CN111080685A - Airplane sheet metal part three-dimensional reconstruction method and system based on multi-view stereoscopic vision - Google Patents
Airplane sheet metal part three-dimensional reconstruction method and system based on multi-view stereoscopic vision Download PDFInfo
- Publication number
- CN111080685A CN111080685A CN201911298654.6A CN201911298654A CN111080685A CN 111080685 A CN111080685 A CN 111080685A CN 201911298654 A CN201911298654 A CN 201911298654A CN 111080685 A CN111080685 A CN 111080685A
- Authority
- CN
- China
- Prior art keywords
- sheet metal
- image
- dimensional
- metal part
- camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000004438 eyesight Effects 0.000 title claims abstract description 46
- 239000002184 metal Substances 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims abstract description 8
- 238000003709 image segmentation Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 5
- 238000010009 beating Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 description 11
- 230000006872 improvement Effects 0.000 description 9
- 238000009776 industrial production Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000005507 spraying Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000003111 delayed effect Effects 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
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a method and a system for three-dimensional reconstruction of an airplane sheet metal part based on multi-view stereoscopic vision, wherein the method comprises the following steps: collecting a tray image containing a plurality of airplane sheet metal parts based on a multi-view stereoscopic vision system; carrying out target detection, image segmentation and background filtering on the tray image to obtain a plurality of part images only containing a single airplane sheet metal part; calibrating a camera of the multi-view stereoscopic vision system to obtain the position of a part image; performing feature extraction and feature matching on the calibrated part image; and recovering the three-dimensional information of the tray image according to the matching result. The three-dimensional reconstruction method and the three-dimensional reconstruction system can perform one-time three-dimensional reconstruction on parts of different types and different quantities on one tray, greatly save the time required by reconstruction and improve the overall reconstruction efficiency.
Description
Technical Field
The invention relates to the technical field of machine vision three-dimensional reconstruction, in particular to a method and a system for three-dimensional reconstruction of an airplane sheet metal part based on multi-view stereoscopic vision.
Background
At present, the people enter the Internet age and step forward to the artificial intelligence age, and a new technological innovation leads a new production life style. The information technology is introduced into the industrial production and manufacturing industry and combined with the traditional industry, so that the production management is more intelligent, and the method is also the transformation direction of the current industrial production.
When the computer vision application focuses on identification, the three-dimensional structure of the article must be restored firstly to further realize interaction and perception; so on the basis of recognition, the next level will go to "three-dimensional reconstruction". Three-dimensional reconstruction comprises three problems, wherein one is that a picture is given at a position, and the picture shooting position is required to be obtained by computer vision; secondly, the stereoscopic vision field is multi-view, model acquisition is carried out mostly on the basis of binocular, and the multi-view can acquire more and more comprehensive structural information relative to the binocular, identify each pixel and carry out more complete recovery; and thirdly, semantic recognition, namely, further automatic recognition by means of visual perception or machines.
On present large-scale civil airliner part spraying automation line, what adopt is that machinery adds the mode of artifical combination to produce, the operation of discerning and spraying is carried out to the part of classification, still need the manual work to operate, if can utilize computer vision technique, carry out multinomial three-dimensional reconstruction through the image to the part, obtain more meticulous model, and match discernment and spatial localization based on three-dimensional model, then rely on robotic arm to carry out the fixed point spraying, realize better interchangeability, the spraying industrial production efficiency of civil aircraft part will be effectively promoted.
Although the three-dimensional reconstruction technology has a relatively mature system in the current academic world and the overall work flow is relatively consistent, the technical bottleneck still exists, and the three-dimensional reconstruction extracts information from a two-dimensional image so as to recover the three-dimensional information, so that feature matching points extracted from the two-dimensional image are the key of the technology, but the matching precision can be determined only by the number of the matching points (namely the number of point clouds), so that the three-dimensional reconstruction cannot perfectly meet the requirements on both the reconstruction precision and the reconstruction speed.
Disclosure of Invention
The invention provides a method and a system for three-dimensional reconstruction of airplane sheet metal parts based on multi-view stereoscopic vision, aiming at the problems that in the prior art, three-dimensional reconstruction needs to be carried out on each part on a tray, the time cost cannot meet the requirement and the efficiency is low.
The invention discloses a three-dimensional reconstruction method of an airplane sheet metal part based on multi-view stereoscopic vision, which comprises the following steps:
collecting a tray image containing a plurality of airplane sheet metal parts based on a multi-view stereoscopic vision system;
carrying out target detection, image segmentation and background filtering on the tray image to obtain a plurality of part images only containing a single airplane sheet metal part;
calibrating a camera of the multi-view stereoscopic vision system to obtain the position of the part image;
performing feature extraction and feature matching on the calibrated part image;
and recovering the three-dimensional information of the tray image according to the matching result.
As a further improvement of the present invention, the multi-view stereo vision system adopts four cameras to form a four-view stereo vision system;
and each camera rotates for one circle to obtain 16-32 images.
As a further improvement of the invention, the camera is calibrated by adopting a Zhang Zhengyou calibration method.
As a further improvement of the invention, an SIFT algorithm is adopted to extract the features of the calibrated part image.
As a further improvement of the present invention, the three-dimensional information of the tray image is restored according to the matching result; the method comprises the following steps:
calculating by utilizing a projective theorem to obtain the position of the camera according to the matching result;
obtaining three-dimensional point cloud of the airplane sheet metal part on the tray image according to the camera position and the tray image;
and constructing a three-dimensional model according to the three-dimensional point cloud, connecting the points into a surface, and recovering the three-dimensional information of the airplane sheet metal part on the tray image.
The invention also discloses a system for three-dimensional reconstruction of the airplane sheet metal part based on multi-view stereoscopic vision, which comprises the following components:
the acquisition module is used for acquiring a tray image containing a plurality of airplane sheet metal parts based on a multi-view stereoscopic vision system;
the processing module is used for carrying out target detection, image segmentation and background filtering on the tray image to obtain a plurality of part images only containing a single airplane sheet metal part;
the camera calibration module is used for calibrating a camera of the multi-view stereoscopic vision system to acquire the position of the part image;
the characteristic extraction and matching module is used for extracting and matching the characteristics of the calibrated part images;
and the three-dimensional reconstruction module is used for recovering the three-dimensional information of the tray image according to the matching result.
As a further improvement of the present invention, the multi-view stereo vision system adopts four cameras to form a four-view stereo vision system;
and each camera rotates for one circle to obtain 16-32 images.
As a further improvement of the invention, the camera is calibrated by adopting a Zhang Zhengyou calibration method.
As a further improvement of the invention, an SIFT algorithm is adopted to extract the features of the calibrated part image.
As a further improvement of the present invention, the three-dimensional information of the tray image is restored according to the matching result; the method comprises the following steps:
calculating by utilizing a projective theorem to obtain the position of the camera according to the matching result;
obtaining three-dimensional point cloud of the airplane sheet metal part on the tray image according to the camera position and the tray image;
and constructing a three-dimensional model according to the three-dimensional point cloud, connecting the points into a surface, and recovering the three-dimensional information of the airplane sheet metal part on the tray image.
Compared with the prior art, the invention has the beneficial effects that:
the three-dimensional reconstruction method and the three-dimensional reconstruction system can perform one-time three-dimensional reconstruction on parts of different types and different quantities on one tray, greatly save the time required by reconstruction and improve the overall reconstruction efficiency.
Drawings
FIG. 1 is a flow chart of a method for three-dimensional reconstruction of an aircraft sheet metal part based on multi-view stereoscopic vision according to an embodiment of the invention;
FIG. 2 is a frame diagram of a three-dimensional reconstruction system for an aircraft sheet metal part based on multi-view stereoscopic vision according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a four-eye stereo vision system according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a portion of an input original image according to one embodiment of the disclosure;
FIG. 5 is a top view of a three-dimensional reconstruction as disclosed in one embodiment of the present invention;
fig. 6 is a side view of a three-dimensional reconstruction as disclosed in one embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The invention is described in further detail below with reference to the attached drawing figures:
example 1:
the invention provides a method and a system for three-dimensional reconstruction of airplane sheet metal parts based on multi-view stereoscopic vision, which are used for acquiring a three-dimensional model of each part through research of three-dimensional scene reconstruction and scene model segmentation under multi-view stereoscopic vision. Under the large-scale industrial production scene, aiming at the large-scale quantity classification and the complex scene, intelligent manufacturing is realized by means of intelligent and mechanical integration, so that the cost can be effectively reduced and the industrial production efficiency can be improved.
1. Health factors: paint mist is inevitably generated in the air in the spraying environment, the noise of the production environment is high, the work in the environment for a long time has influence on the human body, and the manpower is effectively liberated by replacing human eye identification through three-dimensional reconstruction.
2. Efficiency factor: full-automatic production is realized by means of three-dimensional reconstruction, 24-hour uninterrupted production can be realized, the spraying efficiency of each tray is not lower than that of manual operation, and the production efficiency is effectively improved.
3. The development factors are as follows: the intelligent and automatic production is an effective means for improving the competitiveness of future industrial production, and the competitiveness of industrial products is effectively improved through the effective combination and design of computer vision and production.
As shown in fig. 1, the invention provides a three-dimensional reconstruction method of an airplane sheet metal part based on multi-view stereoscopic vision, which comprises the following steps:
s1, collecting tray images containing a plurality of airplane sheet metal parts based on a multi-view stereoscopic vision system; wherein:
there are many methods for obtaining images, such as analyzing the spatial position and size of an object through a depth map, or reproducing the spatial elements of the object through multiple images, and selecting the spatial elements according to the environmental impact of the actual scene, such as: lighting conditions, background noise, part complexity, part overlap, and the like. The method based on multi-image input is most suitable because the parts in the factory are more complex and the stacking degree is also more overlapped, and many key elements are lost when the depth map is used for analysis. Therefore, the invention uses a plurality of line cameras to acquire image information, each image keeps the same shooting angle, so as to ensure that more element information of the part can be contained in the image, and simultaneously, the efficiency of acquiring the image can be improved by using a plurality of cameras.
As shown in fig. 3, the present invention adopts four cameras to form a four-eye stereoscopic vision system, and the four cameras are located on the same horizontal plane and rotate in the horizontal direction by the same angle each time to obtain a plurality of part images with different angles. The number of the image is determined by the angle of each rotation of the four cameras in the horizontal direction; it is envisaged that at least 16 sheets are acquired, i.e. 22.5 ° per rotation, and at most 32 sheets are acquired, i.e. 11.25 ° per rotation. The point cloud model obtained finally is too sparse and cannot be subjected to subsequent processing to form a complete three-dimensional model after experimental exploration of less than 16 pictures; and if the number of the points is more than 32, the points in the point cloud model are overlapped with each other, so that the speed and the efficiency of the system are delayed. The process of acquiring images once by the four-eye stereoscopic vision system is shown in the following figures, images shot by each camera are respectively marked as 'IMG 1', 'IMG 2', 'IMG 3' and 'IMG 4', and images formed by a point P (x, y, z) in an object coordinate system O-XYZ in each camera are respectively a point P1, a point P2, a point P3 and a point P4.
S2, carrying out target detection, image segmentation and background filtering on the tray image to obtain a plurality of part images only containing a single airplane sheet metal part; wherein:
because the acquired original image usually contains a large amount of other redundant signals, namely noise signals; therefore, the image is preprocessed to ensure that the reconstruction is more accurate, the signal-to-noise ratio of the image information can be greatly improved through preprocessing, and unnecessary elements which do not meet the acquisition requirement are filtered.
Because the variety of parts is various, the complexity of the parts is high, and the influence of environmental factors of an off-line factory is also large, the three-dimensional model can be accurately restored in the subsequent reconstruction process; after the image is obtained, firstly, target detection and image segmentation are carried out, and the purpose is to separately identify and match each part and avoid the problem of mutual influence among a plurality of parts; and then, background filtering is carried out, so that the influence of the scene on noise points in the reconstruction process is reduced, noise reduction operation is carried out to a great extent, and preparation is provided for obtaining a point cloud model and three-dimensional reconstruction.
S3, calibrating a camera of the multi-view stereoscopic vision system to obtain the position of a part image; wherein:
the camera calibration can locate the specific position of each image and restore the spatial information where the image is located, and the result of the step greatly influences whether the finally reconstructed model is accurate enough. In image measurement processes and machine vision applications, in order to determine the correlation between the three-dimensional geometric position of a certain point on the surface of an object in space and the corresponding point in the image, a geometric model of camera imaging must be established, and the parameters of the geometric model are the parameters of the camera. Under most conditions, the parameters can be obtained through experiments and calculation, and the camera calibration is the process for solving the parameters.
The invention adopts Zhangzhengyou chessboard calibration method as a camera calibration method, which comprises the specific steps of firstly determining world coordinates of focuses on a chessboard (generally, the upper left corner of an image is selected as the origin of a world coordinate system), then respectively collecting chessboard images by each camera, extracting corner points of the chessboard through analog-to-digital conversion, and finally calibrating the camera and obtaining internal and external parameters of the camera. The Harris angular point detection algorithm is used in the angular point extraction method, has high stability, is simple and easy to understand and realize, and has the advantages of short consumed time and uniform distribution of detected characteristic points.
S4, performing feature extraction and feature matching on the calibrated part image; wherein:
the calibrated image pixels all obtain the image coordinates of the calibrated image pixels, and the characteristic extraction is needed to be carried out when the calibrated image pixels are matched, so that the one-to-one corresponding relation between the object on the image and the actual object is determined;
the method adopts the SIFT algorithm to extract the features of the calibrated part image, the SIFT algorithm searches for an extreme point in the spatial scale, and extracts the position, the scale and the rotation invariant of the extreme point. The essence of the SIFT algorithm is to search key points (feature points) in different scale spaces and calculate the directions of the key points. The key points searched by SIFT are some points which are quite prominent and can not change due to factors such as illumination, affine transformation and noise, such as angular points, edge points, bright points in a dark area, dark points in a bright area and the like. Therefore, an SIFT algorithm is selected for feature extraction, and the influence of noise and scenes on parts can be reduced to the maximum extent.
After extracting the feature points, carrying out feature matching, corresponding the same space point in different images, and establishing the corresponding relation of features among a plurality of images; usually, a feature point in one image may have many matching objects in another image, and there are adverse factors such as lighting conditions, scene shape, interference noise and distortion in the scene, which also cause ambiguous matches. Therefore, it is important to accurately perform unambiguous matching on images; the invention relates to the extraction of feature points of four images, and then more accurately matches in a plurality of images according to the association of the feature points to establish a foundation for reconstructing a three-dimensional model.
S5, according to the matching result, performing sparse reconstruction and dense reconstruction based on VSFM, and recovering three-dimensional information of the tray image; wherein:
the method specifically comprises the following steps:
motion recovery structure or sparse reconstruction: according to the matching result, calculating by utilizing a projective theorem to obtain scene information such as the position of the camera; the method is implemented by a Bundler algorithm;
dense reconstruction: obtaining three-dimensional point cloud of the airplane sheet metal part on the tray image according to the camera position and the tray image; the quality of the point cloud is influenced by the execution efficiency, reconstruction precision and integrity of the image processing precision, and the method is carried out by using a PMVS algorithm;
constructing a three-dimensional model according to the three-dimensional point cloud, connecting the points into a surface, and recovering three-dimensional information of the airplane sheet metal part on the tray image; the algorithm used in this step is the poisson surface reconstruction algorithm.
The specific experimental effect diagram is as follows:
the input tray image (original image) is shown in fig. 4;
the three-dimensional reconstructed disc images are shown in fig. 5 and 6.
Example 2:
based on the specific process of the aircraft sheet metal part three-dimensional reconstruction method based on the multi-view stereo vision, the invention also correspondingly provides an aircraft sheet metal part three-dimensional reconstruction system based on the multi-view stereo vision, which comprises the following steps:
the acquisition module is used for acquiring a tray image containing a plurality of airplane sheet metal parts based on a multi-view stereoscopic vision system;
the processing module is used for carrying out target detection, image segmentation and background filtering on the tray image to obtain a plurality of part images only containing a single airplane sheet metal part;
the camera calibration module is used for calibrating a camera of the multi-view stereoscopic vision system to acquire the position of a part image;
the characteristic extraction and matching module is used for extracting and matching the characteristics of the calibrated part images;
and the three-dimensional reconstruction module is used for performing sparse reconstruction and dense reconstruction based on VSFM according to the matching result and recovering the three-dimensional information of the tray image.
The invention has the advantages that:
the invention is oriented to the actual factory production operation, the reconstruction precision and the reconstruction speed are strictly mastered, and the speed is controlled under the condition of ensuring the precision, so that the whole reconstruction system can be applied to the factory operation; the three-dimensional reconstruction method and the three-dimensional reconstruction system can perform one-time three-dimensional reconstruction on parts of different types and different quantities on one tray, greatly save the time required by reconstruction and improve the overall reconstruction efficiency.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A three-dimensional reconstruction method for an airplane sheet metal part based on multi-view stereoscopic vision is characterized by comprising the following steps:
collecting a tray image containing a plurality of airplane sheet metal parts based on a multi-view stereoscopic vision system;
carrying out target detection, image segmentation and background filtering on the tray image to obtain a plurality of part images only containing a single airplane sheet metal part;
calibrating a camera of the multi-view stereoscopic vision system to obtain the position of the part image;
performing feature extraction and feature matching on the calibrated part image;
and recovering the three-dimensional information of the tray image according to the matching result.
2. The three-dimensional reconstruction method of the airplane sheet metal part as claimed in claim 1, wherein the multi-view stereo vision system adopts four cameras to form a four-view stereo vision system;
and each camera rotates for one circle to obtain 16-32 images.
3. The three-dimensional reconstruction method of an aircraft sheet metal part according to claim 1, characterized in that a Zhang-friend calibration method is adopted to calibrate the camera.
4. The aircraft sheet metal part three-dimensional reconstruction method of claim 1, wherein a SIFT algorithm is adopted to perform feature extraction on the calibrated part image.
5. The aircraft sheet metal part three-dimensional reconstruction method of claim 1, wherein the three-dimensional information of the tray image is restored according to the matching result; the method comprises the following steps:
calculating by utilizing a projective theorem to obtain the position of the camera according to the matching result;
obtaining three-dimensional point cloud of the airplane sheet metal part on the tray image according to the camera position and the tray image;
and constructing a three-dimensional model according to the three-dimensional point cloud, connecting the points into a surface, and recovering the three-dimensional information of the airplane sheet metal part on the tray image.
6. The utility model provides an aircraft panel beating part three-dimensional system of rebuilding based on multi-view stereo vision which characterized in that includes:
the acquisition module is used for acquiring a tray image containing a plurality of airplane sheet metal parts based on a multi-view stereoscopic vision system;
the processing module is used for carrying out target detection, image segmentation and background filtering on the tray image to obtain a plurality of part images only containing a single airplane sheet metal part;
the camera calibration module is used for calibrating a camera of the multi-view stereoscopic vision system to acquire the position of the part image;
the characteristic extraction and matching module is used for extracting and matching the characteristics of the calibrated part images;
and the three-dimensional reconstruction module is used for recovering the three-dimensional information of the tray image according to the matching result.
7. The aircraft sheet metal part three-dimensional reconstruction system of claim 6, wherein the multi-view stereo vision system adopts four cameras to form a four-view stereo vision system;
and each camera rotates for one circle to obtain 16-32 images.
8. An aircraft sheet metal part three-dimensional reconstruction system as claimed in claim 6 wherein calibration of the camera is performed using the Zhang friend calibration method.
9. The aircraft sheet metal part three-dimensional reconstruction system of claim 6, wherein a SIFT algorithm is adopted to perform feature extraction on the calibrated part image.
10. An aircraft sheet metal part three-dimensional reconstruction system as claimed in claim 6 wherein said three-dimensional information of said tray image is restored based on the matching results; the method comprises the following steps:
calculating by utilizing a projective theorem to obtain the position of the camera according to the matching result;
obtaining three-dimensional point cloud of the airplane sheet metal part on the tray image according to the camera position and the tray image;
and constructing a three-dimensional model according to the three-dimensional point cloud, connecting the points into a surface, and recovering the three-dimensional information of the airplane sheet metal part on the tray image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911298654.6A CN111080685A (en) | 2019-12-17 | 2019-12-17 | Airplane sheet metal part three-dimensional reconstruction method and system based on multi-view stereoscopic vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911298654.6A CN111080685A (en) | 2019-12-17 | 2019-12-17 | Airplane sheet metal part three-dimensional reconstruction method and system based on multi-view stereoscopic vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111080685A true CN111080685A (en) | 2020-04-28 |
Family
ID=70314911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911298654.6A Pending CN111080685A (en) | 2019-12-17 | 2019-12-17 | Airplane sheet metal part three-dimensional reconstruction method and system based on multi-view stereoscopic vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111080685A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111968223A (en) * | 2020-08-10 | 2020-11-20 | 哈尔滨理工大学 | Three-dimensional reconstruction system for 3D printing process based on machine vision |
| CN114299237A (en) * | 2021-12-28 | 2022-04-08 | 中铭谷智能机器人(广东)有限公司 | Intelligent identification and deletion method for single sheet metal tool model |
| CN114299237B (en) * | 2021-12-28 | 2024-05-10 | 中铭谷智能机器人(广东)有限公司 | Intelligent identification deleting method for single sheet metal tool model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107194989A (en) * | 2017-05-16 | 2017-09-22 | 交通运输部公路科学研究所 | The scene of a traffic accident three-dimensional reconstruction system and method taken photo by plane based on unmanned plane aircraft |
| CN107560592A (en) * | 2017-08-21 | 2018-01-09 | 河南中光学集团有限公司 | A kind of precision ranging method for optronic tracker linkage target |
| CN109872397A (en) * | 2019-02-18 | 2019-06-11 | 北京工业大学 | A kind of three-dimensional rebuilding method of the airplane parts based on multi-view stereo vision |
| WO2019179200A1 (en) * | 2018-03-22 | 2019-09-26 | 深圳岚锋创视网络科技有限公司 | Three-dimensional reconstruction method for multiocular camera device, vr camera device, and panoramic camera device |
| CN110288713A (en) * | 2019-07-03 | 2019-09-27 | 北京机械设备研究所 | A kind of quick three-dimensional model reconstruction method and system based on multi-vision visual |
-
2019
- 2019-12-17 CN CN201911298654.6A patent/CN111080685A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107194989A (en) * | 2017-05-16 | 2017-09-22 | 交通运输部公路科学研究所 | The scene of a traffic accident three-dimensional reconstruction system and method taken photo by plane based on unmanned plane aircraft |
| CN107560592A (en) * | 2017-08-21 | 2018-01-09 | 河南中光学集团有限公司 | A kind of precision ranging method for optronic tracker linkage target |
| WO2019179200A1 (en) * | 2018-03-22 | 2019-09-26 | 深圳岚锋创视网络科技有限公司 | Three-dimensional reconstruction method for multiocular camera device, vr camera device, and panoramic camera device |
| CN109872397A (en) * | 2019-02-18 | 2019-06-11 | 北京工业大学 | A kind of three-dimensional rebuilding method of the airplane parts based on multi-view stereo vision |
| CN110288713A (en) * | 2019-07-03 | 2019-09-27 | 北京机械设备研究所 | A kind of quick three-dimensional model reconstruction method and system based on multi-vision visual |
Non-Patent Citations (1)
| Title |
|---|
| QINGYANG WU等: "Flexible 3D reconstruction method based onphase-matching in multi-sensor system", 《HTTPS://OPG.OPTICA.ORG》, 28 March 2016 (2016-03-28), pages 1 - 31 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111968223A (en) * | 2020-08-10 | 2020-11-20 | 哈尔滨理工大学 | Three-dimensional reconstruction system for 3D printing process based on machine vision |
| CN114299237A (en) * | 2021-12-28 | 2022-04-08 | 中铭谷智能机器人(广东)有限公司 | Intelligent identification and deletion method for single sheet metal tool model |
| CN114299237B (en) * | 2021-12-28 | 2024-05-10 | 中铭谷智能机器人(广东)有限公司 | Intelligent identification deleting method for single sheet metal tool model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112070818B (en) | Robot disordered grabbing method and system based on machine vision and storage medium | |
| CN110264567B (en) | Real-time three-dimensional modeling method based on mark points | |
| CN109255813B (en) | Man-machine cooperation oriented hand-held object pose real-time detection method | |
| US10109055B2 (en) | Multiple hypotheses segmentation-guided 3D object detection and pose estimation | |
| CN109544456B (en) | Panoramic environment sensing method based on two-dimensional image and three-dimensional point cloud data fusion | |
| CN105894499B (en) | A kind of space object three-dimensional information rapid detection method based on binocular vision | |
| CN103093191B (en) | A kind of three dimensional point cloud is in conjunction with the object identification method of digital image data | |
| CN104463108B (en) | A kind of monocular real time target recognitio and pose measuring method | |
| CN111151463B (en) | Mechanical arm sorting and grabbing system and method based on 3D vision | |
| CN106709950B (en) | Binocular vision-based inspection robot obstacle crossing wire positioning method | |
| CN110176032B (en) | Three-dimensional reconstruction method and device | |
| CN108010123B (en) | Three-dimensional point cloud obtaining method capable of retaining topology information | |
| CN109000557B (en) | A kind of nuclear fuel rod pose automatic identifying method | |
| CN114952809B (en) | Workpiece identification and pose detection method, system and mechanical arm grabbing control method | |
| CN109470149B (en) | Method and device for measuring position and posture of pipeline | |
| CN111524233A (en) | Three-dimensional reconstruction method for dynamic target of static scene | |
| CN112419429B (en) | Large-scale workpiece surface defect detection calibration method based on multiple viewing angles | |
| CN111998862B (en) | BNN-based dense binocular SLAM method | |
| CN112734844B (en) | Monocular 6D pose estimation method based on octahedron | |
| CN112348890A (en) | Space positioning method and device and computer readable storage medium | |
| CN111127556B (en) | Target object identification and pose estimation method and device based on 3D vision | |
| CN113393441B (en) | Layered manufacturing defect detection method based on machine vision | |
| CN114494463A (en) | Robot sorting method and device based on binocular stereoscopic vision technology | |
| Gao et al. | Sparse dense fusion for 3d object detection | |
| Liu et al. | The applications and summary of three dimensional reconstruction based on stereo vision |
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 |