CN106558048B - Screw array dystopy fault detection method and system - Google Patents
Screw array dystopy fault detection method and system Download PDFInfo
- Publication number
- CN106558048B CN106558048B CN201611066397.XA CN201611066397A CN106558048B CN 106558048 B CN106558048 B CN 106558048B CN 201611066397 A CN201611066397 A CN 201611066397A CN 106558048 B CN106558048 B CN 106558048B
- Authority
- CN
- China
- Prior art keywords
- screw
- image
- label
- subgraph
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06T7/0006—Industrial image inspection using a design-rule based approach
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of screw array dystopy fault detection method and system, determine linear first label being arranged in nut, screw area two sides are provided with the second label and third label, when normal, first label, second label and third label are in same straight line, when screw array failure, first label is vertical with second label and third label, obtain covering image, and extract screw area image in covering image, segmentation obtains the subgraph in each screw area, calculate the length of longest line segment in each subgraph, when the length of longest line segment in subgraph is less than preset threshold, determine the screw failure in the subgraph.In whole process, using a variety of image processing means, accurately the automatic diagnosis of screw array dystopy failure is identified.
Description
Technical field
The present invention relates to fault detection technique fields, more particularly to screw array dystopy fault detection method and system.
Background technique
Screw is usually used in fixed object, when two objects to some bigger range contact are fixed, can often adopt
It is fixed with screw array, such as covering screw.
Covering screw can be affected with the presence or absence of abnormal directly to the safety of entire housing construction.It is with aircraft skin
Example, the engineering maintenance of high reliability high quality is aircraft safety flight important guarantee.Currently, taking human as main Maintenance errors in aviation
It is difficult to avoid the aircraft safety hidden danger as caused by human error.
For the detachable covering of aircraft, the installation of a covering is fixed to generally require dozens of even up to a hundred fastly
Formula screw is unloaded, flight crew needs continuous duplicate disassembly mounting screw in entire maintenance process, this simple, repeatedly and withered
Dry work, easily goes wrong, and leads to neglected loading or does not tighten certain screw, causes security risk, or even cause flight safety thing
Therefore.There is an urgent need to a kind of means of automation for this to assist solving the problems, such as this.
Summary of the invention
Based on this, it is necessary to aiming at the problem that there is no screw array dystopy fault detection at present, provide a kind of accurate spiral shell
Follow closely array dystopy fault detection method and system.
A kind of screw array dystopy fault detection method, comprising steps of
Determine that linear first that nut is set in screw marks and be respectively arranged at the second of screw area two sides
Label is marked with third, and when screw array is normal, first label, second label and third label are in
Same straight line, when screw array failure, first label is vertical with second label and third label；
Covering image is obtained, and extracts screw area image in covering image；
Divide screw area image, obtains the subgraph in each screw area；
Calculate the length of longest line segment in each subgraph；
By the length of longest line segment in each subgraph compared with preset threshold, when the length of longest line segment in subgraph is less than
When preset threshold, the screw failure in the subgraph is determined.
A kind of screw array dystopy fault detection system, comprising:
Determining module, for determining that linear first for being set to nut in screw marks and be respectively arranged at screw
The second label and the third of area two sides mark, and when screw array is normal, described first is marked, described second marks and described
Third label is in same straight line, when screw array failure, first label and second label and the third
Label is vertical；
Image zooming-out module for obtaining covering image, and extracts screw area image in covering image；
Divide module and obtains the subgraph in each screw area for dividing screw area image；
Computing module, for calculating the length of longest line segment in each subgraph；
Detection module, for by the length of longest line segment in each subgraph compared with preset threshold, when longest in subgraph
When the length of line segment is less than preset threshold, the screw failure in the subgraph is determined.
Screw array dystopy fault detection method of the present invention and system determine linear first label being arranged in nut,
Screw area two sides are provided with the second label and third label, and when normal, the first label, the second label and third label are in
Same straight line, when screw array failure, first label is vertical with second label and third label, obtains
Covering image, and screw area image in covering image is extracted, segmentation obtains the subgraph in each screw area, calculates in each subgraph most
The length of long line segment determines the screw failure in the subgraph when the length of longest line segment in subgraph is less than preset threshold.
In whole process, using a variety of image processing means, accurately the automatic diagnosis of screw array dystopy failure is identified.
Detailed description of the invention
Fig. 1 is the flow diagram of screw array dystopy fault detection method one embodiment of the present invention；
Fig. 2 is local aircraft skin figure；
Fig. 3 is screw array local aircraft skin figure under normal circumstances；
Fig. 4 is local aircraft skin figure in the case of screw array failure；
Fig. 5 is the flow diagram of second embodiment of screw array dystopy fault detection method of the present invention；
Fig. 6 is that covering takes complement；
Fig. 7 is that covering removes Background；
Fig. 8 is each screw region threshold segmentation figure；
Fig. 9 is screw skeleton drawing；
Figure 10 is each screw region branch point diagram；
Figure 11 is the locating segmentation figure in each screw region；
Figure 12 is each screw state diagnostic graph；
Figure 13 is the optimization figure in each screw region；
Figure 14 is the structural schematic diagram of screw array dystopy fault detection system one embodiment of the present invention；
Figure 15 is the structural schematic diagram of second embodiment of screw array dystopy fault detection system of the present invention.
Specific embodiment
As shown in Figure 1, a kind of screw array dystopy fault detection method, comprising steps of
S100: it determines the first linear label for being set to nut in screw and is respectively arranged at screw area two sides
Second label is marked with third, when screw array is normal, first label, second label and third label
In same straight line, when screw array failure, first label is vertical with second label and third label.
The test object of screw array dystopy fault detection method of the present invention is screw, and specifically, nut is set in screw
It is equipped with the first linear label, screw area two sides are respectively arranged with the second label and third label, when screw array is normal
When, the first label, the second label and third label are in same straight line, when screw array failure, first label
It is vertical with second label and third label.By taking the screw in aircraft skin as an example, as shown in Fig. 2, Fig. 2 is aircraft illiteracy
Pi Tu, in Fig. 2, the feature of aircraft screw is to have a groove (the first label), screw area two at the intermediate position of screw nut
Side indicates entopic two short-terms of screw (the second label is marked with third), normal condition, as shown in figure 3, descending these three
Part is in a straight line, fault condition, lower groove as shown in Figure 4 and screw position tag line near normal.Screw event herein
Barrier is the non-tight condition of screw.
S200: covering image is obtained, and extracts screw area image in covering image.
Covering image can be directly shot using image acquisition equipment or is directly imported from other equipment (such as USB flash disk)
The equipment of the covering image deposited, shooting covering image can be digital camera, smart phone or industrial camera.In covering image
It mainly include screw area image and background image, subsequent operation is operated primarily directed to screw area image, mentioned herein
Take screw area image in covering image.It is non-essential, to avoid background image to the interference of subsequent processing, needs accurately to extract and cover
Screw area image in skin image.
As step S200 includes: Fig. 5 in one of the embodiments,
S220: covering image is converted into gray level image.
For convenient for the processing of image analysis, conversion chromatic image is grayscale image, screw groove (the first label) in grayscale image
It is obvious with image background regions contrast with screw two sides tag line (the second label and third label).
S240: successively carry out taking complementary operation, opening operation, additive operation, median filtering and adaptive to greyscale image data
Thresholding dividing processing is answered, screw area image in covering image is extracted.
Image is carried out to take complementary operation, exchanges screw area and covering background area, as shown in Figure 6.Image surrounding is inclined in Fig. 6
Bright, middle part is partially dark, brightness irregularities, carries out opening operation and additive operation to image, removal image background regions brightness disproportionation
It influences.As shown in fig. 7, screw annular regions have certain interference to the detection identification in screw area, make an uproar to guarantee to eliminate circle ring area
While sound, retain the detailed information of screw groove and tag line, selects median filtering to handle image, after median filtering
Image, entire screw regional luminance is uneven, to eliminate influence of the luminance difference to image segmentation, selects adaptive threshold pair
Image carries out Threshold segmentation, obtains image as shown in Figure 8.
S400: segmentation screw area image obtains the subgraph in each screw area.
There are the corresponding screw area image of multiple screws in screw area image, need respectively to each screw area image into
Row fault detection.It is split here, obtaining screw area image to step S200, obtains the subgraph in each screw area.It is specific next
It says, dividing method can be with are as follows: image obtained by micronization processes step S200 simultaneously subtracts each other therewith, obtains screw skeleton spine image, mentions
The branch point for taking screw skeleton spine image carries out expansion process to screw skeleton spine branch point diagram picture, is connected to each screw area
The branch point in domain, counts the center-of-mass coordinate and region area in each screw region, and image obtained by segmentation step S200 obtains each screw
The subgraph in area.
As shown in figure 5, in one of the embodiments, step S400 comprising steps of
S410: micronization processes to greatest extent are carried out to screw area image, obtain screw skeleton image, wherein to greatest extent
Micronization processes criterion is to approach picture as far as possible under the premise of guaranteeing that the connected pixel area in image is not broken in thinning process
Plain zone centerline.
It carries out micronization processes to greatest extent first, while guaranteeing the connected pixel area in image in thinning process constantly
It splits, approaches pixel zone centerline in thinning process as far as possible.Specifically as shown in figure 9, Fig. 9 is to carry out maximum to screw area image
The image obtained after limit micronization processes, line-like structures are known as the skeleton of image in Fig. 9.
S420: screw skeleton spine image is obtained.
By the image and screw area image subtraction after micronization processes, screw skeleton spine image is obtained.In simple terms, false
Determining screw area image is A image, carries out obtaining B image after micronization processes to greatest extent to it, A image is subtracted B image, is obtained
Obtain screw skeleton spine image C.That is screw skeleton spine image C=A image-B image.
S430: the branch point in screw skeleton spine image is extracted.
For the screw skeleton spine image that step S420 is obtained, branch point therein is extracted.Specifically, it removes first
Step S420 obtain screw skeleton spine image in spine, then, by the image of acquisition again with screw skeleton spine image phase
Subtract, obtain screw image framework spine, finally, determining screw skeleton spine image branch point, and as each screw area key point.
In simple terms, it is assumed that step S420 acquisition is screw skeleton spine image C, removes the spine in screw skeleton spine image C,
Image D is obtained, then screw skeleton spine image C and image D is subtracted each other, obtains screw image framework spine, the screw that will be obtained
Image framework spine is specific as shown in Figure 10 as screw skeleton spine image branch point.
S440: expansion process branch point, with the branch point being connected in each screw area.
Expansion process is carried out to the branch point that step S430 is obtained, with the branch point being connected in each screw area.
S450: counting the center-of-mass coordinate and region area in each screw area, divides screw area image, obtains the son in each screw area
Image.
After the branch point that step S440 is connected in each screw area, the approximate location to each target area may be implemented, into
One step combines each screw area area, then the screw region in divisible image, specific as shown in figure 11.
S600: the length of longest line segment in each subgraph is calculated.
For the subgraph in each screw area obtained step S400, the length of longest line segment in subgraph is calculated separately.Tool
For body, the longest line segment in each subgraph can be calculated using Hough transformation by calculating, i.e., carry out in parameter space simple
Cumulative statistics, by finding the straight line in accumulator peak detection image space in hough space.
S800: by the length of longest line segment in each subgraph compared with preset threshold, when the length of longest line segment in subgraph
When degree is less than preset threshold, the screw failure in the subgraph is determined.
Compare longest line segment and the threshold value in each subgraph, if the longest line segment is less than threshold value, judges in the subgraph
Screw failure, otherwise, the screw in the subgraph is normal, as shown in figure 12.
It is non-essential, as shown in figure 5, being further comprised the steps of: before step S800 in one of the embodiments,
S720: random selection obtains the subgraph at least 2 width screw areas.
To the subgraph in the screw area obtained step S400, at least 2 width are randomly selected.For the standard for improving final fault detection
Exactness, the herein subgraph in available more screw area, it might even be possible to obtain the subgraph in whole screws area.
S740: calculate in the subgraph in the screw area of selection second label third label between longest distance it is equal
Value.
Calculate step S720 obtain screw area subgraph in second label third label between longest distance it is equal
Value, using the accuracy for improving data in a manner of averaging.
S760: by mean value multiplied by proportionality coefficient, preset threshold is obtained, proportionality coefficient is more than or equal to 0.8 and is less than or equal to
0.9。
The mean value that step S740 is obtained obtains preset threshold multiplied by 0.8~0.9.
Specifically, 5~10 width of S400 neutron image, when screw is normal, the longest straight line in the subgraph are randomly choosed
Through the first label, the second label and third label, when the longest line segment in screw failure, the subgraph can not run through three simultaneously
A label, therefore calculate the mean value of longest distance between the second label and third label in each subgraph, by this value multiplied by 0.8~
0.9 is used as threshold value.
Screw array dystopy fault detection method of the present invention determines linear first label being arranged in nut, screw area
Two sides are provided with the second label and third label, and when normal, the first label, the second label and third label are in same
Straight line, when screw array failure, first label is vertical with second label and third label, obtains covering figure
Picture, and screw area image in covering image is extracted, segmentation obtains the subgraph in each screw area, calculates longest line segment in each subgraph
Length, when the length of longest line segment in subgraph be less than preset threshold when, determine the screw failure in the subgraph.Entire mistake
Cheng Zhong accurately identifies the automatic diagnosis of screw array dystopy failure using a variety of image processing means.
As shown in figure 5, in one of the embodiments, before step S400 further include:
S300: expansion and corrosion treatment are successively carried out to screw area image.
In tag line (the second mark of screw groove line segment (the first label) and screw two sides after normal screw area Threshold segmentation
Note and third label) it does not plan a successor between section, to be connected to screw groove line segment and the tag line of screw two sides, successively to image
Expansion and corrosion treatment are carried out, to optimize screw area image, as shown in figure 13.
As shown in figure 14, a kind of screw array dystopy fault detection system, comprising:
Determining module 100, for determining that linear first for being set to nut in screw marks and be respectively arranged at
Screw area two sides second label with third mark, when screw array is normal, it is described first label, it is described second label and
Third label is in same straight line, and when screw array failure, first label marks and described with described second
Third label is vertical.
Image zooming-out module 200 for obtaining covering image, and extracts screw area image in covering image.
Divide module 400 and obtains the subgraph in each screw area for dividing screw area image.
Computing module 600, for calculating the length of longest line segment in each subgraph.
Detection module 800, for by the length of longest line segment in each subgraph compared with preset threshold, when in subgraph most
When the length of long line segment is less than preset threshold, the screw failure in the subgraph is determined.
Screw array dystopy fault detection system of the present invention, determining module 100 determine linear first be arranged in nut
Label, screw area two sides are provided with the second label and third label, when normal, the first label, the second label and third mark
Note is in same straight line, and when screw array failure, first label hangs down with second label and third label
Directly, image zooming-out module 200 obtains covering image, and extracts screw area image in covering image, and the segmentation segmentation of module 400 obtains
The subgraph in each screw area, computing module 600 calculate the length of longest line segment in each subgraph, when longest line segment in subgraph
When length is less than preset threshold, detection module 800 determines the screw failure in the subgraph.In whole process, using a variety of figures
As processing means, accurately the automatic diagnosis of screw array dystopy failure is identified, it is ensured that by the safety of covering housing construction.
As shown in figure 15, image zooming-out module 200 includes: in one of the embodiments,
Gradation conversion unit 220, for covering image to be converted to gray level image.
Extraction unit 240 takes complementary operation, opening operation, additive operation, intermediate value filter for successively carrying out to greyscale image data
Wave and self-adaptive filtering method processing, extract screw area image in covering image.
As shown in figure 15, screw array dystopy fault detection system in one of the embodiments, further include:
Optimization module 300, for successively carrying out expansion and corrosion treatment to screw area image.
As shown in figure 15, segmentation module 400 includes: in one of the embodiments,
Skeleton image acquiring unit 410 obtains screw skeleton for carrying out micronization processes to greatest extent to screw area image
Image, wherein micronization processes criterion is before the connected pixel area in guarantee image is not broken in thinning process to greatest extent
It puts, approaches pixel zone centerline as far as possible.
Spine image acquisition unit 420, for obtaining screw skeleton spine image.
Bifurcation extracting unit 430, for extracting the branch point in screw skeleton spine image.
Expansion cell 440 is used for expansion process branch point, with the branch point being connected in each screw area.
Cutting unit 450 is divided screw area image, is obtained for counting the center-of-mass coordinate and region area in each screw area
The subgraph in each screw area.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (8)
1. a kind of screw array dystopy fault detection method, which is characterized in that comprising steps of
Determine the first linear label that nut is set in screw and the second label for being respectively arranged at screw area two sides
It is marked with third, when screw array is normal, first label, second label and third label are in same
Straight line, when screw array failure, first label is marked with described second and third label is vertical；
Covering image is obtained, and extracts screw area image in the covering image；
Divide screw area image, obtains the subgraph in each screw area；
Calculate the length of longest line segment in each subgraph；
By the length of longest line segment in each subgraph compared with preset threshold, when the length of longest line segment in the subgraph
When less than the preset threshold, the screw failure in the subgraph is determined；
Wherein, segmentation screw area image, the subgraph for obtaining each screw area include:
Micronization processes to greatest extent are carried out to screw area image, obtain screw skeleton image, wherein is described thin to greatest extent
Changing processing criterion is to approach pixel as far as possible under the premise of guaranteeing that the connected pixel area in image is not broken in thinning process
Zone centerline；
Obtain screw skeleton spine image；
Extract the branch point in the screw skeleton spine image；
Branch point described in expansion process, with the branch point being connected in each screw area；
The center-of-mass coordinate and region area for counting each screw area divide screw area image, obtain the subgraph in each screw area.
2. screw array dystopy fault detection method according to claim 1, which is characterized in that described to obtain the covering
The step of screw area image, includes: in image
The covering image is converted into gray level image；
The greyscale image data is successively carried out to take complementary operation, opening operation, additive operation, median filtering and adaptive threshold
Dividing processing extracts screw area image in the covering image.
3. screw array dystopy fault detection method according to claim 1, which is characterized in that the segmentation screw
Area's image, before the step of obtaining the subgraph in each screw area further include:
Expansion and corrosion treatment are successively carried out to screw area image.
4. screw array dystopy fault detection method according to claim 1, which is characterized in that described to calculate each son
The step of length of longest line segment, includes: in image
Longest line segment in each subgraph is calculated using Hough transformation.
5. screw array dystopy fault detection method according to claim 1, which is characterized in that described by each subgraph
Before the step of length of longest line segment is compared with preset threshold as in further include:
Random selection obtains the subgraph at least 2 width screw areas；
Calculate the mean value of longest distance between second label in the subgraph in the screw area chosen and third label；
By the mean value multiplied by proportionality coefficient, preset threshold is obtained, the proportionality coefficient is more than or equal to 0.8 and is less than or equal to 0.9.
6. a kind of screw array dystopy fault detection system characterized by comprising
Determination unit, for determining that linear first for being set to nut in screw marks and be respectively arranged at screw area two
The second label and the third of side mark, when screw array is normal, first label, second label and the third
Label is in same straight line, and when screw array failure, first label is marked with second label and the third
Vertically；
Image zooming-out module for obtaining covering image, and extracts screw area image in the covering image；
Divide module and obtains the subgraph in each screw area for dividing screw area image；
Computing module, for calculating the length of longest line segment in each subgraph；
Detection module, for by the length of longest line segment in each subgraph compared with preset threshold, when in the subgraph
When the length of longest line segment is less than the preset threshold, the screw failure in the subgraph is determined；
Wherein, the segmentation module includes:
Skeleton image acquiring unit obtains screw skeleton drawing for carrying out micronization processes to greatest extent to screw area image
Picture, wherein micronization processes criterion is to guarantee the not broken premise in thinning process of the connected pixel area in image to greatest extent
Under, pixel zone centerline is approached as far as possible；
Spine image acquisition unit, for obtaining screw skeleton spine image；
Bifurcation extracting unit, for extracting the branch point in the screw skeleton spine image；
Expansion cell, for branch point described in expansion process, with the branch point being connected in each screw area；
Cutting unit divides screw area image, obtains each spiral shell for counting the center-of-mass coordinate and region area in each screw area
Follow closely the subgraph in area.
7. screw array dystopy fault detection system according to claim 6, which is characterized in that described image extraction module
Include:
Gradation conversion unit, for the covering image to be converted to gray level image；
Extraction unit takes complementary operation, opening operation, additive operation, median filtering for successively carrying out to the greyscale image data
And self-adaptive filtering method processing, extract screw area image in the covering image.
8. screw array dystopy fault detection system according to claim 6, which is characterized in that further include:
Optimization module, for successively carrying out expansion and corrosion treatment to screw area image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611066397.XA CN106558048B (en) | 2016-11-28 | 2016-11-28 | Screw array dystopy fault detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611066397.XA CN106558048B (en) | 2016-11-28 | 2016-11-28 | Screw array dystopy fault detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106558048A CN106558048A (en) | 2017-04-05 |
| CN106558048B true CN106558048B (en) | 2019-05-24 |
Family
ID=58445446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611066397.XA Active CN106558048B (en) | 2016-11-28 | 2016-11-28 | Screw array dystopy fault detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106558048B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112184588A (en) * | 2020-09-29 | 2021-01-05 | 哈尔滨市科佳通用机电股份有限公司 | Image enhancement system and method for fault detection |
| CN113486739B (en) * | 2021-06-22 | 2024-05-24 | 深圳无境创新科技有限公司 | Screw detection method, device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5221984B2 (en) * | 2008-02-29 | 2013-06-26 | 三菱重工業株式会社 | Fastener looseness detection system and looseness detection method |
| CN103500328A (en) * | 2013-10-16 | 2014-01-08 | 北京航空航天大学 | Method for automatically detecting deflection fault of railway wagon locking plate |
| CN104318582A (en) * | 2014-11-14 | 2015-01-28 | 西南交通大学 | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network on basis of image invariance target positioning |
| CN104680517A (en) * | 2015-01-22 | 2015-06-03 | 清华大学 | Looseness detection method of bolt |
| CN105241679A (en) * | 2015-09-21 | 2016-01-13 | 中国铁道科学研究院电子计算技术研究所 | Method for detecting hidden fault of motor train unit |
| CN105354827A (en) * | 2015-10-08 | 2016-02-24 | 成都唐源电气有限责任公司 | Method and system for intelligently identifying clamp nut shedding in catenary image |
| CN105424711A (en) * | 2015-12-04 | 2016-03-23 | 清华大学苏州汽车研究院（吴江） | Automatic test equipment and method for screw looseness of locomotive |
| CN105424330A (en) * | 2014-08-29 | 2016-03-23 | 北京航空航天大学 | Lorry shaft end bolt fault detecting method and lorry shaft end bolt fault detecting device |
-
2016
- 2016-11-28 CN CN201611066397.XA patent/CN106558048B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5221984B2 (en) * | 2008-02-29 | 2013-06-26 | 三菱重工業株式会社 | Fastener looseness detection system and looseness detection method |
| CN103500328A (en) * | 2013-10-16 | 2014-01-08 | 北京航空航天大学 | Method for automatically detecting deflection fault of railway wagon locking plate |
| CN105424330A (en) * | 2014-08-29 | 2016-03-23 | 北京航空航天大学 | Lorry shaft end bolt fault detecting method and lorry shaft end bolt fault detecting device |
| CN104318582A (en) * | 2014-11-14 | 2015-01-28 | 西南交通大学 | Detection method for bad state of rotating double-lug component pin of high-speed rail contact network on basis of image invariance target positioning |
| CN104680517A (en) * | 2015-01-22 | 2015-06-03 | 清华大学 | Looseness detection method of bolt |
| CN105241679A (en) * | 2015-09-21 | 2016-01-13 | 中国铁道科学研究院电子计算技术研究所 | Method for detecting hidden fault of motor train unit |
| CN105354827A (en) * | 2015-10-08 | 2016-02-24 | 成都唐源电气有限责任公司 | Method and system for intelligently identifying clamp nut shedding in catenary image |
| CN105424711A (en) * | 2015-12-04 | 2016-03-23 | 清华大学苏州汽车研究院（吴江） | Automatic test equipment and method for screw looseness of locomotive |
Non-Patent Citations (2)
| Title |
|---|
| 《光杆六角螺栓的视觉检测》;周志峰;《光学技术》;20120731;第38卷(第4期);第415-420页 |
| 《基于机器视觉的螺钉多参数在线监测》;周桐等;《机械工业标准化与质量》;20151130(第11期);第34-37页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106558048A (en) | 2017-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2608536B1 (en) | Method for counting objects and apparatus using a plurality of sensors | |
| US10152650B2 (en) | Trademark retrieval method, apparatus and system, and computer storage medium | |
| US10691947B2 (en) | Monitoring device | |
| CN102628854A (en) | Automobile instrument board detection system and method | |
| CN110956180B (en) | Detection method and system of counterweight weight, acquisition method and system and crane | |
| CN116563282B (en) | Drilling tool detection method and system based on machine vision | |
| US10430687B2 (en) | Trademark graph element identification method, apparatus and system, and computer storage medium | |
| CN106558048B (en) | Screw array dystopy fault detection method and system | |
| CN109685974A (en) | A kind of detection system and method for library's intelligence also book based on image procossing | |
| CN114004790B (en) | A battery cover quality detection method, device, computer equipment and storage medium | |
| CN111310753B (en) | Meter alignment method and device | |
| CN114066862A (en) | Indicator identification method and system based on color gamut and contour characteristics | |
| US20190117147A1 (en) | Evaluation method for site of color irregularity and color irregularity site evaluation apparatus | |
| CN108133479B (en) | Automatic spinning machine drawing-in monitoring method and device | |
| CN114663457A (en) | Bobbin identification method and system based on circular convolution kernel under complex background | |
| US11922680B2 (en) | Image determination device, image determination method, and non-transitory computer readable medium storing program | |
| CN117274250B (en) | Visual detection method for wear defect of watch bottom cover | |
| CN118229568A (en) | Image edge de-pseudo noise reduction method and device, equipment and storage medium | |
| CN109658452B (en) | Track gauge detection method and device | |
| Muzammil et al. | Application of image processing techniques for the extraction of vehicle number plates over ARM target board | |
| Frucci et al. | Idem: Iris detection on mobile devices | |
| CN110929681A (en) | Wrinkle detection method | |
| Magnier et al. | A quantitative error measure for the evaluation of roof edge detectors | |
| CN110021016B (en) | Calcification detection method | |
| CN112991251B (en) | Method, device and equipment for detecting surface defects |
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 |