CN114445435A - Vehicle body bolt looseness judging method based on mark line displacement deviation - Google Patents
Vehicle body bolt looseness judging method based on mark line displacement deviation Download PDFInfo
- Publication number
- CN114445435A CN114445435A CN202111585664.5A CN202111585664A CN114445435A CN 114445435 A CN114445435 A CN 114445435A CN 202111585664 A CN202111585664 A CN 202111585664A CN 114445435 A CN114445435 A CN 114445435A
- Authority
- CN
- China
- Prior art keywords
- marking line
- marking
- profile
- line
- judging
- 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 27
- 238000006073 displacement reaction Methods 0.000 title claims abstract description 14
- 230000011218 segmentation Effects 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 230000000873 masking effect Effects 0.000 claims abstract description 3
- 239000003550 marker Substances 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 8
- 208000003464 asthenopia Diseases 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a vehicle body bolt looseness judging method based on mark line displacement deviation, which comprises the following steps of: 1) extracting the marked lines by adopting a lightweight semantic segmentation network to obtain a mask image containing the marked lines; 2) fitting the outline and the direction of the marking line according to the masking layout of the marking line; 3) calculating the outline parameters of the marking lines, and classifying the outlines of the marking lines according to the calculation result; 4) calculating the Euclidean distance between the profile of the historical marking line and the central point of the profile of the existing marking line
Defining a preset tolerance d; 5) and judging and outputting a result according to the parameter consistency comparison result. The method for judging the looseness of the vehicle body bolt based on the displacement of the marking line overcomes the limitation that the existing fitting comparison method is difficult to adapt to the change of a complex scene, and has the advantages of realizing efficient inspection, high judgment accuracy, reducing visual fatigue and the like.
Description
Technical Field
The invention belongs to the technical field of rail transit inspection image processing, and particularly relates to a vehicle body bolt looseness judging method based on a mark line displacement deviation.
Background
In recent years, rail transit technology is rapidly developed, subways become very important transportation means in lives of most urban residents, and the rail transit has the advantages of high punctuation rate, large transportation volume, high speed and the like. In order to ensure the safe operation of the train, the subway needs to be regularly inspected, and whether the bolt is loosened is one of important work. The traditional inspection method highly depends on manual work, and has the defects of low inspection efficiency, missed inspection and false inspection caused by visual fatigue, poor working environment and the like.
Along with the development of computer technology and artificial intelligence, some automatic inspection modes have also appeared in the rail transit field, and whether the bolt has a loosening fault is judged by means of a marking line on the nut. However, the existing bolt looseness detection algorithm is mostly judged by adopting a fitting comparison method, and the problems of low accuracy, difficulty in adapting to complex scene changes and the like exist. Therefore, how to select a more reasonable comparison method becomes a key for improving the accuracy of the algorithm.
Disclosure of Invention
The invention aims to provide a vehicle body bolt looseness judging method based on the displacement deviation of a marking line, which is used for solving the limitation of the conventional comparison method and can efficiently judge whether a bolt is loosened as long as a historical image can be provided. The method is realized by adopting the following technical scheme:
the method for judging the looseness of the vehicle body bolt based on the displacement deviation of the marking line comprises the following steps:
1) and (3) marking line segmentation detection: extracting the marked lines by adopting a lightweight semantic segmentation network to obtain a mask image containing the marked lines;
2) marker line profile and orientation fitting: fitting the outline and the direction of the marking line according to the masking layout of the marking line;
3) marking line outline screening: calculating the outline parameters of the marking lines, and classifying the outlines of the marking lines according to the calculation result;
4) and (3) calculating comparison parameters: calculating the Euclidean distance between the profile of the historical marking line and the central point of the profile of the existing marking line
Defining a preset allowable error d;
5) outputting a judgment result: and judging and outputting a result according to the parameter consistency comparison result.
Further, in step 1), the specific steps of the marker line segmentation detection are as follows: and automatically learning the color, shape and texture characteristics of the marking lines based on deep learning for the acquired bolt image, and generating a mask image only containing the marking lines.
Further, in step 2), the specific steps of marking line profile and direction fitting are as follows: for the mask image containing the marking line generated in the step 1), firstly, the marking line outline is extracted, and then the direction of the outline is fitted.
Further, in step 3), the specific steps of marking line profile screening are as follows:
the method comprises the following steps: calculating the inclination angle (the included angle between the contour direction and the horizontal axis of the coordinate), the length-width ratio, the center point coordinate and the shortest distance between the contours;
step two: the contours are classified, considering the following as positive samples: the number of the outlines is 1, and the aspect ratio of the minimum external connection of the outlines is more than 1.5; when the number of the outlines is 2, calculating the angle difference of straight lines in two directions, wherein the angle difference is less than 10 degrees; when the number of the profiles is more than 2, calculating the angle difference of the direction straight lines of the maximum profile and the profile adjacent to the maximum profile, wherein the angle difference is less than 10 degrees.
Further, in step 4), consistency comparison between the existing marking line profile and the historical marking line profile is performed by using the euclidean distance as a comparison parameter, and the formula is as follows:
wherein the content of the first and second substances,
is the abscissa of the center point of the profile of the history marker line,
is the ordinate of the center point of the profile of the history marker line,
is the abscissa of the center point of the outline of the existing marking line,
is the ordinate of the center point of the outline of the existing marking line.
Further, the specific step of outputting the determination result is as follows: if it is
If the output bolt is not loosened; if it is
And the output bolt is loosened.
The method for judging the looseness of the vehicle body bolt based on the displacement of the marking line overcomes the limitation that the existing fitting comparison method is difficult to adapt to the change of a complex scene, and has the advantages of realizing efficient inspection, high judgment accuracy, reducing visual fatigue and the like.
Drawings
FIG. 1 is a schematic flow chart of a determination method according to the present invention;
FIG. 2 is a mask layout containing only 1 marking line generated in the present invention (wherein a is the current image, and b is the historical image);
FIG. 3 is a mask layout containing 2 marking lines generated in the present invention (wherein a is a current image, and b is a history image);
FIG. 4 is a contour direction diagram of only 1 marked line fitted in the present invention (wherein A is the contour diagram of the current image in FIG. 2, and B is the contour diagram of the history image in FIG. 2);
fig. 5 is a contour directional diagram containing 2 marked lines fitted in the present invention (wherein a is the contour diagram of the current image in fig. 3, and B is the contour diagram of the history image in fig. 3).
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings in order to better understand the technical solution.
A method for judging looseness of a vehicle body bolt based on displacement deviation of a marking line is shown in figure 1 in the whole flow, and comprises the following specific steps:
1) and (3) marking line segmentation detection: for the acquired bolt image, based on the deep learning, the characteristics of the color, shape, texture and the like of the mark line are automatically learned, and a mask map containing only the mark line is generated, as shown in fig. 2 and 3.
2) Marker line profile and orientation fitting: for the generated mask image only containing the mark line, firstly finding the central point of the minimum outline bounding rectangle, then fitting a straight line connecting the central point of the minimum outline bounding rectangle and the origin of the coordinate axis, and representing the direction of the outline by using the direction of the straight line, as shown in fig. 4 and 5; fig. 4 is a contour directional diagram fitted to the marked line in fig. 1, and fig. 5 is a contour directional diagram fitted to the marked line in fig. 2.
3) Marking line outline screening: calculating the contour parameters of the marking lines, and classifying the contours of the marking lines according to the calculation result, which comprises the following specific steps:
the method comprises the following steps: calculating the inclination angle, the length ratio, the center point coordinate and the shortest distance between the profiles of the profiles;
step two: the contours are classified, considering the following as positive samples: the number of the outlines is 1, and the minimum circumscribed length-width ratio of the outlines is more than 1.5; when the number of the profiles is 2, calculating the angle difference of the straight lines in the two directions, wherein the angle difference is less than 10 degrees (see fig. 4 and 5); when the number of the profiles is more than 2, calculating the angle difference of the direction straight lines of the maximum profile and the profile adjacent to the maximum profile, wherein the angle difference is less than 10 degrees.
4) And (3) calculating comparison parameters: calculating the Euclidean distance between the profile of the historical marking line and the central point of the profile of the existing marking line
A preset tolerance d is determined, the error given by the example is that the current inclination angle and the historical deviation are less than 10 degrees, the deviation of the center point coordinate and the historical value is less than 20 percent, the shortest distance between the profiles and the historical value deviation are less than 20 percent, and the adjustment can be carried out according to the actual situation;
specifically, the Euclidean distance is used as a comparison parameter to compare the consistency of the existing marking line profile and the historical marking line profile, and the formula is as follows:
wherein the content of the first and second substances,
is the abscissa of the center point of the profile of the history marker line,
is the ordinate of the center point of the profile of the history marker line,
is the abscissa of the center point of the outline of the existing marking line,
is the ordinate of the center point of the outline of the existing marking line.
5) Outputting a judgment result: and judging and outputting a result according to the parameter consistency comparison result. Specifically, the method for outputting the determination result includes: if it is
If the output bolt is not loosened; if it is
And the output bolt is loosened.
Claims (6)
1. A method for judging bolt looseness of a vehicle body based on displacement deviation of a marking line is characterized by comprising the following steps:
1) and (3) marking line segmentation detection: extracting the marked lines by adopting a lightweight semantic segmentation network to obtain a mask image containing the marked lines;
2) marker line profile and orientation fitting: fitting the outline and the direction of the marking line according to the masking layout of the marking line;
3) marking line outline screening: calculating the profile parameters of the marking lines, and classifying the profiles of the marking lines according to the calculation result;
4) and (3) calculating comparison parameters: calculating the Euclidean distance between the profile of the historical marking line and the central point of the profile of the existing marking line
Defining a preset allowable error d;
5) outputting a judgment result: and judging and outputting a result according to the parameter consistency comparison result.
2. The method for judging the looseness of the vehicle body bolt based on the displacement deviation of the marking line as claimed in claim 1, wherein in the step 1), the specific steps of the marking line segmentation detection are as follows: and automatically learning the color, shape and texture characteristics of the marking lines based on deep learning for the acquired bolt image, and generating a mask image only containing the marking lines.
3. The method for judging the bolt looseness of the vehicle body based on the shift deviation of the marking line as claimed in claim 1, wherein in the step 2), the specific steps of fitting the contour and the direction of the marking line are as follows: for the mask image containing the marking line generated in the step 1), firstly, the marking line outline is extracted, and then the direction of the outline is fitted.
4. The method for judging the looseness of the vehicle body bolt based on the displacement deviation of the marking line as claimed in claim 1, wherein in the step 3), the specific steps of screening the outline of the marking line are as follows:
the method comprises the following steps: calculating the inclination angle, the length-width ratio, the center point coordinate and the shortest distance between the profiles of the profiles;
step two: the contours are classified, considering the following as positive samples: the number of the outlines is 1, and the minimum circumscribed length-width ratio of the outlines is more than 1.5; when the number of the outlines is 2, calculating the angle difference of straight lines in two directions, wherein the angle difference is less than 10 degrees; when the number of the profiles is more than 2, calculating the angle difference of the direction straight lines of the maximum profile and the profile adjacent to the maximum profile, wherein the angle difference is less than 10 degrees.
5. The method for judging the bolt looseness of the vehicle body based on the displacement deviation of the marking line as claimed in claim 1, wherein in the step 4), the consistency comparison between the existing marking line profile and the historical marking line profile is carried out by taking the Euclidean distance as a comparison parameter, and the formula is as follows:
wherein the content of the first and second substances,
is the abscissa of the center point of the profile of the history marker line,
is the ordinate of the center point of the profile of the history marker line,
is the abscissa of the center point of the outline of the existing marking line,
is the center of the outline of the existing marking lineThe point ordinate.
6. The method for judging the looseness of the bolt of the vehicle body based on the displacement deviation of the marking line as claimed in claim 1, wherein the specific step of outputting the judgment result is as follows: if it is
If the output bolt is not loosened; if it is
And the output bolt is loosened.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111585664.5A CN114445435A (en) | 2021-12-23 | 2021-12-23 | Vehicle body bolt looseness judging method based on mark line displacement deviation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111585664.5A CN114445435A (en) | 2021-12-23 | 2021-12-23 | Vehicle body bolt looseness judging method based on mark line displacement deviation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114445435A true CN114445435A (en) | 2022-05-06 |
Family
ID=81363940
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111585664.5A Pending CN114445435A (en) | 2021-12-23 | 2021-12-23 | Vehicle body bolt looseness judging method based on mark line displacement deviation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114445435A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117593515A (en) * | 2024-01-17 | 2024-02-23 | 中数智科(杭州)科技有限公司 | Bolt loosening detection system and method for railway vehicle and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009210276A (en) * | 2008-02-29 | 2009-09-17 | Mitsubishi Heavy Ind Ltd | System and method for detecting loosening of fastening implement |
| CN104180983A (en) * | 2014-09-02 | 2014-12-03 | 苏州市计量测试研究所 | Mechanical vibrator fastener monitoring system and monitoring method of mechanical vibrator fastener monitoring system |
| CN110778464A (en) * | 2019-11-15 | 2020-02-11 | 东方电气风电有限公司 | Bolt online monitoring system and method for large wind generating set |
| CN112365461A (en) * | 2020-11-06 | 2021-02-12 | 北京格灵深瞳信息技术有限公司 | Fastener loosening identification method, system, terminal and storage medium |
| CN113469966A (en) * | 2021-06-25 | 2021-10-01 | 西南交通大学 | Train bolt looseness detection method based on anti-loosening line identification |
| CN113639685A (en) * | 2021-08-10 | 2021-11-12 | 杭州申昊科技股份有限公司 | Displacement detection method, device, equipment and storage medium |
-
2021
- 2021-12-23 CN CN202111585664.5A patent/CN114445435A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009210276A (en) * | 2008-02-29 | 2009-09-17 | Mitsubishi Heavy Ind Ltd | System and method for detecting loosening of fastening implement |
| CN104180983A (en) * | 2014-09-02 | 2014-12-03 | 苏州市计量测试研究所 | Mechanical vibrator fastener monitoring system and monitoring method of mechanical vibrator fastener monitoring system |
| CN110778464A (en) * | 2019-11-15 | 2020-02-11 | 东方电气风电有限公司 | Bolt online monitoring system and method for large wind generating set |
| CN112365461A (en) * | 2020-11-06 | 2021-02-12 | 北京格灵深瞳信息技术有限公司 | Fastener loosening identification method, system, terminal and storage medium |
| CN113469966A (en) * | 2021-06-25 | 2021-10-01 | 西南交通大学 | Train bolt looseness detection method based on anti-loosening line identification |
| CN113639685A (en) * | 2021-08-10 | 2021-11-12 | 杭州申昊科技股份有限公司 | Displacement detection method, device, equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117593515A (en) * | 2024-01-17 | 2024-02-23 | 中数智科(杭州)科技有限公司 | Bolt loosening detection system and method for railway vehicle and storage medium |
| CN117593515B (en) * | 2024-01-17 | 2024-03-29 | 中数智科(杭州)科技有限公司 | Bolt loosening detection system and method for railway vehicle and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112906830B (en) | Automatic generation method of ship optimal route based on AIS big data | |
| CN112036508B (en) | Automatic circumferential seam identification method based on shield tunnel lining structure | |
| CN110992490B (en) | Method for automatically extracting indoor map based on CAD building plan | |
| CN110598634B (en) | Machine room sketch identification method and device based on graph example library | |
| KR20200065613A (en) | Method of automatically recognizing and classifying information of design in imaged PID drawings | |
| CN114445435A (en) | Vehicle body bolt looseness judging method based on mark line displacement deviation | |
| CN112396128A (en) | Automatic labeling method for railway external environment risk source sample | |
| CN105528485A (en) | Method for automatic contour extraction and path generation of bitmap | |
| CN112084973B (en) | Tunnel pipe ring identification and labeling method based on orthographic projection image | |
| CN106548479A (en) | A kind of multi-level laser point cloud building border rule method | |
| CN111241994A (en) | Method for extracting remote sensing image rural highway desertification road section for deep learning | |
| CN113269049A (en) | Method for detecting handwritten Chinese character area | |
| Xu et al. | Research on ship trajectory extraction based on multi-attribute DBSCAN optimisation algorithm | |
| CN111806651B (en) | Design and adjustment method of inclined guide chain type anchor system | |
| CN115291240B (en) | Detection method and system for perception and identification of retaining wall behind unloading point in mining area scene | |
| CN111414442A (en) | Navigation mark position checking method based on navigation channel topographic map and water level data | |
| CN105374024A (en) | A method for extracting bridges over water from high resolution satellite images | |
| Chung et al. | Road Pothole Detection Algorithm and Guide Belt Designed for Visually Impaired | |
| CN110481703B (en) | Manufacturing method of marine guide plate | |
| CN114359276A (en) | Steel die blanking optimization scheme obtaining method based on pockmark defects | |
| Vasin et al. | Increasing the effectiveness of intelligent information technology for producing digital graphic documents with weakly formalized description of objects | |
| CN113673776A (en) | Planning management method for ship route | |
| CN112200107A (en) | Invoice text detection method | |
| CN108763817B (en) | Electric underground pipe network matching method based on least square modeling | |
| CN113740364A (en) | Quantitative detection method for layering defects of drilled holes |
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 |