CN110288865A - A kind of system of skill operation supplemental training and detection based on machine vision - Google Patents
A kind of system of skill operation supplemental training and detection based on machine vision Download PDFInfo
- Publication number
- CN110288865A CN110288865A CN201910387052.1A CN201910387052A CN110288865A CN 110288865 A CN110288865 A CN 110288865A CN 201910387052 A CN201910387052 A CN 201910387052A CN 110288865 A CN110288865 A CN 110288865A
- Authority
- CN
- China
- Prior art keywords
- image
- telecommunications
- square
- detection
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Multimedia (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to detection system equipment technical fields, and disclose a kind of system of skill operation supplemental training and detection based on machine vision, including computer 1, the output end telecommunications of the computer 1 is connected with driving control system 2 and acquisition control circuit 3, telecommunications is connected with detection system 4, warning system 5 and camera system 6 to the output end of the driving control system 2 and acquisition control circuit 3 respectively, the output end of the detection system 4 is connect with 5 input terminal telecommunications of warning system, and the output end of the detection system 4 is connect with the input terminal telecommunications of camera system 6.The system of the skill operation supplemental training and detection based on machine vision, Intelligentized regulating and controlling light is carried out to camera system 6 by being equipped with adaptive lighting system 7, it ensure that the accuracy of camera shooting process data, reduce a possibility that data comparison is made a fault, significantly increases the accuracy of the system.
Description
Technical field
The present invention relates to detection system equipment technical field, specially a kind of skill operation based on machine vision assists instruction
Practice the system with detection.
Background technique
Existing skill operation supplemental training is place mat early period of skills training process, is currently needed to skill operation supplemental training
It wants skilled worker to observe and teaching could complete training one by one;Human factor leads to many disadvantages such as training effectiveness is low, operation precision is poor
End.
The template image correctly shown is stored in advance in existing detection method, by acquired image and template image
Carry out Gray-scale Matching, basic thought are as follows: image is considered as by 2D signal with the viewpoint of statistics, is found using the method for statistical correlation
Relevant matches between signal evaluate their similitude using the correlation function of two signals, according to matching degree (percentage) come
The correctness of judgement display image.This method closest to human eye detection method, it can be readily appreciated that but existing for Gray-scale Matching
Problem is also more apparent:
(1) accurate image coordinate is excessively relied on, i.e., if tested image has slight rotation and scaling, even if human eye is sentenced
Disconnected indifference, but the relevant matches degree being calculated can also have a greater change, it is higher so as to cause false detection rate;
(2) flexibility is poor, and traditional gray-scale Matching algorithm is relatively fixed, and the adjustment that can be made in practical application is single, to more
The actual conditions bad adaptability of change.
Therefore it is badly in need of providing a kind of system of skill operation supplemental training and detection based on machine vision.
Summary of the invention
(1) the technical issues of solving
In view of the deficiencies of the prior art, the skill operation supplemental training and inspection that the present invention provides a kind of based on machine vision
The advantages that system of survey has Detection accuracy height, and fault is few.
(2) technical solution
To realize that above-mentioned Detection accuracy is high, few purpose of making mistakes, the invention provides the following technical scheme: a kind of be based on machine
The output end telecommunications of the skill operation supplemental training of vision and the system of detection, including computer 1, the computer 1 is connected with
The output end of driving control system 2 and acquisition control circuit 3, the driving control system 2 and acquisition control circuit 3 distinguishes telecommunications
It is connected with detection system 4, warning system 5 and camera system 6, output end and 5 input terminal of the warning system electricity of the detection system 4
Letter connection, the output end of the detection system 4 are connect with the input terminal telecommunications of camera system 6, and the camera system 6 includes camera shooting
Data storage card 61, the input outlet of the camera data memory card 61 is connect with the output end telecommunications of detection system 4, described to take the photograph
As the output end telecommunications of data storage card 61 is connected with camera 62, the input terminal telecommunications of the camera 62 is connected with adaptively
Lighting system 7, the input terminal output with driving control system 2 and acquisition control circuit 3 respectively of the adaptive lighting system 7
Telecommunications connection is held, is equipped with skill operation platform 8 at the camera lens of the camera 62;
Wherein detection system 4 specific steps are as follows:
Step 1: acquiring general image to be detected from camera data memory card 61, set according to general image information to be detected
The pattern detected needed for fixed sets the ROI of image, intercepts the subgraph of institute's detection zone, and by subgraph gray processing, as to
Detection image;Corresponding template image is read from camera data memory card 61;
Step 2: image to be detected and template image are filled into square image by detection system 4, and it will test image and mould
The barycenter displacement of plate image carries out translation normalization generation translation image to be detected peace and moves Prototype drawing to the center of square image
Picture;
Step 3: computer 1 calculates the Zernike square for translating image peace to be checked and moving template image using fast algorithm;
Step 4: 1 pair of computer calculates the Zernike square that resulting translation image peace to be checked moves template image and carries out ruler
Degree normalization generates dimension normalization square Znm;
Step 5: according to dimension normalization square Znm construct square vector Z src and Ztem, wherein Zsrc be image to be detected to
Amount, Ztem are template gray image vector;
Step 6: calculating the opposite of square vector Z src and Ztem for each of square vector Z src and Ztem element
Match-percentage, and the opposite match-percentage of square vector Z src and Ztem are stored in and determined in feature vector J, construction determines
Feature vector J;
Step 7: the Gray-scale Matching degree of image and template image to be checked is calculated using normalizated correlation coefficient matching method, and
It is converted to percentage and obtains Gray-scale Matching degree;
Feature vector J is determined Step 8: Gray-scale Matching degree match is assigned to as new element, obtains updated sentencing
Determine feature vector J ';
Step 9: calculating the weighted arithmetic average for determining each element in feature vector J', the percentage of similarity is obtained
Match_result;
Step 10: comparing Match_result and given threshold Threshold, testing result is obtained;If Match_
The value of result is greater than given threshold Threshold and thinks that detection is qualified;Complete it is a kind of based on normalizing Zernike square and
Detection of the Gray-scale Matching to being operated on skill operation platform 8.
Preferably, the detection system 4 includes Image Acquisition display end 41, and described image acquires the input of display end 41
End is connect with the output end telecommunications of camera data memory card 61, and the output end telecommunications of described image acquisition display end 41 is connected with number
According to library 42, the output end telecommunications of the database 42 is connected with data difference signal output end 43, and the data difference signal is defeated
The output end of outlet 43 is connect with the input terminal telecommunications of warning system 5.
Preferably, the warning system 5 includes warning lamp 51 and loudspeaker 52, the warning lamp 51 and loudspeaker 52 it is defeated
Enter end to connect with the input terminal telecommunications of data difference signal output end 43.
Preferably, the adaptive lighting system 7 includes photosensitive sensors 71, the input terminal electricity of the photosensitive sensors 71
Letter is connected with data processing end 72, and the input terminal telecommunications at the data processing end 72 is connected with light compensating lamp 73, the light compensating lamp 73
It is mounted at 74 camera lens.
Preferably, the adaptive lighting system 7 is according to workpiece surface reflectivity, workpiece surface and imaging system optic angle
Degree, operating distance measuring condition, the light intensity of adjust automatically lighting source.
Preferably, described 74 image information is acquired using CMOS or CCD camera.
Preferably, the step acquisition control circuit 3 calculates image and template image to be checked using fast algorithm
Zernike square detailed process are as follows:
Square-shaped image g (x, y) is transformed under polar coordinates f (γ, ξ) using square-circle transform, γ, ξ is obtained by following formula:
γ=max | x |, | y |, if | x |=γ, if | y |=γ, the corresponding normalization polar coordinates of pixel (γ, ξ) are as follows: r=2
γ/N, θ=π γ of ξ/4, wherein N is the number of the side length pixel of square image.
Three, beneficial effect
Compared with prior art, the skill operation supplemental training that the present invention provides a kind of based on machine vision and detection
System, have it is following the utility model has the advantages that
It 1, should be based on the skill operation supplemental training of machine vision and the system of detection, by being equipped with adaptive lighting system
7 pairs of camera systems 6 carry out Intelligentized regulating and controlling light, ensure that the accuracy of camera shooting process data, reduce data comparison appearance
A possibility that fault, significantly increases the accuracy of the system.
It 2, should be based on the skill operation supplemental training of machine vision and the system of detection, by detection method with the square of image
Based on feature, the rotation of normalizing Zernike square, translation and scale invariance ensure that the stability of algorithm, even if detection system
Machinery be loaded and have certain error, the image of acquisition has and can also steadily calculate each rank square value when certain deviation.
Detailed description of the invention
Fig. 1 is present system structural block diagram;
Fig. 2 is camera system block diagram of the present invention;
Fig. 3 is the adaptive lighting system block diagram of structure of the invention;
Fig. 4 is present invention monitoring system block diagram;
Fig. 5 is warning system block diagram of the present invention.
In figure: 1, computer;2, driving control system;3, acquisition control circuit;4, detection system;41, Image Acquisition is aobvious
Show end;42, database;43, data difference signal output end;5, warning system;51, warning lamp;52, loudspeaker;6, camera shooting system
System;61, camera data memory card;62, camera;7, adaptive lighting system;71, photosensitive sensors;72, data processing end;
73, light compensating lamp;8, skill operation platform.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Please refer to Fig. 1-5, a kind of system of skill operation supplemental training and detection based on machine vision, including computer
1, the output end telecommunications of computer 1 is connected with driving control system 2 and acquisition control circuit 3, driving control system 2 and acquisition control
Telecommunications is connected with detection system 4, warning system 5 and camera system 6, the output end of detection system 4 to the output end of circuit 3 processed respectively
It is connect with 5 input terminal telecommunications of warning system, the output end of detection system 4 is connect with the input terminal telecommunications of camera system 6, camera shooting system
System 6 includes camera data memory card 61, and the input outlet of camera data memory card 61 and the output end telecommunications of detection system 4 connect
It connects, the output end telecommunications of camera data memory card 61 is connected with camera 62, and the input terminal telecommunications of camera 62 is connected with adaptive
Answer lighting system 7, the input terminal of adaptive lighting system 7 output end with driving control system 2 and acquisition control circuit 3 respectively
Telecommunications connects, and skill operation platform 8 is equipped at the camera lens of camera 62;
Wherein detection system 4 specific steps are as follows:
Step 1: acquiring general image to be detected from camera data memory card 61, set according to general image information to be detected
The pattern detected needed for fixed sets the ROI of image, intercepts the subgraph of institute's detection zone, and by subgraph gray processing, as to
Detection image;Corresponding template image is read from camera data memory card 61;
Step 2: image to be detected and template image are filled into square image by detection system 4, and it will test image and mould
The barycenter displacement of plate image carries out translation normalization generation translation image to be detected peace and moves Prototype drawing to the center of square image
Picture;
Step 3: computer 1 calculates the Zernike square for translating image peace to be checked and moving template image using fast algorithm;
Step 4: 1 pair of computer calculates the Zernike square that resulting translation image peace to be checked moves template image and carries out ruler
Degree normalization generates dimension normalization square Znm;
Step 5: according to dimension normalization square Znm construct square vector Z src and Ztem, wherein Zsrc be image to be detected to
Amount, Ztem are template gray image vector;
Step 6: calculating the opposite of square vector Z src and Ztem for each of square vector Z src and Ztem element
Match-percentage, and the opposite match-percentage of square vector Z src and Ztem are stored in and determined in feature vector J, construction determines
Feature vector J;
Step 7: the Gray-scale Matching degree of image and template image to be checked is calculated using normalizated correlation coefficient matching method, and
It is converted to percentage and obtains Gray-scale Matching degree;
Feature vector J is determined Step 8: Gray-scale Matching degree match is assigned to as new element, obtains updated sentencing
Determine feature vector J ';
Step 9: calculating the weighted arithmetic average for determining each element in feature vector J', the percentage of similarity is obtained
Match_result;
Step 10: comparing Match_result and given threshold Threshold, testing result is obtained;If Match_
The value of result is greater than given threshold Threshold and thinks that detection is qualified;Complete it is a kind of based on normalizing Zernike square and
Detection of the Gray-scale Matching to being operated on skill operation platform 8.
Wherein, detection system 4 includes Image Acquisition display end 41, the input terminal and camera shooting number of Image Acquisition display end 41
It is connected according to the output end telecommunications of memory card 61, the output end telecommunications of Image Acquisition display end 41 is connected with database 42, database
42 output end telecommunications is connected with data difference signal output end 43, and the output end of data difference signal output end 43 and warning are
The input terminal telecommunications connection of system 5.
Wherein, warning system 5 includes warning lamp 51 and loudspeaker 52, the input terminal and data of warning lamp 51 and loudspeaker 52
The input terminal telecommunications of difference signal output end 43 connects.
Wherein, adaptive lighting system 7 includes photosensitive sensors 71, and the input terminal telecommunications of photosensitive sensors 71 is connected with number
According to processing end 72, the input terminal telecommunications at data processing end 72 is connected with light compensating lamp 73, and light compensating lamp 73 is mounted at 74 camera lens.
Wherein, adaptive lighting system 7 is according to workpiece surface reflectivity, workpiece surface and imaging system optical axis angle, work
Make range measurement condition, the light intensity of adjust automatically lighting source.
Wherein, 74 image information is acquired using CMOS or CCD camera.
Wherein, step acquisition control circuit 3 calculates the Zernike square tool of image and template image to be checked using fast algorithm
Body process are as follows:
Square-shaped image g (x, y) is transformed under polar coordinates f (γ, ξ) using square-circle transform, γ, ξ is obtained by following formula:
γ=max | x |, | y |, if | x |=γ, if | y |=γ, the corresponding normalization polar coordinates of pixel (γ, ξ) are as follows: r=2
γ/N, θ=π γ of ξ/4, wherein N is the number of the side length pixel of square image, and Zernike square itself keeps muting sensitive to noise
Perception, and redundancy is few, iamge description ability is strong, the defects of shows to there is excellent inspection (such as display lacuna) for image
Survey recognition capability.Meanwhile present embodiment combines the invariant features information of image with Gray-scale Matching, ensure that in error map
As the accuracy detected in the case of (such as eight segment encodes cross and perpendicular) close with template image feature.
Working principle: first according to the brightness of environment, light filling is carried out by adaptive lighting system 7, then passes through camera shooting
The image data of first 62 record, 8 operator of skill operation platform record simultaneously imports in camera data memory card 61, then from camera shooting
Data storage card 61 acquires general image to be detected, according to the pattern of detection needed for general image information setting to be detected, setting
The ROI of image intercepts the subgraph of institute's detection zone, and by subgraph gray processing, as image to be detected;It is stored up from camera data
It deposits and reads corresponding template image in card 61;Image to be detected and template image are filled into square image by detection system 4, and will
The barycenter displacement of detection image and template image carries out translation normalization and generates translation image to be detected to the center of square image
Peace moves template image;Then computer 1 calculates the Zernike for translating image peace to be checked and moving template image using fast algorithm
Square;Then the Zernike square progress dimension normalization that resulting translation image peace to be checked moves template image is calculated for 1 pair of computer
Generate dimension normalization square Znm, then according to dimension normalization square Znm construct square vector Z src and Ztem, wherein Zsrc be to
Detection image vector, Ztem are template gray image vector, are then directed to each of square vector Z src and Ztem element,
The opposite match-percentage of square vector Z src and Ztem is calculated, and the opposite match-percentage of square vector Z src and Ztem are stored
In determining feature vector J, construction determines feature vector J, finally calculates image to be checked using normalizated correlation coefficient matching method
With the Gray-scale Matching degree of template image, and it is converted to percentage and obtains Gray-scale Matching degree;Using Gray-scale Matching degree match as new
Element, which is assigned to, determines feature vector J, obtains updated judgement feature vector J ', calculates and determine each element in feature vector J'
Weighted arithmetic average, obtain the percentage Match_result of similarity, compare Match_result and given threshold
Threshold obtains testing result;If the value of Match_result, which is greater than given threshold Threshold, thinks that detection is qualified;
Complete a kind of detection based on normalizing Zernike square and Gray-scale Matching to operating on skill operation platform 8.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (7)
1. a kind of system of skill operation supplemental training and detection based on machine vision, including computer (1), the computer
(1) output end telecommunications is connected with driving control system (2) and acquisition control circuit (3), the driving control system (2) and adopts
Telecommunications is connected with detection system (4), warning system (5) and camera system (6) to the output end of collection control circuit (3) respectively, special
Sign is: the output end of the detection system (4) is connect with warning system (5) input terminal telecommunications, the detection system (4) it is defeated
Outlet is connect with the input terminal telecommunications of camera system (6), and the camera system (6) includes camera data memory card (61), described
The input outlet of camera data memory card (61) is connect with the output end telecommunications of detection system (4), the camera data memory card
(61) output end telecommunications is connected with camera (62), and the input terminal telecommunications of the camera (62) is connected with adaptive illumination system
It unites (7), the input terminal of the adaptive lighting system (7) is defeated with driving control system (2) and acquisition control circuit (3) respectively
Outlet telecommunications connects, and is equipped with skill operation platform (8) at the camera lens of the camera (62);
Wherein detection system (4) specific steps are as follows:
Step 1: general image to be detected is acquired from camera data memory card (61), according to general image information setting to be detected
The pattern of required detection sets the ROI of image, the subgraph of institute's detection zone is intercepted, and by subgraph gray processing, as to be checked
Altimetric image;From the corresponding template image of reading in camera data memory card (61);
Step 2: image to be detected and template image are filled into square image by detection system (4), and it will test image and template
The barycenter displacement of image carries out translation normalization generation translation image to be detected peace and moves Prototype drawing to the center of square image
Picture;
Step 3: computer (1) calculates the Zernike square for translating image peace to be checked and moving template image using fast algorithm;
Step 4: computer (1) carries out scale to the Zernike square that resulting translation image peace to be checked moves template image is calculated
Normalization generates dimension normalization square Znm;
Step 5: constructing square vector Z src and Ztem according to dimension normalization square Znm, wherein Zsrc is image to be detected vector,
Ztem is template gray image vector;
Step 6: calculating the opposite matching of square vector Z src and Ztem for each of square vector Z src and Ztem element
Percentage, and the opposite match-percentage of square vector Z src and Ztem are stored in and determined in feature vector J, construction determines feature
Vector J;
Step 7: calculating the Gray-scale Matching degree of image and template image to be checked using normalizated correlation coefficient matching method, and convert
Gray-scale Matching degree is obtained at percentage;
Feature vector J is determined Step 8: Gray-scale Matching degree match is assigned to as new element, and it is special to obtain updated judgement
Levy vector J ';
Step 9: calculating the weighted arithmetic average for determining each element in feature vector J', the percentage of similarity is obtained
Match_result;
Step 10: comparing Match_result and given threshold Threshold, testing result is obtained;If Match_result's
Value is greater than given threshold Threshold and thinks that detection is qualified;It completes a kind of based on normalizing Zernike square and Gray-scale Matching
Detection to being operated on skill operation platform (8).
2. a kind of system of skill operation supplemental training and detection based on machine vision according to claim 1, special
Sign is: the detection system (4) includes Image Acquisition display end (41), and described image acquires the input terminal of display end (41)
It is connect with the output end telecommunications of camera data memory card (61), the output end telecommunications of described image acquisition display end (41) is connected with
The output end telecommunications of database (42), the database (42) is connected with data difference signal output end (43), the data difference
The output end of xor signal output end (43) is connect with the input terminal telecommunications of warning system (5).
3. a kind of system of skill operation supplemental training and detection based on machine vision according to claim 1, special
Sign is: the warning system (5) includes warning lamp (51) and loudspeaker (52), the warning lamp (51) and loudspeaker (52)
Input terminal is connect with the input terminal telecommunications of data difference signal output end (43).
4. a kind of system of skill operation supplemental training and detection based on machine vision according to claim 1, special
Sign is: the adaptive lighting system (7) includes photosensitive sensors (71), the input terminal telecommunications of the photosensitive sensors (71)
It is connected with data processing end (72), the input terminal telecommunications of the data processing end (72) is connected with light compensating lamp (73), the light filling
Lamp (73) is mounted at the camera lens of (74).
5. a kind of system of skill operation supplemental training and detection based on machine vision according to claim 1, special
Sign is: the adaptive lighting system (7) is according to workpiece surface reflectivity, workpiece surface and imaging system optical axis angle, work
Make range measurement condition, the light intensity of adjust automatically lighting source.
6. a kind of system of skill operation supplemental training and detection based on machine vision according to claim 1, special
Sign is: described (74) acquire image information using CMOS or CCD camera.
7. a kind of system of skill operation supplemental training and detection based on machine vision according to claim 1, special
Sign is: the step acquisition control circuit (3) calculates the Zernike square tool of image and template image to be checked using fast algorithm
Body process are as follows:
Square-shaped image g (x, y) is transformed under polar coordinates f (γ, ξ) using square-circle transform, γ, ξ is obtained by following formula: γ=
Max | x |, | y |, if | x |=γ, if | y |=γ, the corresponding normalization polar coordinates of pixel (γ, ξ) are as follows: r=2 γ/N,
The γ of θ=π ξ/4, wherein N is the number of the side length pixel of square image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910387052.1A CN110288865A (en) | 2019-05-10 | 2019-05-10 | A kind of system of skill operation supplemental training and detection based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910387052.1A CN110288865A (en) | 2019-05-10 | 2019-05-10 | A kind of system of skill operation supplemental training and detection based on machine vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110288865A true CN110288865A (en) | 2019-09-27 |
Family
ID=68001731
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910387052.1A Pending CN110288865A (en) | 2019-05-10 | 2019-05-10 | A kind of system of skill operation supplemental training and detection based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110288865A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112183475A (en) * | 2020-10-28 | 2021-01-05 | 镇江启创信息技术有限公司 | Electrical potential safety hazard identification system based on machine vision |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102073877A (en) * | 2011-02-25 | 2011-05-25 | 王晓年 | Method and system for detecting boxing by machine vision |
CN103729631A (en) * | 2014-01-15 | 2014-04-16 | 中国人民解放军国防科学技术大学 | Vision-based connector surface feature automatically-identifying method |
CN104021558A (en) * | 2014-06-16 | 2014-09-03 | 哈尔滨工业大学 | Liquid crystal meter pattern visual detection method based on normalization Zernike moment and gray matching |
CN108286938A (en) * | 2018-02-06 | 2018-07-17 | 陕西理工大学 | A kind of Machine Vision Inspecting System |
-
2019
- 2019-05-10 CN CN201910387052.1A patent/CN110288865A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102073877A (en) * | 2011-02-25 | 2011-05-25 | 王晓年 | Method and system for detecting boxing by machine vision |
CN103729631A (en) * | 2014-01-15 | 2014-04-16 | 中国人民解放军国防科学技术大学 | Vision-based connector surface feature automatically-identifying method |
CN104021558A (en) * | 2014-06-16 | 2014-09-03 | 哈尔滨工业大学 | Liquid crystal meter pattern visual detection method based on normalization Zernike moment and gray matching |
CN108286938A (en) * | 2018-02-06 | 2018-07-17 | 陕西理工大学 | A kind of Machine Vision Inspecting System |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112183475A (en) * | 2020-10-28 | 2021-01-05 | 镇江启创信息技术有限公司 | Electrical potential safety hazard identification system based on machine vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109883533B (en) | Low-frequency vibration measurement method based on machine vision | |
CN107229930B (en) | Intelligent identification method for numerical value of pointer instrument | |
CN112818988B (en) | Automatic identification reading method and system for pointer instrument | |
CN102135236B (en) | Automatic non-destructive testing method for internal wall of binocular vision pipeline | |
US10931924B2 (en) | Method for the generation of a correction model of a camera for the correction of an aberration | |
CN109544628B (en) | Accurate reading identification system and method for pointer instrument | |
US20080049185A1 (en) | Eye location and gaze detection system and method | |
CN104899609B (en) | A kind of mechanical meter recognition methods based on image registration | |
CN111210468A (en) | Image depth information acquisition method and device | |
CN105354825B (en) | The intelligent apparatus of reading matter position and its application in automatic identification read-write scene | |
CN106203370B (en) | A kind of test near and distance system based on computer vision technique | |
CN110966956A (en) | Binocular vision-based three-dimensional detection device and method | |
CN105354822B (en) | The intelligent apparatus of read-write element position and application in automatic identification read-write scene | |
CN110261069B (en) | Detection method for optical lens | |
CN110533686A (en) | Line-scan digital camera line frequency and the whether matched judgment method of speed of moving body and system | |
CN110487214A (en) | A kind of detection system and its detection method of the product qualification rate combined based on photometric stereo and structured light technique | |
CN113375584A (en) | Monocular three-dimensional acquisition structure, monocular three-dimensional multi-gauge visual system and extensometer | |
CN106991378A (en) | Facial orientation detection method, detection means and electronic installation based on depth | |
CN114360043B (en) | Model parameter calibration method, sight tracking method, device, medium and equipment | |
CN109186347A (en) | A kind of detection device and method of riflescope zero position walking momentum | |
CN111738971B (en) | Circuit board stereoscopic scanning detection method based on line laser binocular stereoscopic vision | |
CN110288865A (en) | A kind of system of skill operation supplemental training and detection based on machine vision | |
Yamauchi et al. | Calibration of a structured light system by observing planar object from unknown viewpoints | |
US20200292307A1 (en) | Method and apparatus for determining 3d coordinates of at least one predetermined point of an object | |
CN109212546A (en) | The calculation method and device of binocular camera depth direction measurement error |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190927 |