CN113362248A - Binocular detection system for detecting object strain - Google Patents
Binocular detection system for detecting object strain Download PDFInfo
- Publication number
- CN113362248A CN113362248A CN202110697685.XA CN202110697685A CN113362248A CN 113362248 A CN113362248 A CN 113362248A CN 202110697685 A CN202110697685 A CN 202110697685A CN 113362248 A CN113362248 A CN 113362248A
- Authority
- CN
- China
- Prior art keywords
- strain
- images
- data
- module
- binocular
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000008602 contraction Effects 0.000 claims description 16
- 230000006855 networking Effects 0.000 claims description 8
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000009471 action Effects 0.000 abstract description 7
- 238000005259 measurement Methods 0.000 abstract description 4
- 125000004122 cyclic group Chemical group 0.000 abstract description 3
- 230000001066 destructive effect Effects 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 abstract description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- 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
-
- 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
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- G06T2207/30244—Camera pose
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a binocular detection system for detecting object strain, and particularly relates to the technical field of object strain measurement, wherein the binocular detection system comprises a binocular image acquisition module, an image model processing module, a data processing center and a strain detection module; the binocular image acquisition module is used for acquiring original boundary contour data of a detected object, and comprises a left camera module, a right camera module and a left camera module, and the left camera module and the right camera module are used for acquiring left and right object images; the binocular image acquisition module is used for carrying out nonlinear calibration on the two camera modules, and the two camera modules are calibrated through a calibration method based on OpenCV. The object strain detection method based on binocular vision has good object strain detection precision, effectively improves the object strain detection efficiency, can obtain the strain condition of the object under the action of dynamic load and environmental load, and prevents the integral destructive damage of the system caused by the failure of materials generated at stress concentration parts under the action of long-time cyclic load.
Description
Technical Field
The invention relates to the technical field of object strain measurement, in particular to a binocular detection system for detecting object strain.
Background
An object can deform to some extent under the action of an external force, and the deformation degree is called strain. When the temperature of an object changes, thermal strain is generated. Some objects absorb moisture in the humid air, thereby generating a wet strain.
The strain reaction is the deformation condition generated after the structure is stressed. The strain measurement is of great importance in the application of various types of structural materials in complex working environments of high temperature, high pressure, high speed and the like. The strain measurement result can reflect the mechanical condition of the structural member under the action of the structural characteristics, dynamic load and environmental load in the working process, and can prevent the failure of materials at stress concentration parts under the action of long-time cyclic load from causing the overall destructive damage of the system.
Disclosure of Invention
In order to achieve the purpose, the invention provides the following technical scheme: a binocular detection system for detecting object strain comprises a binocular image acquisition module, an image model processing module, a data processing center and a strain detection module;
the binocular image acquisition module is used for acquiring original boundary contour data of a detected object, and comprises a left camera module, a right camera module and a left camera module, and the left camera module and the right camera module are used for acquiring left and right object images;
the binocular image acquisition module is used for carrying out nonlinear calibration on the two camera modules, calibrating the two camera modules by an OpenCV-based calibration method, carrying out distortion correction on the two acquired object images, eliminating radial distortion and tangential distortion in the images, completing calibration on the camera modules and carrying out maximum likelihood estimation on the result;
the image model processing module controls the two camera modules to acquire images through a third party, carries out preprocessing, binaryzation and filtering denoising on the acquired images, detects the edges of the images through a sobel operator, detects circle center identification points of the images through transformation on the circle center identification points in the images, and sets a proper threshold value to determine the circle center and the circle center pixel coordinate value in the images;
the data processing center matches the two images to restore the three-dimensional information of the images, matches the undeformed images serving as reference images with the deformed images, matches the detected circle center identification points, eliminates the wrong circle center identification points through limit constraint conditions, selects a certain threshold value, and matches the reference images with the deformed images after error analysis;
the strain detection module is used for obtaining four linear equation sets after matching degree of each characteristic point obtained after image matching, image pixel coordinates of the characteristic points and each calibration parameter of the system are combined, obtaining three-dimensional coordinates of matched points of the object through a least square method, and then carrying out strain detection on the three-dimensional coordinates of all identification points and three-dimensional information of the identification points of the images in different states to obtain object strain data.
In a preferred embodiment, the data processing center is further connected with a networking module, and the networking module is used for connecting the network and acquiring the profile data, the object material information, the material strain data and the material thermal expansion and cold contraction data related to the object from the network.
In a preferred embodiment, the data processing center simulates and calculates object material information in an image acquisition scene, and based on profile data information generated under material strain data, profile data information generated under material expansion and contraction with heat, and profile data information generated under material strain data and material expansion and contraction with heat, and through the profile data information, a corresponding three-dimensional model is constructed by using third-party modeling software, and feature point coordinate data information in the three-dimensional model is acquired.
In a preferred embodiment, the strain detection module further performs strain detection on the three-dimensional coordinates of all identification points and the three-dimensional information of the identification points of the different-state images according to feature point coordinate data information of a three-dimensional model generated by profile data information generated under material strain data, so as to obtain object strain data.
In a preferred embodiment, the strain detection module further performs strain detection on the three-dimensional coordinates of all the identification points and the three-dimensional information of the identification points of the images in different states according to feature point coordinate data information of the three-dimensional model generated by profile data information generated under the data of thermal expansion and cold contraction of the material, so as to obtain object strain data.
In a preferred embodiment, the strain detection module further performs strain detection on the three-dimensional coordinates of all the identification points and the three-dimensional information of the identification points of the images in different states according to feature point coordinate data information of the three-dimensional model generated based on the material strain data and the profile data information generated under the material thermal expansion and cold contraction data, so as to obtain object strain data.
Technical effects and advantages of the invention
The object strain detection method based on binocular vision has good object strain detection precision, effectively improves the object strain detection efficiency, can obtain the strain condition of the object under the action of dynamic load and environmental load, and prevents the integral destructive damage of the system caused by the failure of materials generated at stress concentration parts under the action of long-time cyclic load.
Drawings
FIG. 1 is a schematic diagram of the system framework of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments. The embodiments of the present invention have been presented for purposes of illustration and description, and are not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiment was chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.
Example 1
The binocular detection system for detecting the strain of the object as shown in fig. 1 comprises a binocular image acquisition module, an image model processing module, a data processing center and a strain detection module;
the binocular image acquisition module is used for acquiring original boundary contour data of a detected object, and comprises a left camera module, a right camera module and a left camera module, and the left camera module and the right camera module are used for acquiring left and right object images;
the binocular image acquisition module is used for carrying out nonlinear calibration on the two camera modules, calibrating the two camera modules by an OpenCV-based calibration method, carrying out distortion correction on the two acquired object images, eliminating radial distortion and tangential distortion in the images, completing calibration on the camera modules and carrying out maximum likelihood estimation on the result;
the image model processing module controls the two camera modules to acquire images through a third party, carries out preprocessing, binaryzation and filtering denoising on the acquired images, detects the edges of the images through a sobel operator, detects circle center identification points of the images through transformation on the circle center identification points in the images, and sets a proper threshold value to determine the circle center and the circle center pixel coordinate value in the images;
the data processing center matches the two images to restore the three-dimensional information of the images, matches the undeformed images serving as reference images with the deformed images, matches the detected circle center identification points, eliminates the wrong circle center identification points through limit constraint conditions, selects a certain threshold value, and matches the reference images with the deformed images after error analysis;
the strain detection module is used for obtaining four linear equation sets after matching degree of each characteristic point obtained after image matching, image pixel coordinates of the characteristic points and each calibration parameter of the system are combined, obtaining three-dimensional coordinates of matched points of the object through a least square method, and then carrying out strain detection on the three-dimensional coordinates of all identification points and three-dimensional information of the identification points of the images in different states to obtain object strain data.
Example 2
Furthermore, the data processing center is also connected with a networking module, and the networking module is used for connecting a network and acquiring the related contour data, object material information, material strain data and material expansion and contraction data of the object from the network.
The data processing center simulates and calculates the profile data information generated under the material strain data of the object material information in an image acquisition scene, and constructs a corresponding three-dimensional model by using third-party modeling software through the profile data information to acquire the feature point coordinate data information in the three-dimensional model.
The strain detection module obtains the matching degree of each characteristic point obtained after image matching, the image pixel coordinate of the characteristic point and each calibration parameter of the system through simultaneous obtaining four linear equation sets, obtains the matched point three-dimensional coordinate of the object through a least square method, generates characteristic point coordinate data information of a three-dimensional model according to profile data information generated under material strain data, and then carries out strain detection on the three-dimensional coordinates of all identification points and the three-dimensional information of the identification points of the images in different states to obtain object strain data.
Example 3
Furthermore, the data processing center is also connected with a networking module, and the networking module is used for connecting a network and acquiring the related contour data, object material information, material strain data and material expansion and contraction data of the object from the network.
The data processing center simulates and calculates the profile data information generated by the material expansion with heat and contraction with cold in the image acquisition scene, and constructs a corresponding three-dimensional model by using third-party modeling software through the profile data information to acquire the feature point coordinate data information in the three-dimensional model.
The strain detection module obtains the matching degree of each characteristic point obtained after image matching, the image pixel coordinate of the characteristic point and each calibration parameter of the system through simultaneous obtaining four linear equation sets, obtains the matched point three-dimensional coordinate of the object through a least square method, generates characteristic point coordinate data information of a three-dimensional model according to profile data information generated under material thermal expansion and cold contraction data, and then carries out strain detection on the three-dimensional coordinates of all identification points and the three-dimensional information of the image identification points in different states to obtain object strain data.
Example 4
The data processing center simulates and calculates the profile data information generated by the material strain data and the material expansion and contraction data in the image acquisition scene, and constructs a corresponding three-dimensional model by using third-party modeling software through the profile data information to acquire the characteristic point coordinate data information in the three-dimensional model.
The strain detection module obtains the matching degree of each characteristic point obtained after image matching, the image pixel coordinate of the characteristic point and each calibration parameter of the system through simultaneous obtaining four linear equation sets, obtains the matched point three-dimensional coordinate of the object through a least square method, and carries out strain detection on the three-dimensional coordinates of all identification points and the three-dimensional information of the image identification points in different states according to characteristic point coordinate data information of a three-dimensional model generated based on profile data information generated under material strain data and material expansion and contraction data to obtain object strain data.
It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by one of ordinary skill in the art and related arts based on the embodiments of the present invention without any creative effort, shall fall within the protection scope of the present invention. Structures, devices, and methods of operation not specifically described or illustrated herein are generally practiced in the art without specific recitation or limitation.
Claims (6)
1. The utility model provides a binocular detecting system for detecting object is met an emergency which characterized in that: the binocular image acquisition system comprises a binocular image acquisition module, an image model processing module, a data processing center and a strain detection module;
the binocular image acquisition module is used for acquiring original boundary contour data of a detected object, and comprises a left camera module, a right camera module and a left camera module, and the left camera module and the right camera module are used for acquiring left and right object images;
the binocular image acquisition module is used for carrying out nonlinear calibration on the two camera modules, calibrating the two camera modules by an OpenCV-based calibration method, carrying out distortion correction on the two acquired object images, eliminating radial distortion and tangential distortion in the images, completing calibration on the camera modules and carrying out maximum likelihood estimation on the result;
the image model processing module controls the two camera modules to acquire images through a third party, carries out preprocessing, binaryzation and filtering denoising on the acquired images, detects the edges of the images through a sobel operator, detects circle center identification points of the images through transformation on the circle center identification points in the images, and sets a proper threshold value to determine the circle center and the circle center pixel coordinate value in the images;
the data processing center matches the two images to restore the three-dimensional information of the images, matches the undeformed images serving as reference images with the deformed images, matches the detected circle center identification points, eliminates the wrong circle center identification points through limit constraint conditions, selects a certain threshold value, and matches the reference images with the deformed images after error analysis;
the strain detection module is used for obtaining four linear equation sets after matching degree of each characteristic point obtained after image matching, image pixel coordinates of the characteristic points and each calibration parameter of the system are combined, obtaining three-dimensional coordinates of matched points of the object through a least square method, and then carrying out strain detection on the three-dimensional coordinates of all identification points and three-dimensional information of the identification points of the images in different states to obtain object strain data.
2. A binocular detection system for detecting strain of an object according to claim 1, wherein: the data processing center is also connected with a networking module, and the networking module is used for connecting a network and acquiring the related contour data of the object, the object material information, the material strain data and the material expansion with heat and contraction with cold data from the network.
3. A binocular detection system for detecting strain of an object according to claim 1, wherein: the data processing center simulates and calculates object material information in an image acquisition scene, profile data information generated under material strain data, profile data information generated under material expansion and contraction data and profile data information generated under material strain data and material expansion and contraction data are used, and a corresponding three-dimensional model is constructed through the profile data information and third-party modeling software to acquire feature point coordinate data information in the three-dimensional model.
4. A binocular detection system for detecting strain of an object according to claim 3, wherein: and the strain detection module is also used for carrying out strain detection on the three-dimensional coordinates of all identification points and the three-dimensional information of the identification points of the images in different states according to characteristic point coordinate data information of the three-dimensional model generated by contour data information generated under material strain data to obtain object strain data.
5. A binocular detection system for detecting strain of an object according to claim 3, wherein: and the strain detection module is also used for carrying out strain detection on the three-dimensional coordinates of all identification points and the three-dimensional information of the identification points of the images in different states according to characteristic point coordinate data information of the three-dimensional model generated by profile data information generated under the thermal expansion and cold contraction data of the material, so as to obtain object strain data.
6. A binocular detection system for detecting strain of an object according to claim 3, wherein: and the strain detection module is also used for carrying out strain detection on the three-dimensional coordinates of all identification points and the three-dimensional information of the identification points of the images in different states according to characteristic point coordinate data information of the three-dimensional model generated based on the material strain data and the contour data information generated under the material thermal expansion and cold contraction data, so as to obtain object strain data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110697685.XA CN113362248A (en) | 2021-06-23 | 2021-06-23 | Binocular detection system for detecting object strain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110697685.XA CN113362248A (en) | 2021-06-23 | 2021-06-23 | Binocular detection system for detecting object strain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113362248A true CN113362248A (en) | 2021-09-07 |
Family
ID=77535819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110697685.XA Pending CN113362248A (en) | 2021-06-23 | 2021-06-23 | Binocular detection system for detecting object strain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113362248A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117367308A (en) * | 2023-11-24 | 2024-01-09 | 江苏省特种设备安全监督检验研究院 | Three-dimensional full-field strain measurement method and application thereof in mechanical equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335568A (en) * | 2015-11-13 | 2016-02-17 | 北京航空航天大学 | Superplastic forming mold design method based on finite element technique with consideration of thermal expansion |
| CN106969706A (en) * | 2017-04-02 | 2017-07-21 | 聊城大学 | Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision |
| CN108053449A (en) * | 2017-12-25 | 2018-05-18 | 北京工业大学 | Three-dimensional rebuilding method, device and the binocular vision system of binocular vision system |
| WO2019062291A1 (en) * | 2017-09-29 | 2019-04-04 | 歌尔股份有限公司 | Binocular vision positioning method, device, and system |
-
2021
- 2021-06-23 CN CN202110697685.XA patent/CN113362248A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335568A (en) * | 2015-11-13 | 2016-02-17 | 北京航空航天大学 | Superplastic forming mold design method based on finite element technique with consideration of thermal expansion |
| CN106969706A (en) * | 2017-04-02 | 2017-07-21 | 聊城大学 | Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision |
| WO2019062291A1 (en) * | 2017-09-29 | 2019-04-04 | 歌尔股份有限公司 | Binocular vision positioning method, device, and system |
| CN108053449A (en) * | 2017-12-25 | 2018-05-18 | 北京工业大学 | Three-dimensional rebuilding method, device and the binocular vision system of binocular vision system |
Non-Patent Citations (1)
| Title |
|---|
| 管媛媛: "基于双目立体视觉的大尺寸物体变形检测", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117367308A (en) * | 2023-11-24 | 2024-01-09 | 江苏省特种设备安全监督检验研究院 | Three-dimensional full-field strain measurement method and application thereof in mechanical equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5297403B2 (en) | Position / orientation measuring apparatus, position / orientation measuring method, program, and storage medium | |
| CN114399554B (en) | Calibration method and system of multi-camera system | |
| CN109099852A (en) | Structural fault detection method and system for measuring relative deformation of wind turbine blade | |
| CN101639947A (en) | Image-based plant three-dimensional shape measurement and reconstruction method and system | |
| CN108109169B (en) | Pose estimation method and device based on rectangular identifier and robot | |
| Alemán-Flores et al. | Line detection in images showing significant lens distortion and application to distortion correction | |
| CN102982537A (en) | Scene change detection method and scene change detection system | |
| CN113362248A (en) | Binocular detection system for detecting object strain | |
| CN111182240B (en) | Temperature drift self-compensation method for image sensor | |
| CN115077425A (en) | Product detection equipment and method based on structured light three-dimensional vision | |
| CN113138026A (en) | Temperature measurement method and device based on temperature measurement system and computer equipment | |
| CN105654474A (en) | Mechanical arm positioning method based on visual guidance and device thereof | |
| CN105389825A (en) | Image processing method and system | |
| CN104217079A (en) | Method for measuring axial fan of wind driven generator by reversing technology | |
| CN108389204B (en) | Degraded image fuzzy kernel double-parameter direct estimation method for high-speed online detection | |
| CN111928949A (en) | Thermal image temperature measuring method and device, computer equipment and storage medium | |
| CN109313811A (en) | Auto-correction method, the apparatus and system of view-based access control model system vibration displacement | |
| CN114820820B (en) | 3D detection method for computer backshell | |
| CN114511120B (en) | Power equipment fault diagnosis method based on temperature vision electric wire | |
| CN114119842B (en) | Rendering method and system based on SSIM (structural similarity) and PSNR (Peak Signal to noise ratio) algorithm and computer readable storage medium | |
| CN115471616A (en) | Weld joint three-dimensional reconstruction method, device, processor and system | |
| CN105043275A (en) | Image processing-based icing thickness measurement method for power transmission line | |
| CN114111576A (en) | Aircraft skin clearance surface difference detection method and sensor | |
| Winstroth et al. | Wind turbine rotor blade monitoring using digital image correlation: 3d simulation of the experimental setup | |
| CN110702078B (en) | Indoor and outdoor integrated map construction method based on 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210907 |
|
| RJ01 | Rejection of invention patent application after publication |