CN110490865B - Stud point cloud segmentation method based on high light reflection characteristic of stud - Google Patents
Stud point cloud segmentation method based on high light reflection characteristic of stud Download PDFInfo
- Publication number
- CN110490865B CN110490865B CN201910779707.XA CN201910779707A CN110490865B CN 110490865 B CN110490865 B CN 110490865B CN 201910779707 A CN201910779707 A CN 201910779707A CN 110490865 B CN110490865 B CN 110490865B
- Authority
- CN
- China
- Prior art keywords
- stud
- point cloud
- area
- image
- segmentation
- 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
- 230000011218 segmentation Effects 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000010363 phase shift Effects 0.000 claims abstract description 9
- 238000010586 diagram Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 4
- 238000002310 reflectometry Methods 0.000 claims 2
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000010339 dilation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a stud point cloud segmentation method based on high light reflection characteristics of a stud, which comprises the following steps: 1) respectively collecting a gray scale image and a phase shift image of the area where the stud to be detected is located; 2) carrying out binarization on the gray level image, and screening an overexposure area to obtain a binary image; 3) performing multiple expansion operations on the binary image to enable the edge of a single overexposure area to form a single connected area; acquiring a minimum circumscribed rectangle of the outline of the single-connection area; 4) and measuring three-dimensional point cloud in the minimum circumscribed rectangle area by using the phase shift diagram, respectively carrying out cylindrical segmentation on the obtained point cloud, outputting a segmentation result, and successfully segmenting, wherein a stud exists in the corresponding minimum circumscribed rectangle, otherwise, no stud exists. The method initially positions the stud by utilizing the high-light-reflection area of the stud and can quickly and accurately segment the stud point cloud data through subsequent calculation.
Description
Technical Field
The invention relates to the field of visual detection, in particular to a stud point cloud segmentation method based on high light reflection characteristics of a stud.
Background
It is often desirable in the manufacturing arts to detect the pose of a stud to determine the weld location of the stud and whether the stud is perpendicular to the weld plane. The space information of the stud is difficult to be given on the image plane, so that the three-dimensional point cloud data of the stud to be detected needs to be acquired through a three-dimensional scanner, and the space pose of the stud is calculated.
When the space pose of the stud is calculated in the three-dimensional space, the corresponding calculation can be carried out only by dividing the point cloud data of the stud. At present, stud point cloud segmentation is mainly based on the following three modes: firstly, point cloud registration; secondly, the stud is directly regarded as a cylinder and is divided by adopting a ransac method; and thirdly, directly segmenting the region where the stud is located from the image, setting the region as an interested region, and outputting only the point cloud in the interested region according to the measurement result.
When the point cloud registration method is adopted, complete stud point cloud data needs to be obtained in advance, for the field of automobile manufacturing, studs of various types can be adopted on each automobile, point cloud registration operation is huge, registration needs to be completed with long consumption, and the requirement for high-efficiency measurement in the manufacturing industry cannot be met.
When the point cloud is segmented by adopting the ransac method, the stud can only be regarded as a cylinder for segmentation, but the actually obtained stud point cloud has less point cloud data because of the high light reflection characteristic of the stud, and the segmentation error is very easy to occur.
When the point cloud is segmented by image segmentation, the point cloud is influenced by the light reflecting characteristic of the stud, the image interference is very strong, the image segmentation algorithm generally fails, the segmentation success rate is low, and the requirement on the reliability of stud measurement cannot be met.
Disclosure of Invention
In order to solve the technical problems, the invention provides a stud point cloud segmentation method based on high light reflection characteristics of a stud.
Therefore, the technical scheme of the invention is as follows:
a stud point cloud segmentation method based on high stud light reflection characteristics comprises the following steps:
1) respectively collecting a gray scale image and a phase shift image of the area where the stud to be detected is located;
2) carrying out binarization on the gray level image, and screening an overexposure area to obtain a binary image;
3) performing multiple expansion operations on the binary image to enable the edge of a single overexposure area to form a single connected area; acquiring a minimum circumscribed rectangle of the outline of the single connected region;
4) and measuring the three-dimensional point cloud in the minimum circumscribed rectangular area by using the phase shift diagram, respectively carrying out cylindrical segmentation on the obtained point cloud, outputting a segmentation result, and successfully segmenting, wherein a stud exists in the corresponding minimum circumscribed rectangle, otherwise, no stud exists.
Further, when the binarization is performed in the step 2), the threshold value is set to be 230-250.
Further, the method also comprises the step 5) of calculating the pose between the stud and the bottom plate by using the divided point cloud.
The method provided by the invention utilizes the high-light-reflection characteristic of the stud to carry out coarse positioning on the stud, and carries out expansion operation by taking the stud as a reference to determine the position of the stud. The method overcomes the prejudice that the final detection result is influenced by considering that the overexposed area is interference in the conventional image processing.
Drawings
FIG. 1 is a grayscale diagram of a stud region to be tested according to an embodiment;
FIG. 2 is a binary map obtained by the embodiment;
FIG. 3 is a diagram illustrating the result of the dilation operation performed on a binary image according to an exemplary embodiment;
FIG. 4 is a diagram illustrating the result of the minimum bounding rectangle for each connected region according to the preferred embodiment;
5(a), 5(b), 5(c) and 5(d) are graphs of results obtained by measuring three-dimensional point clouds of four exposure areas respectively in the specific embodiment;
fig. 6(a) and 6(b) are the final output segmentation results of the embodiment.
Detailed Description
The technical solution of the present invention is described in detail below with reference to the accompanying drawings and the detailed description.
A stud point cloud segmentation method based on high stud light reflection characteristics comprises the following steps:
1) respectively collecting a gray scale map (shown in figure 1) and a phase shift map of the area where the stud to be detected is located; the gray scale image is used for extracting the stud, and the phase shift image is used for measuring three-dimensional point cloud on the surface of the measured object;
2) carrying out binarization on the gray level image, and screening an overexposure area to obtain a binary image; the method utilizes the high light reflection characteristic of the stud to divide the stud in a gray scale image; the high light reflection characteristic of the stud enables the stud to have an overexposure area no matter how the stud is shot from any angle;
during binarization, the threshold value can be set to be 230-250, and FIG. 2 shows the output result when the threshold value is set to be 245;
3) the white areas of the binarized image are not continuous but exist in small areas, so that the binarized image needs to be morphologically processed to be an adjacent white area as a whole. Therefore, the binary image is subjected to multiple expansion operations, so that the edge of a single overexposure area can form a single connected area (as shown in FIG. 3); acquiring a minimum bounding rectangle of the outline of the single connected region (as shown in FIG. 4);
4) and measuring the three-dimensional point cloud in the minimum circumscribed rectangular area by using the phase shift diagram (as shown in fig. 5), respectively performing cylindrical segmentation on the obtained point cloud, outputting a segmentation result (as shown in fig. 6), wherein a stud exists in the corresponding minimum circumscribed rectangle, and otherwise, no stud exists.
Calculating the pose between the stud and the bottom plate by using the divided point cloud, wherein the calculation result in the figure 6 is as follows: the included angle between the large stud and the bottom plate is 89.076 degrees, the intersection point coordinates are (-10.205, -17.258 and 218.002 degrees), the included angle between the small stud and the bottom plate is 88.989 degrees, and the intersection point coordinates are (12.803, -0.864 and 215.944 degrees).
The method utilizes the high light reflection characteristic of the stud to carry out coarse positioning on the stud, and expansion operation is carried out by taking the stud as a reference to determine the position of the stud. The method overcomes the prejudice that the final detection result is influenced by considering that the overexposed area is interference in the conventional image processing. The detection result is accurate, and the detection process only consumes 0.156s in the specific embodiment.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. The foregoing description is not intended to be exhaustive or to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable others skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications thereof. It is intended that the scope of the invention be defined by the following claims and their equivalents.
Claims (3)
1. A stud point cloud segmentation method based on high stud reflection characteristics is characterized by comprising the following steps:
1) respectively collecting a gray scale image and a phase shift image of the area where the stud to be detected is located;
2) carrying out binarization on the gray level image, and screening an overexposure area to obtain a binary image;
3) performing multiple expansion operations on the binary image to enable the edge of a single overexposure area to form a single connected area; acquiring a minimum circumscribed rectangle of the outline of the single connected region;
4) and measuring the three-dimensional point cloud of the area in the minimum circumscribed rectangle by using the phase shift diagram, respectively carrying out cylindrical segmentation on the obtained point cloud, outputting a segmentation result, and successfully segmenting, wherein a stud exists in the corresponding minimum circumscribed rectangle, otherwise, no stud exists.
2. The stud point cloud segmentation method based on the high-reflectivity characteristic of the stud as claimed in claim 1, wherein: and 2) setting the threshold value to be 230-250 during binarization in the step 2).
3. The stud point cloud segmentation method based on the high-reflectivity characteristic of the stud as claimed in claim 1, wherein: and 5) calculating the pose between the stud and the bottom plate by using the divided point cloud.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910779707.XA CN110490865B (en) | 2019-08-22 | 2019-08-22 | Stud point cloud segmentation method based on high light reflection characteristic of stud |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910779707.XA CN110490865B (en) | 2019-08-22 | 2019-08-22 | Stud point cloud segmentation method based on high light reflection characteristic of stud |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110490865A CN110490865A (en) | 2019-11-22 |
CN110490865B true CN110490865B (en) | 2022-04-01 |
Family
ID=68552828
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910779707.XA Active CN110490865B (en) | 2019-08-22 | 2019-08-22 | Stud point cloud segmentation method based on high light reflection characteristic of stud |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110490865B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113808131B (en) * | 2021-11-16 | 2022-01-25 | 成都数联云算科技有限公司 | Method, system, device and medium for identifying connector defects |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103345743A (en) * | 2013-06-18 | 2013-10-09 | 宁波成电泰克电子信息技术发展有限公司 | Image segmentation method for intelligent flaw detection of cell tail end |
CN109583304A (en) * | 2018-10-23 | 2019-04-05 | 宁波盈芯信息科技有限公司 | A kind of quick 3D face point cloud generation method and device based on structure optical mode group |
CN109615657A (en) * | 2018-12-03 | 2019-04-12 | 易思维(天津)科技有限公司 | Method for calculating pose of threaded target object based on point cloud data |
CN109631847A (en) * | 2018-12-03 | 2019-04-16 | 易思维(天津)科技有限公司 | Threaded target pose calculation method based on point cloud data |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10438371B2 (en) * | 2017-09-22 | 2019-10-08 | Zoox, Inc. | Three-dimensional bounding box from two-dimensional image and point cloud data |
-
2019
- 2019-08-22 CN CN201910779707.XA patent/CN110490865B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103345743A (en) * | 2013-06-18 | 2013-10-09 | 宁波成电泰克电子信息技术发展有限公司 | Image segmentation method for intelligent flaw detection of cell tail end |
CN109583304A (en) * | 2018-10-23 | 2019-04-05 | 宁波盈芯信息科技有限公司 | A kind of quick 3D face point cloud generation method and device based on structure optical mode group |
CN109615657A (en) * | 2018-12-03 | 2019-04-12 | 易思维(天津)科技有限公司 | Method for calculating pose of threaded target object based on point cloud data |
CN109631847A (en) * | 2018-12-03 | 2019-04-16 | 易思维(天津)科技有限公司 | Threaded target pose calculation method based on point cloud data |
Non-Patent Citations (2)
Title |
---|
基于视觉信息的索道钢丝绳检测算法研究;陈晓亮;《中国优秀硕士学位论文全文数据库 信息科技辑》;20151215;正文第3.2.2节 * |
螺柱分拣系统中视觉识别技术研究;刘哲;《万方数据知识服务平台》;20150730;正文第3章 * |
Also Published As
Publication number | Publication date |
---|---|
CN110490865A (en) | 2019-11-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107507167B (en) | Cargo tray detection method and system based on point cloud plane contour matching | |
US10115035B2 (en) | Vision system and analytical method for planar surface segmentation | |
EP3176751B1 (en) | Information processing device, information processing method, computer-readable recording medium, and inspection system | |
CN109685760B (en) | MATLAB-based SLM powder bed powder laying image convex hull depression defect detection method | |
CN107239742A (en) | A kind of gauge pointer scale value calculating method | |
CN111160477B (en) | Image template matching method based on feature point detection | |
Yogeswaran et al. | 3d surface analysis for automated detection of deformations on automotive body panels | |
CN111222507A (en) | Automatic identification method of digital meter reading and computer readable storage medium | |
CN115294527B (en) | Subway tunnel damage detection method based on computer vision | |
CN113490965A (en) | Image tracking processing method and device, computer equipment and storage medium | |
CN107274446B (en) | Method for identifying sharp geometric edge points by using normal consistency | |
CN110490865B (en) | Stud point cloud segmentation method based on high light reflection characteristic of stud | |
US6829382B2 (en) | Structure-guided automatic alignment for image processing | |
Zhou et al. | An adaptive clustering method detecting the surface defects on linear guide rails | |
Buck et al. | Enhanced ship detection from overhead imagery | |
JP2002140713A (en) | Image processing method and image processor | |
CN109191489B (en) | Method and system for detecting and tracking aircraft landing marks | |
CN112991327B (en) | Steel grid welding system, method and terminal equipment based on machine vision | |
Getahun et al. | A robust lane marking extraction algorithm for self-driving vehicles | |
CN113554688B (en) | O-shaped sealing ring size measurement method based on monocular vision | |
Kröger et al. | Performance evaluation on contour extraction using Hough transform and RANSAC for multi-sensor data fusion applications in industrial food inspection | |
CN115760898A (en) | World coordinate positioning method for road sprinklers in mixed Gaussian domain | |
CN110298799B (en) | PCB image positioning correction method | |
CN115187744A (en) | Cabinet identification method based on laser point cloud | |
CN111009036B (en) | Grid map correction method and device in synchronous positioning and map construction |
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 | ||
CP01 | Change in the name or title of a patent holder |
Address after: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee after: Yi Si Si (Hangzhou) Technology Co.,Ltd. Address before: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee before: ISVISION (HANGZHOU) TECHNOLOGY Co.,Ltd. |
|
CP01 | Change in the name or title of a patent holder |