CN107274454A - A kind of circular array scaling board Feature Points Extraction - Google Patents
A kind of circular array scaling board Feature Points Extraction Download PDFInfo
- Publication number
- CN107274454A CN107274454A CN201710445416.8A CN201710445416A CN107274454A CN 107274454 A CN107274454 A CN 107274454A CN 201710445416 A CN201710445416 A CN 201710445416A CN 107274454 A CN107274454 A CN 107274454A
- Authority
- CN
- China
- Prior art keywords
- circle
- point
- image
- oval
- scaling board
- 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.)
- Granted
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 18
- 230000004323 axial length Effects 0.000 claims description 18
- 230000003993 interaction Effects 0.000 claims description 3
- 239000007787 solid Substances 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of circular array scaling board Feature Points Extraction, belong to camera calibration technical field.The present invention is according to camera model first against the approach of camera calibration, by this relation of the model parameter of image coordinate and world coordinates solution video camera of known features point, the precision for analyzing feature point extraction directly determines calibration result, propose a kind of new oval center of circle feature extraction algorithm, this method has of a relatively high precision, the image coordinate for the characteristic point that existing feature extraction algorithm is obtained and the matching problem of space point coordinates are solved well simultaneously, and realize that the oval center of circle is automatically extracted.
Description
Technical field
The present invention relates to a kind of circular array scaling board Feature Points Extraction, belong to camera calibration technical field.
Background technology
The approach of camera calibration is, according to camera model, to be solved by the image coordinate and world coordinates of known features point
The model parameter of video camera, the precision of feature point extraction directly determines calibration result, the essence that existing many algorithm characteristics points are extracted
Degree is very high, and the image coordinate of characteristic point and the matching degree of space point coordinates be not high, situation about mutually obscuring is there is also sometimes, directly
Tape splicing goes to calculate strong influence calibration result.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of circular array scaling board Feature Points Extraction, first against taking the photograph
The approach of camera calibration is, according to camera model, the mould of video camera to be solved by the image coordinate and world coordinates of known features point
This relation of shape parameter, the precision for analyzing feature point extraction directly determines calibration result, proposes that a kind of new oval center of circle is special
Extraction algorithm is levied, this method has of a relatively high precision, while solving the feature that existing feature extraction algorithm is obtained well
The image coordinate of point and the matching problem of space point coordinates.The precision that existing many algorithm characteristics points are extracted is very high, characteristic point
Image coordinate and the matching degree of space point coordinates be not high, and situation about mutually obscuring is there is also sometimes, and calculating of directly taking is very big
Have impact on calibration result.Characteristic point center of circle precision and match of a relatively high, favorable repeatability that this algorithm is extracted, make follow-up
The effect of camera calibration is more preferable.
The technical solution adopted by the present invention is：A kind of circular array scaling board Feature Points Extraction, comprises the following steps：
Step1, design and produce circular array (6 × 8）Scaling board；
Step2, scaling board is placed in needs the CCD camera demarcated to gather the image of circular array scaling board within sweep of the eye；
Step3, suitable position is adjusted to by adjusting threshold value sliding shoe binaryzation is carried out to the image that collects；
Step4, findContours functions in OpenCV are utilized to extract profiles all in image；
Step5, for each elliptic contour, directly ellipse is fitted using least square fitting algorithm, solves it
Centre coordinate, long axial length and short axle are long, and are stored in the variable set；
Step6, according to CCD camera distortion it is relatively small the characteristics of, oval major axis and short axle in the image collected it
Than being approximately equal to 1, the ratio between major axis and short axle are more than 4/3 oval rejecting；
Step7, the average value for calculating remaining oval long axial length and short axle length；
Step8, because the oval size of the scaling board that designs and produces is the same, all elliptical shaft length are more or less the same in image, root
Obtained axial length average value is calculated according to step Step7, long axial length or short axle length in remaining ellipse is less than 3/4 or more than 5/4
The oval rejecting of axial length average value；
Step9, setting judge scope；
Step10, the oval center of circle in the upper left corner pointed out manually using cursor of mouse in the form of man-machine interaction on image；
Step11, using cursor point as judge scope center, find and belong in the range of this in the variable for having oval central coordinate of circle
That central coordinate of circle；
Step12, the step Step11 central coordinate of circle found is stored in (point [0] [0] .x, point [0] [0] .y)；
Step13, the oval center of circle in the upper right corner pointed out manually using cursor of mouse on image；
Step14, execution step Step11 find the central coordinate of circle in the range of this and are stored in (point [0] [7] .x, point
[0][7].y)
Step15, the oval center of circle in the lower left corner pointed out manually using cursor of mouse on image；
Step16, execution step Step11 find the central coordinate of circle in the range of this and are stored in (point [5] [0] .x, point
[5][0].y)
Step17, the oval center of circle in the lower right corner pointed out manually using cursor of mouse on image；
Step18, execution step Step11 find the central coordinate of circle in the range of this and are stored in (point [5] [7] .x, point
[5][7].y)；
Step19, the central coordinate of circle according to four angles and scaling board circle position distribution (6 × 8）Calculate all characteristic point centers of circle
Relative coordinate, and judged according to the scope set in step Step9 using center of circle relative coordinate as the center of search judgement scope
The corresponding sequence number in all centers of circle, and be stored in (point [i] [j] .x, point [i] [j] .y)；Angle point grid is completed, and most
Obtain eventually with array sequence number i, j is the coordinate of label image characteristic point.
In the step Step1, the solid dark circle that designed scaling board is a diameter of 40mm carries out (6 × 8）Distribution,
Distance of center circle is 90mm.
In the step Step9, what is set judges scope as rectangular box of 1/4 axial length as the length of side.
The beneficial effects of the invention are as follows：The inventive method has of a relatively high precision, while solving existing spy well
Levy the image coordinate for the characteristic point that extraction algorithm is obtained and the matching problem of space point coordinates.Existing many algorithm characteristics points are extracted
Precision it is very high, the image coordinate of characteristic point and the matching degree of space point coordinates be not high, busy to there is also the feelings mutually obscured
Condition, calculating strong influence of directly taking calibration result.Characteristic point center of circle precision and match relatively that this algorithm is extracted
Height, favorable repeatability makes the effect of follow-up camera calibration more preferable.
Brief description of the drawings
The overall flow chart of steps of Fig. 1 this hair inventions；
Step2 camera acquisitions are to image in Fig. 2 the method for the invention；
Obtained after binary map, rejected after ellipse fitting after unrelated ellipse by adjusting threshold value in Fig. 3 the method for the invention
Obtained ellipse and center of circle figure.
Embodiment
The present invention is further elaborated with accompanying drawing with reference to embodiments, but the present invention protection content be not limited to it is described
Scope.
Embodiment 1：As Figure 1-3, a kind of circular array scaling board Feature Points Extraction, comprises the following steps：
Step1, design and produce circular array (6 × 8）Scaling board；
Step2, scaling board is placed in needs the CCD camera demarcated to gather the image of circular array scaling board within sweep of the eye；
Step3, suitable position is adjusted to by adjusting threshold value sliding shoe binaryzation is carried out to the image that collects；
Step4, findContours functions in OpenCV are utilized to extract profiles all in image；
Step5, for each elliptic contour, directly ellipse is fitted using least square fitting algorithm, solves it
Centre coordinate, long axial length and short axle are long, and are stored in the variable set；
Step6, according to CCD camera distortion it is relatively small the characteristics of, oval major axis and short axle in the image collected it
Than being approximately equal to 1, the ratio between major axis and short axle are more than 4/3 oval rejecting；
Step7, the average value for calculating remaining oval long axial length and short axle length；
Step8, because the oval size of the scaling board that designs and produces is the same, all elliptical shaft length are more or less the same in image, root
Obtained axial length average value is calculated according to step Step7, long axial length or short axle length in remaining ellipse is less than 3/4 or more than 5/4
The oval rejecting of axial length average value；
Step9, setting judge scope；
Step10, the oval center of circle in the upper left corner pointed out manually using cursor of mouse in the form of man-machine interaction on image；
Step11, using cursor point as judge scope center, find and belong in the range of this in the variable for having oval central coordinate of circle
That central coordinate of circle；
Step12, the step Step11 central coordinate of circle found is stored in (point [0] [0] .x, point [0] [0] .y)；
Step13, the oval center of circle in the upper right corner pointed out manually using cursor of mouse on image；
Step14, execution step Step11 find the central coordinate of circle in the range of this and are stored in (point [0] [7] .x, point
[0][7].y)
Step15, the oval center of circle in the lower left corner pointed out manually using cursor of mouse on image；
Step16, execution step Step11 find the central coordinate of circle in the range of this and are stored in (point [5] [0] .x, point
[5][0].y)
Step17, the oval center of circle in the lower right corner pointed out manually using cursor of mouse on image；
Step18, execution step Step11 find the central coordinate of circle in the range of this and are stored in (point [5] [7] .x, point
[5][7].y)；
Step19, the central coordinate of circle according to four angles and scaling board circle position distribution (6 × 8）Calculate all characteristic point centers of circle
Relative coordinate, and judged according to the scope set in step Step9 using center of circle relative coordinate as the center of search judgement scope
The corresponding sequence number in all centers of circle, and be stored in (point [i] [j] .x, point [i] [j] .y)；Angle point grid is completed, and most
Obtain eventually with array sequence number i, j is label image characteristic point（That is the center of circle）Coordinate.
Further, in the step Step1, the solid dark circle that designed scaling board is a diameter of 40mm carries out (6
×8）Distribution, distance of center circle is 90mm.
Further, in the step Step9, surely judge scope can suitably adjust, used in the present embodiment 1/4 axial length for
The rectangular box of the length of side.
Above in association with accompanying drawing to the present invention embodiment be explained in detail, but the present invention be not limited to it is above-mentioned
Embodiment, can also be before present inventive concept not be departed from the knowledge that those of ordinary skill in the art possess
Put that various changes can be made.
Claims (3)
1. a kind of circular array scaling board Feature Points Extraction, it is characterised in that：Comprise the following steps：
Step1, design and produce circular array (6 × 8）Scaling board；
Step2, scaling board is placed in needs the CCD camera demarcated to gather the image of circular array scaling board within sweep of the eye；
Step3, suitable position is adjusted to by adjusting threshold value sliding shoe binaryzation is carried out to the image that collects；
Step4, findContours functions in OpenCV are utilized to extract profiles all in image；
Step5, for each elliptic contour, directly ellipse is fitted using least square fitting algorithm, solves it
Centre coordinate, long axial length and short axle are long, and are stored in the variable set；
Step6, according to CCD camera distortion it is relatively small the characteristics of, oval major axis and short axle in the image collected it
Than being approximately equal to 1, the ratio between major axis and short axle are more than 4/3 oval rejecting；
Step7, the average value for calculating remaining oval long axial length and short axle length；
Step8, because the oval size of the scaling board that designs and produces is the same, all elliptical shaft length are more or less the same in image, root
Obtained axial length average value is calculated according to step Step7, long axial length or short axle length in remaining ellipse is less than 3/4 or more than 5/4
The oval rejecting of axial length average value；
Step9, setting judge scope；
Step10, the oval center of circle in the upper left corner pointed out manually using cursor of mouse in the form of man-machine interaction on image；
Step11, using cursor point as judge scope center, find and belong in the range of this in the variable for having oval central coordinate of circle
That central coordinate of circle；
Step12, the step Step11 central coordinate of circle found is stored in (point [0] [0] .x, point [0] [0] .y)；
Step13, the oval center of circle in the upper right corner pointed out manually using cursor of mouse on image；
Step14, execution step Step11 find the central coordinate of circle in the range of this and are stored in (point [0] [7] .x, point
[0][7].y)
Step15, the oval center of circle in the lower left corner pointed out manually using cursor of mouse on image；
Step16, execution step Step11 find the central coordinate of circle in the range of this and are stored in (point [5] [0] .x, point
[5][0].y)
Step17, the oval center of circle in the lower right corner pointed out manually using cursor of mouse on image；
Step18, execution step Step11 find the central coordinate of circle in the range of this and are stored in (point [5] [7] .x, point
[5][7].y)；
Step19, the central coordinate of circle according to four angles and scaling board circle position distribution (6 × 8）Calculate all characteristic point centers of circle
Relative coordinate, and judged according to the scope set in step Step9 using center of circle relative coordinate as the center of search judgement scope
The corresponding sequence number in all centers of circle, and be stored in (point [i] [j] .x, point [i] [j] .y)；Angle point grid is completed, and most
Obtain eventually with array sequence number i, j is the coordinate of label image characteristic point.
2. circular array scaling board Feature Points Extraction according to claim 1, it is characterised in that：The step Step1
In, the solid dark circle that designed scaling board is a diameter of 40mm carries out (6 × 8）Distribution, distance of center circle is 90mm.
3. circular array scaling board Feature Points Extraction according to claim 1, it is characterised in that：The step Step9
In, what is set judges scope as rectangular box of 1/4 axial length as the length of side.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710445416.8A CN107274454B (en) | 2017-06-14 | 2017-06-14 | Method for extracting characteristic points of circular array calibration plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710445416.8A CN107274454B (en) | 2017-06-14 | 2017-06-14 | Method for extracting characteristic points of circular array calibration plate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107274454A true CN107274454A (en) | 2017-10-20 |
| CN107274454B CN107274454B (en) | 2020-12-15 |
Family
ID=60067530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710445416.8A Active CN107274454B (en) | 2017-06-14 | 2017-06-14 | Method for extracting characteristic points of circular array calibration plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107274454B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108734745A (en) * | 2018-05-18 | 2018-11-02 | 湖南拓视觉信息技术有限公司 | Scaling method, device and projection device |
| CN114061480A (en) * | 2020-08-03 | 2022-02-18 | 上海飞机制造有限公司 | Method for detecting appearance of workpiece |
| CN114529613A (en) * | 2021-12-15 | 2022-05-24 | 深圳市华汉伟业科技有限公司 | Method for extracting characteristic point high-precision coordinates of circular array calibration plate |
| CN114972509A (en) * | 2022-05-26 | 2022-08-30 | 北京利君成数字科技有限公司 | Method for quickly identifying tableware position |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1801896A (en) * | 2006-01-17 | 2006-07-12 | 东南大学 | Video camera rating data collecting method and its rating plate |
| CN101334894A (en) * | 2008-07-31 | 2008-12-31 | 上海交通大学 | Video camera parameter calibration method by adopting single circle as marker |
| CN101650828A (en) * | 2009-09-07 | 2010-02-17 | 东南大学 | Method for reducing random error of round object location in camera calibration |
| ES2392799A1 (en) * | 2011-03-22 | 2012-12-13 | Universidad De Vigo | Pattern for the automatic geometric calibration of thermographic cameras (Machine-translation by Google Translate, not legally binding) |
-
2017
- 2017-06-14 CN CN201710445416.8A patent/CN107274454B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1801896A (en) * | 2006-01-17 | 2006-07-12 | 东南大学 | Video camera rating data collecting method and its rating plate |
| CN101334894A (en) * | 2008-07-31 | 2008-12-31 | 上海交通大学 | Video camera parameter calibration method by adopting single circle as marker |
| CN101650828A (en) * | 2009-09-07 | 2010-02-17 | 东南大学 | Method for reducing random error of round object location in camera calibration |
| ES2392799A1 (en) * | 2011-03-22 | 2012-12-13 | Universidad De Vigo | Pattern for the automatic geometric calibration of thermographic cameras (Machine-translation by Google Translate, not legally binding) |
Non-Patent Citations (2)
| Title |
|---|
| AHMED KHALLAAYOUN等: "A blind iterative calibration method for high resolution DOA estimation", 《IEEE》 * |
| 杨根齐等: "基于圆环点的亚像素摄像机自标定方法", 《中国测试》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108734745A (en) * | 2018-05-18 | 2018-11-02 | 湖南拓视觉信息技术有限公司 | Scaling method, device and projection device |
| CN108734745B (en) * | 2018-05-18 | 2021-02-09 | 湖南拓视觉信息技术有限公司 | Calibration method and device and projection equipment |
| CN114061480A (en) * | 2020-08-03 | 2022-02-18 | 上海飞机制造有限公司 | Method for detecting appearance of workpiece |
| CN114061480B (en) * | 2020-08-03 | 2024-04-05 | 上海飞机制造有限公司 | Method for detecting appearance of workpiece |
| CN114529613A (en) * | 2021-12-15 | 2022-05-24 | 深圳市华汉伟业科技有限公司 | Method for extracting characteristic point high-precision coordinates of circular array calibration plate |
| CN114972509A (en) * | 2022-05-26 | 2022-08-30 | 北京利君成数字科技有限公司 | Method for quickly identifying tableware position |
| CN114972509B (en) * | 2022-05-26 | 2023-09-29 | 北京利君成数字科技有限公司 | Method for quickly identifying tableware position |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107274454B (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107274454A (en) | A kind of circular array scaling board Feature Points Extraction | |
| CN109785379B (en) | Method and system for measuring size and weight of symmetrical object | |
| CN110426051B (en) | Lane line drawing method and device and storage medium | |
| CN101789126B (en) | Three-dimensional human body motion tracking method based on volume pixels | |
| CN109308718B (en) | Space personnel positioning device and method based on multiple depth cameras | |
| CN107238374B (en) | A kind of classification of concave plane part and recognition positioning method | |
| WO2021208442A1 (en) | Three-dimensional scene reconstruction system and method, device, and storage medium | |
| CN107886528A (en) | Distribution line working scene three-dimensional rebuilding method based on a cloud | |
| KR20180044279A (en) | System and method for depth map sampling | |
| CN113077476B (en) | Height measurement method, terminal device and computer storage medium | |
| CN104408445A (en) | Automatic real-time human body detecting method | |
| CN106600650A (en) | Binocular visual sense depth information obtaining method based on deep learning | |
| CN106969730A (en) | A kind of top fruit sprayer volume measuring method based on unmanned plane Detection Techniques | |
| CN104331924B (en) | Three-dimensional rebuilding method based on single camera SFS algorithms | |
| CN112070759A (en) | Forklift pallet detection and positioning method and system | |
| CN103198477A (en) | Apple fruitlet bagging robot visual positioning method | |
| CN105606123B (en) | A kind of method of the photogrammetric automatic correcting digital ground elevation model of low-altitude aerial | |
| CN113406975B (en) | Bionic intelligent multi-unmanned aerial vehicle cluster autonomous formation navigation control method and device | |
| CN102818544A (en) | On-line measurement method for pitch circle center of automobile hub bolt hole and central eccentric distance of central hole | |
| CN105551043B (en) | Unmanned plane image data real-time processing method | |
| US10614321B2 (en) | Travel lane detection method and travel lane detection device | |
| CN112509054A (en) | Dynamic calibration method for external parameters of camera | |
| CN114332689A (en) | Citrus identification and positioning method, device, equipment and storage medium | |
| CN113222838A (en) | Unmanned aerial vehicle autonomous line patrol method based on visual positioning | |
| CN105987670A (en) | Tire impression depth data processing method, system and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |