CN113092487A - Rapid detection method for full-surface flaws of safety belt roller - Google Patents
Rapid detection method for full-surface flaws of safety belt roller Download PDFInfo
- Publication number
- CN113092487A CN113092487A CN202110388839.7A CN202110388839A CN113092487A CN 113092487 A CN113092487 A CN 113092487A CN 202110388839 A CN202110388839 A CN 202110388839A CN 113092487 A CN113092487 A CN 113092487A
- Authority
- CN
- China
- Prior art keywords
- image
- roller
- safety belt
- steps
- following
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 15
- 230000007547 defect Effects 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000003384 imaging method Methods 0.000 claims abstract description 4
- 238000005259 measurement Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 29
- 238000000605 extraction Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000005286 illumination Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000007670 refining Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 abstract description 3
- 230000010354 integration Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8809—Adjustment for highlighting flaws
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8829—Shadow projection or structured background, e.g. for deflectometry
-
- 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
Landscapes
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention belongs to the technical field of surface detection, and particularly relates to a rapid detection method for full-surface flaws of a safety belt roller, which specifically comprises the following steps: step one, a double-channel linear light source is used as an illuminating light source, a linear array camera is used as an imaging element, laser is projected onto a measuring surface of a roller to be measured, defects such as pits, bulges, scratches and the like are highlighted, the linear array camera is used for collecting laser projection images, step two, algorithm processing is carried out on the images collected in the step one, a suspicious region is searched, and the images of the suspicious region are reported after being segmented; and step three, rotating the roller to adjust the area in the measuring surface, and repeating the operation until the measurement of all the side surfaces of the roller is completed. The defects of the prior art are overcome, the defect of the surface of the roller is rapidly found by adopting a mode of optical detection matched with algorithm processing, the defect of manual detection is overcome, and the product quality is improved.
Description
Technical Field
The invention belongs to the technical field of surface detection, and particularly relates to a rapid detection method for full-surface flaws of a safety belt roller.
Background
The safety belt can be extended and retracted-when the safety belt is not tightened, the body can be easily tilted forward. However, when the vehicle is impacted and the human body leans forwards rapidly, the safety belt can be suddenly tightened and the human body is tightly fixed.
The conventional safety belt device is internally provided with a roller, and if the safety belt is pulled rapidly, for example, under the condition of a car accident, the inside clip can be taken out by centrifugal force due to the rapid rotation of the roller of the safety belt, so that the safety belt is locked rapidly, and a person on a seat is fixed on a chair. The safety belt will relax when the peak of the impact has passed or when the person has been protected by the airbag so as not to crush the ribs of the person. The purpose of ensuring the safety of drivers and passengers is achieved through the series of actions.
At present, the surface of the safety belt roller is mainly detected or the surface of the safety belt roller is detected by a manual method, and the manual method has the following problems:
(1) in long-term single repetitive work, workers are easy to fatigue, and unqualified products flow into the application market;
(2) the manual force of different workers is different, and the judgment on the qualification of the limit piece generates corresponding difference;
(3) the manual detection cannot detect the small defects, and the quality of the product is affected.
Disclosure of Invention
The invention aims to provide a method for rapidly detecting defects on the whole surface of a safety belt roller, which overcomes the defects of the prior art, rapidly discovers the defects on the surface of the roller by adopting a mode of optical detection matched with algorithm processing, overcomes the defects of manual detection, and improves the product quality.
In order to solve the problems, the technical scheme adopted by the invention is as follows:
a rapid detection method for the defects of the whole surface of a safety belt roller specifically comprises the following steps:
the method comprises the following steps that firstly, a double-channel linear light source is used as an illumination light source, a linear array camera is used as an imaging element, laser is projected onto a measuring surface of a roller to be measured, defects such as pits, bulges and scratches are highlighted, and a laser projection image is acquired by the linear array camera;
step two, performing algorithm processing on the image acquired in the step one, searching for a suspicious region, segmenting the image of the suspicious region and reporting;
and step three, rotating the roller to adjust the area in the measuring surface, and repeating the operation until the measurement of all the side surfaces of the roller is completed.
Further, in the first step, the linear array camera is erected perpendicular to the roller measuring surface, the two-channel linear light sources are two laser generators which are bilaterally symmetrical about the linear array camera, the laser generators are erected obliquely to the roller measuring surface, the inclined angle between the laser generators and the roller measuring surface is 45-60 degrees, and the laser generators project laser lines with uniform thickness and uniform intervals to the surface of the plate.
Further, the algorithm processing in the second step includes the following steps:
(1) preprocessing and filtering the acquired roller measuring surface image to inhibit noise information in the acquisition process;
(2) carrying out gradient transformation on the filtered image, carrying out edge extraction on the image through an edge extraction algorithm, and carrying out binarization on an output characteristic map;
(3) carrying out integral operation on the edge binary image to obtain a corresponding integral image;
(4) carrying out grid division on the edge two-dimensional drawing, calculating the energy density of edge points in each grid by using an integral graph, and extracting the grid as a candidate area when the energy density in a certain grid is greater than a threshold value;
(5) and combining the adjacent candidate areas, and performing fine search on the combined areas to obtain the possible areas.
Further, in the step (1), the gaussian filtering is adopted to carry out convolution operation on the image to obtain a discrete gaussian weight matrix, and then normalization processing is carried out on the discrete gaussian weight matrix to reduce the influence of noise points in the image.
Further, in the step (2), a Canny operator is adopted, first-order difference of the image is extracted, all points which are not extreme values are restrained, connected points on the image are connected through double thresholds, the obtained gradient image is normalized into 0 and 1 images, and gradient information of the image is calculated, so that the edge of the image is extracted.
Further, the formula of the integration operation in step (3) is as follows:
wherein, i, j is a coordinate point in the original image,
x, y-coordinate point of the current integral to be calculated,
g (x) -the value of the corresponding point;
AreaSum(x,y,w,h)＝SAT(x,y)-SAT(x-w,y)-SAT(x,y-h)+SAT(s-w,y-h)
wherein, AreaSum (x, y, w, h) corresponds to the sum of the numerical points in the original rectangle.
Further, the energy density in step (4) is calculated according to the following formula:
where E (i, j) -the block energy,
i, j-row index, column index,
w, h-block width, block height.
Further, the specific method for refining the search in the step (5) is as follows: and taking each candidate area as a point, inputting the current search point, circularly searching eight points around the current central point by taking the current search point as a center, iterating after finding the defect block, and searching by taking the iterated points as the center until the search of all the candidate areas is completed.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention adopts the matching of the dual-channel linear light source and the linear array camera to obtain the high-definition color image of the test area, can enhance the display effect of the defect and meet the requirement of optical detection.
2. The invention extracts the edge of the image through the edge algorithm and uses the integral graph to improve the calculation speed, thereby meeting the real-time requirement, having fast algorithm operation, only l0ms for processing each image and having the comprehensive identification accuracy rate of 96.9 percent.
Drawings
Fig. 1 is a schematic structural diagram of a method for rapidly detecting a full-surface flaw of a seat belt roller.
Fig. 2 is an enlarged schematic view of a point a in the rapid detection method for the full-surface flaw of the belt roller.
Detailed Description
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.
As shown in fig. 1-2, the method for rapidly detecting the flaws on the whole surface of the safety belt roller specifically comprises the following steps:
the method comprises the following steps that firstly, a double-channel linear light source is used as an illumination light source, a linear array camera is used as an imaging element, laser is projected onto a measuring surface of a roller to be measured, defects such as pits, bulges and scratches are highlighted, and a laser projection image is acquired by the linear array camera;
step two, performing algorithm processing on the image acquired in the step one, searching for a suspicious region, segmenting the image of the suspicious region and reporting;
and step three, rotating the roller to adjust the area in the measuring surface, and repeating the operation until the measurement of all the side surfaces of the roller is completed.
Further, in the first step, the linear array camera is erected perpendicular to the roller measuring surface, the two-channel linear light sources are two laser generators which are bilaterally symmetrical about the linear array camera, the laser generators are erected obliquely to the roller measuring surface, the inclined angle between the laser generators and the roller measuring surface is 45-60 degrees, and the laser generators project laser lines with uniform thickness and uniform intervals to the surface of the plate.
Further, the algorithm processing in the second step includes the following steps:
(1) preprocessing and filtering the acquired roller measuring surface image to inhibit noise information in the acquisition process;
(2) carrying out gradient transformation on the filtered image, carrying out edge extraction on the image through an edge extraction algorithm, and carrying out binarization on an output characteristic map;
(3) carrying out integral operation on the edge binary image to obtain a corresponding integral image;
(4) carrying out grid division on the edge two-dimensional drawing, calculating the energy density of edge points in each grid by using an integral graph, and extracting the grid as a candidate area when the energy density in a certain grid is greater than a threshold value;
(5) and combining the adjacent candidate areas, and performing fine search on the combined areas to obtain the possible areas.
Further, in the step (1), the gaussian filtering is adopted to carry out convolution operation on the image to obtain a discrete gaussian weight matrix, and then normalization processing is carried out on the discrete gaussian weight matrix to reduce the influence of noise points in the image.
Further, in the step (2), a Canny operator is adopted, first-order difference of the image is extracted, all points which are not extreme values are restrained, connected points on the image are connected through double thresholds, the obtained gradient image is normalized into 0 and 1 images, and gradient information of the image is calculated, so that the edge of the image is extracted.
Further, the formula of the integration operation in step (3) is as follows:
wherein, i, j is a coordinate point in the original image,
x, y-coordinate point of the current integral to be calculated,
g (x) -the value of the corresponding point;
AreaSum(x,y,w,h)＝SAT(x,y)-SAT(x-w,y)-SAT(x,y-h)+SAT(s-w,y-h)(2)
wherein, AreaSum (x, y, w, h) corresponds to the sum of the numerical points in the original rectangle.
Further, the energy density in step (4) is calculated according to the following formula:
where E (i, j) -the block energy,
i, j-row index, column index,
w, h-block width, block height.
Through the calculation of the formula (2) and the formula (3), the sum of the gradient values in any rectangle can be calculated within the time of a constant O (1), so that the calculation efficiency is obviously improved; after the integral operation is carried out on the whole gradient map, extracting blocks larger than a threshold value as candidate areas according to the energy density of each block calculated by formula (1)
Further, the specific method for refining the search in the step (5) is as follows: taking each candidate area as a point, inputting a current search point, circularly searching eight points around the current center point by taking the current search point as a center, iterating after finding a defect block, and searching again by taking the iterated points as the center until the search of all candidate areas is completed; after the adjacent candidate areas are combined, a complete suspected defect area can be obtained, and no matter whether the defect is dark or bright, the extraction of the quasi-defect area can be rapidly completed as long as the gradient characteristic is obvious.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (8)
1. A quick detection method for the full surface flaw of a safety belt roller is characterized by comprising the following steps: the method specifically comprises the following steps:
the method comprises the following steps that firstly, a double-channel linear light source is used as an illumination light source, a linear array camera is used as an imaging element, laser is projected onto a measuring surface of a roller to be measured, defects such as pits, bulges and scratches are highlighted, and a laser projection image is acquired by the linear array camera;
step two, performing algorithm processing on the image acquired in the step one, searching for a suspicious region, segmenting the image of the suspicious region and reporting;
and step three, rotating the roller to adjust the area in the measuring surface, and repeating the operation until the measurement of all the side surfaces of the roller is completed.
2. The method for rapidly detecting the flaws on the whole surface of the safety belt roller as claimed in claim 1, wherein the method comprises the following steps: in the first step, the linear array camera is erected perpendicular to the roller measuring surface, the two-channel linear light source adopts two laser generators which are bilaterally symmetrical about the linear array camera, the laser generators are erected obliquely to the roller measuring surface, the inclined included angle between the laser generators and the roller measuring surface is 45-60 degrees, and the laser generators project laser lines with uniform thickness and uniform intervals to the surface of the plate.
3. The method for rapidly detecting the flaws on the whole surface of the safety belt roller as claimed in claim 1, wherein the method comprises the following steps: the algorithm processing in the step two comprises the following steps:
(1) preprocessing and filtering the acquired roller measuring surface image to inhibit noise information in the acquisition process;
(2) carrying out gradient transformation on the filtered image, carrying out edge extraction on the image through an edge extraction algorithm, and carrying out binarization on an output characteristic map;
(3) carrying out integral operation on the edge binary image to obtain a corresponding integral image;
(4) carrying out grid division on the edge two-dimensional drawing, calculating the energy density of edge points in each grid by using an integral graph, and extracting the grid as a candidate area when the energy density in a certain grid is greater than a threshold value;
(5) and combining the adjacent candidate areas, and performing fine search on the combined areas to obtain the possible areas.
4. The method for rapidly detecting the flaws on the whole surface of the safety belt roller as claimed in claim 3, wherein the method comprises the following steps: and (2) performing convolution operation on the image by adopting Gaussian filtering in the step (1) to obtain a discrete Gaussian weight matrix, and performing normalization processing on the discrete Gaussian weight matrix to reduce the influence of noise points in the image.
5. The method for rapidly detecting the flaws on the whole surface of the safety belt roller as claimed in claim 3, wherein the method comprises the following steps: in the step (2), a Canny operator is adopted, first-order difference of the image is extracted, all points which are not extreme values are inhibited, connected points on the image are connected through double thresholds, the obtained gradient image is normalized into 0 and 1 images, and gradient information of the image is calculated so as to extract the edge of the image.
6. The method for rapidly detecting the flaws on the whole surface of the safety belt roller as claimed in claim 3, wherein the method comprises the following steps: the formula of the integral operation in the step (3) is as follows:
wherein, i, j is a coordinate point in the original image,
x, y-coordinate point of the current integral to be calculated,
g (x) -the value of the corresponding point;
AreaSum(x,y,w,h)＝SAT(x,y)-SAT(x-w,y)-SAT(x,y-h)+SAT(s-w,y-h)
wherein, AreaSum (x, y, w, h) corresponds to the sum of the numerical points in the original rectangle.
7. The method for rapidly detecting the flaws on the whole surface of the safety belt roller as claimed in claim 3, wherein the method comprises the following steps: the calculation formula of the energy density in the step (4) is as follows:
where E (i, j) -the block energy,
i, j-row index, column index,
w, h-block width, block height.
8. The method for rapidly detecting the flaws on the whole surface of the safety belt roller as claimed in claim 3, wherein the method comprises the following steps: the specific method for refining the search in the step (5) is as follows: and taking each candidate area as a point, inputting the current search point, circularly searching eight points around the current central point by taking the current search point as a center, iterating after finding the defect block, and searching by taking the iterated points as the center until the search of all the candidate areas is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110388839.7A CN113092487A (en) | 2021-04-12 | 2021-04-12 | Rapid detection method for full-surface flaws of safety belt roller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110388839.7A CN113092487A (en) | 2021-04-12 | 2021-04-12 | Rapid detection method for full-surface flaws of safety belt roller |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113092487A true CN113092487A (en) | 2021-07-09 |
Family
ID=76676515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110388839.7A Withdrawn CN113092487A (en) | 2021-04-12 | 2021-04-12 | Rapid detection method for full-surface flaws of safety belt roller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113092487A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113960069A (en) * | 2021-10-22 | 2022-01-21 | 中铁二十二局集团第五工程有限公司 | Method for establishing surface morphology of cable through laser line scanning |
-
2021
- 2021-04-12 CN CN202110388839.7A patent/CN113092487A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113960069A (en) * | 2021-10-22 | 2022-01-21 | 中铁二十二局集团第五工程有限公司 | Method for establishing surface morphology of cable through laser line scanning |
| CN113960069B (en) * | 2021-10-22 | 2024-03-19 | 中铁二十二局集团第五工程有限公司 | Method for establishing cable surface morphology through laser line scanning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yu et al. | A coarse-to-fine model for rail surface defect detection | |
| CN102288613B (en) | Surface defect detecting method for fusing grey and depth information | |
| CN102636490B (en) | Method for detecting surface defects of dustproof cover of bearing based on machine vision | |
| Tao et al. | Weak scratch detection and defect classification methods for a large-aperture optical element | |
| US9881212B2 (en) | Infrared image based early detection of oil spills in water | |
| CN104851086A (en) | Image detection method for cable rope surface defect | |
| CN103871053A (en) | Vision conspicuousness-based cloth flaw detection method | |
| CN109632808A (en) | Seamed edge defect inspection method, device, electronic equipment and storage medium | |
| CN104101600A (en) | Method and apparatus for detecting fine cracks on cross section of continuous casting slab | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN104458764B (en) | Curved uneven surface defect identification method based on large-field-depth stripped image projection | |
| CN104751474A (en) | Cascade quick image defect segmentation method | |
| CN101739549A (en) | Face detection method and system | |
| CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
| CN104240252A (en) | Detecting Algorithm for cracks of surface of high-temperature billet of machine vision bar | |
| CN104517295A (en) | Partition method and system for three-dimensional terahertz image | |
| TWI512284B (en) | Bubble inspection system for glass | |
| CN113092487A (en) | Rapid detection method for full-surface flaws of safety belt roller | |
| Lin et al. | Surface defect detection of machined parts based on machining texture direction | |
| CN104899890A (en) | Detection method based on polarized light imaging technology | |
| Hashmi et al. | Computer-vision based visual inspection and crack detection of railroad tracks | |
| Phan et al. | Pavement crack extraction method from mobile laser scanning point cloud | |
| Lin et al. | Defect detection system for optical element surface based on machine vision | |
| Khaliluzzaman et al. | Zebra-crossing detection based on geometric feature and vertical vanishing point | |
| Schmugge et al. | Automatic detection of cracks during power plant inspection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210709 |
|
| WW01 | Invention patent application withdrawn after publication |