CN112164052B - Railway sleeper defect detection method based on terahertz imaging - Google Patents
Railway sleeper defect detection method based on terahertz imaging Download PDFInfo
- Publication number
- CN112164052B CN112164052B CN202011056628.5A CN202011056628A CN112164052B CN 112164052 B CN112164052 B CN 112164052B CN 202011056628 A CN202011056628 A CN 202011056628A CN 112164052 B CN112164052 B CN 112164052B
- Authority
- CN
- China
- Prior art keywords
- sleeper
- gray
- defect detection
- terahertz
- point
- 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
- 241001669679 Eleotris Species 0.000 title claims abstract description 64
- 230000007547 defect Effects 0.000 title claims abstract description 55
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 238000003384 imaging method Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000003708 edge detection Methods 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims description 9
- 208000020673 hypertrichosis-acromegaloid facial appearance syndrome Diseases 0.000 claims description 6
- 238000006073 displacement reaction Methods 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a railway sleeper defect detection method based on terahertz imaging, which comprises the steps of scanning a railway sleeper to be detected by utilizing a terahertz imaging device to generate a gray scale map; preprocessing the gray level image to obtain a processed gray level image; carrying out Sobel edge detection on the preprocessed gray level graph to obtain characteristic points of linear distribution of a sleeper boundary line; substituting the characteristic points linearly distributed on the boundary line of the sleeper into Hough linear detection to extract a sleeper area to be subjected to defect detection; and presetting a gray value matrix, comparing the sleeper area to be subjected to defect detection with the gray value matrix, and identifying the sleeper defect based on the gray correlation degree to obtain a sleeper defect judgment result. The method can solve the problems of low efficiency, high strength and insufficient safety of the rail defect detection method in the prior art, and has the advantages of high efficiency, strong accuracy, time saving and labor saving.
Description
Technical Field
The invention relates to the technical field of rail detection, in particular to a railway sleeper defect detection method based on terahertz imaging.
Background
In the long-term use process of the railway track, the surface of the track inevitably has defects of cracks, abrasion, flatness and the like, and sleepers along the track are damaged, peeled off and fallen. If the defects are not checked in time and the defective sleepers are repaired, serious traffic accidents can be caused. At present, although various types of rail detection vehicles have been developed, the rail detection vehicles are expensive and inconvenient to popularize on the whole road, so that the detection of the railway rail state in China is still mainly completed by a manual inspection mode at present, but the traditional manual detection method has the defects of high labor intensity, low working efficiency, easiness in influence of subjective consciousness of a detector on a final detection result and the like.
At present, more and more railway lines are provided with running motor train unit trains, and normal running of the motor train unit is required to be guaranteed, so that daily inspection of the railway lines is usually arranged to be carried out at midnight, workers feel fatigue more easily at the moment and are difficult to guarantee to obtain a reliable inspection result, and meanwhile, certain challenge is brought to detection of the finished track state within short skylight time.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the railway sleeper defect detection method based on terahertz imaging, which can solve the problems of low efficiency, high strength and insufficient safety of the rail defect detection method in the prior art.
In order to solve the technical problems, the invention adopts the following technical scheme:
the method for detecting the defects of the railway sleepers based on the terahertz imaging comprises the following steps:
s1, scanning the railway sleeper to be detected by using a terahertz imaging device to generate a gray scale image;
s2, preprocessing the gray-scale image to obtain a processed gray-scale image;
s3, carrying out Sobel edge detection on the preprocessed gray level image to obtain characteristic points of linear distribution of a sleeper boundary line;
s4, substituting the characteristic points linearly distributed on the boundary line of the sleeper into Hough linear detection, and extracting a sleeper area to be subjected to defect detection;
and S5, presetting a gray value matrix, comparing the sleeper area to be subjected to defect detection with the gray value matrix, and identifying the sleeper defect based on the gray correlation degree to obtain a sleeper defect judgment result.
The method for detecting the defects of the railway sleepers based on the terahertz imaging has the main beneficial effects that:
the terahertz imaging-based detection method is used as a non-contact detection method, and abrasion to a detection object in the detection process is avoided. The problems of unstable detection quality, high operation cost and the like in the conventional manual detection of defects can be well solved, and the method has the advantages of high speed and high precision. Because detect through terahertz imaging device, the automated processing level is higher, can greatly reduce railway personnel work load, discovers the sleeper defect problem as early as possible, improves and patrols and examines efficiency.
Drawings
FIG. 1 is a flow chart of a railway sleeper defect detection method based on terahertz imaging.
Fig. 2 is a structural model diagram of a terahertz imaging device.
Detailed Description
The invention will be further described with reference to the accompanying drawings in which:
as shown in fig. 1, it is a flowchart of the method for detecting railroad tie defects based on terahertz imaging according to the present invention.
The method for detecting the defects of the railway sleepers based on the terahertz imaging comprises the following steps:
s1, scanning the railway sleeper to be detected by using a terahertz imaging device to generate a gray scale image;
further, as shown in fig. 2, the terahertz imaging device includes a housing, and a controller in the housing, the controller is electrically connected to the terahertz continuous wave source arranged in the housing, the terahertz detector on the housing, and the electrically controlled displacement stage, respectively, and a lens is arranged on the housing at a position in front of the terahertz continuous wave source.
Preferably, the terahertz continuous wave source comprises a gunn diode.
Further, the method for generating the gray map comprises the following steps:
s1-1, the Gunn diode oscillates to generate terahertz waves, and the terahertz detector detects the reflected terahertz waves in a point-by-point scanning mode;
and S1-2, recording the intensity information of the terahertz waves reflected back to the detector from different point positions of the measured substance by the controller to generate a gray scale map.
The method does not need a time delay device and pause on a scanning point, so that the imaging speed is improved by many times compared with the spectral scanning imaging speed. The resolution of imaging is determined by terahertz ray focusing light spots, is millimeter-scale, and parameters of an optical system can be adjusted according to different requirements in actual use, so that the measurement accuracy is ensured.
And S2, preprocessing the gray-scale image to obtain a processed gray-scale image.
The method for preprocessing the gray-scale image comprises the following steps:
s2-1, carrying out high-frequency noise reduction on the gray-scale image through a spatial filtering algorithm, filtering out interference information, and obtaining the gray-scale image after noise reduction.
The spatial filtering algorithm comprises the following steps:
S2-1A, setting the size of a gray scale image f (x, y) to be processed as MxN and the size of a spatial filtering processing template as mxn;
S2-1B, taking each pixel point in the image as the center of the template, and processing each pixel point through a preset filtering rule, wherein the transformation formula is as follows:
wherein w (s, t) is the weight of each point in the template;
the processed value of each pixel point is determined by the surrounding m multiplied by n pixel points.
And S2-1C, for the edge of the gray scale image, the edge cannot be used as a pixel point of the center of the template, the processing is not carried out, and the original value is reserved. Therefore, the image after noise reduction is smoother, and less high-frequency noise is generated.
And S2-2, improving the contrast between the background and the target image in the gray-scale image by a gray-scale threshold method for the gray-scale image after noise reduction to obtain a preprocessed gray-scale image.
Specifically, the grayscale thresholding method includes:
setting the gray level T as a threshold value, wherein the value range is 0-255, then:
i.e. in the grey map f (x, y) the grey values are transformed to 255 if they are greater than T and to 0-T if they are less than T.
And S3, carrying out Sobel edge detection on the preprocessed gray level graph to obtain characteristic points of linear distribution of the sleeper boundary line.
The Sobel operator is a discrete difference operator, is a method for calculating approximate gradient of image gray, and has the basic idea that pixel points on the left side and the right side of a certain column in a gray image are subjected to difference, and as the gray value of an edge is obviously smaller or larger than surrounding pixel points, the difference results are obviously different, so that a vertical edge is extracted; similarly, the horizontal edge is extracted by performing the difference in the same manner after the pixel matrix is transposed.
Further, the method for obtaining the characteristic points of the sleeper boundary line straight line distribution comprises the following steps:
s3-1, obtaining gradient G in the image along the x and y directions through a Sobel operatorxAnd Gy:
Wherein S isxAnd SyIs a sobel convolution factor, and I is a gray value;
s3-2, calculating an approximate gradient and a gradient direction at each pixel of the image:
wherein G is an approximate gradient, and theta is a gradient direction angle;
s3-3, setting threshold GmaxIf at a certain pointGradient G is greater than GmaxIf the point is a boundary point, setting the point as a white point, otherwise, setting the point as a black point;
and S3-4, connecting the white points to obtain the boundary line of the sleeper and obtaining the characteristic points of the linear distribution of the boundary line of the sleeper.
And S4, substituting the characteristic points linearly distributed on the boundary line of the sleeper into the Hough linear detection, and extracting the sleeper area to be subjected to defect detection.
Further, the method for detecting the sleeper area to be detected with defects comprises the following steps:
s4-1, describing a straight line by adopting polar coordinates, and mapping points (x, y) in characteristic points of straight line distribution of a sleeper boundary line to a rho-theta parameter space:
ρ=xcosθ+ysinθ;
s4-2, setting the detected straight line in the first quadrant, passing through the point (m, n), and obtaining the value ranges of rho and theta by the linear polar coordinate equation:
wherein if and only if x and y are both maximum values and θ + Φ ± 90 ° are satisfied:
s4-3, enabling parameters of the Haff transform accumulator to correspond to the image size, randomly taking a theta value according to set precision, calculating a rho value, carrying out Haff transform on the image, storing a transform result in the Haff transform accumulator, and accumulating according to the theta and rho values to obtain collinear points;
s4-4, repeating the step S4-3 until theta takes all values to obtain the total number of collinear points;
s4-5, setting a threshold value, and obtaining an accurate boundary line of the sleeper when the number of collinear points is larger than the threshold value;
and S4-6, extracting a sleeper area to be subjected to defect detection according to the accurate boundary line of the sleeper.
And S5, presetting a gray value matrix, comparing the sleeper area to be subjected to defect detection with the gray value matrix, and identifying the sleeper defect based on the gray correlation degree to obtain a sleeper defect judgment result.
Further, the method for obtaining the sleeper defect judgment result comprises the following steps:
s5-1, setting the extracted data matrix to be tested as follows:
X={xi=(xi(1),xi(2),…,xi(n)),i=0,1,…,m},
the reference data matrix is:
Y={yi=(yi(1),yi(2),…,yi(n)),i=0,1,…,m},
s5-2, solving a first-order difference quotient, and finding the slope of the longitudinal data of the matrix at each point:
Δxi(k)=xi(k+1)-xi(k),k=1,2,…n-1;i=0,1,…,m,
Δyi(k)=yi(k+1)-yi(k),k=1,2,…n-1;i=0,1,…,m;
s5-3, calculating the correlation coefficient r of each longitudinal sequence0,i(k):
S5-4, calculating the relevance r of each longitudinal sequence0,i:
The association degree between each column of the data matrix to be detected and each column of the preset reference sequence can be obtained. And judging whether the sleeper is defective or not according to the grey correlation degree of each column.
S5-5, when r0,iWhen the value is lower than the preset value, the sleeper is indicated to have defects.
The closer the relevance is to 1, the greater the relevance between the column and the preset sequence is, if the relevance of a certain column is lower than the preset value, the defect of the sleeper is indicated, and the lower the relevance is, the more serious the defect is.
The above description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
Claims (10)
1. A railway sleeper defect detection method based on terahertz imaging is characterized by comprising the following steps:
s1, scanning the railway sleeper to be detected by using a terahertz imaging device to generate a gray scale image;
s2, preprocessing the gray scale image to obtain a preprocessed gray scale image;
s3, carrying out Sobel edge detection on the preprocessed gray level image to obtain characteristic points of linear distribution of a sleeper boundary line;
s4, substituting the characteristic points linearly distributed on the boundary line of the sleeper into Hough linear detection, and extracting a sleeper area to be subjected to defect detection;
and S5, presetting a gray value matrix, comparing the sleeper area to be subjected to defect detection with the gray value matrix, and identifying the sleeper defect based on the gray correlation degree to obtain a sleeper defect judgment result.
2. The railway sleeper defect detection method based on terahertz imaging is characterized in that the terahertz imaging device comprises a shell, a controller is arranged in the shell, the controller is respectively and electrically connected with a terahertz continuous wave source arranged in the shell, a terahertz detector arranged on the shell and an electric control displacement table, and a lens is arranged on the shell at the position on the front side of the terahertz continuous wave source.
3. The railroad tie defect detection method based on terahertz imaging according to claim 2, wherein the terahertz continuous wave source comprises a gunn diode.
4. The railroad tie defect detection method based on terahertz imaging according to claim 1, wherein the method for generating a gray scale map comprises:
s1-1, the Gunn diode oscillates to generate terahertz waves, and the terahertz detector detects the reflected terahertz waves in a point-by-point scanning mode;
and S1-2, recording the intensity information of the terahertz waves reflected back to the detector from different point positions of the measured substance by the controller to generate a gray scale map.
5. The railroad tie defect detection method based on terahertz imaging according to claim 1, wherein the method for preprocessing the gray scale map comprises:
s2-1, carrying out high-frequency noise reduction on the gray level image through a spatial filtering algorithm to obtain a noise-reduced gray level image;
and S2-2, improving the contrast between the background and the target image in the gray-scale image by a gray-scale threshold method for the gray-scale image after noise reduction to obtain a preprocessed gray-scale image.
6. The railroad tie defect detection method based on terahertz imaging according to claim 5, wherein the spatial filtering algorithm comprises:
S2-1A, setting the size of a gray scale image f (x, y) to be processed as MxN and the size of a spatial filtering processing template as mxn;
S2-1B, taking each pixel point in the image as the center of the template, and processing each pixel point through a preset filtering rule, wherein the transformation formula is as follows:
wherein w (s, t) is the weight of each point in the template;
S2-1C, for the edge of the gray scale image, the edge cannot be used as a pixel point of the center of the template, and the original value is reserved.
8. the railway sleeper defect detection method based on terahertz imaging according to claim 1, wherein the method for obtaining the characteristic points of sleeper boundary line straight line distribution comprises the following steps:
s3-1, obtaining gradient G in the image along the x and y directions through a Sobel operatorxAnd Gy:
Wherein S isxAnd SyIs a sobel convolution factor, and I is a gray value;
s3-2, calculating an approximate gradient and a gradient direction at each pixel of the image:
wherein G is an approximate gradient, and theta is a gradient direction angle;
s3-3, setting threshold GmaxIf the gradient G at a certain point is greater than GmaxIf the point is a boundary point, setting the point as a white point, otherwise, setting the point as a black point;
and S3-4, connecting the white points to obtain the boundary line of the sleeper and obtaining the characteristic points of the linear distribution of the boundary line of the sleeper.
9. The railway sleeper defect detection method based on terahertz imaging according to claim 1, wherein the method for extracting the sleeper region to be subjected to defect detection comprises the following steps:
s4-1, describing a straight line by adopting polar coordinates, and mapping points (x, y) in characteristic points of straight line distribution of a sleeper boundary line to a rho-theta parameter space:
ρ=xcosθ+ysinθ;
s4-2, setting the detected straight line in the first quadrant, passing through the points (M, N), and obtaining the value ranges of rho and theta by a straight line polar coordinate equation:
wherein if and only if x and y are both maximum values and θ + Φ ± 90 ° are satisfied:
s4-3, enabling parameters of the Haff transform accumulator to correspond to the image size, randomly taking a theta value according to set precision, calculating a rho value, carrying out Haff transform on the image, storing a transform result in the Haff transform accumulator, and accumulating according to the theta and rho values to obtain collinear points;
s4-4, repeating the step S4-3 until theta takes all values to obtain the total number of collinear points;
s4-5, setting a threshold value, and obtaining an accurate boundary line of the sleeper when the number of collinear points is larger than the threshold value;
and S4-6, extracting a sleeper area to be subjected to defect detection according to the accurate boundary line of the sleeper.
10. The railway sleeper defect detection method based on terahertz imaging according to claim 1, wherein the method for obtaining the sleeper defect judgment result comprises the following steps:
s5-1, setting a matrix of a sleeper area to be subjected to defect detection as follows:
X={xi=(xi(1),xi(2),…,xi(n)),i=0,1,…,m},
the gray value matrix is:
Y={yi=(yi(1),yi(2),…,yi(n)),i=0,1,…,m},
s5-2, solving a first-order difference quotient, and finding the slope of the longitudinal data of the matrix at each point:
Δxi(k)=xi(k+1)-xi(k),k=1,2,…n-1;i=0,1,…,m,
Δyi(k)=yi(k+1)-yi(k),k=1,2,…n-1;i=0,1,…,m;
s5-3, calculating the correlation coefficient r of each longitudinal sequence0,i(k):
S5-4, calculating the relevance r of each longitudinal sequence0,i:
S5-5, when r0,iWhen the value is lower than the preset value, the sleeper is indicated to have defects.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011056628.5A CN112164052B (en) | 2020-09-30 | 2020-09-30 | Railway sleeper defect detection method based on terahertz imaging |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011056628.5A CN112164052B (en) | 2020-09-30 | 2020-09-30 | Railway sleeper defect detection method based on terahertz imaging |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112164052A CN112164052A (en) | 2021-01-01 |
CN112164052B true CN112164052B (en) | 2021-10-15 |
Family
ID=73860831
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011056628.5A Active CN112164052B (en) | 2020-09-30 | 2020-09-30 | Railway sleeper defect detection method based on terahertz imaging |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112164052B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115436384A (en) * | 2022-11-07 | 2022-12-06 | 国网山东省电力公司荣成市供电公司 | Distribution box surface defect detection system and method based on unmanned aerial vehicle image |
CN116703920B (en) * | 2023-08-07 | 2023-10-20 | 济宁市华祥石墨制品有限公司 | Graphite thermal insulation barrel crack detection method based on image processing |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN206020324U (en) * | 2016-09-12 | 2017-03-15 | 国网天津市电力公司 | A kind of distribution transformer winding material the cannot-harm-detection device |
CN107356599A (en) * | 2017-06-23 | 2017-11-17 | 厦门大学 | A kind of Terahertz lossless detection method of ceramic matric composite |
CN107767369A (en) * | 2017-09-27 | 2018-03-06 | 杭州迈锐钶科技有限公司 | A kind of the defects of buret detection method and device |
CN107907547A (en) * | 2017-09-27 | 2018-04-13 | 杭州迈锐钶科技有限公司 | It is a kind of biomedicine buret the defects of detection method and device |
CN108974043A (en) * | 2018-08-09 | 2018-12-11 | 铁路愿景欧洲有限公司 | Railroad track survey system |
CN109671056A (en) * | 2018-12-03 | 2019-04-23 | 西安交通大学 | A kind of compound sleeper porosity defects detection method based on radioscopic image |
CN110223296A (en) * | 2019-07-08 | 2019-09-10 | 山东建筑大学 | A kind of screw-thread steel detection method of surface flaw and system based on machine vision |
CN110596142A (en) * | 2019-10-18 | 2019-12-20 | 云南电网有限责任公司电力科学研究院 | Terahertz imaging-based defect detection method and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4766897B2 (en) * | 2004-12-13 | 2011-09-07 | 株式会社東京精密 | Image defect inspection method, image defect inspection apparatus, and appearance inspection apparatus |
-
2020
- 2020-09-30 CN CN202011056628.5A patent/CN112164052B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN206020324U (en) * | 2016-09-12 | 2017-03-15 | 国网天津市电力公司 | A kind of distribution transformer winding material the cannot-harm-detection device |
CN107356599A (en) * | 2017-06-23 | 2017-11-17 | 厦门大学 | A kind of Terahertz lossless detection method of ceramic matric composite |
CN107767369A (en) * | 2017-09-27 | 2018-03-06 | 杭州迈锐钶科技有限公司 | A kind of the defects of buret detection method and device |
CN107907547A (en) * | 2017-09-27 | 2018-04-13 | 杭州迈锐钶科技有限公司 | It is a kind of biomedicine buret the defects of detection method and device |
CN108974043A (en) * | 2018-08-09 | 2018-12-11 | 铁路愿景欧洲有限公司 | Railroad track survey system |
CN109671056A (en) * | 2018-12-03 | 2019-04-23 | 西安交通大学 | A kind of compound sleeper porosity defects detection method based on radioscopic image |
CN110223296A (en) * | 2019-07-08 | 2019-09-10 | 山东建筑大学 | A kind of screw-thread steel detection method of surface flaw and system based on machine vision |
CN110596142A (en) * | 2019-10-18 | 2019-12-20 | 云南电网有限责任公司电力科学研究院 | Terahertz imaging-based defect detection method and system |
Non-Patent Citations (1)
Title |
---|
基于共生矩阵和霍夫变换的磨粒纹理提取及识别;王国亮;《中国优秀硕士学位论文全文数据库 信息科技辑》;20180315;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112164052A (en) | 2021-01-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111145161B (en) | Pavement crack digital image processing and identifying method | |
CN109754368B (en) | Crack splicing method in bridge quality detection | |
CN114757949B (en) | Wire and cable defect detection method and system based on computer vision | |
CN112164052B (en) | Railway sleeper defect detection method based on terahertz imaging | |
Jie et al. | Real-time rail head surface defect detection: A geometrical approach | |
CN110211101A (en) | A kind of rail surface defect rapid detection system and method | |
JP5287177B2 (en) | Trolley wire wear and displacement measuring device by image processing | |
Wang | Unsupervised recognition and characterization of the reflected laser lines for robotic gas metal arc welding | |
CN111369516A (en) | Transformer bushing heating defect detection method based on infrared image recognition | |
CN111754460A (en) | Method, system and storage medium for automatically detecting gap of point switch | |
CN115482195A (en) | Train part deformation detection method based on three-dimensional point cloud | |
CN108876771B (en) | Undercut welding defect detection method | |
CN115601359A (en) | Welding seam detection method and device | |
CN109614868A (en) | Automobile tire decorative pattern graph line identifying system | |
CN110322508B (en) | Auxiliary positioning method based on computer vision | |
CN116433527A (en) | Road surface laser line extraction device and method | |
JP4293653B2 (en) | Appearance inspection method | |
Khaliluzzaman et al. | Zebra-crossing detection based on geometric feature and vertical vanishing point | |
CN114266748B (en) | Method and device for judging surface integrity of process board in field of rail traffic overhaul | |
KR101637977B1 (en) | Feature point detecting method of welding joint using laser vision system | |
KR102519717B1 (en) | Apparatus and method for detecting welding bead with improved accuracy | |
KR102585146B1 (en) | Pothole detection device and method based on deep learning | |
CN114266719A (en) | Hough transform-based product detection method | |
CN109064417B (en) | Subway tunnel image processing method and device | |
CN113537015A (en) | Method for identifying rail scratches, method for routing inspection and related device |
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 |