CN109993723A - A kind of pillow spring classification and Detection method based on machine vision - Google Patents
A kind of pillow spring classification and Detection method based on machine vision Download PDFInfo
- Publication number
- CN109993723A CN109993723A CN201711458585.1A CN201711458585A CN109993723A CN 109993723 A CN109993723 A CN 109993723A CN 201711458585 A CN201711458585 A CN 201711458585A CN 109993723 A CN109993723 A CN 109993723A
- Authority
- CN
- China
- Prior art keywords
- pillow spring
- pillow
- spring
- point cloud
- high angle
- 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- Withdrawn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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/30164—Workpiece; Machine component
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Library & Information Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
A kind of pillow spring classification and Detection method based on machine vision, comprising the following steps: step 1, typing pillow spring type;Step 2, the parameter of 3D vision imaging device is adjusted;Step 3, the characteristic radius value and classification range of pillow spring are set according to user demand;The feature free high angle value and acceptability limit of pillow spring are set according to user demand;Step 4,3D vision imaging device shoots the point cloud data of pillow spring and sends data to computer;Step 5, the image processing module of computer handles the point cloud data in step 4, judge whether to have in the point cloud data pillow spring whether there is or not;Step 6, the image processing module of computer calculates the free high angle value and radius value of pillow spring;Step 7, the data categorization module of computer judges the type of the pillow spring.Multiple types pillow spring group may be implemented using method of the invention and organize the automatic classification and detection of interior pillow spring, have the advantages that efficiency is fast, detection accuracy is high, accuracy rate is high.
Description
Technical field
The present invention relates to pillow spring fields, refer in particular to a kind of pillow spring classification and Detection method based on machine vision.
Background technique
Train servicing depot usually requires to measure the free high angle value of pillow spring before pillow spring assembly, by actual measured value
It is compared with the acceptability limit of setting, to judge that pillow spring is qualified or not.The pillow spring of train servicing depot is usually by a variety of different models
Pillow spring group composition, inside the pillow spring group of every kind of model again comprising spring in spring in the outer spring of bolster, bolster, the outer spring of damping, damping this
Four kinds of pillow springs.The standard free high of spring is different in the outer spring of general bolster, bolster, the standard free high of spring in the outer spring of damping, damping
It is identical.
The pillow spring of multiple types and type to realizing that pillow spring automatic detection brings difficulty, detect it is previous as need
Worker is wanted to carry out manual sort to pillow spring.Although can also currently be classified by pillow spring classifier to pillow spring, pillow spring point
Class owner will distinguish pillow spring by detection height, there is still a need for manually being separated interior spring and outer spring for the first time when feeding,
Its detection accuracy is low and most pillow springs that can only be directed to same model, needed when pillow spring model changes it is artificial more
Change parameter.
Summary of the invention
Against the above deficiency, the present invention proposes a kind of pillow spring classification and Detection method based on machine vision.
The purpose of the present invention is what is be achieved through the following technical solutions:
A kind of pillow spring classification and Detection method based on machine vision, comprising the following steps:
Step 1, check whether the pillow spring type contained in this batch pillow spring group to be detected is all present in Computer Database
In: if there is the pillow spring type not existed in database, then increase the type and characteristic parameter of corresponding pillow spring newly;If nothing,
Into in next step;
Step 2, location parameter, angle parameter, time for exposure and the field range of 3D vision imaging device are adjusted, it is clear to obtain
Clear target point cloud data;
Step 3, the characteristic radius value and classification range of pillow spring are set according to user demand;
The feature free high angle value and acceptability limit of pillow spring are set according to user demand;
Step 4,3D vision imaging device is shot the point cloud data of pillow spring and sends data to computer by shooting signal;
Step 5, the image processing module of computer handles the point cloud data in step 4, judges in the point cloud data
Whether pillow spring is had: if it is not, return step 4;If so, then entering in next step;
Step 6, the image processing module of computer calculates the free high angle value and radius value of pillow spring;
Step 7, the data categorization module of computer is by the free high angle value and radius value and database of the pillow spring calculated in step 6
In already present all kinds of pillow springs feature free high angle value and characteristic radius value compare, determine the type of the pillow spring.
Specific step is as follows for the free high angle value and radius value of calculating pillow spring described in step 6:
(1) image processing module of computer calculates the free high angle value of pillow spring: being partitioned into only based on preset height comprising support
The point cloud of disk;To segmentation only comprising the data reduction plane of pallet, identifies tray upper surface and calculate tray upper surface
Plane parameter;It is coordinately transformed according to point cloud data of the plane parameter of tray upper surface to pillow spring, by the point cloud of pillow spring
The coordinate origin and coordinate system transformation of data are to tray upper surface;According to preset pillow spring altitude range, it is partitioned into comprising pillow
The point cloud of spring upper surface;The maximum planes vertical to the data reduction normal vector comprising pillow spring upper surface are pillow spring upper surface;Meter
The height value for calculating pillow spring upper surface is the free high angle value of pillow spring;
(2) the image processing module image processing system of computer calculates the radius value of pillow spring: using clustering procedure to recognizing
Pillow spring upper end millet cake cloud cluster, extract the most point cloud group of counting, the point cloud of the pillow spring upper surface after as denoising;To denoising
The point cloud of pillow spring upper surface afterwards carries out Least Square Circle fitting, obtains pillow spring radius value.
Further include step 8, have determined that whether the pillow spring of type is qualified in the data detection module judgment step 7 of computer,
It specifically includes:
By pillow spring free high angle value calculated in step 7 compared with the feature free high angle value of the type pillow spring, such as in qualification
Qualifying signal is then exported in range and is sent into subsequent work stations;Unqualified signal is exported if not in acceptability limit, and is picked
It removes.
Multiple types pillow spring group may be implemented using method of the invention and organize the automatic classification and detection of interior pillow spring, have
The advantage that efficiency is fast, detection accuracy is high, accuracy rate is high.
Detailed description of the invention
Fig. 1 is flow diagram of the invention.
Specific embodiment
The present invention will be further described with reference to the accompanying drawing.
A kind of pillow spring classification and Detection method based on machine vision provided by the invention, as shown in Figure 1, including following step
It is rapid:
Step 1, check whether the pillow spring type contained in this batch pillow spring group to be detected is all present in Computer Database
In: if there is the pillow spring type not existed in database, then increase the type and characteristic parameter of corresponding pillow spring newly;If nothing,
Into in next step;
Step 2, location parameter, angle parameter, time for exposure and the field range of 3D vision imaging device are adjusted, it is clear to obtain
Clear target point cloud data;
Step 3, the characteristic radius value and classification range of pillow spring are set according to user demand;
The feature free high angle value and acceptability limit of pillow spring are set according to user demand;
Step 4,3D vision imaging device is shot the point cloud data of pillow spring and sends data to computer by shooting signal;
Step 5, the image processing module of computer handles the point cloud data in step 4, judges in the point cloud data
Whether pillow spring is had: if it is not, return step 4;If so, then entering in next step;
Step 6, the image processing module of computer calculates the free high angle value and radius value of pillow spring;
Step 7, the data categorization module of computer is by the free high angle value and radius value and database of the pillow spring calculated in step 6
In already present all kinds of pillow springs feature free high angle value and characteristic radius value compare, determine the type of the pillow spring.
Specific step is as follows for the free high angle value and radius value of calculating pillow spring described in step 6:
(1) image processing module of computer calculates the free high angle value of pillow spring: being partitioned into only based on preset height comprising support
The point cloud of disk;To segmentation only comprising the data reduction plane of pallet, identifies tray upper surface and calculate tray upper surface
Plane parameter;It is coordinately transformed according to point cloud data of the plane parameter of tray upper surface to pillow spring, by the point cloud of pillow spring
The coordinate origin and coordinate system transformation of data are to tray upper surface;According to preset pillow spring altitude range, it is partitioned into comprising pillow
The point cloud of spring upper surface;The maximum planes vertical to the data reduction normal vector comprising pillow spring upper surface are pillow spring upper surface;Meter
The height value for calculating pillow spring upper surface is the free high angle value of pillow spring;
(2) the image processing module image processing system of computer calculates the radius value of pillow spring: using clustering procedure to recognizing
Pillow spring upper end millet cake cloud cluster, extract the most point cloud group of counting, the point cloud of the pillow spring upper surface after as denoising;To denoising
The point cloud of pillow spring upper surface afterwards carries out Least Square Circle fitting, obtains pillow spring radius value.
Further include step 8, have determined that whether the pillow spring of type is qualified in the data detection module judgment step 7 of computer,
It specifically includes:
By pillow spring free high angle value calculated in step 7 compared with the feature free high angle value of the type pillow spring, such as in qualification
Qualifying signal is then exported in range and is sent into subsequent work stations;Unqualified signal is exported if not in acceptability limit, and is picked
It removes.
Compared with prior art, a kind of pillow spring classification and Detection method based on machine vision provided by the invention can be real
Existing multiple types pillow spring group and in organizing pillow spring automatic classification and detection, with that efficiency is fast, detection accuracy is high, accuracy rate is high is excellent
Point.
Claims (3)
1. a kind of pillow spring classification and Detection method based on machine vision, which comprises the following steps:
Step 1, check whether the pillow spring type contained in this batch pillow spring group to be detected is all present in Computer Database
In: if there is the pillow spring type not existed in database, then increase the type and characteristic parameter of corresponding pillow spring newly;If nothing,
Into in next step;
Step 2, location parameter, angle parameter, time for exposure and the field range of 3D vision imaging device are adjusted, it is clear to obtain
Clear target point cloud data;
Step 3, the characteristic radius value and classification range of pillow spring are set according to user demand;
The feature free high angle value and acceptability limit of pillow spring are set according to user demand;
Step 4,3D vision imaging device is shot the point cloud data of pillow spring and sends data to computer by shooting signal;
Step 5, the image processing module of computer handles the point cloud data in step 4, judges in the point cloud data
Whether pillow spring is had: if it is not, return step 4;If so, then entering in next step;
Step 6, the image processing module of computer calculates the free high angle value and radius value of pillow spring;
Step 7, the data categorization module of computer is by the free high angle value and radius value and database of the pillow spring calculated in step 6
In already present all kinds of pillow springs feature free high angle value and characteristic radius value compare, determine the type of the pillow spring.
2. a kind of pillow spring classification and Detection method based on machine vision as described in claim 1, which is characterized in that step 6 institute
Specific step is as follows for the free high angle value and radius value for the calculating pillow spring stated:
(1) image processing module of computer calculates the free high angle value of pillow spring: being partitioned into only based on preset height comprising support
The point cloud of disk;To segmentation only comprising the data reduction plane of pallet, identifies tray upper surface and calculate tray upper surface
Plane parameter;It is coordinately transformed according to point cloud data of the plane parameter of tray upper surface to pillow spring, by the point cloud of pillow spring
The coordinate origin and coordinate system transformation of data are to tray upper surface;According to preset pillow spring altitude range, it is partitioned into comprising pillow
The point cloud of spring upper surface;The maximum planes vertical to the data reduction normal vector comprising pillow spring upper surface are pillow spring upper surface;Meter
The height value for calculating pillow spring upper surface is the free high angle value of pillow spring;
(2) the image processing module image processing system of computer calculates the radius value of pillow spring: using clustering procedure to recognizing
Pillow spring upper end millet cake cloud cluster, extract the most point cloud group of counting, the point cloud of the pillow spring upper surface after as denoising;To denoising
The point cloud of pillow spring upper surface afterwards carries out Least Square Circle fitting, obtains pillow spring radius value.
3. a kind of pillow spring classification and Detection method based on machine vision as described in claim 1, which is characterized in that further include step
Rapid 8, have determined that whether the pillow spring of type is qualified in the data detection module judgment step 7 of computer;It specifically includes:
By pillow spring free high angle value calculated in step 7 compared with the feature free high angle value of the type pillow spring, such as in qualification
Qualifying signal is then exported in range and is sent into subsequent work stations;Unqualified signal is exported if not in acceptability limit, and is picked
It removes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711458585.1A CN109993723A (en) | 2017-12-28 | 2017-12-28 | A kind of pillow spring classification and Detection method based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711458585.1A CN109993723A (en) | 2017-12-28 | 2017-12-28 | A kind of pillow spring classification and Detection method based on machine vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109993723A true CN109993723A (en) | 2019-07-09 |
Family
ID=67108260
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711458585.1A Withdrawn CN109993723A (en) | 2017-12-28 | 2017-12-28 | A kind of pillow spring classification and Detection method based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109993723A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111957592A (en) * | 2020-08-06 | 2020-11-20 | 姜斌 | Railway wagon bogie sleeper spring sorting system and sorting method thereof |
WO2021088245A1 (en) * | 2019-11-05 | 2021-05-14 | 南京拓控信息科技股份有限公司 | Visual inspection and intelligent selection and matching system for truck bolster spring, and use method |
CN114001648A (en) * | 2020-07-28 | 2022-02-01 | 南京景曜智能科技有限公司 | Spring coil number detection device and detection method |
CN114004990A (en) * | 2020-07-28 | 2022-02-01 | 南京景曜智能科技有限公司 | System and method for efficiently judging type of occipital spring |
-
2017
- 2017-12-28 CN CN201711458585.1A patent/CN109993723A/en not_active Withdrawn
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021088245A1 (en) * | 2019-11-05 | 2021-05-14 | 南京拓控信息科技股份有限公司 | Visual inspection and intelligent selection and matching system for truck bolster spring, and use method |
CN114001648A (en) * | 2020-07-28 | 2022-02-01 | 南京景曜智能科技有限公司 | Spring coil number detection device and detection method |
CN114004990A (en) * | 2020-07-28 | 2022-02-01 | 南京景曜智能科技有限公司 | System and method for efficiently judging type of occipital spring |
CN114004990B (en) * | 2020-07-28 | 2024-05-14 | 南京景曜智能科技有限公司 | System and method for efficiently judging type of sleeper spring |
CN111957592A (en) * | 2020-08-06 | 2020-11-20 | 姜斌 | Railway wagon bogie sleeper spring sorting system and sorting method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109993723A (en) | A kind of pillow spring classification and Detection method based on machine vision | |
CN106384079B (en) | A kind of real-time pedestrian tracting method based on RGB-D information | |
KR102056664B1 (en) | Method for work using the sensor and system for performing thereof | |
CN109978938A (en) | A kind of pillow spring detection method based on machine vision | |
CN107705563B (en) | Laser radar-based continuous vehicle speed detection method | |
CN109741314A (en) | A kind of visible detection method and system of part | |
CN103729631A (en) | Vision-based connector surface feature automatically-identifying method | |
CN110866894B (en) | Cross-granularity sheet metal part identification system and method based on machine vision technology | |
CN105139384B (en) | The method and apparatus of defect capsule detection | |
CN105478363A (en) | Defective product detection and classification method and system based on three-dimensional figures | |
CN108664860B (en) | Method and device for identifying room plan | |
CN110047133A (en) | A kind of train boundary extraction method towards point cloud data | |
CN107273421B (en) | High-accuracy mode identification and detection method for aroma type and quality of tea | |
CN110619336A (en) | Goods identification algorithm based on image processing | |
CN103245667A (en) | Method and system for automatically detecting mechanical scratches | |
CN103196918A (en) | Key assembling detection method for vehicle air conditioner control panel | |
CN105989600A (en) | Characteristic point distribution statistics-based power distribution network device appearance detection method and system | |
CN113240731B (en) | Method and device for determining central position of tray, electronic equipment and storage medium | |
CN114332622A (en) | Label detection method based on machine vision | |
CN113446932A (en) | Non-contact crack measuring method and system | |
CN102968618A (en) | Static hand gesture recognition method fused with BoF model and spectral clustering algorithm | |
CN103544495A (en) | Method and system for recognizing of image categories | |
CN103093214A (en) | Pedestrian detection method based on on-board infrared camera | |
CN108985325A (en) | A kind of classification method, device, equipment and system | |
CN116051540B (en) | Method and system for acquiring positioning pose of transformer wiring terminal based on point cloud model |
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: 20190709 |
|
WW01 | Invention patent application withdrawn after publication |