CN109978938A - A kind of pillow spring detection method based on machine vision - Google Patents
A kind of pillow spring detection method based on machine vision Download PDFInfo
- Publication number
- CN109978938A CN109978938A CN201711460226.XA CN201711460226A CN109978938A CN 109978938 A CN109978938 A CN 109978938A CN 201711460226 A CN201711460226 A CN 201711460226A CN 109978938 A CN109978938 A CN 109978938A
- Authority
- CN
- China
- Prior art keywords
- pillow spring
- pillow
- data processing
- spring
- point cloud
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
A kind of pillow spring detection method based on machine vision, includes the following steps: step 1, and according to detection demand, the acceptability limit of the detection parameters of pillow spring is arranged;Step 2, the parameter of 3D vision imaging device is adjusted, to obtain clearly target area point cloud data;Step 3, data processing starts to act after obtaining pillow spring arriving signal with control system, target area point cloud data including pillow spring is included by the control vision imaging device acquisition of the control module of data processing and control system, and target area point cloud data is sent to data processing and control system;Step 4, data processing module calculates the parameter values for detection of pillow spring;Step 5, data detection module judges that pillow spring is qualified or not.It can disposably realize the detection of multiple parameters automatically using method of the invention, detection efficiency is high, rhythm is fast, and precision is high, the subsequent tracing and statistical analysis that testing result can also save convenient for pillow spring testing result.
Description
Technical field
The present invention relates to pillow spring detection fields, refer in particular to a kind of pillow spring detection method based on machine vision.
Background technique
Train servicing depot generallys use following manner detection train sleeper spring: as measured pillow spring certainly by detection machine or height gauge
By height value, using the degree of corrosion etc. of outer diameter callipers detection round steel diameter.That is numerous detection projects of pillow spring generally require to rely on
A variety of different type machines or artificial one by onechecking, process is more and complicated and inefficient, also easily because human error influences
The accuracy rate of detection, detection accuracy is not high caused by limiting because of detection instrument itself.
Summary of the invention
Against the above deficiency, the present invention proposes a kind of pillow spring 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 detection method based on machine vision, includes the following steps:
Step 1, according to detection demand, the detection parameters free high angle value of pillow spring and the acceptability limit of radius value are set;
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 area point cloud data;
Step 3, data processing and control system start to act after obtaining pillow spring arriving signal, by data processing and control system
Control module controls vision imaging device acquisition and includes the target area point cloud data including pillow spring, and by target area point cloud number
According to being sent to data processing and control system;
Step 4, the data processing module of data processing and control system handles target area point cloud data, calculates pillow
The detection parameters of spring, specifically include:
(1) data processing module calculates the free high angle value of pillow spring: being partitioned into based on preset height only includes pallet
Point cloud;To segmentation only comprising the data reduction plane of pallet, identifies tray upper surface and calculate the flat of tray upper surface
Face 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 data of pillow spring
Coordinate origin and coordinate system transformation to tray upper surface;According to preset pillow spring altitude range, it is partitioned into comprising in pillow spring
The point cloud of end face;The maximum planes vertical to the data reduction normal vector comprising pillow spring upper surface are pillow spring upper surface;Calculate pillow
The height value of spring upper surface is the free high angle value of pillow spring;
(2) data processing module calculates the radius value of pillow spring: using clustering procedure to the pillow spring upper end millet cake cloud recognized
Cluster extracts most point cloud group of counting, the point cloud of the pillow spring upper surface after as denoising;To the pillow spring upper surface after denoising
Point cloud carries out Least Square Circle fitting, obtains pillow spring radius value;
Step 5, the data detection module of data processing and control system will be in detection parameters calculated in step 4 and step 1
The acceptability limit of the correspondence detection parameters of setting compares, and qualifying signal is exported if in acceptability limit and is sent into subsequent work stations;
Unqualified signal is exported if not in acceptability limit, and is rejected.
The mode that data processing described in step 3 and control system obtain pillow spring arriving signal is photoelectric sensor.
The detection parameters of pillow spring described in step 1 further include 5/8 angle value and 1/4 high level, are specifically carried out in the steps below
Detection:
(1) data processing module calculates 5/8 angle value of pillow spring: stepping through to pillow spring upper end millet cake cloud, asks each
The angle of point and circle center line connecting and reference axis x, calculates 5/8 angle value of pillow spring;
(2) data processing module calculates 1/4 height of pillow spring: it is the smallest to obtain z value for point all in traversal central diameter first
Point, the pillow spring free high angle value obtained in step 4 subtract its z value, as 1/4 high absolute value;It is then based on pillow spring freedom
Height value is partitioned into the point cloud of pillow spring middle section, clusters to a cloud, isolates each pillow spring circle and seeks the matter of pillow spring circle
The average value of heart distance, as pillow spring pitch;It is finally the 1/4 of pillow spring divided by pillow spring pitch by 1/4 high absolute value
High level.
Data processing and control system further include the data memory module for saving calculated detected value in step 4, are used for
The retrospect of pillow spring testing result and statistical analysis.
Free high angle value, radius value, 5/8 angle value, 1/4 high level can disposably be realized using method of the invention automatically
Detection, detection efficiency is high, rhythm is fast, and precision is high, testing result can also save convenient for pillow spring testing result subsequent tracing and
Statistical analysis.
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 detection method based on machine vision provided by the invention, as shown in Figure 1, including the following steps:
Step 1, according to detection demand, the detection parameters free high angle value of pillow spring and the acceptability limit of radius value are set;
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 area point cloud data;
Step 3, data processing and control system start to act after obtaining pillow spring arriving signal, by data processing and control system
Control module controls vision imaging device acquisition and includes the target area point cloud data including pillow spring, and by target area point cloud number
According to being sent to data processing and control system;
Step 4, the data processing module of data processing and control system handles target area point cloud data, calculates pillow
The detection parameters of spring, specifically include:
(1) data processing module calculates the free high angle value of pillow spring: being partitioned into based on preset height only includes pallet
Point cloud;To segmentation only comprising the data reduction plane of pallet, identifies tray upper surface and calculate the flat of tray upper surface
Face 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 data of pillow spring
Coordinate origin and coordinate system transformation to tray upper surface;According to preset pillow spring altitude range, it is partitioned into comprising in pillow spring
The point cloud of end face;The maximum planes vertical to the data reduction normal vector comprising pillow spring upper surface are pillow spring upper surface;Calculate pillow
The height value of spring upper surface is the free high angle value of pillow spring;
(2) data processing module calculates the radius value of pillow spring: using clustering procedure to the pillow spring upper end millet cake cloud recognized
Cluster extracts most point cloud group of counting, the point cloud of the pillow spring upper surface after as denoising;To the pillow spring upper surface after denoising
Point cloud carries out Least Square Circle fitting, obtains pillow spring radius value;
Step 5, the data detection module of data processing and control system will be in detection parameters calculated in step 4 and step 1
The acceptability limit of the correspondence detection parameters of setting compares, and qualifying signal is exported if in acceptability limit and is sent into subsequent work stations;
Unqualified signal is exported if not in acceptability limit, and is rejected.
The mode that data processing described in step 3 and control system obtain pillow spring arriving signal is photoelectric sensor.
The detection parameters of pillow spring described in step 1 further include 5/8 angle value and 1/4 high level, are specifically carried out in the steps below
Detection:
(1) data processing module calculates 5/8 angle value of pillow spring: stepping through to pillow spring upper end millet cake cloud, asks each
The angle of point and circle center line connecting and reference axis x, calculates 5/8 angle value of pillow spring;
(2) data processing module calculates 1/4 height of pillow spring: it is the smallest to obtain z value for point all in traversal central diameter first
Point, the pillow spring free high angle value obtained in step 4 subtract its z value, as 1/4 high absolute value;It is then based on pillow spring freedom
Height value is partitioned into the point cloud of pillow spring middle section, clusters to a cloud, isolates each pillow spring circle and seeks the matter of pillow spring circle
The average value of heart distance, as pillow spring pitch;It is finally the 1/4 of pillow spring divided by pillow spring pitch by 1/4 high absolute value
High level.
Data processing and control system further include the data memory module for saving calculated detected value in step 4, are used for
The retrospect of pillow spring testing result and statistical analysis.
Compared with prior art, a kind of pillow spring detection method based on machine vision provided by the invention, can be primary
Property realize the detection of free high angle value, radius value, 5/8 angle value, 1/4 high level automatically, detection efficiency is high, rhythm is fast, and precision is high, inspection
Subsequent tracing and statistical analysis convenient for pillow spring testing result can also be saved by surveying result.
Claims (4)
1. a kind of pillow spring detection method based on machine vision, which comprises the steps of:
Step 1, according to detection demand, the detection parameters free high angle value of pillow spring and the acceptability limit of radius value are set;
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 area point cloud data;
Step 3, data processing and control system start to act after obtaining pillow spring arriving signal, by data processing and control system
Control module controls vision imaging device acquisition and includes the target area point cloud data including pillow spring, and by target area point cloud number
According to being sent to data processing and control system;
Step 4, the data processing module of data processing and control system handles target area point cloud data, calculates pillow
The detection parameters of spring, specifically include:
(1) data processing module calculates the free high angle value of pillow spring: being partitioned into based on preset height only includes pallet
Point cloud;To segmentation only comprising the data reduction plane of pallet, identifies tray upper surface and calculate the flat of tray upper surface
Face 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 data of pillow spring
Coordinate origin and coordinate system transformation to tray upper surface;According to preset pillow spring altitude range, it is partitioned into comprising in pillow spring
The point cloud of end face;The maximum planes vertical to the data reduction normal vector comprising pillow spring upper surface are pillow spring upper surface;Calculate pillow
The height value of spring upper surface is the free high angle value of pillow spring;
(2) data processing module calculates the radius value of pillow spring: using clustering procedure to the pillow spring upper end millet cake cloud recognized
Cluster extracts most point cloud group of counting, the point cloud of the pillow spring upper surface after as denoising;To the pillow spring upper surface after denoising
Point cloud carries out Least Square Circle fitting, obtains pillow spring radius value;
Step 5, the data detection module of data processing and control system will be in detection parameters calculated in step 4 and step 1
The acceptability limit of the correspondence detection parameters of setting compares, and qualifying signal is exported if in acceptability limit and is sent into subsequent work stations;
Unqualified signal is exported if not in acceptability limit, and is rejected.
2. a kind of pillow spring detection method based on machine vision as described in claim 1, which is characterized in that number described in step 3
It is photoelectric sensor according to the mode that processing obtains pillow spring arriving signal with control system.
3. a kind of pillow spring detection method based on machine vision as described in claim 1, which is characterized in that described in step 1
The detection parameters of pillow spring further include 5/8 angle value and 1/4 high level, specifically detected in the steps below:
(1) data processing module calculates 5/8 angle value of pillow spring: stepping through to pillow spring upper end millet cake cloud, asks each
The angle of point and circle center line connecting and reference axis x, calculates 5/8 angle value of pillow spring;
(2) data processing module calculates 1/4 height of pillow spring: it is the smallest to obtain z value for point all in traversal central diameter first
Point, the pillow spring free high angle value obtained in step 4 subtract its z value, as 1/4 high absolute value;It is then based on pillow spring freedom
Height value is partitioned into the point cloud of pillow spring middle section, clusters to a cloud, isolates each pillow spring circle and seeks the matter of pillow spring circle
The average value of heart distance, as pillow spring pitch;It is finally the 1/4 of pillow spring divided by pillow spring pitch by 1/4 high absolute value
High level.
4. a kind of pillow spring detection method based on machine vision as described in claim 1, which is characterized in that data processing and control
System processed further include save step 4 in calculated detected value data memory module, for pillow spring testing result retrospect and
Statistical analysis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711460226.XA CN109978938A (en) | 2017-12-28 | 2017-12-28 | A kind of pillow spring detection method based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711460226.XA CN109978938A (en) | 2017-12-28 | 2017-12-28 | A kind of pillow spring detection method based on machine vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109978938A true CN109978938A (en) | 2019-07-05 |
Family
ID=67074779
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711460226.XA Pending CN109978938A (en) | 2017-12-28 | 2017-12-28 | A kind of pillow spring detection method based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109978938A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110425978A (en) * | 2019-07-31 | 2019-11-08 | 合肥康普曼数字技术有限公司 | A kind of quality detecting system and its method of battery tray |
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 |
CN113034485A (en) * | 2021-04-09 | 2021-06-25 | 浙江欧视电科技有限公司 | Circle detection method integrating Hough transformation and caliper clustering |
CN113125439A (en) * | 2019-12-31 | 2021-07-16 | 南京璟一机器人工程技术有限公司 | Spring end face detection system and detection method thereof |
WO2021184757A1 (en) * | 2020-03-14 | 2021-09-23 | 苏州艾吉威机器人有限公司 | Robot vision terminal positioning method and device, and computer-readable storage medium |
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 |
CN114580585A (en) * | 2022-03-03 | 2022-06-03 | 南京拓控信息科技股份有限公司 | Method for identity recognition and visual calibration of tray assembly |
-
2017
- 2017-12-28 CN CN201711460226.XA patent/CN109978938A/en active Pending
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110425978A (en) * | 2019-07-31 | 2019-11-08 | 合肥康普曼数字技术有限公司 | A kind of quality detecting system and its method of battery tray |
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 |
CN113125439A (en) * | 2019-12-31 | 2021-07-16 | 南京璟一机器人工程技术有限公司 | Spring end face detection system and detection method thereof |
CN113125439B (en) * | 2019-12-31 | 2023-11-07 | 南京景曜智能科技有限公司 | Spring end face detection system and detection method thereof |
WO2021184757A1 (en) * | 2020-03-14 | 2021-09-23 | 苏州艾吉威机器人有限公司 | Robot vision terminal positioning method and device, and computer-readable storage medium |
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 |
CN113034485A (en) * | 2021-04-09 | 2021-06-25 | 浙江欧视电科技有限公司 | Circle detection method integrating Hough transformation and caliper clustering |
CN114580585A (en) * | 2022-03-03 | 2022-06-03 | 南京拓控信息科技股份有限公司 | Method for identity recognition and visual calibration of tray assembly |
CN114580585B (en) * | 2022-03-03 | 2023-07-25 | 南京拓控信息科技股份有限公司 | Identity recognition and visual calibration method for tray assembly |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109978938A (en) | A kind of pillow spring detection method based on machine vision | |
CN109506580B (en) | Spot-facing quality determining method based on line laser 3-D scanning | |
CN109520436B (en) | Butterfly spring three-dimensional size automatic measurement system based on machine vision and measurement method thereof | |
CN208887632U (en) | Construction detection system and monitoring computer equipment based on 3 D laser scanning | |
CN109029293A (en) | A kind of line scanning feeler position and attitude error scaling method in blade face type detection | |
CN109765240B (en) | Device and method for detecting stitch defects of industrial parts | |
CN110672020A (en) | Stand tree height measuring method based on monocular vision | |
CN103759672A (en) | Vision measurement method for ice cream stick plane contour dimensions | |
CN115077425B (en) | Product detection equipment and method based on structured light three-dimensional vision | |
CN108151766B (en) | Positioning method of magnetic nails, positioning navigation error correction method of magnetic nails and positioning device | |
CN102778196A (en) | Image size measuring method based on laser calibration | |
CN105509653A (en) | Method and system for visual measurement of profile of machine part | |
CN102920459A (en) | Human body circumference parameter measuring method based on three-dimensional point cloud | |
CN106705850B (en) | A kind of terminal quality determining method based on image | |
CN109359537A (en) | Human face posture angle detecting method neural network based and system | |
CN105043381A (en) | Magnetic nail-based positioning method | |
CN103134441A (en) | Large wind tunnel flexible spraying pipe laser tracking measurement method | |
CN109993723A (en) | A kind of pillow spring classification and Detection method based on machine vision | |
CN113570550B (en) | Gold wire bonding size detection method based on three-dimensional point cloud | |
CN107560543A (en) | A kind of camera optical axis offset correction device and method based on binocular stereo vision | |
CN108627103A (en) | A kind of 2D laser measurement methods of parts height dimension | |
CN110544276A (en) | Least square method ellipse fitting piston skirt maximum point size measurement method | |
CN204881558U (en) | Mould curved surface machining error and roughness are at quick -witted detection device | |
CN110986784A (en) | Reference coordinate acquisition method and application thereof | |
CN113390340B (en) | Method for detecting spatial position of spherical center of corner spherical surface in discontinuous region |
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 |