CN106709952A - Automatic calibration method of display screen - Google Patents

Automatic calibration method of display screen Download PDF

Info

Publication number
CN106709952A
CN106709952A CN201611018418.0A CN201611018418A CN106709952A CN 106709952 A CN106709952 A CN 106709952A CN 201611018418 A CN201611018418 A CN 201611018418A CN 106709952 A CN106709952 A CN 106709952A
Authority
CN
China
Prior art keywords
image
point
row
gray
display screen
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
Application number
CN201611018418.0A
Other languages
Chinese (zh)
Other versions
CN106709952B (en
Inventor
谭登峰
康三顺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Kernel Optoelectronics Technology Co Ltd
Original Assignee
Nanjing Kernel Optoelectronics Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing Kernel Optoelectronics Technology Co Ltd filed Critical Nanjing Kernel Optoelectronics Technology Co Ltd
Priority to CN201611018418.0A priority Critical patent/CN106709952B/en
Publication of CN106709952A publication Critical patent/CN106709952A/en
Application granted granted Critical
Publication of CN106709952B publication Critical patent/CN106709952B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20224—Image subtraction

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention provides an automatic calibration method of a display screen. The method comprises the following steps of: correcting a camera; obtaining a background image of the display screen, and graying a white checkerboard image and a black checkerboard image to obtain a screen background gray scale image, a white checkerboard gray scale image and a black checkerboard gray scale image; respectively differencing the white checkerboard gray scale image and the black checkerboard gray scale image with the screen background gray scale image, taking absolute values and carrying out n times of mid-value smoothing filtration and Gaussian smoothing filtration; setting a gray scale threshold value of pixels, when the difference between pixel gray scale values corresponding to the two images obtained in above steps is greater than the set gray scale threshold value, setting the pixel value at a corresponding position as a corresponding difference value, and otherwise, setting the pixel value as zero; carrying out n times of mid-value smoothing filtration and Gaussian smoothing filtration on the newly generated images and then carrying out binarization; and carrying out profile feature extraction on the obtained binary images, detecting coordinate information of each image corner point through a profile sequence, and carrying out array correspondence according to the obtained coordinate information.

Description

A kind of automatic calibration method of display screen
Technical field
The invention belongs to the technical field of image procossing, and in particular to a kind of automatic calibration method of display screen.
Background technology
The existing demarcation to display screen generally uses manual mode, but due to the installation site and display screen of camera There is certain visual angle relation in curtain region, therefore the screen area of camera collection needs to be demarcated, could be with the touch-control of screen Region is mapped, but the difference such as distance, the resolution ratio of camera, the size of display screen by camera and display screen Influence, causes the touch point precision of manual demarcation low, and touch point number is more, and manual calibration process is not easy to, and influences user Experience.
The content of the invention
The invention provides a kind of automatic calibration method of display screen, completed to display using the mode of image recognition The automatic Calibration process of screen so that the demarcation to display screen becomes easy, and improves the precision of demarcation.
The invention provides a kind of automatic calibration method of display screen, comprise the following steps：
S1：Correction camera；
S2：Obtain the Background of display screen, white chessboard trrellis diagram and black chessboard trrellis diagram；
S3：After Background respectively to above-mentioned display screen, white chessboard trrellis diagram and black chessboard trrellis diagram carry out gray processing Obtain screen background gray-scale map, white gridiron pattern gray-scale map and black gridiron pattern gray-scale map；
S4：Above-mentioned white chessboard gray-scale map and screen background gray-scale map are carried out to seek difference and take absolute value, and to newly-generated Image carry out the filtering of n median smoothing and Gaussian smoothing filter；Wherein 0<n<100；
S5：Above-mentioned black chessboard gray-scale map and screen background gray-scale map are carried out to seek difference and take absolute value, and to newly-generated Image carry out the filtering of n median smoothing and Gaussian smoothing filter；Wherein 0<n<100；
S6：The gray threshold of pixel is set, when each corresponding grey scale pixel value of step S4 and step S5 gained images Difference more than setting gray threshold when, the grey scale pixel value of its relevant position is set to corresponding difference, less than setting ash During degree threshold value, the grey scale pixel value of relevant position is set to 0, and n median smoothing filtering and height are carried out to newly-generated image This smothing filtering；Wherein 0<n<100；
S7：Binaryzation carried out to the image that step S6 is produced, and binary map to obtaining carries out the feature extraction of profile；
S8：By the coordinate information of each image angle point of profile Sequence Detection；Rows*cols point is detected, wherein Rows is the number of the point that image a line is present, and cols is the number of the point that the row of image one are present, 0<rows<100,0<cols< 100；And correspondence is ranked up according to the coordinate information for obtaining.
Preferably, the method that black chessboard trrellis diagram is obtained in described step S2 is to be divided into the display screen of m contact The m/4 black chessboard trrellis diagram of small rectangle, the wherein value of m need to set according to the size of the resolution ratio of display screen.
Preferably, the method that black chessboard trrellis diagram is obtained in described step S2 is to be divided into the display screen of m contact The m/4 black chessboard trrellis diagram of small rectangle, the wherein value of m need to set according to the size of the resolution ratio of display screen.
Preferably, the method for feature extraction of profile is carried out in described step S7 to the binary map for obtaining for retrieval is described All profiles of binary picture, and compression level, vertical and oblique part only retains the terminal part of profile, by terminal Part is saved in the profile sequence of formation image in a sequence.
Preferably, described step S8 is ranked up corresponding method and comprises the following steps according to the coordinate information for obtaining：
S81：If the upper left corner of screen is the origin of coordinates, the position coordinates of each pixel is (x, y), if the pixel Abscissa x it is smaller with ordinate y sums, then the pixel is closer in the screen upper left corner；
S82：Assuming that screen picture length is imagelengthIf, imagelength- x and y sums are smaller, then the pixel Closer in the screen upper right corner；
S83：The point of the leftmost point of screen first row and first row rightmost is detected by above-mentioned steps, if 2 points of seats Mark is respectively (x1, y1) and (x2, y2), and this 2 points slope angles of formation are drawn by θ=arctan ((y2-y1)/(x2-x1)) Degree；Rough sequence is carried out to all of pixel using the above method；
S84：The coordinate ranking results after above-mentioned rough sequence are obtained, the abscissa x put by each, ordinate y, and step By being ranked up to all points from small to large, then preceding rows point is the to the θ formula y*cos θ-x*sin θ that rapid S83 is calculated The point that one row is possessed, and pixel to the first row is ranked up from small to large according to its abscissa, obtains first row Sequence correspondence；
S85：Carry out step S81 to step S84 one by one to remaining (rows*cols-rows) individual point, obtain second row most The point on the left side and the point of second row rightmost, and second row rows point；Similarly, the coordinate of every other row is obtained according to this The sequence correspondence of information；
S86:By the preceding rows point (sum of first row) in the corresponding result of above-mentioned sequence according to abscissa from it is small to It is ranked up greatly, that is, obtain first row is correctly ordered correspondence, being correctly ordered for the 2nd to cols row is similarly obtained according to this right Should.
As can be seen from the above technical solution, a kind of automatic calibration method of display screen that the present invention is provided, is respectively adopted White gridiron pattern gray-scale map and black gridiron pattern gray-scale map carry out seeking difference and taking absolute value with screen background gray-scale map, then with set Fixed pixel grey scale threshold value is compared, and if greater than the gray threshold of setting, then it is right to be set to the pixel value of its relevant position The difference answered, during less than the gray threshold for setting, 0 is set to by the grey scale pixel value of its relevant position；And then it is new to what is obtained Image binaryzation is gone forward side by side the wide feature extraction of road wheel, and the coordinate for obtaining each image angle point by the contour feature sequence for obtaining is believed Breath, so to obtain coordinate information be ranked up correspondence, the accurate of automatic identification can be improved using above-mentioned this method Property, solve the problems, such as that the touch point precision of existing manual demarcation is low, improve the experience of user.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the automatic calibration method of display screen provided in an embodiment of the present invention；
Fig. 2 is a kind of flow that corresponding method is ranked up according to the coordinate information for obtaining provided in an embodiment of the present invention Figure；
Fig. 3 is a kind of design sketch of the automatic calibration method of display screen provided in an embodiment of the present invention.
Specific embodiment
Technical scheme is further described below in conjunction with specific embodiment.It should be appreciated that being described herein as Specific embodiment be only used to explain the present invention, be not intended to limit the present invention.
A kind of automatic calibration method of display screen is the embodiment of the invention provides, as shown in figure 1, comprising the following steps：
S1：Correction camera；
S2：Obtain the Background of display screen, white chessboard trrellis diagram and black chessboard trrellis diagram；
S3：After Background respectively to above-mentioned display screen, white chessboard trrellis diagram and black chessboard trrellis diagram carry out gray processing Obtain screen background gray-scale map, white gridiron pattern gray-scale map and black gridiron pattern gray-scale map；
S4：Above-mentioned white chessboard gray-scale map and screen background gray-scale map are carried out to seek difference and take absolute value, and to newly-generated Image carry out the filtering of n median smoothing and Gaussian smoothing filter；Wherein 0<n<100；
S5：Above-mentioned black chessboard gray-scale map and screen background gray-scale map are carried out to seek difference and take absolute value, and to newly-generated Image carry out the filtering of n median smoothing and Gaussian smoothing filter；Wherein 0<n<100；
Wherein above-mentioned steps S5 and step S6 carries out n median smoothing filtering and Gaussian smoothing filter to newly-generated image Ripple；Both undesirable miscellaneous point in image can have been filtered out, the information needed in image had been saved again.
S6：The gray threshold of pixel is set, when each corresponding grey scale pixel value of step S4 and step S5 gained images Difference more than setting gray threshold when, the grey scale pixel value of relevant position is set to corresponding difference, less than setting gray scale During threshold value, the grey scale pixel value of its relevant position is set to 0；And n median smoothing filtering and height are carried out to newly-generated image This smothing filtering；Wherein 0<n<100；
S7：Binaryzation carried out to the image that step S6 is produced, and binary map to obtaining carries out the feature extraction of profile；
S8：By the coordinate information of each image angle point of profile Sequence Detection, rows*cols contact is detected, wherein Rows is the number of the point that image a line is present, and cols is the number of the point that the row of image one are present, wherein 0<rows<100,0< cols<100；And correspondence is ranked up according to the coordinate information for obtaining.
As can be seen from the above technical solution, the automatic calibration method of a kind of display screen provided in an embodiment of the present invention, point Do not employ white gridiron pattern gray-scale map and black gridiron pattern gray-scale map carries out seeking difference and taking absolutely with screen background gray-scale map respectively To value, then it is compared with the pixel grey scale threshold value of setting, if greater than the gray threshold of setting, then by the picture of its relevant position Plain gray value is set to corresponding difference, during less than the gray threshold for setting, the grey scale pixel value of its relevant position is set into 0；Enter And the new image binaryzation to obtaining is gone forward side by side the wide feature extraction of road wheel, each figure is obtained by the contour feature sequence for obtaining The coordinate information of image angle point, so to obtain coordinate information be ranked up correspondence, can be improved using above-mentioned this method The accuracy of automatic identification, solves the problems, such as that the touch point precision of existing manual demarcation is low, improves the experience of user.
Preferably, the method that black chessboard trrellis diagram is obtained in described step S2 is to be divided into the display screen of m contact The m/4 black chessboard trrellis diagram of small rectangle, the wherein value of m need to set according to the size of the resolution ratio of display screen.
Preferably, the method that black chessboard trrellis diagram is obtained in described step S2 is to be divided into the display screen of m contact The m/4 black chessboard trrellis diagram of small rectangle, the wherein value of m need to set according to the size of the resolution ratio of display screen.
The value of above-mentioned m can determine according to the resolution ratio of display screen, such as the display screen of 640*480, typically 96 contacts are taken during demarcation, i.e., the value of m now is 96.
Preferably, the method for feature extraction of profile is carried out in described step S7 to the binary map for obtaining for retrieval is described All profiles of binary picture, and compression level, vertical and oblique part only retains the terminal part of profile, by terminal Part is saved in the profile sequence of formation image in a sequence.
Other modes can certainly be taken carries out the feature extraction of profile, such as the side such as labeling method of two-value connected domain Formula.
A kind of coordinate information according to acquisition provided in an embodiment of the present invention is ranked up corresponding method, as shown in Fig. 2 Comprise the following steps：
S81：If the upper left corner of screen is the origin of coordinates, the position coordinates of each pixel is (x, y), if the pixel Abscissa x it is smaller with ordinate y sums, then the pixel is closer in the screen upper left corner；
S82：Assuming that screen picture length is imagelengthIf, imagelength- x and y sums are smaller, then the pixel Closer in the screen upper right corner；
S83：The point of the leftmost point of screen first row and first row rightmost is detected by above-mentioned steps, if 2 points of seats Mark is respectively (x1, y1) and (x2, y2), and this 2 points slope angles of formation are drawn by θ=arctan ((y2-y1)/(x2-x1)) Degree；Rough sequence is carried out to all of pixel using the above method；
S84：The coordinate ranking results after above-mentioned rough sequence are obtained, the abscissa x put by each, ordinate y, and step By being ranked up to all points from small to large, then preceding rows point is the to the θ formula y*cos θ-x*sin θ that rapid S83 is calculated The point that one row is possessed, and pixel to the first row is ranked up from small to large according to its abscissa, obtains first row Sequence correspondence；
S85：Carry out step S81 to step S84 one by one to remaining (rows*cols-rows) individual point, obtain second row most The point on the left side and the point of second row rightmost, and second row rows point；Similarly, the coordinate of every other row is obtained according to this The sequence correspondence of information；
S86:By the preceding rows point (sum of first row) in the corresponding result of above-mentioned sequence according to abscissa from it is small to It is ranked up greatly, that is, obtain first row is correctly ordered correspondence, being correctly ordered for the 2nd to cols row is similarly obtained according to this right Should.
A kind of automatic calibration method of display screen is the embodiment of the invention provides, effect as shown in Figure 3 can be obtained Figure, corrects infrared camera first, obtains the Background for display screen such as Fig. 3 (a), such as Fig. 3 (b) be white chessboard trrellis diagram and If Fig. 3 (c) is black chessboard trrellis diagram；Background respectively to above-mentioned display screen, white chessboard trrellis diagram and black chessboard trrellis diagram Such as Fig. 3 (d) screen background gray-scale maps, such as Fig. 3 (e) white gridiron pattern gray-scale maps are obtained after carrying out gray processing and as Fig. 3 (f) is black Color gridiron pattern gray-scale map；Above-mentioned white chessboard gray-scale map and screen background gray-scale map are carried out to seek difference and take absolute value, and to new The image such as Fig. 3 (g) of generation carry out the acquisition such as new images of Fig. 3 (h) after n median smoothing filtering and Gaussian smoothing filter；Its The span of middle n is 0<n<100；Above-mentioned black chessboard gray-scale map and screen background gray-scale map are carried out to seek difference and take definitely Value, and acquisition such as Fig. 3 (j) after n median smoothing filtering and Gaussian smoothing filter are carried out to newly-generated image such as Fig. 3 (i) New images；Wherein the span of n is 0<n<100；The gray threshold of pixel is set, each is corresponding as Fig. 3 (h) and Fig. 3 (j) The difference of grey scale pixel value more than setting gray threshold when, the pixel value of its relevant position is set to corresponding difference, less than setting During fixed gray threshold, the grey scale pixel value of relevant position is set to 0；Obtain new image such as Fig. 3 (k)；And to newly-generated Image carries out n median smoothing filtering and Gaussian smoothing filter；New image such as Fig. 3 (l) is obtained, the wherein span of n is 0 <n<100；Carry out binaryzation to the new image for producing, and Fig. 3 (m) to obtaining carries out the feature extraction of profile, obtains such as Fig. 3 The profile sequence of the new images of (n), by coordinate information such as Fig. 3 (o) of each image angle point of profile retrieval, and according to obtaining The coordinate information for taking is ranked up correspondence, obtains the sequence corresponding diagram such as Fig. 3 (p).
In sum, a kind of automatic calibration method of display screen provided in an embodiment of the present invention, solves existing hand The low problem of the dynamic touch point precision demarcated, can improve the accuracy of automatic identification, improve the experience of user.
Implementation method above is the preferred embodiment of the present invention, not thereby limits patent protection model of the invention Enclose.Those skilled in the art belonging to any present invention, are not departing from the premise of spirit and scope disclosed in this invention Under, the equivalent structure done to present disclosure each falls within claimed the scope of the claims with the conversion of equivalent step Within.

Claims (5)

1. a kind of automatic calibration method of display screen, it is characterised in that comprise the following steps：
S1：Correction camera；
S2：Obtain the Background of display screen, white chessboard trrellis diagram and black chessboard trrellis diagram；
S3：Background respectively to above-mentioned display screen, white chessboard trrellis diagram and black chessboard trrellis diagram are obtained after carrying out gray processing Screen background gray-scale map, white gridiron pattern gray-scale map and black gridiron pattern gray-scale map；
S4：Above-mentioned white chessboard gray-scale map and screen background gray-scale map are carried out to seek difference and take absolute value, and to newly-generated figure As carrying out n median smoothing filtering and Gaussian smoothing filter；Wherein 0<n<100；
S5：Above-mentioned black chessboard gray-scale map and screen background gray-scale map are carried out to seek difference and take absolute value, and to newly-generated figure As carrying out n median smoothing filtering and Gaussian smoothing filter；Wherein 0<n<100；
S6：The gray threshold of pixel is set, when the difference of each corresponding grey scale pixel value of step S4 and step S5 gained images During more than the gray threshold for setting, the pixel value gray scale of relevant position is set to corresponding difference, less than the gray threshold of setting When, the grey scale pixel value of its relevant position is set to 0；And the filtering of n median smoothing is carried out to newly-generated image and Gauss is flat Sliding filtering；Wherein 0<n<100；
S7：Binaryzation carried out to the image that step S6 is produced, and binary map to obtaining carries out the feature extraction of profile, obtains aobvious The profile sequence of display screen curtain；
S8：By the coordinate information of each image angle point of profile Sequence Detection, rows*cols point is detected, wherein rows is The number of the point that image a line is present, cols is the number of the point that the row of image one are present, 0<rows<100,0<cols<100, and Coordinate information according to obtaining is ranked up correspondence.
2. automatic calibration method according to claim 1, it is characterised in that white gridiron pattern is obtained in described step S2 The method of figure is that the display screen of m contact is divided into the m/4 white chessboard trrellis diagram of small rectangle, and the wherein value of m needs basis The size setting of the resolution ratio of display screen.
3. automatic calibration method according to claim 1, it is characterised in that black gridiron pattern is obtained in described step S2 The method of figure is that the display screen of m contact is divided into the m/4 black chessboard trrellis diagram of small rectangle, and the wherein value of m needs basis The size setting of the resolution ratio of display screen.
4. automatic calibration method according to claim 1, it is characterised in that the binary map in described step S7 to obtaining The method for carrying out the feature extraction of profile is to retrieve all profiles of the binary picture, and compression level, it is vertical and oblique Part, only retain the terminal part of profile, terminal part is saved in a sequence profile sequence for forming image.
5. automatic calibration method according to claim 1, it is characterised in that described step S8 is according to the coordinate letter for obtaining Breath is ranked up corresponding method and comprises the following steps：
S81：If the upper left corner of screen is the origin of coordinates, the position coordinates of each pixel is (x, y), if the horizontal stroke of the pixel Coordinate x is smaller with ordinate y sums, then the pixel is closer in the screen upper left corner；
S82：Assuming that screen picture length is imagelengthIf, imagelength- x and y sums are smaller, then the pixel is got over and leaned on It is bordering on the screen upper right corner；
S83：The point of the leftmost point of screen first row and first row rightmost is detected by above-mentioned steps, if two point coordinates point Not Wei (x1, y1) and (x2, y2), by θ=arctan ((y2-y1)/(x2-x1)) draw this 2 points formation slope angles； Rough sequence is carried out to all of pixel using the above method；
S84：The coordinate ranking results after above-mentioned rough sequence are obtained, the abscissa x put by each, ordinate y, and step By being ranked up to all points from small to large, then preceding rows point is first to the θ formula y*cos θ-x*sin θ that S83 is calculated The possessed point of row, and pixel to the first row is ranked up from small to large according to its abscissa, obtains first row Sequence correspondence；
S85：Carry out step S81 to step S84 one by one to remaining (rows*cols-rows) individual point, obtain second row Far Left Point and second row rightmost point, and second row rows point；Similarly, the coordinate information of every other row is obtained according to this Sequence correspondence；
S86:Preceding rows point (sum of first row) in the corresponding result of above-mentioned sequence is entered from small to large according to abscissa Row sequence, that is, obtain first row is correctly ordered correspondence, and the 2nd to cols row is similarly obtained according to this is correctly ordered correspondence.
CN201611018418.0A 2016-11-18 2016-11-18 A kind of automatic calibration method of display screen Active CN106709952B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611018418.0A CN106709952B (en) 2016-11-18 2016-11-18 A kind of automatic calibration method of display screen

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611018418.0A CN106709952B (en) 2016-11-18 2016-11-18 A kind of automatic calibration method of display screen

Publications (2)

Publication Number Publication Date
CN106709952A true CN106709952A (en) 2017-05-24
CN106709952B CN106709952B (en) 2018-11-13

Family

ID=58939923

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611018418.0A Active CN106709952B (en) 2016-11-18 2016-11-18 A kind of automatic calibration method of display screen

Country Status (1)

Country Link
CN (1) CN106709952B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109035164A (en) * 2018-07-13 2018-12-18 北京控制工程研究所 A kind of method and system that fast robust image veiling glare inhibits
CN110264531A (en) * 2019-06-27 2019-09-20 信利光电股份有限公司 A kind of catching for X-comers takes method, apparatus, system and readable storage medium storing program for executing
CN110866955A (en) * 2019-10-10 2020-03-06 深圳市圆周率软件科技有限责任公司 Vehicle-mounted panoramic image calibration method and system
CN111311556A (en) * 2020-01-21 2020-06-19 上海悦易网络信息技术有限公司 Mobile phone defect position identification method and equipment
CN112052700A (en) * 2019-06-06 2020-12-08 北京京东尚科信息技术有限公司 Image binarization threshold matrix determination and graphic code information identification method and device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1865845A (en) * 2006-06-22 2006-11-22 上海交通大学 Method for making calibrating plate on flat display screen
CN102799318A (en) * 2012-08-13 2012-11-28 深圳先进技术研究院 Human-machine interaction method and system based on binocular stereoscopic vision
US20130072297A1 (en) * 2011-09-19 2013-03-21 Sony Computer Entertainment America Llc Systems and methods for calibration and biasing for game controller

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1865845A (en) * 2006-06-22 2006-11-22 上海交通大学 Method for making calibrating plate on flat display screen
US20130072297A1 (en) * 2011-09-19 2013-03-21 Sony Computer Entertainment America Llc Systems and methods for calibration and biasing for game controller
CN102799318A (en) * 2012-08-13 2012-11-28 深圳先进技术研究院 Human-machine interaction method and system based on binocular stereoscopic vision

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109035164A (en) * 2018-07-13 2018-12-18 北京控制工程研究所 A kind of method and system that fast robust image veiling glare inhibits
CN109035164B (en) * 2018-07-13 2022-03-04 北京控制工程研究所 Method and system for quickly suppressing stray light of robust image
CN112052700A (en) * 2019-06-06 2020-12-08 北京京东尚科信息技术有限公司 Image binarization threshold matrix determination and graphic code information identification method and device
CN112052700B (en) * 2019-06-06 2024-04-05 北京京东乾石科技有限公司 Image binarization threshold matrix determination and graphic code information identification method and device
CN110264531A (en) * 2019-06-27 2019-09-20 信利光电股份有限公司 A kind of catching for X-comers takes method, apparatus, system and readable storage medium storing program for executing
CN110866955A (en) * 2019-10-10 2020-03-06 深圳市圆周率软件科技有限责任公司 Vehicle-mounted panoramic image calibration method and system
CN110866955B (en) * 2019-10-10 2024-02-27 圆周率科技(常州)有限公司 Vehicle-mounted panoramic image calibration method and system
CN111311556A (en) * 2020-01-21 2020-06-19 上海悦易网络信息技术有限公司 Mobile phone defect position identification method and equipment
CN111311556B (en) * 2020-01-21 2023-02-03 上海万物新生环保科技集团有限公司 Mobile phone defect position identification method and equipment

Also Published As

Publication number Publication date
CN106709952B (en) 2018-11-13

Similar Documents

Publication Publication Date Title
CN107506798B (en) Water level monitoring method based on image recognition
CN109785291B (en) Lane line self-adaptive detection method
CN106709952A (en) Automatic calibration method of display screen
CN105069394B (en) Quick Response Code weighted average gray level method coding/decoding method and system
CN106446894B (en) A method of based on outline identification ball-type target object location
CN102629322B (en) Character feature extraction method based on stroke shape of boundary point and application thereof
CN110084241B (en) Automatic ammeter reading method based on image recognition
CN106682629A (en) Identification number identification algorithm in complicated background
CN103729655A (en) Detection method for sheet element visual positioning
CN109784344A (en) A kind of non-targeted filtering method of image for ground level mark identification
CN109583365B (en) Method for detecting lane line fitting based on imaging model constrained non-uniform B-spline curve
CN109858325B (en) Table detection method and device
CN105608429B (en) Robust method for detecting lane lines based on difference excitation
CN103198476B (en) Image detection method of thick line type cross ring mark
CN107563330B (en) Horizontal inclined license plate correction method in surveillance video
CN101551900A (en) Detection method for video mosaic images
CN110245600B (en) Unmanned aerial vehicle road detection method for self-adaptive initial quick stroke width
CN103745221A (en) Two-dimensional code image correction method
CN104331695A (en) Robust round identifier shape quality detection method
CN104537342A (en) Quick lane line detection method combined with ridge boundary detection and Hough transformation
CN106407973A (en) Robust recognition method for AR code marked on cylinder
CN103914829B (en) Method for detecting edge of noisy image
CN108492306A (en) A kind of X-type Angular Point Extracting Method based on image outline
CN115240197A (en) Image quality evaluation method, image quality evaluation device, electronic apparatus, scanning pen, and storage medium
CN104463126A (en) Automatic slant angle detecting method for scanned document image

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant