CN116740060B - Dimensional detection method of prefabricated components based on point cloud geometric feature extraction - Google Patents
Dimensional detection method of prefabricated components based on point cloud geometric feature extraction Download PDFInfo
- Publication number
- CN116740060B CN116740060B CN202311009724.8A CN202311009724A CN116740060B CN 116740060 B CN116740060 B CN 116740060B CN 202311009724 A CN202311009724 A CN 202311009724A CN 116740060 B CN116740060 B CN 116740060B
- Authority
- CN
- China
- Prior art keywords
- point
- point cloud
- plane
- equation
- prefabricated components
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 238000000605 extraction Methods 0.000 title claims abstract description 23
- 239000013598 vector Substances 0.000 claims abstract description 75
- 230000011218 segmentation Effects 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000005259 measurement Methods 0.000 claims abstract description 5
- 230000007613 environmental effect Effects 0.000 claims abstract description 4
- 230000008859 change Effects 0.000 claims description 8
- 238000003709 image segmentation Methods 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 2
- 230000001976 improved effect Effects 0.000 abstract description 7
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 125000003275 alpha amino acid group Chemical group 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011065 in-situ storage Methods 0.000 description 2
- 238000007670 refining Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009439 industrial construction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011031 large-scale manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for detecting the size of an assembled prefabricated part based on the extraction of geometrical characteristics of point clouds, which comprises the steps of firstly, finely dividing the point cloud foreground and the background of the assembled prefabricated part based on normal vectors, so that the point cloud of the assembled prefabricated part is divided from the environmental background; then, after the geometric characteristics of the point cloud of the prefabricated part are extracted, fitting the edge line of the prefabricated part according to the geometric characteristics of the point cloud, and calculating according to the fitted edge line to obtain the size information of the prefabricated part; and finally, adding 3D text labels of the size information of the prefabricated parts under the point cloud visual interface. According to the method, the edge line is fitted and the characteristic points are extracted based on the segmentation result of the cloud data of the real measurement points of the prefabricated components, so that the size of the prefabricated components is calculated, the purpose of automatic size detection is achieved, the detection efficiency is improved, and meanwhile, the accuracy of size detection is guaranteed.
Description
Technical Field
The invention relates to the field of assembly type building industry, in particular to an assembly type prefabricated part size detection method based on point cloud geometric feature extraction.
Background
The building is an important direction of development of the building industry, and is a building assembled by processing various types of building components in advance in a factory and then transporting the building components to a construction site through reliable connection. Compared with the existing cast-in-situ structure building, the cast-in-situ structure building has the advantages of large-scale production, high construction speed and low construction cost.
In an industrial construction prefabricated component production plant, a plurality of prefabricated components of different types are often produced according to the order requirements. In order to reduce the cost, the existing manufacturing enterprises generally adopt a mode that a plurality of types of components are produced by converting processes on the same production line. In production, different products have various technical categories, large operation process difference and complex index system. The assembled prefabricated components are large in size, various in types and complex in structure; this brings great difficulty to the design of the automated and intelligent technical scheme for the quality detection of the prefabricated components. In the existing automatic detection method, in the process of detecting the prefabricated components, the accuracy of a detection result is often difficult to meet the requirement, and even the detection result needs to be checked manually.
The existing quality detection methods are limited to human eye detection and steel ruler detection, the detection efficiency is low, the quality detection is easy to be influenced by human, and the quality detection result is required to be recorded by paper, so that the intelligent degree is low. The common component size detection and assembly modes all require a great deal of human intervention. Instruments such as a level gauge, a theodolite, a total station and the like can only observe a single point, the detection efficiency is low, and rapid and effective detection can not be carried out on multiple components and large-size components. Especially when measuring large components. In addition, factory-produced prefabricated components are susceptible to damage during transportation and assembly. In the manufacturing stage, the problems of component size errors, component position deviation, surface quality defects and the like may be caused by reasons of material problems, template manufacturing defects and the like.Existing 2The computer vision technology can automatically detect, but has large limitation, is easily influenced by shooting angles, and cannot visualize quality inspection results.
Disclosure of Invention
The invention aims to provide an assembled prefabricated part size detection method based on point cloud geometric feature extraction, which is used for fitting edge lines and extracting feature points based on a segmentation result of assembled prefabricated part real-point cloud data, further calculating the size of an assembled prefabricated part, realizing the purpose of automatic size detection of the assembled prefabricated part, improving the detection efficiency and ensuring the accuracy of size detection.
The technical scheme of the invention is as follows:
the method for detecting the size of the prefabricated part based on the point cloud geometric feature extraction specifically comprises the following steps:
(1) The method comprises the steps of carrying out segmentation on the point cloud foreground and the background of the prefabricated part based on the refinement of normal vector, so that the point cloud of the prefabricated part is segmented from the environment background;
(2) Extracting geometric features of the point cloud of the prefabricated part;
(3) Fitting the edge line of the prefabricated part according to the geometric characteristics of the point cloud of the prefabricated part, and calculating according to the fitted edge line to obtain the size information of the prefabricated part;
(4) 3 adding size information of prefabricated part under point cloud visualization interfaceText labels.
The specific mode for carrying out the point cloud foreground-background segmentation of the prefabricated component based on the normal vector refinement comprises the following steps:
s11, refining normal vector: traversing each point in the point cloud of the prefabricated component, acquiring adjacent point sets of each point, and calculating curvature change and normal difference between a normal vector of each point and a normal vector of a current point of any point in each adjacent point set; when the curvature change and the normal direction difference exceed the set threshold values, taking the curvature change and the normal direction difference as residual error items, constructing a linear equation set, and calculating an adjustment value of an algorithm vector by solving the linear equation set; updating the normal vector of the current point according to the adjustment value of the normal vector to obtain a refined normal vector, repeating the steps, iterating for a plurality of times to adjust and optimize the normal vector of each point until the preset iteration times are reached, outputting the optimized normal vector as a new normal vector, and orienting the new normal vector to realize the refinement of the normal vector;
s12, performing image segmentation based on region growth refined by normal vector, performing secondary region growth segmentation when segmentation is not complete, and passing through a threshold value based on the condition of over-segmentationThe plane segmentation method is used for circularly recursively acquiring the maximum bin of the over-segmentation result, and finally, the point cloud of the prefabricated component is segmented from the environment background.
The said threshold valueThe plane segmentation method specifically comprises the following steps:
a. establishing a plane model: randomly selecting three points in the point cloud data to establish an initial plane model;
b. single plane fitting: after a plane model is built and a fitting plane is built, calculating the distance between each point in the point cloud and the fitting plane, and counting the number of internal points;
c. multi-plane fitting: judging whether the current fitted plane model is reasonable or not according to the number of the internal points, and when the number of the internal points reaches a preset threshold value, considering that the current plane model is better to fit, and taking the current plane model as a final segmentation result; when the number of the inner points is insufficient, reconstructing the inner points into a new point cloud, and executing the steps on the new point cloudObtaining a new oneDividing the new division result with the step +.>And (3) comparing the segmentation results of the cells, and selecting the group with the largest surface element as the final segmentation result.
The specific mode for extracting the geometric features of the prefabricated part point cloud is edge extraction of the prefabricated part point cloud, and the specific steps are as follows:
point-to-pointNeighborhood point->Fitting the tangent plane by least squares, +.> =1，2，…，/>The method comprises the steps of carrying out a first treatment on the surface of the The general expression of the plane equation is shown in formula (1):
（1）；
the least square equation corresponding to each neighborhood point is shown in formula (2):
（2）；
i.e.（3）；
Solving the equation of the above formula (3) to obtain parameters、/>And->Carrying out formula (1) and obtaining a plane equation;
point to PointNeighborhood point->Projection onto tangential plane, point->The projection point in the tangential plane is，/>And->The parametric equation of (2) is shown in the following formula (4):
（4）；
will beSubstituting tangential plane equation to obtain +.>：
（5）；
Wherein,,、/>、/>、/>are constants in the tangential plane equation, and the projection point coordinates ++can be obtained by substituting the formula (5) into the formula (4)>；
In dotsProjection points of +.>For starting point, & lt + & gt>Defining a vector for the endpoint +.>Wherein any vector is taken>The vector product of the vector and the normal vector of the tangential plane is calculated as a vector +.>Then sequentially finding the vector +.>Respectively and vector->Vector->Included angle->、/>When->Included angle->The value of (2) is replaced by->The method comprises the steps of carrying out a first treatment on the surface of the For formula (6)>Sorting, selecting the maximum +.>As maximum angle->；
（6）；
Comparing adjacent two vectorsMaximum included angle->With the magnitude of the set angle threshold, when the maximum included angle +>If the angle is larger than the set angle threshold, then the point +.>Added to the set of boundary points.
The fitting of the edge line of the prefabricated part is to fit a straight line in the boundary point set by randomly selecting a group of points, and evaluate the fitting effect by calculating the distance from other points to the straight line.
When the edge of one plane of the prefabricated component is rectangular, grouping the edge straight lines through the geometric features of the straight lines when fitting the edge lines, and then selecting a group of points after grouping to fit the straight lines.
The fitting of the edge line of the prefabricated part is to perform a straight line fitting algorithm for a plurality of times, so that all boundary points of the plane of the prefabricated part are fitted, and a plurality of fitting straight lines are obtained; calculating the size of the prefabricated part, namely calculating the distance between every two fitting straight lines, and obtaining the size information of the prefabricated part by solving the shortest distance between the two fitting straight lines; comparing the calculated size information of the prefabricated part with the size of the standard prefabricated part, namely calculating by the formula (7) to obtain measurement accuracy：
（7）；
In the formula (7), the amino acid sequence of the compound,for the dimensional information of prefabricated components of the assembly type, +.>Is the size of a standard prefabricated part.
The invention has the advantages that:
(1) According to the method for detecting the size of the prefabricated part based on the point cloud geometric feature extraction, which is provided by the invention, the point cloud segmentation part provides a method for segmenting the point cloud foreground and the background of the prefabricated part based on the normal vector refinement, and the image segmentation is performed based on the region growth of the normal vector refinement, so that the accuracy of segmenting the point cloud foreground and the background is improved, and better initial data is provided for the automatic size detection of the subsequent prefabricated part.
(2) When the geometric features of the point cloud of the prefabricated component are extracted, the boundary feature extraction algorithm based on the normal line improved by the search strategy is adopted, and the boundary feature extraction algorithm based on the normal line improved by the search strategy is implemented by comparing one point with the neighborhood point thereofVector included angle projected in tangential plane to judge whether the point is boundary point or not, the search strategy improvement means that the radius of normal calculation is searched and calculatedThe combination of neighbor searches becomes a hybrid search, thereby balancing the search speed and accuracy; compared with the traditional edge feature extraction algorithm, the method has higher detection precision, is more flexible in detection mode for components with different shapes, breaks the bottleneck of traditional detection, and enables quality detection to be paperless, intelligent and visual.
(3) The invention is based on 3Visual technique, 2->Vision means that by taking a picture of a plane with a camera and then identifying the object by image analysis or comparison, the features on the object plane can be seen, which can be used for absence/presence detection, and 3Visually acquired data are mainly 3 +.>The three-dimensional point cloud data collected by the sensor not only can sense whether the components exist in the scene, but also can accurately detect the size and the position orientation of the components, and the detection data is more comprehensive and accurate.
Detailed Description
The following description will clearly and fully describe the technical solutions of the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The method for detecting the size of the prefabricated part based on the point cloud geometric feature extraction specifically comprises the following steps:
(1) And the point cloud foreground and the background of the prefabricated component are segmented based on the refinement of the normal vector, so that the point cloud of the prefabricated component is segmented from the environment background (prefabricated factory), and the specific mode is as follows:
s11, refining normal vector: traversing each point in the point cloud of the prefabricated component, acquiring adjacent point sets of each point, and calculating curvature change and normal difference between a normal vector of each point and a normal vector of a current point of any point in each adjacent point set; when the curvature change and the normal direction difference exceed the set threshold values, taking the curvature change and the normal direction difference as residual error items, constructing a linear equation set, and calculating an adjustment value of an algorithm vector by solving the linear equation set; updating the normal vector of the current point according to the adjustment value of the normal vector to obtain a refined normal vector, repeating the steps, iterating for a plurality of times to adjust and optimize the normal vector of each point until the preset iteration times are reached, outputting the optimized normal vector as a new normal vector, and orienting the new normal vector to realize the refinement of the normal vector;
s12, performing image segmentation based on region growth refined by normal vector, performing secondary region growth segmentation when segmentation is not complete, and passing through a threshold value based on the condition of over-segmentationThe plane segmentation method comprises the steps of circularly recursively obtaining the maximum bin of an over-segmentation result, and finally, segmenting the point cloud of the prefabricated component from an environmental background;
wherein, based on threshold valueThe plane segmentation method specifically comprises the following steps:
a. establishing a plane model: randomly selecting three points in the point cloud data to establish an initial plane model;
b. single plane fitting: after a plane model is built and a fitting plane is built, calculating the distance between each point in the point cloud and the fitting plane, and counting the number of internal points;
c. multi-plane fitting: judging whether the current fitted plane model is reasonable or not according to the number of the internal points, and when the number of the internal points reaches a preset threshold value, considering that the current plane model is better to fit, and taking the current plane model as a final segmentation result; when the number of the inner points is insufficient, reconstructing the inner points into a new point cloud, and executing the steps on the new point cloudObtaining a new segmentation result, and combining the new segmentation result with the step +.>Comparing the segmentation results of the (a), and selecting a group with the largest surface element as a final segmentation result;
(2) Extracting geometric features of the point cloud of the prefabricated part, wherein the specific mode is edge extraction of the point cloud of the prefabricated part, and the specific steps are as follows:
point-to-pointNeighborhood point->Fitting the tangent plane by least squares, +.> =1，2，…，/>The method comprises the steps of carrying out a first treatment on the surface of the The general expression of the plane equation is shown in formula (1):
（1）；
the least square equation corresponding to each neighborhood point is shown in formula (2):
（2）；
i.e.（3）；
Solving the equation of the above formula (3) to obtain parameters、/>And->Carrying out formula (1) and obtaining a plane equation;
point to PointNeighborhood point->Projection onto tangential plane, point->The projection point in the tangential plane is，/>And->The parametric equation of (2) is shown in the following formula (4):
（4）；
will beSubstituting tangential plane equation to obtain +.>：
（5）；
Wherein,,、/>、/>、/>are constants in the tangential plane equation, and the projection point coordinates ++can be obtained by substituting the formula (5) into the formula (4)>；
In dotsProjection points of +.>For starting point, & lt + & gt>Defining a vector for the endpoint +.>Wherein any vector is taken>The vector product of the vector and the normal vector of the tangential plane is calculated as a vector +.>Then sequentially finding the vector +.>Respectively and vector->Vector->Included angle->、/>When->Included angle->The value of (2) is replaced by->The method comprises the steps of carrying out a first treatment on the surface of the For formula (6)>Sorting, selecting the maximum +.>As maximum angle->；
（6）；
Comparing adjacent two vectorsMaximum included angle->With the magnitude of the set angle threshold, when the maximum included angle +>If the angle is larger than the set angle threshold, then the point +.>Adding the boundary points into the boundary point set;
(3) Fitting the edge line of the prefabricated part according to the geometric characteristics of the point cloud of the prefabricated part, and calculating according to the fitted edge line to obtain the size information of the prefabricated part;
fitting of the edge lines of the prefabricated part is that a plurality of edge lines are fitted simultaneously: fitting straight lines by randomly selecting a group of points in the boundary point set, fitting all boundary points of the plane of the prefabricated part by executing a straight line fitting algorithm for a plurality of times, thereby obtaining a plurality of fitting straight lines, calculating the distance between every two fitting straight lines, obtaining the size information of the prefabricated part by solving the shortest distance between the two fitting straight lines, comparing the calculated size information of the prefabricated part with the size of a standard prefabricated part, namely obtaining the measurement precision by calculating according to a formula (7)：
（7）；
In the formula (7), the amino acid sequence of the compound,for the dimensional information of prefabricated components of the assembly type, +.>Is the size of a standard prefabricated part;
when the edge of one plane of the prefabricated component is rectangular, grouping the edge straight lines through geometric features (such as the start point, the end point, the direction vector and the like of the straight lines) of the straight lines when fitting the edge lines, and then selecting a group of points after grouping to fit the straight lines;
(4) 3 adding size information of prefabricated part under point cloud visualization interfaceText labels.
In order to verify the validity of the invention, the embodiment adopts an experimental method to verify the validity and accuracy of the size detection method of the assembled prefabricated part, and the specific experimental process comprises the following steps: the method comprises the steps of segmenting a foreground and a background of a component point cloud, extracting geometric features of the component point cloud, and automatically detecting the size and displaying a detection result.
1. Component point cloud foreground and background segmentation:
the improved effect of the experimental algorithm is that the indoor data set is disclosedAnd (3) performing verification, wherein two six classes of boxes, stacked boxes, shielding objects, cylindrical objects, mixed objects and complex scenes are selected. Through experiments, the invention has good accuracy and recall rate in object segmentation.
2. Extracting geometric features of component point clouds:
the embodiment mainly adopts the traditional technologyThe algorithm, the traditional boundary feature extraction algorithm based on the normal and the boundary feature extraction algorithm based on the normal with improved search strategy are compared, so that the effectiveness of the invention is embodied. By carrying out experiments on point clouds of 14 members with different shapes, compared with other two algorithms, the algorithm provided by the invention has the greatest number of extracted effective boundary points.
3. Automated size detection:
the experiment is to model six different types of components (the numbers are respectively、/>、、/>、/>、/>) Wherein->、/>、/>The length is the same as that of the real component, belonging to the qualified component, < ->、/>Setting an error of +5mm, < > on the real member>Setting error-1 mm. Tests were performed on six different types of components to determine if the invention is able to accurately detect if the dimensions of the components meet quality standards. To further verify the accuracy of the dimensions of the detection member of the present invention, the experiment was divided into three steps:
(1) And verifying the influence of the distance for acquiring the point cloud data on the experimental result. Express boxes (150 mm×290 mm) similar to the shape of the members were measured at different distances, and the experimental results are shown in table 1 below:
table 1 error table of measured data for different distances
；
(2) The error of the collected point cloud is about 2mm within the distance range of 600mm-1600mm, which is obtained from the above table 1, and the measurement is performedThe precision reaches 98 percent. Thus, 1400mm was chosen as the reference distance when the component point cloud was acquired. Reference to national standard1, allowing deviation of the size of the prefabricated part to be +/-5 mm, adding a risk assessment mechanism, setting the deviation to be low risk within the range of 1mm, and considering the deviation to be qualified without taking any measures; setting the deviation within the range of 1-3mm as a stroke risk, considering that the deviation is possibly unqualified, and suggesting a secondary spot check of a quality inspector; for deviations in the range of 3-5mm, setting the deviation as a high risk, considering that the deviation is high in possibility of failure, releasing warning, and reminding a quality inspector to focus on manual rechecking of the components.
（3）、、/>And->The component is detected as a qualified component,>and->The component is at high risk and needs to be re-checked manually for the second time,/->The component is a medium risk, and the sampling inspection is reminded to be performed again.
After comparing with the manual recheck, the invention meets the quality inspection standard in the detection accuracy of the yard in the factory or outside the factory, realizes the preliminary screening work of the quality detection link, realizes the automation, improves the detection efficiency and ensures the detection accuracy.
Because the number of the point clouds is large, the time is too long when the edge extraction is carried out, and the down-sampling treatment is carried out on the point clouds by adopting an octree sampling method, so that the edge extraction time is reduced, and the efficiency is improved.
4. And (3) displaying a detection result:
selecting an area needing size detection from the point cloud object, selecting a marked point in the area, visualizing the point cloud by using a visualization tool, selecting the marked point by means of mouse interaction and the like, correlating the detected size information with the point cloud data, and displaying the size information at the marked point.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311009724.8A CN116740060B (en) | 2023-08-11 | 2023-08-11 | Dimensional detection method of prefabricated components based on point cloud geometric feature extraction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311009724.8A CN116740060B (en) | 2023-08-11 | 2023-08-11 | Dimensional detection method of prefabricated components based on point cloud geometric feature extraction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116740060A CN116740060A (en) | 2023-09-12 |
| CN116740060B true CN116740060B (en) | 2023-10-20 |
Family
ID=87902929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311009724.8A Active CN116740060B (en) | 2023-08-11 | 2023-08-11 | Dimensional detection method of prefabricated components based on point cloud geometric feature extraction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116740060B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117853666B (en) * | 2024-03-07 | 2024-07-19 | 法奥意威(苏州)机器人系统有限公司 | Point cloud cylinder detection method and device based on subdivision octree |
| CN118071115B (en) * | 2024-04-18 | 2024-06-21 | 广州天奕技术股份有限公司 | Multi-source heterogeneous monitoring system, method, device and equipment |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2947463A1 (en) * | 2015-11-11 | 2017-05-11 | General Electric Company | Method and system for automated shaped cooling hole measurement |
| CN107025685A (en) * | 2017-04-11 | 2017-08-08 | 南京林业大学 | Airborne building summit cloud modeling method under topology ambiguity |
| CN108846888A (en) * | 2018-04-23 | 2018-11-20 | 北京建筑大学 | A kind of Gu wooden building components fine size information automation extracting method |
| CN110060344A (en) * | 2019-04-25 | 2019-07-26 | 重庆大学 | A kind of prefabricated components overall dimensions reverse modeling method based on point cloud data |
| CN110992341A (en) * | 2019-12-04 | 2020-04-10 | 沈阳建筑大学 | A segmentation-based method for building extraction from airborne LiDAR point cloud |
| CN111598916A (en) * | 2020-05-19 | 2020-08-28 | 金华航大北斗应用技术有限公司 | Preparation method of indoor occupancy grid map based on RGB-D information |
| CN113487722A (en) * | 2021-06-18 | 2021-10-08 | 浙江大学 | Automatic concrete member detection method based on three-dimensional laser scanning method |
| CN113498530A (en) * | 2018-12-20 | 2021-10-12 | 艾奎菲股份有限公司 | Object size marking system and method based on local visual information |
| CN113628166A (en) * | 2021-07-12 | 2021-11-09 | 广东电网有限责任公司广州供电局 | Method and device for detecting geometric dimension of breaker chamber of switch cabinet |
| CN114417524A (en) * | 2021-12-27 | 2022-04-29 | 西北工业大学 | Dimensional accuracy analysis and AR visualization method of thin-walled cylinder based on point cloud |
| CN115597494A (en) * | 2022-12-15 | 2023-01-13 | 安徽大学绿色产业创新研究院（Cn） | Precision detection method and system for prefabricated part preformed hole based on point cloud |
| CN115880274A (en) * | 2023-01-03 | 2023-03-31 | 上海建工四建集团有限公司 | Prefabricated part quality detection method and system based on three-dimensional computer vision |
| CN115962731A (en) * | 2022-12-05 | 2023-04-14 | 长春工业大学 | A detection method for stamping geometric dimension error of plate heat exchanger |
| CN116012399A (en) * | 2022-10-27 | 2023-04-25 | 东南大学 | Point cloud plane identification and edge detection method |
| CN116242277A (en) * | 2023-02-17 | 2023-06-09 | 北京卫星制造厂有限公司 | Automatic measurement method for size of power supply cabinet structural member based on full-field three-dimensional vision |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11321953B2 (en) * | 2020-03-25 | 2022-05-03 | Hong Kong Applied Science and Technology Research Institute Company Limited | Method and apparatus for posture, dimension and shape measurements of objects in 3D scenes |
| CN112697044B (en) * | 2020-12-17 | 2021-11-26 | 北京航空航天大学 | Static rigid object vision measurement method based on unmanned aerial vehicle platform |
-
2023
- 2023-08-11 CN CN202311009724.8A patent/CN116740060B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2947463A1 (en) * | 2015-11-11 | 2017-05-11 | General Electric Company | Method and system for automated shaped cooling hole measurement |
| CN107025685A (en) * | 2017-04-11 | 2017-08-08 | 南京林业大学 | Airborne building summit cloud modeling method under topology ambiguity |
| CN108846888A (en) * | 2018-04-23 | 2018-11-20 | 北京建筑大学 | A kind of Gu wooden building components fine size information automation extracting method |
| CN113498530A (en) * | 2018-12-20 | 2021-10-12 | 艾奎菲股份有限公司 | Object size marking system and method based on local visual information |
| CN110060344A (en) * | 2019-04-25 | 2019-07-26 | 重庆大学 | A kind of prefabricated components overall dimensions reverse modeling method based on point cloud data |
| CN110992341A (en) * | 2019-12-04 | 2020-04-10 | 沈阳建筑大学 | A segmentation-based method for building extraction from airborne LiDAR point cloud |
| CN111598916A (en) * | 2020-05-19 | 2020-08-28 | 金华航大北斗应用技术有限公司 | Preparation method of indoor occupancy grid map based on RGB-D information |
| CN113487722A (en) * | 2021-06-18 | 2021-10-08 | 浙江大学 | Automatic concrete member detection method based on three-dimensional laser scanning method |
| CN113628166A (en) * | 2021-07-12 | 2021-11-09 | 广东电网有限责任公司广州供电局 | Method and device for detecting geometric dimension of breaker chamber of switch cabinet |
| CN114417524A (en) * | 2021-12-27 | 2022-04-29 | 西北工业大学 | Dimensional accuracy analysis and AR visualization method of thin-walled cylinder based on point cloud |
| CN116012399A (en) * | 2022-10-27 | 2023-04-25 | 东南大学 | Point cloud plane identification and edge detection method |
| CN115962731A (en) * | 2022-12-05 | 2023-04-14 | 长春工业大学 | A detection method for stamping geometric dimension error of plate heat exchanger |
| CN115597494A (en) * | 2022-12-15 | 2023-01-13 | 安徽大学绿色产业创新研究院（Cn） | Precision detection method and system for prefabricated part preformed hole based on point cloud |
| CN115880274A (en) * | 2023-01-03 | 2023-03-31 | 上海建工四建集团有限公司 | Prefabricated part quality detection method and system based on three-dimensional computer vision |
| CN116242277A (en) * | 2023-02-17 | 2023-06-09 | 北京卫星制造厂有限公司 | Automatic measurement method for size of power supply cabinet structural member based on full-field three-dimensional vision |
Non-Patent Citations (2)
| Title |
|---|
| A new method for building roof segmentation from airborne LiDAR point cloud data;Deming Kong等;《Meas. Sci. Technol.》;第1-13页 * |
| 激光点云用于预制构件尺寸检测的方法研究;杜永军等;《现代交通技术》;第19卷(第4期);第39-45页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116740060A (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116740060B (en) | Dimensional detection method of prefabricated components based on point cloud geometric feature extraction | |
| CN111537517B (en) | An Unmanned Intelligent Stamping Defect Identification Method | |
| CN107609557B (en) | Pointer instrument reading identification method | |
| CN102135417B (en) | A fully automatic 3D feature extraction method | |
| CN114049294B (en) | Road surface technical condition detection method and equipment based on three-dimensional contour | |
| CN105335973B (en) | Apply to the visual processing method of strip machining production line | |
| CN114037675B (en) | Airplane sample plate defect detection method and device | |
| CN110455187B (en) | A three-dimensional vision-based detection method for box workpiece welds | |
| CN107301648B (en) | Redundant point cloud removing method based on overlapping area boundary angle | |
| CN105180890A (en) | Rock mass structural plane attitude measuring method integrating laser point cloud and digital image | |
| CN108846888A (en) | A kind of Gu wooden building components fine size information automation extracting method | |
| CN107516098A (en) | A Method of Extracting 3D Information of Object Outline Based on Edge Curvature Angle | |
| CN107798326A (en) | A kind of profile visual detection algorithm | |
| CN111028345B (en) | An automatic identification and docking method for circular pipelines in a port scene | |
| CN103400373A (en) | Method for automatically identifying and positioning coordinates of image point of artificial mark in camera calibration control field | |
| CN113487722A (en) | Automatic concrete member detection method based on three-dimensional laser scanning method | |
| CN116305436A (en) | Existing bridge monitoring method based on combination of three-dimensional laser scanning and BIM | |
| CN112365534A (en) | Large coal pile volume measurement method based on monocular camera three-dimensional reconstruction | |
| CN107679458A (en) | The extracting method of roadmarking in a kind of road color laser point cloud based on K Means | |
| CN115597494B (en) | A precision detection method and system for reserved holes of prefabricated components based on point cloud | |
| CN112561989A (en) | Method for identifying hoisting object in construction scene | |
| CN113870326B (en) | Structural damage mapping, quantifying and visualizing method based on image and three-dimensional point cloud registration | |
| CN111091534A (en) | A method for detecting and locating PCB board defects based on target detection | |
| CN101098492A (en) | Method for Determining the Topological Relationship of Targets and Camera Calibration Targets That Can Be Arbitrarily Placed | |
| CN111091121B (en) | Ellipse dial plate detection and correction method based on image processing |
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 |