CN111833316A - Pavement crack identification method and device - Google Patents
Pavement crack identification method and device Download PDFInfo
- Publication number
- CN111833316A CN111833316A CN202010606332.XA CN202010606332A CN111833316A CN 111833316 A CN111833316 A CN 111833316A CN 202010606332 A CN202010606332 A CN 202010606332A CN 111833316 A CN111833316 A CN 111833316A
- Authority
- CN
- China
- Prior art keywords
- crack
- pavement
- type
- judging
- cracks
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000000463 material Substances 0.000 claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000010422 painting Methods 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 230000000007 visual effect Effects 0.000 claims abstract description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 14
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 101100332288 Dictyostelium discoideum dst3 gene Proteins 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- UPBAOYRENQEPJO-UHFFFAOYSA-N n-[5-[[5-[(3-amino-3-iminopropyl)carbamoyl]-1-methylpyrrol-3-yl]carbamoyl]-1-methylpyrrol-3-yl]-4-formamido-1-methylpyrrole-2-carboxamide Chemical compound CN1C=C(NC=O)C=C1C(=O)NC1=CN(C)C(C(=O)NC2=CN(C)C(C(=O)NCCC(N)=N)=C2)=C1 UPBAOYRENQEPJO-UHFFFAOYSA-N 0.000 description 4
- 101100278585 Dictyostelium discoideum dst4 gene Proteins 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 101100332287 Dictyostelium discoideum dst2 gene Proteins 0.000 description 1
- 244000068988 Glycine max Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method Methods 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/40—Filling a planar surface by adding surface attributes, e.g. colour or texture
-
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a technical scheme of a pavement crack identification method and a device, comprising the following steps: preprocessing a pavement source material of the pavement crack acquisition device to obtain a processed material meeting the requirement; performing image processing on the processed material, wherein the image processing comprises painting and calculating a connected domain of the crack, determining a first crack type of the crack and classifying; and judging according to the classified first crack type and the characteristic data corresponding to the first crack type, and taking the second crack type as a final recognition result for visual output. The invention has the beneficial effects that: the method realizes real-time road detection or data source detection by hardware, visually displays the result through background processing, thereby judging the size and type of the road crack and judging whether the final purpose of repairing is needed.
Description
Technical Field
The invention relates to the field of computers, in particular to a method and a device for identifying pavement cracks.
Background
The timely detection of the road quality can prolong the service life of the road and avoid hidden troubles brought by road surface diseases to the driving safety. Considering that the manual detection method has the defects of low efficiency, low precision, high risk coefficient and the like, the automatic detection system of the pavement cracks becomes a hot research problem in the road maintenance direction, and the automatic crack detection algorithm is the core content of the automatic detection system.
According to the existing road crack detection related algorithm at home and abroad, from the viewpoint of crack detection on a crack image, a traditional Pulse Coupled Neural Network (PCNN) model needs to be simplified and improved, so that the calculation complexity of the traditional PCNN in the simulation process can be reduced, the original neuron operation characteristics are reserved, and the PCNN model can be applied to the target detection of the crack image. Aiming at the problems that the optimal detection of the crack image cannot be determined by the PCNN and the pulse threshold has a nonlinear factor, a Genetic Algorithm (GA) and simplified PCNN-based crack image detection method-GA-PCNN is provided.
Road crack recognition based on opencv is an algorithm package based on BSD permission, and has the problems that if the quantity of original materials processed at a time is too large or influence factors are too large, the processing time is greatly increased, the processed materials are not perfect, and further processing is needed, the recognition accuracy after processing cannot be guaranteed to reach 100%, operation processing based on software is suspended, and after hardware is connected, further program modification and testing are carried out, so that the operation is complicated and the efficiency is low.
Disclosure of Invention
The invention aims to solve at least one of the technical problems in the prior art, and provides a method and a device for identifying pavement cracks.
The technical scheme of the invention comprises a pavement crack identification method, which is characterized by comprising the following steps: s100, preprocessing a pavement source material of the pavement crack acquisition device to obtain a processed material meeting the requirement; s200, performing image processing on the processed material, wherein the image processing comprises painting and calculating a connected domain of the crack, determining a first crack type of the crack and classifying; and S300, judging according to the classified first crack type and the characteristic data corresponding to the first crack type, and taking the second crack type as a final recognition result for visual output.
The method for identifying a road surface crack, wherein S100 comprises: importing a source material, and executing primary denoising processing on the source material; judging the condition of the processed material, if the noise processing degree is in accordance with the set range, outputting the processed material, and judging the type; and if the noise processing degree does not conform to the self-defined range, carrying out secondary denoising processing.
According to the pavement crack identification method, the first denoising treatment comprises the following steps: and carrying out Gaussian blur on the source material, eliminating noise, and converting the source material into a gray level image.
According to the pavement crack identification method, the secondary denoising treatment comprises the following steps: and carrying out flooding filling on the gray level image, and carrying out denoising.
The method for identifying a road surface crack, wherein S200 comprises: and calculating the number of connected domains connecting the processed materials through painting, and judging that the road cracks belong to linear cracks or block cracks.
The method for identifying a road surface crack, wherein S300 comprises: if the crack is a linear crack, judging conditions according to projection data obtained from the crack material on a plane coordinate axis respectively, wherein the crack meeting set conditions is a transverse crack, and otherwise, the crack is a longitudinal crack; if the crack is a block crack, the number of connected domains is calculated through painting, and the crack is refined into the block crack and the reticular crack under the set condition.
The method for identifying pavement cracks, wherein the method further comprises the following steps: and if the crack is a block crack, marking the connected region to be black and white, calculating the number of the connected region blocks displayed in the number of the black connected regions, and judging the crack to be one of the block crack, the reticular crack, the wire-mounted crack, the transverse crack and the longitudinal crack according to the number of the blocks.
According to the pavement crack identification method, the image processing is based on an opencv algorithm, and based on BSD permission, an interface is provided for python language through the BSD permission to complete image identification.
The invention also relates to a method for identifying road surface cracks, comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor implements any of the method steps when executing the computer program.
The invention has the beneficial effects that: the method realizes real-time road detection or data source detection by hardware, visually displays the result through background processing, thereby judging the size and type of the road crack and judging whether the final purpose of repairing is needed.
Drawings
The invention is further described below with reference to the accompanying drawings and examples;
FIG. 1 illustrates an overall flow diagram according to an embodiment of the invention;
FIG. 2 is a flowchart illustrating a detailed method for evaluating health education according to an embodiment of the present invention;
fig. 3 shows a diagram of an apparatus according to an embodiment of the invention.
Detailed Description
Reference will now be made in detail to the present preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number.
In the description of the present invention, the consecutive reference numbers of the method steps are for convenience of examination and understanding, and the implementation order between the steps is adjusted without affecting the technical effect achieved by the technical solution of the present invention by combining the whole technical solution of the present invention and the logical relationship between the steps.
In the description of the present invention, unless otherwise explicitly defined, terms such as set, etc. should be broadly construed, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the detailed contents of the technical solutions.
Fig. 1 shows a general flow diagram according to an embodiment of the invention, the flow comprising: s100, preprocessing a pavement source material of the pavement crack acquisition device to obtain a processed material meeting the requirement; s200, performing image processing on the processed material, wherein the image processing comprises painting and calculating a connected domain of the crack, determining a first crack type of the crack and classifying; and S300, judging according to the classified first crack type and the characteristic data corresponding to the first crack type, and taking the second crack type as a final recognition result for visual output.
Fig. 2 is a flowchart illustrating a detailed method for evaluating health education according to an embodiment of the present invention, and 1, a source material is imported and subjected to denoising processing to reduce error influence caused by external factors such as lighting and angle. And (4) judging the condition of the processed material, and outputting the processed material for type judgment if the noise processing degree is in accordance with a self-defined range. If the noise processing degree is not in the self-defined range, processing is carried out, including:
FIG. 1 illustrates the denoising process, with the following code:
def contours_demo(image);
dst2 ═ cv. gaussian blur (binary, 3, 3), 0) # quadratic gaussian blur process
dst3=cv.bilateralFilter(dst2,0,100,5)
#cv.imshow("binary2",dst3)
90pxZng ═ dst3.copy () # flood filling, and denoising was performed
h,w=dst3.shape[:2]
mask=np.zeros([h+2,w+2],np.uint8)
cv.floodFi11(copyImg.mask,(30,30),(0,255,255),(10 100,100),(G0,50,50),cv.FLOODFILL_FIXED_RALTGE)
#cv.imshow("fi11_color_demo",copyImg)
2. Performing program execution on the processed material, calculating the number of connected domains of the connected processed material through painting, judging whether the road crack belongs to a linear crack or a block crack, and refining the specific type;
3. aiming at the linear cracks, projection data on x and y axes in the crack material are obtained, condition judgment is carried out according to the data, the cracks meeting certain conditions are transverse cracks, and the cracks meeting certain conditions are longitudinal cracks otherwise
4. Aiming at the block cracks, the number of connected domains is calculated through painting, the connected domains are refined into the block cracks and the reticular cracks under certain conditions, and part of codes are as follows:
dst5=cv.bitwise_not(dst4)
1 (measure. label) (dst5, consistency. 2) #8 connected domain marker dst6 (color. 1 (2) rgb) # to black and white, and the number of black connected domains print (region number) (1 (s. max ()) # shows the number of connected domain blocks (marker starting from 0) cv
if(labels.max.().=5):
print (crack type is block crack)
iflabels. max0, 10):
print (crack type is block crack')
iflabels.max O〉10):
print (crack type is a reticular crack) if (w < h):
print (crack type is transverse crack ") area 0
for i in range(h);
forjin range(w);
if dst4[i,j]==255;
area+=1;
print(area)。
Fig. 3 shows a diagram of an apparatus according to an embodiment of the invention. The apparatus comprises a memory 100 and a processor 200, wherein the processor 200 stores a computer program for performing: preprocessing a pavement source material of the pavement crack acquisition device to obtain a processed material meeting the requirement; performing image processing on the processed material, wherein the image processing comprises painting and calculating a connected domain of the crack, determining a first crack type of the crack and classifying; and judging according to the classified first crack type and the characteristic data corresponding to the first crack type, and taking the second crack type as a final recognition result for visual output. Wherein the memory 100 is used for storing data.
The technical scheme of the invention is based on the opencv algorithm and BSD permission, and provides an interface for the design of image processing realized in the python language environment.
Firstly, an original material picture is imported, and the material is subjected to noise removing processing such as Gaussian blur, so that the error influence on the source material caused by objective factors such as angles and illumination is reduced. Secondly, expanding the processed material, and connecting some fine crack lines to form a connected domain, so as to further reduce errors, painting and calculating the connected domain, and obtaining the road cracks of specific types according to thinning conditions.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (9)
1. A method for identifying cracks in a pavement, the method comprising:
s100, preprocessing a pavement source material of the pavement crack acquisition device to obtain a processed material meeting the requirement;
s200, performing image processing on the processed material, wherein the image processing comprises painting and calculating a connected domain of the crack, determining a first crack type of the crack and classifying;
s300, judging according to the classified first crack type and the characteristic data corresponding to the first crack type to obtain a second crack type, and taking the second crack type as a final recognition result and carrying out visual output.
2. The road surface crack recognition method according to claim 1, wherein the S100 includes:
importing a source material, and executing primary denoising processing on the source material;
judging the condition of the processed material, if the noise processing degree is in accordance with the set range, outputting the processed material, and judging the type;
and if the noise processing degree does not conform to the self-defined range, carrying out secondary denoising processing.
3. The method for identifying a road surface crack according to claim 2, wherein the first denoising process includes: and carrying out Gaussian blur on the source material, eliminating noise, and converting the source material into a gray level image.
4. The method for identifying pavement cracks according to claim 3, wherein the second denoising process comprises: and carrying out flooding filling on the gray level image, and carrying out denoising.
5. The road surface crack recognition method according to claim 1, wherein the S200 includes: and calculating the number of connected domains connecting the processed materials through painting, and judging that the road cracks belong to linear cracks or block cracks.
6. The road surface crack recognition method according to claim 1, wherein the S300 includes:
if the crack is a linear crack, judging conditions according to projection data obtained from the crack material on a plane coordinate axis respectively, wherein the crack meeting set conditions is a transverse crack, and otherwise, the crack is a longitudinal crack;
if the crack is a block crack, the number of connected domains is calculated through painting, and the crack is refined into the block crack and the reticular crack under the set condition.
7. The method for identifying pavement cracks according to claim 1, further comprising:
and if the crack is a block crack, marking the connected region to be black and white, calculating the number of the connected region blocks displayed in the number of the black connected regions, and judging the crack to be one of the block crack, the reticular crack, the wire-mounted crack, the transverse crack and the longitudinal crack according to the number of the blocks.
8. The pavement crack recognition method of claim 1, wherein the image processing is based on an opencv algorithm, and wherein the image recognition is accomplished in a python language by providing an interface to a BSD license based on the BSD license.
9. A method device for identifying a road surface crack, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to carry out the method steps of any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010606332.XA CN111833316A (en) | 2020-06-29 | 2020-06-29 | Pavement crack identification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010606332.XA CN111833316A (en) | 2020-06-29 | 2020-06-29 | Pavement crack identification method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111833316A true CN111833316A (en) | 2020-10-27 |
Family
ID=72899452
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010606332.XA Pending CN111833316A (en) | 2020-06-29 | 2020-06-29 | Pavement crack identification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111833316A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106087677A (en) * | 2016-06-02 | 2016-11-09 | 上海华城工程建设管理有限公司 | Asphalt pavement crack type automatic identifying method |
WO2017130699A1 (en) * | 2016-01-26 | 2017-08-03 | 富士フイルム株式会社 | Crack information detection device, crack information detection method, and crack information detection program |
CN111145161A (en) * | 2019-12-28 | 2020-05-12 | 北京工业大学 | Method for processing and identifying pavement crack digital image |
CN111310558A (en) * | 2019-12-28 | 2020-06-19 | 北京工业大学 | Pavement disease intelligent extraction method based on deep learning and image processing method |
-
2020
- 2020-06-29 CN CN202010606332.XA patent/CN111833316A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017130699A1 (en) * | 2016-01-26 | 2017-08-03 | 富士フイルム株式会社 | Crack information detection device, crack information detection method, and crack information detection program |
CN106087677A (en) * | 2016-06-02 | 2016-11-09 | 上海华城工程建设管理有限公司 | Asphalt pavement crack type automatic identifying method |
CN111145161A (en) * | 2019-12-28 | 2020-05-12 | 北京工业大学 | Method for processing and identifying pavement crack digital image |
CN111310558A (en) * | 2019-12-28 | 2020-06-19 | 北京工业大学 | Pavement disease intelligent extraction method based on deep learning and image processing method |
Non-Patent Citations (2)
Title |
---|
刘轩然: "基于面阵相机的隧道裂缝图像采集与检测技术" * |
罗瑞: "基于图像处理的路面裂缝检测算法研究" * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108961217B (en) | Surface defect detection method based on regular training | |
WO2022012110A1 (en) | Method and system for recognizing cells in embryo light microscope image, and device and storage medium | |
CN113160257B (en) | Image data labeling method, device, electronic equipment and storage medium | |
CN111681162B (en) | Defect sample generation method and device, electronic equipment and storage medium | |
CN111351789B (en) | Method, system and electronic device for detecting/maintaining equipment | |
CN109241867B (en) | Method and device for recognizing digital rock core image by adopting artificial intelligence algorithm | |
CN110555375B (en) | Method for identifying filling information of answer sheet | |
CN111476758A (en) | Defect detection method and device for AMO L ED display screen, computer equipment and storage medium | |
CN114708325A (en) | Method for quickly positioning rubber production problem based on rubber blooming defect | |
CN114596290A (en) | Defect detection method, defect detection device, storage medium, and program product | |
CN112017157A (en) | Method for identifying damage point in optical element laser damage threshold test | |
CN114723762A (en) | Automatic knee joint CT image segmentation method and device and electronic equipment | |
CN117576106B (en) | Pipeline defect detection method and system | |
CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
CN111833316A (en) | Pavement crack identification method and device | |
CN116797602A (en) | Surface defect identification method and device for industrial product detection | |
CN108171705A (en) | The foreign bodies detection algorithm of liquid in a kind of Clear glass bottles and jars | |
CN115619799B (en) | Grain image segmentation method and system based on transfer learning | |
CN115338091B (en) | High-speed image transmission and analysis system under 5G application | |
CN116485801A (en) | Rubber tube quality online detection method and system based on computer vision | |
CN115393589A (en) | Universal DCS process flow chart identification conversion method, system and medium | |
CN112287898A (en) | Method and system for evaluating text detection quality of image | |
CN116843572B (en) | Image restoration method based on coordinates | |
CN114627114B (en) | Method, system, device and medium for measuring severity of product defect | |
US20220383030A1 (en) | Using few shot learning on recognition system for character image in industrial processes |
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 |