CN112819820A - Pavement asphalt repair detection method based on machine vision - Google Patents
Pavement asphalt repair detection method based on machine vision Download PDFInfo
- Publication number
- CN112819820A CN112819820A CN202110219433.6A CN202110219433A CN112819820A CN 112819820 A CN112819820 A CN 112819820A CN 202110219433 A CN202110219433 A CN 202110219433A CN 112819820 A CN112819820 A CN 112819820A
- Authority
- CN
- China
- Prior art keywords
- area
- image
- repairing
- strip
- gray
- 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.)
- Granted
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
-
- 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
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10024—Color 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The invention provides a machine vision-based pavement asphalt repair detection method, which comprises the following steps: inputting a road surface image to be detected, and converting the input road surface image to be detected into a gray image from a color mode; calculating a gray average value of the gray image, taking a ratio of the gray average value to a preset threshold value as a gray correction coefficient, and dividing the gray image and the gray correction coefficient to obtain a corrected image; judging the repairing type; detecting the candidate area; detecting and describing the block patching; detecting and describing the strip repairing; and adding the block repairing detection result graph and the strip repairing detection result graph, and outputting to obtain a final repairing detection result. The method of the invention does not need to train and label the data set, saves the training cost in the early stage, can obtain the output picture in real time, accelerates the processing speed and improves the efficiency of the road surface detection system.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a pavement asphalt repair detection method based on machine vision.
Background
At present, detection methods for pavement asphalt repair mainly include a detection method based on a convolutional neural network, a detection method based on a local texture binary pattern and an image feature extraction detection method based on window contrast.
The main ideas of the methods are as follows:
(1) the road surface repairing detection method based on the convolutional neural network comprises the steps of obtaining a plurality of frames of road surface sample images, and training a plurality of convolutional neural network models to obtain trained network models; determining a target convolutional neural network model of the plurality of trained convolutional neural network models; and inputting the road surface image to be detected into the target convolutional neural network model to obtain road surface repairing information in the road surface image to be detected.
(2) The road surface repairing detection method based on the local texture binary pattern is characterized in that a local rectangular binary pattern calculation method aiming at linear characteristics of road surface repairing diseases is adopted, LRBP (local rectangular binary pattern) feature vectors are extracted from road surface images, the obtained LRBP feature vectors of the road surface repairing disease images and the LRBP feature vectors of normal road surface images are subjected to machine learning to obtain a classifier of the repairing diseases, the classifier is used for detecting and identifying the road surface repairing diseases, and the identification and detection of the road surface repairing diseases are achieved.
(3) The method for detecting the pavement patching based on the window contrast comprises the steps of firstly carrying out image deblurring processing on a road disease image by using a unified restoration method, extracting patching image information by using a window contrast algorithm, then removing pseudo patching information by combining original image information and secondarily using the window contrast algorithm, and accurately and quickly extracting image pavement patching target information.
The existing detection algorithm has the following problems:
(1) the road surface repairing detection method based on the convolutional neural network has the following problems: the method can not achieve real-time detection, is suitable for pictures with high contrast, low noise and simpler scenes, does not contain obstacles such as fallen leaves, water stains, lane lines, shadows and the like, underestimates the complexity of road surface repairing images, and is difficult to meet the requirements of practical engineering application.
(2) The road surface repairing detection method based on the local texture binary pattern has the following problems: the method is easy to be interfered by background noise when detecting and repairing, and is suitable for detecting in a simple scene that the road surface is smooth and the repaired edge is obvious. In reality, the road conditions are complex, the repairing shape is complex and changeable, the interference on the extracted feature vector is large, and the detection accuracy faces a great challenge.
(3) The problem of the road surface repairing detection method based on the window contrast ratio is that: the method detects that the repair area is incomplete and has a large part of defects, the removed false repair area only comprises isolated small target areas such as stains, asphalt or repair raw materials, and the false repair area which is very similar to repair, such as ruts, water stains and the like, cannot be removed.
Reference documents: the vehicle-mounted automatic detection method of road surface disease repairing image is characterized by Zhangxihua, Jinggen, Wangping, etc. (J).
Disclosure of Invention
According to the technical problems that the repair area is incomplete and a large part of the repair area is incomplete, the method for detecting the asphalt repair of the pavement based on the machine vision is provided. The invention mainly utilizes a machine vision-based pavement asphalt repair detection method, which is characterized by comprising the following steps:
step S1: inputting a road surface image to be detected, and converting the input road surface image to be detected from color into a gray image P1;
Step S2: calculating the grayscale image P1The average value of the gray scale is mu, the ratio of the average value of the gray scale mu to a preset threshold value is used as a gray scale correction coefficient, and the gray scale image P is used1Dividing the gray scale correction coefficient to obtain a corrected image P2;
Step S3: to pairJudging the repair type; calculating the grayscale image P1The ratio of the number of pixels with the medium gray scale value lower than 0.7 mu is c, and if c is larger than a set threshold xi, blocky repair may exist in the image; if c is less than or equal to xi, strip-shaped repairing possibly exists in the image;
step S4: detecting the candidate area; detecting an image P by a region detection method2Each of the connected regions; and counting the area of each connected region and the gray image P1Mean value of gray scale in (1);
step S5: detecting and describing the block patching;
step S6: detecting and describing the strip repairing;
step S7: and adding the block repairing detection result graph C and the strip repairing detection result graph D, and outputting to obtain a final repairing detection result.
Further, the detecting and describing the block patching further comprises the following steps:
step S51: screening the blocky repair area based on the area attribute; judging whether the area of the current region is in the range [ a ]1,a2](ii) a If the area is within the range, judging the area as a block-shaped repairing area from the aspect of area attribute characteristics;
step S52: screening the blocky repairing area based on the gray attribute characteristics; judging whether the current area is in the gray level image P1If the mean value of the gray levels in the image is smaller than a set threshold value d, judging that the current area is a block-shaped repairing area from the aspect of gray level attribute characteristics;
step S53: screening a block-shaped repairing area based on the geometrical structure characteristics; establishing a minimum circumscribed rectangle of the current region, setting the ratio of the number of pixel points in the minimum circumscribed rectangle of the region as q, and if q is larger than delta, judging that the current region is a blocky repairing region from the aspect of geometric structure characteristics;
step S54: describing a block repairing area; defining a blank image A with the same size as the input road surface image to be detected, storing all the block repairing areas into the image A, marking the block repairing area corresponding to the image A in the input road surface image to be detected with yellow color, and generating a block repairing detection result image C.
Further, the detecting and describing the strip repairing further comprises the following steps:
step S61: screening strip repair regions based on area attributes; judging whether the area of the current region is in the range [ a ]3,a4]Within; if the area is within the range, judging the area to be a strip-shaped repairing area from the aspect of area attribute characteristics.
Step S62: screening strip-shaped repairing areas based on the gray attribute characteristics;
step S63: removing water stain interference based on quantity prior; the number of strip-shaped repairing in the road surface image is limited, and generally does not exceed tau strips; counting the total number of the repair areas in the strip repair candidate graph B to be n, if n is larger than tau, judging that the result is a water stain false detection graph, and emptying the candidate graph B without subsequent screening; if n is less than or equal to tau, then carrying out the next step of geometric structural feature screening;
step S64: screening strip-shaped repairing areas based on geometrical structure characteristics; traversing the connected region, calculating the horizontal projection and the vertical projection of the region, and performing median filtering to remove noise influence; and (4) taking the average minimum width value of the strip-shaped repair as phi, and respectively dividing the filtered horizontal projection sequence and the filtered vertical projection sequence by phi and then rounding to obtain a result sequence which is recorded as s1、s2(ii) a Sequence of results in horizontal direction s1For example, the total length of the sequence is counted as l, the mode of the sequence is γ, the maximum length value of the continuous occurrence of γ is λ, and the ratio ρ of the maximum length value of the continuous occurrence of γ in the total length in the horizontal direction of the repair is ρIf gamma is less than omega and rho is more than theta, judging the area to be a strip-shaped repairing area; if the condition is not met, judging that the connected domain is a false detection water stain area, and removing the area from the candidate image B;
step S65: describing a strip-shaped repairing area; marking the strip-shaped repairing area corresponding to the image B in the original image to be detected with yellow color to generate a final strip-shaped repairing detection result image D.
Further, the screening of the strip-shaped repair area based on the gray attribute features further comprises the following steps:
step S621: setting a gray threshold: setting a gray level threshold value of a detection repairing area as alpha and a gray level difference threshold value of the repairing area and a background area as beta according to the image gray level mean value mu;
step S622: screening strip repair areas: defining an all-zero image B with the same size as the original image, recording the gray average value of the current area in the original image as eta, if eta is less than alpha and mu-eta is less than beta, judging the current area as a strip-shaped repairing area from the gray characteristic angle, and setting the area of the area corresponding to B as 1; and traversing all suspected areas, and screening the gray features to generate a final strip-shaped repairing candidate image B.
Compared with the prior art, the invention has the following advantages:
the method of the invention does not need to train and label the data set, saves the training cost in the early stage, can obtain the output picture in real time, accelerates the processing speed and improves the efficiency of the road surface detection system. There is good performance on different data sets, more than optimized for a single data set.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic view of the overall process of the present invention.
FIG. 2 is an input/output image of a strip asphalt repair test according to the present invention; wherein (a) is an input image; (b) to output a detection result image.
FIG. 3 is an input/output image of a strip asphalt repair test according to the present invention; wherein (a) is an input image; (b) to output a detection result image.
FIG. 4 is an input/output image of the block asphalt repair test of the present invention; wherein (a) is an input image; (b) to output a detection result image.
FIG. 5 is an input/output image of the block asphalt repair test of the present invention; wherein (a) is an input image; (b) to output a detection result image.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
As shown in fig. 1-5, the present invention provides a machine vision-based road asphalt repair detection method, which comprises the following steps:
step S1: inputting a road surface image to be detected, and converting the input road surface image to be detected from color into a gray image P1;
Step S2: calculating the grayscale image P1Ash of (2)The average value of the degree is mu, the ratio of the average value of the gray scale mu to a preset threshold value is used as a gray scale correction coefficient, and the gray scale image P is used1Dividing the gray scale correction coefficient to obtain a corrected image P2;
Step S3: judging the repairing type; calculating the grayscale image P1The ratio of the number of pixels with the medium gray scale value lower than 0.7 mu is c, and if c is larger than a set threshold xi, blocky repair may exist in the image; if c is less than or equal to xi, strip-shaped repairing possibly exists in the image; as a preferred embodiment, ξ is preferably 0.016 in the present application.
Step S4: detecting the candidate area; detecting an image P by a region detection method2Each of the connected regions; and counting the area of each connected region and the gray image P1Mean value of gray scale in (1);
step S5: the patch is detected and described. The detecting and describing the block patching further comprises the following steps:
step S51: screening the blocky repair area based on the area attribute; judging whether the area of the current region is in the range [ a ]1,a2](ii) a If the area is within the range, the area is judged to be a block-shaped repairing area from the aspect of area attribute characteristics. As a preferred embodiment, in the present application, the range is defined as [100000, 350000 ]]It is to be understood that in other embodiments, the specific range may be set according to the actual area size.
Step S52: screening the blocky repairing area based on the gray attribute characteristics; judging whether the current area is in the gray level image P1If the mean value of the gray levels in (1) is less than a set threshold value d, wherein d is preferably 90, the current area is judged to be a block-shaped repairing area from the aspect of gray level attribute characteristics;
step S53: screening a block-shaped repairing area based on the geometrical structure characteristics; establishing a minimum circumscribed rectangle of the current region, setting the ratio of the number of pixel points in the minimum circumscribed rectangle of the region as q, and if q is greater than delta, wherein delta is preferably 0.7, judging that the current region is a block-shaped repairing region from the aspect of geometrical structure characteristics;
step S54: describing a block repairing area; defining a blank image A with the same size as the input road surface image to be detected, storing all the block repairing areas into the image A, marking the block repairing area corresponding to the image A in the input road surface image to be detected with yellow color, and generating a block repairing detection result image C.
Step S6: the stripe repair test is described. The detecting and describing the strip repair further comprises the following steps:
step S61: screening strip repair regions based on area attributes; judging whether the area of the current region is in the range [ a ]3,a4]Wherein the preferred range is [3000,80000 ]](ii) a If the area is within the range, judging the area to be a strip-shaped repairing area from the aspect of area attribute characteristics.
Step S62: and screening the strip-shaped repairing area based on the gray attribute characteristics.
The screening of the strip-shaped repairing area based on the gray attribute characteristics further comprises the following steps:
step S621: setting a gray threshold: setting a gray level threshold value of a detection repairing area as alpha and a gray level difference threshold value of the repairing area and a background area as beta according to the image gray level mean value mu;
step S622: screening strip repair areas: defining an all-zero image B with the same size as the original image, recording the gray average value of the current area in the original image as eta, if eta is less than alpha and mu-eta is less than beta, judging the current area as a strip-shaped repairing area from the gray characteristic angle, and setting the area of the area corresponding to B as 1; and traversing all suspected areas, and screening the gray features to generate a final strip-shaped repairing candidate image B.
Step S63: removing water stain interference based on quantity prior; the number of strip-shaped repairs in the road surface image is limited, and generally does not exceed tau strips, wherein tau is preferably 3; counting the total number of the repair areas in the strip repair candidate graph B to be n, if n is larger than tau, judging that the result is a water stain false detection graph, and emptying the candidate graph B without subsequent screening; if n is less than or equal to tau, then carrying out the next step of geometric structural feature screening;
step S64: screening strip-shaped repairing areas based on geometrical structure characteristics; traversing the connected region, calculating the horizontal projection and the vertical projection of the region, and performing median filtering to remove noise influence; and (4) taking the average minimum width value of the strip-shaped repair as phi, and respectively dividing the filtered horizontal projection sequence and the filtered vertical projection sequence by phi and then rounding to obtain a result sequence which is recorded as s1、s2(ii) a Sequence of results in horizontal direction s1For example, the total length of the sequence is counted as l, the mode of the sequence is γ, the maximum length value of the continuous occurrence of γ is λ, and the ratio ρ of the maximum length value of the continuous occurrence of γ in the total length in the horizontal direction of the repair is ρIf gamma is less than omega and rho is more than theta, wherein omega is preferably 3, and theta is preferably 0.7, judging the area to be a strip-shaped repairing area; if the condition is not met, judging that the connected domain is a false detection water stain area, and removing the area from the candidate image B;
step S65: describing a strip-shaped repairing area; marking the strip-shaped repairing area corresponding to the image B in the original image to be detected with yellow color to generate a final strip-shaped repairing detection result image D.
Step S7: and adding the block repairing detection result graph C and the strip repairing detection result graph D, and outputting to obtain a final repairing detection result.
Example (b):
1) the experimental results are shown in fig. 2 and 3, and the strip asphalt repair area detected by the gray marks can completely and accurately detect and describe the repair area in the pavement image, and has good detection effect on the pavement repair images with large quantity and complex shapes.
2) As shown in fig. 4 and 5, the block asphalt repair area detected by the gray mark can completely and accurately detect and describe the block asphalt repair area in the road surface image.
3) The method does not need to train and label the data set, saves the training cost in the early stage, can obtain the output picture in real time, accelerates the processing speed and improves the efficiency of the road surface detection system. There is good performance on different data sets, more than optimized for a single data set.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments. In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (4)
1. A pavement asphalt repair detection method based on machine vision is characterized by comprising the following steps:
s1: inputting a road surface image to be detected, and converting the input road surface image to be detected from color into a gray image P1;
S2: calculating the grayscale image P1The average value of the gray scale is mu, the ratio of the average value of the gray scale mu to a preset threshold value is used as a gray scale correction coefficient, and the gray scale image P is used1Dividing the gray scale correction coefficient to obtain a corrected image P2;
S3: judging the repairing type; calculating the grayscale image P1The ratio of the number of pixels with the medium gray scale value lower than 0.7 mu is c, and if c is larger than a set threshold xi, blocky repair may exist in the image; if c is less than or equal to xi, strip-shaped repairing possibly exists in the image;
S4:detecting the candidate area; detecting an image P by a region detection method2Each of the connected regions; and counting the area of each connected region and the gray image P1Mean value of gray scale in (1);
s5: detecting and describing the block patching;
s6: detecting and describing the strip repairing;
s7: and adding the block repairing detection result graph C and the strip repairing detection result graph D, and outputting to obtain a final repairing detection result.
2. The machine vision-based pavement asphalt repair detection method according to claim 1, wherein the step of detecting and describing the block repair further comprises the following steps:
s51: screening the blocky repair area based on the area attribute; judging whether the area of the current region is in the range [ a ]1,a2](ii) a If the area is within the range, judging the area as a block-shaped repairing area from the aspect of area attribute characteristics;
s52: screening the blocky repairing area based on the gray attribute characteristics; judging whether the current area is in the gray level image P1If the mean value of the gray levels in the image is smaller than a set threshold value d, judging that the current area is a block-shaped repairing area from the aspect of gray level attribute characteristics;
s53: screening a block-shaped repairing area based on the geometrical structure characteristics; establishing a minimum circumscribed rectangle of the current region, setting the ratio of the number of pixel points in the minimum circumscribed rectangle of the region as q, and if q is larger than delta, judging that the current region is a blocky repairing region from the aspect of geometric structure characteristics;
s54: describing a block repairing area; defining a blank image A with the same size as the input road surface image to be detected, storing all the block repairing areas into the image A, marking the block repairing area corresponding to the image A in the input road surface image to be detected with yellow color, and generating a block repairing detection result image C.
3. The machine vision-based pavement asphalt repair detection method according to claim 1, wherein the step of detecting and describing the strip repair further comprises the following steps:
s61: screening strip repair regions based on area attributes; judging whether the area of the current region is in the range [ a ]3,a4]Within; if the area is within the range, judging the area to be a strip-shaped repairing area from the aspect of area attribute characteristics.
S62: screening strip-shaped repairing areas based on the gray attribute characteristics;
s63: removing water stain interference based on quantity prior; the number of strip-shaped repairing in the road surface image is limited, and generally does not exceed tau strips; counting the total number of the repair areas in the strip repair candidate graph B to be n, if n is larger than tau, judging that the result is a water stain false detection graph, and emptying the candidate graph B without subsequent screening; if n is less than or equal to tau, then carrying out the next step of geometric structural feature screening;
s64: screening strip-shaped repairing areas based on geometrical structure characteristics; traversing the connected region, calculating the horizontal projection and the vertical projection of the region, and performing median filtering to remove noise influence; and (4) taking the average minimum width value of the strip-shaped repair as phi, and respectively dividing the filtered horizontal projection sequence and the filtered vertical projection sequence by phi and then rounding to obtain a result sequence which is recorded as s1、s2(ii) a Sequence of results in horizontal direction s1For example, the total length of the sequence is counted as l, the mode of the sequence is γ, the maximum length value of the continuous occurrence of γ is λ, and the ratio ρ of the maximum length value of the continuous occurrence of γ in the total length in the horizontal direction of the repair is ρIf gamma is less than omega and rho is more than theta, judging the area to be a strip-shaped repairing area; if the condition is not met, judging that the connected domain is a false detection water stain area, and removing the area from the candidate image B;
s65: describing a strip-shaped repairing area; marking the strip-shaped repairing area corresponding to the image B in the original image to be detected with yellow color to generate a final strip-shaped repairing detection result image D.
4. The machine vision-based pavement asphalt repair detection method according to claim 3, wherein the screening of the strip repair area based on the gray attribute features further comprises the following steps:
s621: setting a gray threshold: setting a gray level threshold value of a detection repairing area as alpha and a gray level difference threshold value of the repairing area and a background area as beta according to the image gray level mean value mu;
s622: screening strip repair areas: defining an all-zero image B with the same size as the original image, recording the gray average value of the current area in the original image as eta, if eta is less than alpha and mu-eta is less than beta, judging the current area as a strip-shaped repairing area from the gray characteristic angle, and setting the area of the area corresponding to B as 1; and traversing all suspected areas, and screening the gray features to generate a final strip-shaped repairing candidate image B.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110219433.6A CN112819820B (en) | 2021-02-26 | 2021-02-26 | Road asphalt repairing and detecting method based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110219433.6A CN112819820B (en) | 2021-02-26 | 2021-02-26 | Road asphalt repairing and detecting method based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112819820A true CN112819820A (en) | 2021-05-18 |
CN112819820B CN112819820B (en) | 2023-06-16 |
Family
ID=75864153
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110219433.6A Active CN112819820B (en) | 2021-02-26 | 2021-02-26 | Road asphalt repairing and detecting method based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112819820B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109035218A (en) * | 2018-07-09 | 2018-12-18 | 武汉武大卓越科技有限责任公司 | Pavement patching method for detecting area |
US20190154442A1 (en) * | 2016-01-15 | 2019-05-23 | Fugro Roadware Inc. | High speed stereoscopic pavement surface scanning system and method |
CN109815961A (en) * | 2018-12-25 | 2019-05-28 | 山东省交通规划设计院 | A kind of pavement patching class Defect inspection method based on local grain binary pattern |
CN109919856A (en) * | 2019-01-21 | 2019-06-21 | 重庆交通大学 | Bituminous pavement construction depth detection method based on binocular vision |
-
2021
- 2021-02-26 CN CN202110219433.6A patent/CN112819820B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190154442A1 (en) * | 2016-01-15 | 2019-05-23 | Fugro Roadware Inc. | High speed stereoscopic pavement surface scanning system and method |
CN109035218A (en) * | 2018-07-09 | 2018-12-18 | 武汉武大卓越科技有限责任公司 | Pavement patching method for detecting area |
CN109815961A (en) * | 2018-12-25 | 2019-05-28 | 山东省交通规划设计院 | A kind of pavement patching class Defect inspection method based on local grain binary pattern |
CN109919856A (en) * | 2019-01-21 | 2019-06-21 | 重庆交通大学 | Bituminous pavement construction depth detection method based on binocular vision |
Non-Patent Citations (1)
Title |
---|
张玉雪;唐振民;钱彬;徐威;: "融入视觉注意机制的路面裂缝检测与识别", 计算机工程, no. 04 * |
Also Published As
Publication number | Publication date |
---|---|
CN112819820B (en) | 2023-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109191459B (en) | Automatic identification and rating method for continuous casting billet macrostructure center segregation defect | |
CN109961049B (en) | Cigarette brand identification method under complex scene | |
CN107543828B (en) | Workpiece surface defect detection method and system | |
CN108038883B (en) | Crack detection and identification method applied to highway pavement video image | |
KR101403876B1 (en) | Method and Apparatus for Vehicle License Plate Recognition | |
CN106683119B (en) | Moving vehicle detection method based on aerial video image | |
US6026177A (en) | Method for identifying a sequence of alphanumeric characters | |
Deb et al. | An efficient method of vehicle license plate recognition based on sliding concentric windows and artificial neural network | |
CN111145161A (en) | Method for processing and identifying pavement crack digital image | |
CN110415260B (en) | Smoke image segmentation and identification method based on dictionary and BP neural network | |
CN108509950B (en) | Railway contact net support number plate detection and identification method based on probability feature weighted fusion | |
Azad et al. | A novel and robust method for automatic license plate recognition system based on pattern recognition | |
CN113780110A (en) | Method and device for detecting weak and small targets in image sequence in real time | |
CN110689003A (en) | Low-illumination imaging license plate recognition method and system, computer equipment and storage medium | |
CN115272350A (en) | Method for detecting production quality of computer PCB mainboard | |
CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
CN109978916B (en) | Vibe moving target detection method based on gray level image feature matching | |
CN107832732B (en) | Lane line detection method based on treble traversal | |
CN116912184B (en) | Weak supervision depth restoration image tampering positioning method and system based on tampering area separation and area constraint loss | |
CN110349119B (en) | Pavement disease detection method and device based on edge detection neural network | |
Danilescu et al. | Road anomalies detection using basic morphological algorithms | |
CN112819820A (en) | Pavement asphalt repair detection method based on machine vision | |
CN112465817B (en) | Pavement crack detection method based on directional filter | |
Yuhan et al. | Detection of road surface crack based on PYNQ | |
KR20230082346A (en) | Method of detecting defect of manufactured product based on high-resolution image using autoencoder and convolutional neural network |
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 |