CN110068279B - Prefabricated part plane circular hole extraction method based on point cloud data - Google Patents
Prefabricated part plane circular hole extraction method based on point cloud data Download PDFInfo
- Publication number
- CN110068279B CN110068279B CN201910341004.9A CN201910341004A CN110068279B CN 110068279 B CN110068279 B CN 110068279B CN 201910341004 A CN201910341004 A CN 201910341004A CN 110068279 B CN110068279 B CN 110068279B
- Authority
- CN
- China
- Prior art keywords
- point
- edge
- circular hole
- cloud data
- list
- 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
Images
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
-
- 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
- G01B11/12—Measuring arrangements characterised by the use of optical techniques for measuring diameters internal diameters
-
- 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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/168—Segmentation; Edge detection involving transform domain methods
-
- 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
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a prefabricated part plane circular hole extraction method based on point cloud data. The method comprises the steps of inputting point cloud data, obtaining an edge point list, fitting a round hole, correcting the radius of the round hole and the like. The method enables the circular hole reverse modeling of the prefabricated part to effectively reduce a large amount of human intervention in the traditional reverse modeling work, and provides technical support for the non-contact detection and the circular hole reverse modeling of the prefabricated part.
Description
Technical Field
The invention relates to the technical field of building management and information, in particular to a prefabricated part plane circular hole extraction method based on point cloud data.
Background
The three-dimensional laser scanning technology is a high and new technology which begins to appear in the middle of the nineties of the last century and is a breakthrough on another mapping technology after a GPS space positioning system. The method is used for rapidly acquiring the three-dimensional coordinates of the surface of a measured object and the surface reflectivity of the measured object in a large-area high-resolution manner by a high-speed laser scanning measurement method. The method can quickly acquire a large amount of space point location information, and provides a brand new technical means for establishing a three-dimensional image model of an object. Due to the characteristics of rapidness, non-contact, real-time, dynamic, initiative, high density, high precision, digitalization, automation and the like, the application of the system can possibly cause the revolution of a measurement technology again like a GPS. By utilizing the three-dimensional laser scanning technology, the contour of the prefabricated part can be scanned, and the surface point cloud data of the prefabricated part can be obtained. The high-density point cloud can carry out non-contact detection on the prefabricated part, and efficient reverse modeling on the measured part is completed by processing point cloud data.
At present, when detecting holes of prefabricated parts, technicians need to use manual measuring means such as a tape measure or a steel ruler, the efficiency is low, and a large amount of labor and time are consumed. In addition, according to the prior art, when the point cloud data of the prefabricated part is subjected to BIM reverse modeling, the round hole is usually subjected to size recovery according to a building drawing, or is subjected to rollover according to the position of the actual manually measured round hole of the prefabricated part, or is roughly subjected to manual modeling according to the approximate outline of the point cloud data. However, the above methods all require a great deal of manual operation to determine the position and size of the circular hole.
Therefore, in order to avoid subjective errors and excessive labor consumption which are easily caused by manual hole detection and reverse modeling under the condition of large data scale, it is urgently needed to develop a planar circular hole extraction method.
Disclosure of Invention
The invention aims to provide a prefabricated part plane circular hole extraction method based on point cloud data, and aims to solve the problems in the prior art.
The technical scheme adopted for achieving the purpose of the invention is that the method for extracting the plane circular hole of the prefabricated part based on the point cloud data comprises the following steps:
1) inputting point cloud data of a plane of the prefabricated member with the round hole.
2) Processing the point cloud data input in the step 1) by using an edge extraction algorithm to obtain an edge point list comprising an inner edge and an outer edge.
3) Increasing the number of nearest neighbor points, and processing the point cloud data input in the step 1) by using an edge extraction algorithm again to obtain an edge point list only containing outer edges.
4) And (3) making a difference between the edge point list obtained in the step 2) and the edge point list obtained in the step 3) to obtain an edge point list only containing inner edges.
5) Fitting the edge point list only containing the inner edge obtained in the step 4), outputting fitted round hole information, and adding the round hole information into the round hole list.
6) Correcting the radius of the round hole obtained in the step 5), and replacing the corresponding radius of the round hole in the round hole list.
Further, the step 2) specifically comprises the following steps:
2.1) calculate M nearest neighbors to each point.
2.2) centered at each point, dividing its neighborhood by eight degrees. It is determined whether all of the eight regions fall within the nearest neighbors of the point. If not, marking the point as an edge point.
Further, the step 3) specifically comprises the following steps:
3.1) calculating the N nearest neighbors of each point. Wherein N is 5M.
3.2) taking each point as a center, equally dividing the neighborhood of each point according to the angle eight, and judging whether the eight regions all fall into the nearest neighbor point of the point. If not, marking the point as an edge point.
Further, in the step 5), the circle center coordinates and the radius of the circle are solved by adopting a Hough circle detection algorithm.
Further, in step 6), the radial direction of each circle from the center of the circle is taken as the search direction, and the center of each circle in the round hole list obtained in step 5) is taken as the starting point, and the search is performed according to the search direction. When the termination condition is satisfied, the search is stopped. The distance between the stopping point and the circle center is the corrected radius of the circular hole. And replacing the corresponding circular hole radius in the circular hole list in the step 5) by using the corrected circular hole radius.
The technical effects of the invention are undoubted:
A. performing edge extraction on the point cloud data of the prefabricated part to obtain a set of inner edge points;
B. the problem of round hole extraction of the prefabricated part is effectively solved, so that the round hole extraction of the prefabricated part becomes automatic, and the reverse modeling process of the round hole of the large-scale prefabricated part is greatly reduced;
C. and obtaining a set of round hole information after effective fitting and correction.
Drawings
FIG. 1 is a process flow diagram;
FIG. 2 is a schematic diagram of an edge extraction algorithm;
FIG. 3 is a point cloud data of an original prefabricated component;
FIG. 4 is point cloud data including an inner edge and an outer edge;
FIG. 5 is a point cloud data including only outer edges;
FIG. 6 is a point cloud data containing only inner edges;
fig. 7 is a circular hole obtained after fitting and correcting point cloud data only including an inner edge.
Detailed Description
The present invention is further illustrated by the following examples, but it should not be construed that the scope of the above-described subject matter is limited to the following examples. Various substitutions and alterations can be made without departing from the technical idea of the invention and the scope of the invention is covered by the present invention according to the common technical knowledge and the conventional means in the field.
Example 1:
referring to fig. 1, the embodiment discloses a method for extracting a plane circular hole of a prefabricated part based on point cloud data, which comprises the following steps:
1) inputting point cloud data of a plane with a round hole in the prefabricated part.
2) Processing the point cloud data input in the step 1) by using an edge extraction algorithm to obtain an edge point list comprising an inner edge and an outer edge.
2.1) calculating a certain number of nearest neighbors of each point.
2.2) as shown in fig. 2, taking each point as the center, dividing the neighborhood into eight equal parts according to the angle, judging whether all the eight areas fall into the nearest neighbor point of the point, if not, marking the point as the edge point. In particular, by controlling the number of nearest neighbors, different classes of edge points can be obtained. Referring to fig. 4, according to the point cloud number of the specific embodiment, when edge extraction is adopted, the number M of nearest neighboring points is set as the point cloud number/100, and an edge extraction algorithm is used for processing, so as to obtain an edge point list including an inner edge and an outer edge.
3) Increasing the number of the nearest neighbor points to 5 times in the step 2), and processing the point cloud data input in the step 1) by using an edge extraction algorithm again to obtain an edge point list only containing outer edges.
3.1) calculating N nearest neighbors of each point; wherein N is 5M;
3.2) taking each point as a center, equally dividing the neighborhood of each point according to the angle eight, and judging whether the eight regions all fall into the nearest neighbor point of the point; if not, marking the point as an edge point.
Referring to fig. 5, according to the point cloud number of the specific embodiment, when edge extraction is adopted, the number N of nearest neighboring points is set to be point cloud number/20, and an edge extraction algorithm is used for processing, so as to obtain an edge point list including an outer edge.
4) The list of edge points containing only the outer edge obtained in step 3) is subtracted from the list of edge points containing the inner edge and the outer edge obtained in step 2), leaving a list of edge points containing only the inner edge as shown in fig. 6.
5) Fitting the edge point list only containing the inner edge obtained in the step 4), outputting fitted round hole information, and adding the fitted round hole information into the round hole list. In this embodiment, a Hough circle detection (Hough circle detection) algorithm is used to solve the circle center coordinates and the radius of the circular holes.
The principle of the Hough circle detection algorithm is as follows: given the functional relationship of the circle:
(x-a)2+(y-b)2＝r2
in the parameter space, x and y are known quantities, a, b and r are unknown quantities, one point (x, y) on the image space corresponds to a cone in the parameter space, a circle of the image space corresponds to a point where the cone cluster intersects, the three-dimensional parameter of the specific point in the parameter space is constant, the circle of the image space with a certain radius and a certain circle center coordinate is represented, the parameter space is rasterized, voting is performed by using each point on the image space, and the output parameter is determined by accumulating the local maximum value of the number of votes in the parameter space, so that the circle is detected, and the circle center and the radius are obtained.
When Hough circle detection is carried out, r in a certain range is traversed by taking a point (x, y) on each inner edge as a circle center in a parameter space, only intersection points of circles are selected to participate in voting so as to reduce the calculated amount, round hole parameters with the voting result larger than 10 are selected, only one group of repeated parameters is reserved, and a coordinate and radius list of the round holes is obtained.
6) Correcting the radius of the round hole obtained in the step 5), and replacing the corresponding radius of the round hole in the round hole list in the step 5). In this embodiment, a radial direction of each circle away from the center of the circle is taken as a search direction, the center of each circle in the circular hole list obtained in step 5) is taken as a starting point, searching is performed according to the search direction, a corresponding termination condition is set, when the condition is met, the searching is stopped, and a distance between the stop point and the center of the circle is the corrected radius of the circular hole. Replacing the radius of the corresponding round hole in the round hole list in the step 5) with the radius of the obtained round hole. As shown in fig. 7, when searching in the radial direction from the center of the circle, when the number of points in the 1mm wide circular band with the distance from the point to the center of the circle as the radius exceeds 5, the search is stopped, the distance from the point to the center of the circle at this time is the corrected radius of the circular hole, and the corrected radius is replaced with the corresponding radius of the circular hole in the circular hole list in the step 5).
It should be noted that the embodiment can be applied to any prefabricated part plane with holes, and the edges in the prefabricated part point cloud data are extracted and further processed to obtain the circular holes on the prefabricated part. The problem of complex operation among the prefabricated component hole quality testing process, labour cost consumes greatly is solved to this embodiment to and when carrying out BIM conventional reverse modeling to prefabricated component point cloud data, round hole modeling need carry out the problem of measuring repeatedly, provides technical support for the reverse modeling of the round hole of large-scale prefabricated component point cloud data, is practically effectual.
Claims (5)
1. A prefabricated part plane circular hole extraction method based on point cloud data is characterized by comprising the following steps:
1) inputting point cloud data of a plane with a round hole of the prefabricated part;
2) processing the point cloud data input in the step 1) by using an edge extraction algorithm to obtain an edge point list comprising an inner edge and an outer edge;
3) increasing the number of nearest neighbor points, and processing the point cloud data input in the step 1) by using an edge extraction algorithm again to obtain an edge point list only containing outer edges;
4) subtracting the edge point list obtained in the step 2) from the edge point list obtained in the step 3) to obtain an edge point list only containing inner edges;
5) fitting the edge point list only containing the inner edge obtained in the step 4), outputting fitted round hole information, and adding the round hole information into the round hole list;
6) correcting the radius of the round hole obtained in the step 5), and replacing the corresponding radius of the round hole in the round hole list.
2. The method for extracting the plane circular hole of the prefabricated part based on the point cloud data as claimed in claim 1, wherein the step 2) specifically comprises the following steps:
2.1) calculating M nearest neighbors of each point;
2.2) taking each point as a center, and dividing the neighborhood into eight equal parts according to the angle; judging whether the eight regions all fall into the nearest neighbor point of the point; if not, marking the point as an edge point.
3. The method for extracting the plane circular hole of the prefabricated part based on the point cloud data as claimed in claim 2, wherein the step 3) specifically comprises the following steps:
3.1) calculating N nearest neighbors of each point; wherein N is 5M;
3.2) taking each point as a center, equally dividing the neighborhood of each point according to the angle eight, and judging whether the eight regions all fall into the nearest neighbor point of the point; if not, marking the point as an edge point.
4. The method for extracting the plane circular hole of the prefabricated part based on the point cloud data as claimed in claim 1, wherein the circle center coordinates and the radius of the circle are solved by adopting a Hough circle detection algorithm in the step 5).
5. The method for extracting a plane circular hole of a prefabricated part based on point cloud data as claimed in claim 1, wherein in the step 6), a search is performed according to the search direction by taking the radial direction of each circle from the center of the circle as the search direction and taking the center of each circle in the circular hole list obtained in the step 5) as a starting point; when the termination condition is satisfied, stopping the search; the distance between the stopping point and the circle center is the corrected radius of the circular hole; and replacing the corresponding circular hole radius in the circular hole list in the step 5) by using the corrected circular hole radius.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910341004.9A CN110068279B (en) | 2019-04-25 | 2019-04-25 | Prefabricated part plane circular hole extraction method based on point cloud data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910341004.9A CN110068279B (en) | 2019-04-25 | 2019-04-25 | Prefabricated part plane circular hole extraction method based on point cloud data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110068279A CN110068279A (en) | 2019-07-30 |
| CN110068279B true CN110068279B (en) | 2021-02-02 |
Family
ID=67368882
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910341004.9A Active CN110068279B (en) | 2019-04-25 | 2019-04-25 | Prefabricated part plane circular hole extraction method based on point cloud data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110068279B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114087989B (en) * | 2021-11-19 | 2023-09-22 | 江苏理工学院 | Method and system for measuring three-dimensional coordinates of circle center of positioning hole of automobile cylinder workpiece |
Family Cites Families (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101477691B (en) * | 2008-12-26 | 2011-04-20 | 武汉大学 | Discrete point zone topology boundary tracking process based on edge length ratio constraint |
| CN101750015B (en) * | 2009-12-11 | 2011-04-20 | 东南大学 | Gravel pit earth volume measuring method based on digital image technology |
| US10019812B2 (en) * | 2011-03-04 | 2018-07-10 | General Electric Company | Graphic overlay for measuring dimensions of features using a video inspection device |
| CN103226833B (en) * | 2013-05-08 | 2015-08-05 | 清华大学 | A kind of point cloud data segmentation method based on three-dimensional laser radar |
| US9547901B2 (en) * | 2013-11-05 | 2017-01-17 | Samsung Electronics Co., Ltd. | Method and apparatus for detecting point of interest (POI) in three-dimensional (3D) point clouds |
| CN103886593B (en) * | 2014-03-07 | 2016-08-17 | 华侨大学 | A kind of based on three-dimensional point cloud curved surface circular hole detection method |
| CN104463851B (en) * | 2014-11-19 | 2018-05-22 | 哈尔滨工业大学深圳研究生院 | A kind of sole edge line automatic tracking method based on robot |
| US20160379366A1 (en) * | 2015-06-25 | 2016-12-29 | Microsoft Technology Licensing, Llc | Aligning 3d point clouds using loop closures |
| CN105261047B (en) * | 2015-09-08 | 2019-04-09 | 北京控制工程研究所 | A kind of docking ring center extracting method based on short distance short arc segments image |
| CN106887003B (en) * | 2017-01-06 | 2019-06-07 | 沈阳工业大学 | Point cloud edge extracting method based on eight neighborhood depth difference |
| CN106845535B (en) * | 2017-01-06 | 2019-08-02 | 沈阳工业大学 | Typical Components recognition methods based on cloud |
| KR101858902B1 (en) * | 2017-06-26 | 2018-05-16 | 한국도로공사 | System for extracting position information of object in point cloud data by using component |
| US10297074B2 (en) * | 2017-07-18 | 2019-05-21 | Fuscoe Engineering, Inc. | Three-dimensional modeling from optical capture |
| CN107516098B (en) * | 2017-07-30 | 2021-08-10 | 华南理工大学 | Target contour three-dimensional information extraction method based on edge curvature angle |
| CN108376266A (en) * | 2018-03-13 | 2018-08-07 | 中国电子科技集团公司第二十八研究所 | One-class support vector machines Optimization Method of Kernel Parameter based on sample edge point internal point |
| CN109345523B (en) * | 2018-09-21 | 2022-08-16 | 中国科学院苏州生物医学工程技术研究所 | Surface defect detection and three-dimensional modeling method |
| CN109410342A (en) * | 2018-09-28 | 2019-03-01 | 昆明理工大学 | A kind of point cloud compressing method retaining boundary point |
| CN109655019B (en) * | 2018-10-29 | 2021-02-02 | 北方工业大学 | Cargo volume measurement method based on deep learning and three-dimensional reconstruction |
-
2019
- 2019-04-25 CN CN201910341004.9A patent/CN110068279B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110068279A (en) | 2019-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106969703B (en) | Method and system for automated formed cooling hole measurement | |
| CN102589435B (en) | Efficient and accurate detection method of laser beam center under noise environment | |
| CN110060338B (en) | Prefabricated part point cloud identification method based on BIM model | |
| CN102441581A (en) | Machine vision-based device and method for online detection of structural steel section size | |
| CN113865508B (en) | Automatic detection device and method for through hole rate of sound lining of honeycomb sandwich composite material | |
| CN115014198B (en) | Reinforcing steel bar installation detection method based on three-dimensional laser scanning | |
| CN116740060B (en) | Method for detecting size of prefabricated part based on point cloud geometric feature extraction | |
| CN113487722A (en) | Automatic concrete member detection method based on three-dimensional laser scanning method | |
| CN109118476B (en) | Method and device for detecting integrity of edge profile of part | |
| CN108917711B (en) | Tunnel engineering three-dimensional laser scanning sectional measurement method and system | |
| CN111524154B (en) | Image-based tunnel segment automatic segmentation method | |
| CN110068279B (en) | Prefabricated part plane circular hole extraction method based on point cloud data | |
| CN114549751A (en) | Template monitoring system and method for box girder production | |
| CN116309118A (en) | Tunnel point cloud denoising method and system based on ray method | |
| CN115235375A (en) | Multi-circle characteristic parameter measuring method, detecting method and device for cover plate type workpiece | |
| CN112085708A (en) | Method and equipment for detecting defects of straight line edge in product outer contour | |
| JP5964803B2 (en) | Data processing method and data processing apparatus | |
| JP2012037488A (en) | Shape inspection device and shape inspection method | |
| CN116385356A (en) | Method and system for extracting regular hexagonal hole features based on laser vision | |
| CN115545426A (en) | Prefabricated part production progress analysis system based on BIM and three-dimensional laser scanning | |
| CN110021027B (en) | Edge cutting point calculation method based on binocular vision | |
| CN115511718A (en) | PCB image correction method and device, terminal equipment and storage medium | |
| Wieczorowski et al. | Influence of Selected Measurement Conditions on the Reliability of the Representation of Ring and Rim Features | |
| CN112629432B (en) | Interactive hole site multi-angle scanning control method and device | |
| Kucharski et al. | Influence of Selected Measurement Conditions on the Reliability of the Representation of Ring and Rim Features |
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 |