the width of a crack boundary, and an image obtained through the expansion is marked as a Sobel _ ROI;
2.3 calculating the correlation between CTA _ ROI and Sobel _ ROI;
2.4 if the correlation calculated in 2.3 is greater than th2, set the value of ROI area to CTA _ ROI, otherwise 0;
2.5 traversing the Image according to the size of the area set in the step 2.3, and obtaining an Image ImageBw by using 2.1-2.4;
and 2.6, refining the obtained ImageBw and proposing interference.
Further, the method for calculating the correlation between the CTA _ ROI and the Sobel _ ROI in 2.3 is as follows
coef=S/(M*N)
Wherein M and N are the height and width of the ROI respectively; s is the statistical sum of points with the same value.
Further, the 2.6 is specifically
2.6.1 removing a region with a smaller area for the binary image ImageBw obtained by 2.5, and then communicating the length-width ratio of the region and the gray level change characteristics of a crack region to remove the interference of pipelines or noise;
2.6.2 connecting and thinning the cracks, and connecting the cracks with similar angles and closer distances.
Further, the 2.6.1 specifically includes obtaining an external ellipse of each connected region, if the connected region is not a single branch, segmenting the region according to nodes to obtain the length and the width of the region, and if the length is short or the length-width ratio is small, determining that the region is not a crack; then, other interferences are removed by utilizing the characteristics that the surface of the crack is darker than that of normal concrete and the gray level change is quicker; secondly, linear interferences such as pipelines and the like are removed by utilizing the characteristics of dark crack area, bright periphery and small brightness difference of two sides.
Further, the 2.6.2 specifically is that in the connection process, the end point of the crack is used as a starting point to extend to two ends, the 2.1-2.4 is used to identify the local part, the crack position is obtained, and for the interference area, the deleted area in the 2.6.1 is used to further remove.
Further, the third step is specifically
3.1 calculating a gradient image of the image to be segmented, and overlapping the original image and the gradient image to form a detail enhanced image;
3.2, image segmentation is carried out on the non-leakage area and the leakage area by using improved CTA according to the characteristics of the leakage area;
3.3 calculating CTA value of each pixel in the image to form a CTA matrix; performing double-threshold division processing on the CTA matrix to obtain a segmentation image of a water leakage area and a water non-leakage area;
and 3.4, performing morphological treatment on the image subjected to CTA threshold treatment, removing the miscellaneous points with smaller area, and performing smooth treatment on the boundary to obtain the leakage water disease area.
Further, 3.2 is specifically
3.2.1 in the region detection, the criterion for the formation of the CTA value is rewritten as:
wherein:
in the formula, m is the number of directions; vi is the average value of the gray values in the ith direction; σ i is the ith direction gray value variance;feature vectors in the ith direction; xlIn m directionsThe feature vector of (2);the conditional probability value of the ith direction; v, sigma is the mean value and variance of the gray value of the square area;
3.2.2 according to the local information surrounded by the square, the average characteristic attribute is dynamically adjusted, the segmentation of the region is completed, and the dependence on the global characteristic attribute of the image does not exist.
Compared with the prior art, the invention has the following advantages and effects: the method can effectively identify the apparent tunnel diseases, simultaneously weaken cable interference and influence caused by illumination change, effectively make up for the defects of time consumption, labor consumption and strong subjectivity of manual detection of the tunnel surface, simultaneously improve the detection accuracy, improve the engineering efficiency and provide an effective means for tunnel quality safety detection.
Drawings
FIG. 1 is a flow chart of a method for detecting defects on a tunnel surface according to the present invention.
FIG. 2 is a schematic illustration of a tunnel crack defect in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of a tunnel water leakage defect according to an embodiment of the present invention;
FIG. 4 is a schematic illustration of an input image identifying a crack according to an embodiment of the invention;
FIG. 5 is a schematic illustration of crack block identification effects according to an embodiment of the invention;
FIG. 6 is a schematic diagram of the local crack identification effect according to the embodiment of the invention;
FIG. 7 is a schematic diagram illustrating the effect of the interference removal of crack identification according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of the final crack identification effect according to an embodiment of the invention;
fig. 9 is a schematic diagram of a leakage water detection input image according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of a gradient image of leakage water according to an embodiment of the present invention;
FIG. 11 is a schematic diagram of an original image of leakage water superimposed with a gradient image according to an embodiment of the present invention;
FIG. 12 is an improved CTA process result image according to an embodiment of the invention;
fig. 13 is a water leakage recognition result image according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following drawings and specific embodiments, it being understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention.
As shown in fig. 1, the tunnel surface defect detection method of the present invention can automatically identify and detect the lining cracks and water leakage defects in the tunnel, as shown in fig. 2 and 3, effectively make up for the time-consuming and labor-consuming disadvantage of manually detecting the tunnel surface defects, and improve the detection accuracy. The method comprises the following steps:
s1: and reading the apparent tunnel image and performing image preprocessing.
1.1, preprocessing an original image by adopting Gaussian low-pass filtering, wherein the original image is shown in FIG. 4, so that the influence of particles, dust and the like of a tunnel lining fireproof layer on a subsequent identification effect is reduced; the original Image is recorded as ImageOrg, and the preprocessed Image is recorded as Image.
1.2 due to the problems of variable actual tunnel environment, light supplement and the like, the illumination of an image is not uniform; the threshold value is set to satisfy the problem of image variability, and the image needs to be subjected to blocking processing. After a number of experiments, a 50 x 50(pixel) sized region was used in this example.
S2: accurately identifying the cracks through combination of a CTA (computed tomography angiography) measurement algorithm and edge detection based on the crack image characteristics;
2.1 select ROI (region Of interest) region, calculate CTA value Of image, and according to the feature that the number Of pixels in the image Of the crack is small and CTA value on the crack is large, use CTA value probability density distribution function to set the cumulative distribution value greater than th (in this example, th is set to 0.75) as 1, otherwise set to 0, and mark as CTA _ ROI.
2.2 by using Sobel edge detection method, obtaining the edge of the image in the ROI, where the crack is actually a long and narrow region defect, and the edge detection only obtains the boundary, and the CTA value calculates the whole region, if comparing the two, the edge detection result needs to be morphologically expanded, and the morphological structure element size can be obtained by calculating the crack boundary width. The image after dilation was designated as Sobel _ ROI.
2.3 calculate the correlation of CTA _ ROI and Sobel _ ROI. The correlation calculation method is as follows:
coef=S/(M*N)
in the formula: m and N are respectively the height and width of the ROI area; s is the statistical sum of points with the same value.
2.4 if coef calculated in step S23 is greater than th2, the value of ROI region is set to CTA _ ROI, otherwise 0 (i.e. target is 1, background is 0). The value of th2 is set to 0.5, and because the background is particularly complex, if the value of th2 is large, disease information will be filtered out, and serious influence is caused on disease identification; meanwhile, the area of the sub-image containing a small target is also set to 0.
2.5 traversing Image according to the size of the region size set in step S23, and obtaining an Image ImageBw by steps S21 to S24, as shown in fig. 5.
2.6, thinning the obtained ImageBw and eliminating interference.
Because ImageBw is a binary image and has a large amount of noise, the image needs to be morphologically processed to obtain a final effect image, and the method is as follows:
2.6.1 for the binary image ImageBw obtained in the step 2.5, firstly, obtaining an external ellipse of each connected region, if the connected region is not a single branch, segmenting the region according to nodes to obtain the length and the width of the region, and if the length is shorter or the length-width ratio is smaller, judging the region not to be a crack; then, other interferences are removed by utilizing the characteristics that the surface of the crack is darker than that of normal concrete and the gray level change is quicker; secondly, linear interference of pipelines and the like is removed by utilizing the characteristic that the gray scale of a crack region is canyon type, namely the crack region is dark, the periphery is bright and the brightness difference value of the two sides is small.
2.6.2 joining and thinning the cracks. And connecting the cracks with close angles and distances.
In the connection process, the end point of the crack is used as a starting point to extend to the two ends, the local part can be identified by using the steps 2.1-2.4, the crack position is obtained, and the deleted region in the step 2.6.1 can be used for further removing the interference region. The darker area in the center of the identified area is further extracted, and the final crack identification position can be obtained, as shown in fig. 7.
S3: according to the characteristics of the water leakage image, an improved CTA algorithm is adopted, and a morphological processing method is combined to realize the identification and the positioning of the water leakage of the tunnel structure.
Considering that the characteristics of the lining surface area polluted by the leakage water are different from those of the lining surface area not polluted by the leakage water, the characteristic that the leakage water area presents a block shape and the obvious directivity of pixels of the leakage water area relative to the uncontaminated area are reflected, the embodiment adopts an improved CTA algorithm to quickly identify the leakage water area of the image, and the identification method comprises the following steps:
3.1 calculating the gradient image of the image to be segmented as shown in FIG. 9 and the gradient image as shown in FIG. 10, and overlapping the original image and the gradient image as shown in FIG. 11 to form a detail enhanced image.
3.2 extracting a certain pixel point P in the image, considering that the pixel point is taken as the center, the half width is taken as d, the square area taking 2 × d +1 as the side length respectively considers the characteristics of the pixel points contained in the square in m directions (0 degree, 45 degrees, 90 degrees and 135 degrees can be taken), and the characteristics are compared with the average characteristic attribute of all the pixel characteristics of the area where the square is located, according to the condition that the area pixel which is not polluted by the leakage water has an unobvious direction, and the area pixel which is polluted by the leakage water has the characteristic of more obvious directivity, the segmentation of the non-leakage water area and the leakage water area can be realized.
In the region detection, the criterion for the formation of the CTA value is rewritten as:
wherein:
in the formula: m is the number of directions; vi is the average value of the gray values in the ith direction; σ i is the ith direction gray value variance;feature vectors in the ith direction; xlFeature vectors in m directions;the conditional probability value of the ith direction; v, sigma is the mean value and variance of the gray values of the square area.
When the current pixel P has strong directivity, thenThe direction corresponding to the value is the direction of the current pixel, and the value is smaller, and the variance is larger, so the CTA value of the pixel is smaller; if the current pixel P does not haveStrong directivity, thenThe value is larger while the variance is smaller, the CTA value has a larger value.
According to the local information surrounded by the square, the average characteristic attribute is dynamically adjusted, the segmentation of the region can be completed, and the dependence on the global characteristic attribute of the image does not exist.
3.3 calculating CTA value of each pixel in the image to form a CTA matrix; the CTA matrix is subjected to a dual threshold partition process to obtain a segmented image of the leaked water region and the non-leaked water region, as shown in fig. 12.
3.4 morphological treatment is carried out on the image after CTA threshold treatment, the image is firstly corroded, then morphological expansion is carried out, the miscellaneous points with smaller area are removed, and the boundary is smoothened, so that the leakage water disease area can be obtained, as shown in figure 13.
S4: and outputting the recognition effect image.
From the above description, the system of the present embodiment analyzes the image characteristics of the tunnel crack and the water leakage fault; based on the crack image characteristics, the crack can be accurately identified through the combination of a CTA (computed tomography angiography) measurement algorithm and edge detection; according to the characteristics of the water leakage image, the improved CTA algorithm is adopted, and a morphological processing method is combined, so that the identification and the positioning of the tunnel water leakage can be realized.
By applying the technical scheme described in the embodiment, apparent tunnel diseases can be effectively identified, cable interference and influence caused by illumination change are reduced, the defects of time consumption, labor consumption and strong subjectivity in manual detection of the tunnel surface are effectively overcome, the detection accuracy is improved, the engineering efficiency is improved, and an effective means is provided for tunnel quality safety detection.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a mobile terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments illustrated in the drawings, the present invention is not limited to the embodiments, which are illustrative rather than restrictive, and it will be apparent to those skilled in the art that many more modifications and variations can be made without departing from the spirit of the invention and the scope of the appended claims.
Claims (9)
1. A tunnel surface defect detection method is characterized by comprising the following steps:
the method comprises the following steps: reading in an apparent image of the tunnel, and performing image preprocessing;
step two: accurately identifying the cracks through combination of a CTA (computed tomography angiography) measurement algorithm and edge detection based on the crack image characteristics;
step three: according to the characteristics of the water leakage image, an improved CTA algorithm is adopted, and a morphological processing method is combined to realize the identification and the positioning of the water leakage of the tunnel structure;
step four: and outputting the recognition effect image.
2. A tunnel surface defect inspection method according to claim 1, characterized in that: the step one is specifically
1.1, preprocessing an image by adopting Gaussian low-pass filtering to reduce the influence of particles, dust and the like of a tunnel lining fireproof layer on a subsequent recognition effect; wherein the original Image is recorded as ImageOrg, and the preprocessed Image is recorded as Image;
1.2, the preprocessed image is processed in a blocking mode, and the size of the area is set.
3. A tunnel surface defect inspection method according to claim 1, characterized in that: the second step is specifically that
2.1 selecting an ROI area, calculating a CTA value of the image, setting the cumulative distribution value larger than th as 1 by using a CTA value probability density distribution function, and otherwise, setting the cumulative distribution value as 0 and marking as CTA _ ROI;
2.2, acquiring the edge of the image in the ROI area by using a Sobel edge detection method; performing morphological expansion on the edge detection result, wherein the size of a morphological structural element can be obtained by calculating the width of a crack boundary, and an image obtained through the expansion is marked as a Sobel _ ROI;
2.3 calculating the correlation between CTA _ ROI and Sobel _ ROI;
2.4 if the correlation calculated in 2.3 is greater than th2, set the value of ROI area to CTA _ ROI, otherwise 0;
2.5 traversing the Image according to the size of the area set in the step 2.3, and obtaining an Image ImageBw by using 2.1-2.4;
and 2.6, refining the obtained ImageBw and proposing interference.
4. A tunnel surface defect inspection method according to claim 3, wherein: the method for calculating the correlation between CTA _ ROI and Sobel _ ROI in 2.3 is as follows
coef=S/(M*N)
Wherein M and N are the height and width of the ROI respectively; s is the statistical sum of points with the same value.
5. A tunnel surface defect inspection method according to claim 3, wherein: said 2.6 is specifically
2.6.1 removing a region with a smaller area for the binary image ImageBw obtained by 2.5, and then communicating the length-width ratio of the region and the gray level change characteristics of a crack region to remove the interference of pipelines or noise;
2.6.2 connecting and thinning the cracks, and connecting the cracks with similar angles and closer distances.
6. A tunnel surface defect inspection method according to claim 5, wherein: 2.6.1, firstly, acquiring an external ellipse of each connected region, if the connected region is not a single branch, segmenting the region according to nodes to acquire the length and the width of the region, and if the length is shorter or the length-width ratio is smaller, determining that the region is not a crack; then, other interferences are removed by utilizing the characteristics that the surface of the crack is darker than that of normal concrete and the gray level change is quicker; secondly, linear interferences such as pipelines and the like are removed by utilizing the characteristics of dark crack area, bright periphery and small brightness difference of two sides.
7. A tunnel surface defect inspection method according to claim 5, wherein: and 2.6.2 specifically, in the connection process, extending from the end point of the crack to two ends, identifying the local part by using 2.1-2.4 to obtain the position of the crack, and further removing the deleted region in 2.6.1 for the interference region.
8. A tunnel surface defect inspection method according to claim 1, characterized in that: the third step is specifically that
3.1 calculating a gradient image of the image to be segmented, and overlapping the original image and the gradient image to form a detail enhanced image;
3.2, image segmentation is carried out on the non-leakage area and the leakage area by using improved CTA according to the characteristics of the leakage area;
3.3 calculating CTA value of each pixel in the image to form a CTA matrix; performing double-threshold division processing on the CTA matrix to obtain a segmentation image of a water leakage area and a water non-leakage area;
and 3.4, performing morphological treatment on the image subjected to CTA threshold treatment, removing the miscellaneous points with smaller area, and performing smooth treatment on the boundary to obtain the leakage water disease area.
9. A tunnel surface defect inspection method according to claim 8, wherein: the 3.2 is specifically
3.2.1 in the region detection, the criterion for the formation of the CTA value is rewritten as:
wherein:
in the formula, m is the number of directions; vi is the average value of the gray values in the ith direction; σ i is the ith direction gray value variance;feature vectors in the ith direction; xlFeature vectors in m directions;the conditional probability value of the ith direction; v, sigma is the mean value and variance of the gray value of the square area;
3.2.2 according to the local information surrounded by the square, the average characteristic attribute is dynamically adjusted, the segmentation of the region is completed, and the dependence on the global characteristic attribute of the image does not exist.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010311648.6A CN111507971A (en) | 2020-04-20 | 2020-04-20 | Tunnel surface defect detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010311648.6A CN111507971A (en) | 2020-04-20 | 2020-04-20 | Tunnel surface defect detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111507971A true CN111507971A (en) | 2020-08-07 |
Family
ID=71864785
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010311648.6A Withdrawn CN111507971A (en) | 2020-04-20 | 2020-04-20 | Tunnel surface defect detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111507971A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112113978A (en) * | 2020-09-22 | 2020-12-22 | 成都国铁电气设备有限公司 | Vehicle-mounted tunnel defect online detection system and method based on deep learning |
CN112435228A (en) * | 2020-11-19 | 2021-03-02 | 中国民航大学 | Airport pavement crack detection method based on high-density anisotropic characteristics |
CN113239432A (en) * | 2021-05-07 | 2021-08-10 | 石家庄铁道大学 | Regional block detection recommendation method for panoramic image of subway tunnel |
CN113763357A (en) * | 2021-09-08 | 2021-12-07 | 中国矿业大学 | Mining area ground crack accurate identification and continuous extraction method based on visible light image |
CN113960049A (en) * | 2021-10-19 | 2022-01-21 | 中南大学 | Tunnel surface disease detection device and detection method |
CN117392126A (en) * | 2023-12-08 | 2024-01-12 | 四川省水利科学研究院 | Hydraulic tunnel defect detection method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106053475A (en) * | 2016-05-24 | 2016-10-26 | 浙江工业大学 | Tunnel disease full-section dynamic rapid detection device based on active panoramic vision |
CN106504246A (en) * | 2016-11-08 | 2017-03-15 | 太原科技大学 | The image processing method of tunnel slot detection |
CN107154040A (en) * | 2017-05-08 | 2017-09-12 | 重庆邮电大学 | A kind of tunnel-liner surface image crack detection method |
CN107862677A (en) * | 2017-10-16 | 2018-03-30 | 中铁第四勘察设计院集团有限公司 | The Tunnel Lining Cracks recognition methods of thresholding algorithm and system between a kind of class based on gradient |
CN109697717A (en) * | 2018-12-20 | 2019-04-30 | 上海同岩土木工程科技股份有限公司 | A kind of Lining Crack recognition methods searched for automatically based on image |
CN109767426A (en) * | 2018-12-13 | 2019-05-17 | 同济大学 | A kind of shield tunnel percolating water detection method based on characteristics of image identification |
CN110044924A (en) * | 2019-05-13 | 2019-07-23 | 招商局重庆交通科研设计院有限公司 | A kind of vcehicular tunnel Defect inspection method based on image |
CN110378950A (en) * | 2019-06-18 | 2019-10-25 | 上海同岩土木工程科技股份有限公司 | A kind of tunnel structure crack identification method merged based on gray scale and gradient |
-
2020
- 2020-04-20 CN CN202010311648.6A patent/CN111507971A/en not_active Withdrawn
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106053475A (en) * | 2016-05-24 | 2016-10-26 | 浙江工业大学 | Tunnel disease full-section dynamic rapid detection device based on active panoramic vision |
CN106504246A (en) * | 2016-11-08 | 2017-03-15 | 太原科技大学 | The image processing method of tunnel slot detection |
CN107154040A (en) * | 2017-05-08 | 2017-09-12 | 重庆邮电大学 | A kind of tunnel-liner surface image crack detection method |
CN107862677A (en) * | 2017-10-16 | 2018-03-30 | 中铁第四勘察设计院集团有限公司 | The Tunnel Lining Cracks recognition methods of thresholding algorithm and system between a kind of class based on gradient |
CN109767426A (en) * | 2018-12-13 | 2019-05-17 | 同济大学 | A kind of shield tunnel percolating water detection method based on characteristics of image identification |
CN109697717A (en) * | 2018-12-20 | 2019-04-30 | 上海同岩土木工程科技股份有限公司 | A kind of Lining Crack recognition methods searched for automatically based on image |
CN110044924A (en) * | 2019-05-13 | 2019-07-23 | 招商局重庆交通科研设计院有限公司 | A kind of vcehicular tunnel Defect inspection method based on image |
CN110378950A (en) * | 2019-06-18 | 2019-10-25 | 上海同岩土木工程科技股份有限公司 | A kind of tunnel structure crack identification method merged based on gray scale and gradient |
Non-Patent Citations (1)
Title |
---|
何国华 等: "基于数字图像的隧道表观病害识别方法研究", 《重庆交通大学学报(自然科学版)》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112113978A (en) * | 2020-09-22 | 2020-12-22 | 成都国铁电气设备有限公司 | Vehicle-mounted tunnel defect online detection system and method based on deep learning |
CN112435228A (en) * | 2020-11-19 | 2021-03-02 | 中国民航大学 | Airport pavement crack detection method based on high-density anisotropic characteristics |
CN113239432A (en) * | 2021-05-07 | 2021-08-10 | 石家庄铁道大学 | Regional block detection recommendation method for panoramic image of subway tunnel |
CN113239432B (en) * | 2021-05-07 | 2022-06-10 | 石家庄铁道大学 | Regional block detection recommendation method for panoramic image of subway tunnel |
CN113763357A (en) * | 2021-09-08 | 2021-12-07 | 中国矿业大学 | Mining area ground crack accurate identification and continuous extraction method based on visible light image |
CN113763357B (en) * | 2021-09-08 | 2023-11-28 | 中国矿业大学 | Mining area ground crack accurate identification and continuous extraction method based on visible light image |
CN113960049A (en) * | 2021-10-19 | 2022-01-21 | 中南大学 | Tunnel surface disease detection device and detection method |
CN117392126A (en) * | 2023-12-08 | 2024-01-12 | 四川省水利科学研究院 | Hydraulic tunnel defect detection method |
CN117392126B (en) * | 2023-12-08 | 2024-03-15 | 四川省水利科学研究院 | Hydraulic tunnel defect detection method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111507971A (en) | Tunnel surface defect detection method | |
Lei et al. | A novel tunnel-lining crack recognition system based on digital image technology | |
Noh et al. | Automatic crack detection on concrete images using segmentation via fuzzy C-means clustering | |
Dorafshan et al. | Automatic surface crack detection in concrete structures using OTSU thresholding and morphological operations | |
Wang et al. | Towards an automated condition assessment framework of underground sewer pipes based on closed-circuit television (CCTV) images | |
CN112837290B (en) | Crack image automatic identification method based on seed filling algorithm | |
Yu et al. | Efficient crack detection method for tunnel lining surface cracks based on infrared images | |
Qu et al. | Lining seam elimination algorithm and surface crack detection in concrete tunnel lining | |
CN115345885A (en) | Method for detecting appearance quality of metal fitness equipment | |
CN111899288A (en) | Tunnel leakage water area detection and identification method based on infrared and visible light image fusion | |
Zhou et al. | Automatic sewer defect detection and severity quantification based on pixel-level semantic segmentation | |
Zuo et al. | Classifying cracks at sub-class level in closed circuit television sewer inspection videos | |
CN111402267A (en) | Segmentation method, device and terminal for epithelial cell nucleus in prostate cancer pathological image | |
Li et al. | A deep learning-based fine crack segmentation network on full-scale steel bridge images with complicated backgrounds | |
CN111767874B (en) | Pavement disease detection method based on deep learning | |
CN114882400A (en) | Aggregate detection and classification method based on AI intelligent machine vision technology | |
JP2000028541A (en) | Crack detection method for concrete surface | |
CN109767426B (en) | Shield tunnel water leakage detection method based on image feature recognition | |
Parrany et al. | A new image processing strategy for surface crack identification in building structures under non‐uniform illumination | |
CN110672632A (en) | Tunnel disease identification method | |
CN113610052A (en) | Tunnel water leakage automatic identification method based on deep learning | |
Gao et al. | Intelligent crack damage detection system in shield tunnel using combination of retinanet and optimal adaptive selection | |
CN110942026A (en) | Capsule robot drain pipe disease detection method and system based on deep learning | |
CN115541591A (en) | Method and system for detecting abrasion edge of carbon pantograph slider of train | |
CN115456973A (en) | Method, device and equipment for establishing leakage water disease detection and identification model |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200807 |