CN104699323A - Method for optically positioning touch point based on image processing - Google Patents
Method for optically positioning touch point based on image processing Download PDFInfo
- Publication number
- CN104699323A CN104699323A CN201310649886.8A CN201310649886A CN104699323A CN 104699323 A CN104699323 A CN 104699323A CN 201310649886 A CN201310649886 A CN 201310649886A CN 104699323 A CN104699323 A CN 104699323A
- Authority
- CN
- China
- Prior art keywords
- center
- image
- coordinate system
- camera
- mould plate
- 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
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a method for optically positioning a touch point based on image processing. The method comprises the following steps of camera calibration and camera measurement, wherein the external parameters of a camera are calculated during camera calibration, the external parameters are the proportional relationship between the relative physical position and the measurement scale of an image coordinate system and a world coordinate system, and the corrected real physical position of the actual touch point is calculated and output through utilizing the calibrated parameters. The method supports the rotating and the like of the camera, the algorithm is robust, and the touch position on a touch screen can be accurately and rapidly positioned.
Description
Technical field
The present invention, about a kind of optical positioning method, refers to that a kind of cost is low, the touch point optical positioning method based on image procossing of the accurate quick position touch location of energy especially.
Background technology
Measurement and positioning based on camera is used widely at present in industry-by-industry, by camera while guarantee precision, and can the position of the accurate touch of quick position touch-screen.
Current infrared collimation technique, mostly calibrated by the click of man-machine interaction, generally after entering calibration mode, touch-screen provides calibration target over the display, then calibration personnel is clicked by hand or other touching object, but adopt in this way, the calibration touch point precision comparison that touch-screen obtains is low; In order to improve this calibrating mode, have employed the large-scale correcting device that cost compare is high, as adopted engraving machine or other equipment, ensure to click precision, in order to target alignment point can be clicked more accurately, the recognition technologies such as image procossing are used, but further increase cost again simultaneously, and the correcting device of this similar engraving machine, too clumsy, calibration efficiency is low, can not meet the demand of high efficiency on production line.
Summary of the invention
In view of this, fundamental purpose of the present invention is to provide a kind of cost low and the touch point optical positioning method based on image procossing of the accurate quick position touch location of energy.
For achieving the above object, the invention provides the touch point optical positioning method based on image procossing, the method includes following steps:
Step one, carry out camera calibration, calculate camera external parameter, this external parameter is the relative physical location of image coordinate system and world coordinate system and the dimension scale relation of measurement, and this step one specifically comprises:
(1) Program Generating regulation mould plate is utilized;
(2) pre-service is carried out to the image of regulation mould plate, remove noise;
(3) analyze camera and world coordinate system relation, draw dimension scale Scale and the camera view center real offset of the measurement of image coordinate system and world coordinate system;
Step 2, carry out camera measurement, its concrete implementation step is:
(1) pair is generated containing another regulation mould plate image directive;
(2) carry out Image semantic classification, remove noise, get rid of the target jamming problem that tool structure light leak causes;
(3) Objective extraction, finds center Center(centerX, the centerY of this regulation mould plate);
(4) camera Attitude estimation, finds the reference positive dirction in calibration process;
(5) according to dimension scale Scale and the camera view center real offset of the measurement with reference to the image coordinate system drawn in positive dirction and camera calibration and world coordinate system, the true physical location of actual touch point is exported.
In (1) of described step one, this regulation mould plate is provided with equidistantly and the identical multiple marker dots of the size linearly arranged, and the distance DistReal on calculation template between actual two marker dots centers.
(3) of described step one specifically comprise:
I, judge the attitude of camera at frock timing, to obtain positional information ImgC(positonX, the positonY of frock), this ImgC is the center of image;
II, posture analysis: the center finding the marker dots of image alignment template, carry out fitting a straight line to multiple center, and judge corresponding matching straight line out and the angle of transverse axis;
III, template center extract: according to the center image coordinate of each marker dots calculated in above-mentioned steps II, averaged, draw the center C(screenCenterX of regulation mould plate, screenCenterY), simultaneously in computed image adjacent two marker dots center between distance, each distance average is as the distance DistImg between the marker dots center of two on final image;
The position relationship of the straight line of IV, the position judging the center C of picture centre ImgC and calibration template and institute's matching, the ImgC under computed image coordinate system is relative to the skew (deltaX ', deltaY ') of C;
V, using the dimension scale relation of the ratio Scale between DistReal and DistImg as image coordinate system and world coordinate system, according to ImgC relative to C skew (deltaX ', deltaY '), calculate camera view center real offset (deltaX, deltaY) of final world coordinate system.
In described Step II, the extraction at the center of marker dots in this regulation mould plate, being the profile by extracting each marker dots, carrying out ellipse fitting to profile, find the center of circle of each ellipse, and this oval center of circle is the center of marker dots.
In (3) of described step 2, edge filter is carried out to the calibration chart picture obtained, extract the profile information of image, then carry out hough conversion, find straight line; According to the straight line found, be divided into two groups according to slope difference, often group comprises two parallel straight lines, two groups of straight lines intersect between two, according to intersection point image coordinate averaged, obtain final regulation mould plate center Center(centerX, centerY) image coordinate.
(5) of described step 2 specifically comprise:
I, reference positive dirction according to the physical alignment image analyzed in correspondence image, calculate the anglec of rotation Beta with horizontal direction;
II, the regulation mould plate center Center(centerX extracted according to (3) in step 2, and picture centre ImgC(positonX centerY), positonY), regulation mould plate center Center to picture centre ImgC is defined as vector AB, calculates the Distance geometry direction vector of line segment between regulation mould plate center Center and picture centre ImgC;
III, according to anglec of rotation Beta in step I and calibrating parameters Scale, calculate corresponding vector AB physical deflection (deltaPhysicalX, deltaPhysicalY) relative under world coordinate system and direction;
IV, according to camera calibration parameter d eltaX, deltaY, after calculating corresponding rotation Beta angle, to should offset component (deltaRealX, deltaRealY) under angle, as the correction of final physical coordinate;
The V, (deltaPhysicalX obtained according to analytical calculation, deltaPhysicalY), (deltaRealX, deltaRealY), to given physical location (physicalX, physicalY) carry out add operation, obtain the true physical location (physicalX+ deltaPhysicalX+ deltaRealX, physicalY+ deltaPhysicalY+ deltaRealY) of touch point corresponding to calibrating installation center.
(1) alignment template image of described step 2 has inverted "L" shaped mark.
The optical positioning method based on image procossing that the present invention proposes is a kind of quick self-adapted localizing objects algorithm, and it supports the problems such as camera rotation, algorithm robust, can touch location accurately and on quick position touch-screen.
Accompanying drawing explanation
Fig. 1 is the image of the regulation mould plate that the present invention is read by camera in camera calibration;
Fig. 2 carries out fitting a straight line to the marker dots center in regulation mould plate;
Fig. 3 is the present invention in camera is measured by the image containing directive regulation mould plate that camera reads;
Fig. 4 is to inverted "L" shaped sign image process in Fig. 3 and finds template center;
Fig. 5 is the reference positive dirction figure mono-finding template;
Fig. 6 is the reference positive dirction figure bis-finding template;
Fig. 7 is the schematic diagram of regulation mould plate center and picture centre line;
Fig. 8 is the flow chart of steps of the touch point optical positioning method that the present invention is based on image procossing.
Embodiment
For ease of having further understanding to method of the present invention and the effect that reaches, the existing preferred embodiment that develops simultaneously by reference to the accompanying drawings is described in detail as follows.
Utilize the measurement of camera, accurately and determine the touch location of touch-screen fast, shown in figure 8, the optical positioning method based on image procossing of the present invention has following steps:
First will carry out camera calibration, calculate camera external parameter, this external parameter is dimension scale relation and the camera view center real offset of the measurement of image coordinate system and world coordinate system.Realize camera calibration and need following steps:
(1) camera calibration needs concrete target to realize, the present invention utilizes Program Generating regulation mould plate as target, this regulation mould plate is provided with equidistantly and the identical multiple marker dots (as shown in Figure 1) of the size linearly arranged, according to given template, calculate the distance DistReal between actual two marker dots centers in template.
(2) pre-service is carried out to the image of the regulation mould plate photographed, comprise removal noise, or the relations such as marker dots profile number are judged, ensure that the view data obtained is effective.
(3) analyze camera and world coordinate system relation, draw the relative physical location of image coordinate system and world coordinate system and the dimension scale of measurement, it specifically comprises the steps:
I, judge the attitude of camera, at frock timing, camera must be ajusted as far as possible, obtain the positional information ImgC(positonX of frock, positonY), this ImgC is the center of image, and wherein positonX is the horizontal ordinate of picture centre ImgC, and positonY is the ordinate of picture centre ImgC;
II, posture analysis: the center finding the marker dots of image alignment template, carry out fitting a straight line to multiple center, as shown in Figure 2, judge corresponding matching straight line the l out and angle Theta of transverse axis; The extraction at the center of this marker dots, by extracting the profile of each marker dots, can carry out ellipse fitting to profile, finding the center of circle of each ellipse, be i.e. the center of marker dots;
III, template center extract: according to the center image coordinate of each marker dots calculated in above-mentioned steps II, averaged, draw the center C(screenCenterX of regulation mould plate, screenCenterY), the i.e. upper physical location information of screen, wherein screenCenterX is the horizontal ordinate of regulation mould plate center C, and screenCenterY is the ordinate of regulation mould plate center C; Simultaneously in computed image adjacent two marker dots center between distance, each distance average is as the distance DistImg between the marker dots center of two on final image;
IV, judge picture centre ImgC and calibration template center C position with fall the position relationship of " L ", the ImgC under computed image coordinate system is relative to the skew (deltaX ', deltaY ') of C;
V, using the dimension scale relation of the ratio Scale between DistReal and DistImg as image coordinate system and world coordinate system, according to ImgC relative to C skew (deltaX ', deltaY '), calculate (the deltaX of final world coordinate system, deltaY), i.e. camera view center real offset.
Again carry out camera measurement, its concrete implementation step is:
(1) generate another secondary regulation mould plate, and take with video camera, obtain image (as shown in Figure 3), this calibration chart picture has inverted "L" shaped mark, this more accurate image has directivity.
(2) carry out Image semantic classification, remove noise, get rid of the target jamming problem that tool structure light leak causes.
(3) Objective extraction: carry out edge filter to the calibration chart picture obtained, extracts the profile information of inverted "L" shaped mark, then carries out hough conversion, finds straight line; According to the straight line found, two groups are divided into according to slope difference, often group comprises two parallel straight lines, these two groups of straight lines are vertical in theory, and then two groups of straight lines intersect between two, according to intersection point image coordinate averaged, obtain final regulation mould plate center Center(centerX, centerY) image coordinate (as shown in Figure 4), wherein centerX is the horizontal ordinate of regulation mould plate center Center, and centerY is the ordinate of regulation mould plate center Center.
(4) camera Attitude estimation: by two kinds of slopes in regulation mould plate center Center and above-mentioned steps (3), draw two straight lines, find these two straight lines respectively with the intersection point of inverted "L" shaped mark profile end, namely two end points end1(end1X are found, end1Y) and end2(end2X, end2Y); According to the shape of giving solid plate, calculate the vector vec1(end1X-centerX of Center to end1, end1Y-centerY), the vector vec2(end2X-centerX of Center to end2, end2Y-centerY), adopt sine, calculate the mutual alignment relation direct of two vector vec1, vec2.
Order, vec1.x=end1X-centerX, vec1.y=end1Y-centerY; Vec2.x=end2X-centerX, vec2.y=end2Y-centerY;
direct = (vec1.x*vec2.y-vec1.y*vec2.x) / sqrt((vec1.x*vec1.x+vec1.y*vec1.y) *(vec2.x*vec2.x+vec2.y*vec2.y) );
If direct is >=0, the direction that so vec1 is corresponding is positive dirction; Otherwise the direction that vec2 is corresponding is positive dirction; Finding center Center with the line direction of the end points of left side right-angle line is in the counterclockwise direction positive dirction, the reference diagram target reference direction namely provided in true calibration process;
Straight line as Fig. 5 and Fig. 6 alignment template center Center to end points end1 is reference line corresponding to positive dirction.
(5) carry out coordinate output according to reference direction and camera correction parameter, specifically comprise the following steps:
I, reference positive dirction according to the physical alignment image analyzed in correspondence image, calculate the anglec of rotation Beta with true horizon direction;
II, the regulation mould plate center Center(centerX extracted according to step (3), and picture centre ImgC(positonX centerY), positonY), AB is stored according to vector, calculate the Distance geometry direction of 2 line line segments, the i.e. Distance geometry direction of line segment between regulation mould plate center Center and picture centre ImgC, as shown in Figure 7;
III, according to anglec of rotation Beta in step I, calculate corresponding vector AB physical deflection (deltaPhysicalX, deltaPhysicalY) relative under world coordinate system and direction with calibrating parameters Scale; Corresponding computing formula:
deltaPhysicalX=|AB|*cos(Beta)；
deltaPhysicalY=|AB|*sin(Beta)；
IV, according to camera calibration parameter d eltaX, deltaY, after calculating corresponding rotation Beta angle, to should offset component (deltaRealX, deltaRealY) under angle, as the correction of final physical coordinate, corresponding computing formula:
deltaRealX= deltaX*cos(Beta)+deltaY*sin(Beta);
deltaRealY= deltaY*cos(Beta)-deltaX*sin(Beta);；
The V, (deltaPhysicalX obtained according to analytical calculation, deltaPhysicalY), (deltaRealX, deltaRealY), to given physical location (physicalX, physicalY) carry out add operation, obtain the true physical location (physicalX+ deltaPhysicalX+ deltaRealX, physicalY+ deltaPhysicalY+ deltaRealY) of touch point corresponding to calibrating installation center.
The optical positioning method based on image procossing that the present invention proposes is a kind of quick self-adapted localizing objects algorithm, and it supports the problems such as camera rotation, algorithm robust, can touch location accurately and on quick position touch-screen.
The above, be only preferred embodiment of the present invention, be not intended to limit protection scope of the present invention.
Claims (7)
1., based on a touch point optical positioning method for image procossing, it is characterized in that, the method includes following steps:
Step one, carry out camera calibration, calculate camera external parameter, this external parameter is the relative physical location of image coordinate system and world coordinate system and the dimension scale relation of measurement, and this step one specifically comprises:
(1) Program Generating regulation mould plate is utilized;
(2) pre-service is carried out to the image of regulation mould plate, remove noise;
(3) analyze camera and world coordinate system relation, draw dimension scale Scale and the camera view center real offset of the measurement of image coordinate system and world coordinate system;
Step 2, carry out camera measurement, its concrete implementation step is:
(1) pair is generated containing another regulation mould plate image directive;
(2) carry out Image semantic classification, remove noise, get rid of the target jamming problem that tool structure light leak causes;
(3) Objective extraction, finds center Center(centerX, the centerY of this regulation mould plate);
(4) camera Attitude estimation, finds the reference positive dirction in calibration process;
(5) according to dimension scale Scale and the camera view center real offset of the measurement with reference to the image coordinate system drawn in positive dirction and camera calibration and world coordinate system, the true physical location of actual touch point is exported.
2. as claimed in claim 1 based on the touch point optical positioning method of image procossing, it is characterized in that, in (1) of described step one, this regulation mould plate is provided with equidistantly and the identical multiple marker dots of the size linearly arranged, and the distance DistReal on calculation template between actual two marker dots centers.
3., as claimed in claim 2 based on the touch point optical positioning method of image procossing, it is characterized in that, (3) of described step one specifically comprise:
I, judge the attitude of camera at frock timing, to obtain positional information ImgC(positonX, the positonY of frock), this ImgC is the center of image;
II, posture analysis: the center finding the marker dots of image alignment template, carry out fitting a straight line to multiple center, and judge corresponding matching straight line out and the angle of transverse axis;
III, template center extract: according to the center image coordinate of each marker dots calculated in above-mentioned steps II, averaged, draw the center C(screenCenterX of regulation mould plate, screenCenterY), simultaneously in computed image adjacent two marker dots center between distance, each distance average is as the distance DistImg between the marker dots center of two on final image;
The position relationship of the straight line of IV, the position judging the center C of picture centre ImgC and calibration template and institute's matching, the ImgC under computed image coordinate system is relative to the skew (deltaX ', deltaY ') of C;
V, using the dimension scale relation of the ratio Scale between DistReal and DistImg as image coordinate system and world coordinate system, according to ImgC relative to C skew (deltaX ', deltaY '), calculate camera view center real offset (deltaX, deltaY) of final world coordinate system.
4. as claimed in claim 3 based on the touch point optical positioning method of image procossing, it is characterized in that, in described Step II, the extraction at the center of marker dots in this regulation mould plate, it is the profile by extracting each marker dots, carry out ellipse fitting to profile, find the center of circle of each ellipse, this oval center of circle is the center of marker dots.
5. as claimed in claim 1 based on the touch point optical positioning method of image procossing, it is characterized in that, in (3) of described step 2, edge filter is carried out to the calibration chart picture obtained, extract the profile information of image, then carry out hough conversion, find straight line; According to the straight line found, be divided into two groups according to slope difference, often group comprises two parallel straight lines, two groups of straight lines intersect between two, according to intersection point image coordinate averaged, obtain final regulation mould plate center Center(centerX, centerY) image coordinate.
6., as claimed in claim 3 based on the touch point optical positioning method of image procossing, it is characterized in that, (5) of described step 2 specifically comprise:
I, reference positive dirction according to the physical alignment image analyzed in correspondence image, calculate the anglec of rotation Beta with horizontal direction;
II, the regulation mould plate center Center(centerX extracted according to (3) in step 2, and picture centre ImgC(positonX centerY), positonY), regulation mould plate center Center to picture centre ImgC is defined as vector AB, calculates the Distance geometry direction vector of line segment between regulation mould plate center Center and picture centre ImgC;
III, according to anglec of rotation Beta in step I and calibrating parameters Scale, calculate corresponding vector AB physical deflection (deltaPhysicalX, deltaPhysicalY) relative under world coordinate system and direction;
IV, according to camera calibration parameter d eltaX, deltaY, after calculating corresponding rotation Beta angle, to should offset component (deltaRealX, deltaRealY) under angle, as the correction of final physical coordinate;
The V, (deltaPhysicalX obtained according to analytical calculation, deltaPhysicalY), (deltaRealX, deltaRealY), to given physical location (physicalX, physicalY) carry out add operation, obtain the true physical location (physicalX+ deltaPhysicalX+ deltaRealX, physicalY+ deltaPhysicalY+ deltaRealY) of touch point corresponding to calibrating installation center.
7. as claimed in claim 1 based on the touch point optical positioning method of image procossing, it is characterized in that (1) alignment template image of described step 2 having inverted "L" shaped mark.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310649886.8A CN104699323B (en) | 2013-12-06 | 2013-12-06 | A kind of touch point optical positioning method based on image procossing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310649886.8A CN104699323B (en) | 2013-12-06 | 2013-12-06 | A kind of touch point optical positioning method based on image procossing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104699323A true CN104699323A (en) | 2015-06-10 |
| CN104699323B CN104699323B (en) | 2017-11-14 |
Family
ID=53346525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310649886.8A Expired - Fee Related CN104699323B (en) | 2013-12-06 | 2013-12-06 | A kind of touch point optical positioning method based on image procossing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104699323B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105021127A (en) * | 2015-06-25 | 2015-11-04 | 哈尔滨工业大学 | Surface mounting machine reference camera calibration method |
| CN107146205A (en) * | 2017-03-21 | 2017-09-08 | 北京建筑大学 | A kind of distorted image correction method, position of touch recognition methods and device |
| CN108510463A (en) * | 2018-05-07 | 2018-09-07 | 凌云光技术集团有限责任公司 | A kind of antidote and device of fault image |
| CN109164932A (en) * | 2018-08-02 | 2019-01-08 | 深圳市德名利电子有限公司 | A kind of touch control identification method and touch device |
Citations (6)
| 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 |
| CN102063721A (en) * | 2011-01-06 | 2011-05-18 | 大连理工大学 | Method for compensating inclination of straight calibration object in calibration process of external parameter of vision system |
| CN102508565A (en) * | 2011-11-17 | 2012-06-20 | Tcl集团股份有限公司 | Remote control cursor positioning method and device, remote control and cursor positioning system |
| CN102523395A (en) * | 2011-11-15 | 2012-06-27 | 中国科学院深圳先进技术研究院 | Television system having multi-point touch function, touch positioning identification method and system thereof |
| CN102663731A (en) * | 2012-03-13 | 2012-09-12 | 广东威创视讯科技股份有限公司 | Fast calibration method and system of optical axis of camera lens in optical touch system |
| US20120287240A1 (en) * | 2011-05-11 | 2012-11-15 | Tyzx, Inc. | Camera calibration using an easily produced 3d calibration pattern |
-
2013
- 2013-12-06 CN CN201310649886.8A patent/CN104699323B/en not_active Expired - Fee Related
Patent Citations (6)
| 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 |
| CN102063721A (en) * | 2011-01-06 | 2011-05-18 | 大连理工大学 | Method for compensating inclination of straight calibration object in calibration process of external parameter of vision system |
| US20120287240A1 (en) * | 2011-05-11 | 2012-11-15 | Tyzx, Inc. | Camera calibration using an easily produced 3d calibration pattern |
| CN102523395A (en) * | 2011-11-15 | 2012-06-27 | 中国科学院深圳先进技术研究院 | Television system having multi-point touch function, touch positioning identification method and system thereof |
| CN102508565A (en) * | 2011-11-17 | 2012-06-20 | Tcl集团股份有限公司 | Remote control cursor positioning method and device, remote control and cursor positioning system |
| CN102663731A (en) * | 2012-03-13 | 2012-09-12 | 广东威创视讯科技股份有限公司 | Fast calibration method and system of optical axis of camera lens in optical touch system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105021127A (en) * | 2015-06-25 | 2015-11-04 | 哈尔滨工业大学 | Surface mounting machine reference camera calibration method |
| CN105021127B (en) * | 2015-06-25 | 2017-07-28 | 哈尔滨工业大学 | A kind of benchmark camera calibration method of chip mounter |
| CN107146205A (en) * | 2017-03-21 | 2017-09-08 | 北京建筑大学 | A kind of distorted image correction method, position of touch recognition methods and device |
| CN107146205B (en) * | 2017-03-21 | 2019-12-13 | 北京建筑大学 | Distorted image correction method, touch position identification method and device |
| CN108510463A (en) * | 2018-05-07 | 2018-09-07 | 凌云光技术集团有限责任公司 | A kind of antidote and device of fault image |
| CN108510463B (en) * | 2018-05-07 | 2020-12-25 | 凌云光技术股份有限公司 | Method and device for correcting distorted image |
| CN109164932A (en) * | 2018-08-02 | 2019-01-08 | 深圳市德名利电子有限公司 | A kind of touch control identification method and touch device |
| CN109164932B (en) * | 2018-08-02 | 2021-07-23 | 深圳市德明利技术股份有限公司 | Touch identification method and touch device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104699323B (en) | 2017-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ye et al. | A new method based on hough transform for quick line and circle detection | |
| CN103499297B (en) | A kind of high-precision measuring method based on CCD | |
| CN104729406B (en) | A kind of machine vision localization method of element pasted on surface | |
| CN105261022B (en) | PCB board matching method and device based on outer contour | |
| CN104217441A (en) | Mechanical arm positioning fetching method based on machine vision | |
| CN106441163B (en) | A kind of contactless column measuring for verticality method and device | |
| CN104036513A (en) | Three-dimensional bent-pipe multi-camera visual inspection method and system thereof | |
| CN104699323A (en) | Method for optically positioning touch point based on image processing | |
| CN103593838B (en) | A kind of cross-correlation gray level image matching method and device fast | |
| CN106504287B (en) | Monocular vision object space positioning system based on template | |
| CN107421473A (en) | The two beam laser coaxial degree detection methods based on image procossing | |
| CN102589530A (en) | Method for measuring position and gesture of non-cooperative target based on fusion of two dimension camera and three dimension camera | |
| CN107145890A (en) | A kind of pointer dashboard automatic reading method under remote various visual angles environment | |
| Wei et al. | Calibration method for line structured light vision sensor based on vanish points and lines | |
| CN104123725B (en) | A kind of computational methods of single line array camera homography matrix H | |
| Wang et al. | Error analysis and improved calibration algorithm for LED chip localization system based on visual feedback | |
| CN106097316A (en) | The substrate position identifying processing method of laser scribing means image identification system | |
| Takai et al. | Accurate registration of MMS point clouds of urban areas using trajectory | |
| CN102841679A (en) | Non-contact man-machine interaction method and device | |
| Yang et al. | Auto-recognition Method for Pointer-type Meter Based on Binocular Vision. | |
| CN104819690A (en) | Double-camera machine vision positioning method of surface mounted component | |
| CN101950409A (en) | Quadrant-based encoding label point design method | |
| CN206410679U (en) | A kind of contactless column verticality measurement device | |
| CN206281468U (en) | A kind of contactless detection device of columnar object perpendicularity | |
| CN201576308U (en) | Registration system for complex curved surface |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171114 Termination date: 20201206 |