CN106354333B - A method of improving touch-control system tracking precision - Google Patents
A method of improving touch-control system tracking precision Download PDFInfo
- Publication number
- CN106354333B CN106354333B CN201610873002.0A CN201610873002A CN106354333B CN 106354333 B CN106354333 B CN 106354333B CN 201610873002 A CN201610873002 A CN 201610873002A CN 106354333 B CN106354333 B CN 106354333B
- Authority
- CN
- China
- Prior art keywords
- matching degree
- control system
- contact
- tracking precision
- system tracking
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
- G06F3/0416—Control or interface arrangements specially adapted for digitisers
- G06F3/0418—Control or interface arrangements specially adapted for digitisers for error correction or compensation, e.g. based on parallax, calibration or alignment
Abstract
The invention discloses a kind of methods improving touch-control system tracking precision, area matched method, outline method and coordinate matching method are combined by weight, it solves the deficiency for going to matching track by one-side evaluation criterion well, is provided for subsequent track following a kind of with reference to solution.
Description
Technical field
The present invention relates to motion tracking technology field, especially a kind of method improving touch-control system tracking precision.
Background technology
With the development of computer technology and digital image processing techniques, the application field of computer vision technique is rapid
It widens, target following has become one very active project of computer vision field.The automatic tracing control system of moving target
The realization purpose of system is to acquire the sequence of video images of target with camera, and analyzes the fortune of target in real time by computer
It is dynamic, the kinematic parameter of target is obtained, target is directed toward always in this, as Main Basiss control camera.
Tracking technique depends on the judgement adjusted the distance to determine the trace point for belonging to some specific movement locus at present, but real
When hypotelorism or because the problem of shooting frame rate during border, starting with from Distance Judgment solves tracking problem and can inevitably encounter
The bottleneck of accuracy rate, be embodied in when belong to point of the point of another movement locus apart from this movement locus previous frame closer to when
It waits, will occur to track mistake.On the other hand, the side of accuracy is more also improved by area matched or outline
Method, still, all these methods are all to lay particular emphasis on the one hand to go to solve the problems, such as matching accuracy, according to actual conditions, meeting
There are some errors in judgement, mistake selects matching process, in turn results in tracking result inaccuracy.
Invention content
To solve the above-mentioned problems, the present invention proposes a kind of method improving touch-control system tracking precision.
The concrete scheme of the present invention is as follows:
A method of improve touch-control system tracking precision, the touch-control system include screen (1), video camera (2) and
Host (3), video camera (2) are connect with host (3) by data line, and host (3) is connect with screen (1) by video line, step
It is as follows:
S1:Video camera (2) captures the image of previous frame and present frame of each contact on screen (1), is transferred to described
Host (3);
S2:The host (3) receives the image that the video camera (2) is transmitted, and is detected, tracks to contact track,
In, the area of each contact is respectively area11, area12, area13 ... in previous frame image, area1n (n=1,2,
3 ..., n represent the serial number of contact in previous frame image), the area of each contact is respectively area21 in current frame image,
Area22, area23 ..., area2m (m=1,2,3 ..., m represent the serial number of contact in current frame image), in previous frame image
In the coordinate of each contact be respectively (x11, y11), (x12, y12), (x13, y13) ..., (x1n, y1n), in current frame image
In the coordinate of each contact be respectively (x21, y21), (x22, y22), (x23, y23) ..., (x2m, y2m), in previous frame image
In the long axis of each contact be respectively Long axis11, Long axis12, Long axis13 ..., Long axis1n, short axle
Respectively minor axis11, minor axis12, minor axis13 ..., minor axis1n, it is every in current frame image
The long axis of a contact is respectively Long axis21, Long axis22, Long axis23 ..., Long axis2m, short axle difference
For minor axis21, minor axis22, minor axis23 ..., minor axis2m;
S3:The host (3) calculates in previous frame image according to above-mentioned result of calculation in each contact and current frame image
Area matched degree, long axis matching degree, short axle matching degree and the coordinate matching degree of each contact, all area matched degree form area
Matching degree matrix, all long axis matching degrees form long axis matching degree matrix, and all short axle matching degrees form short axle matching degree matrix,
All coordinate matching degree form coordinate matching degree matrix;
S4:The host (3) calculates total matching degree matrix according to above-mentioned result of calculation, will be each in total matching degree matrix
The value sequence of total matching degree, matches the track of each contact according to ranking results, and result of calculation is transferred to screen
(1);
S5:The result of calculation that screen (1) receiving host (3) is transmitted, and show.
Preferably, the calculation formula of area matched degree is in the step S3
Preferably, area matched degree matrix is in the step S3
Preferably, the calculation formula of long axis matching degree is in the step S3
Preferably, the calculation formula of the step S3 short-and-medium axle matching degrees is
Preferably, long axis matching degree matrix is in the step S3
Preferably, the step S3 short-and-medium axles matching degree matrix is
Preferably, further include the setting of distance threshold d in the step S3.
Preferably, the calculation formula of coordinate matching degree is in the step S3
Preferably, coordinate matching degree matrix is in the step S3
Preferably, in the step S4 further include area matched degree weight K1, long axis matching degree weight K2, short axle matching degree
The setting of weight K3 and coordinate matching degree weight K4.
Preferably, the K2=K3.
Preferably, the calculation formula of total matching degree matrix is in the step S4
Compared with prior art, the present invention having the advantages that:
A variety of matching process are passed through weight knot by a kind of method improving touch-control system tracking precision proposed by the present invention
Altogether, it solves the deficiency for going to matching track by one-side evaluation criterion well, is provided for subsequent track following
It is a kind of to refer to solution.
Description of the drawings
Fig. 1 is a kind of schematic diagram of method improving touch-control system tracking precision proposed by the present invention;
Fig. 2 is the schematic diagram of the touch-control system of the present invention.
Description of the drawings
1 screen, 2 video camera, 3 host
Specific implementation mode
Below in conjunction with the specific implementation mode technical solution that present invention be described in more detail.It should be appreciated that being described herein as
Specific implementation mode be only used to explain the present invention, be not intended to limit the present invention.
Fig. 2 is the schematic diagram of the touch-control system of the present invention, and video camera (2) is connect with host (3) by data line, host
(3) it is connect by video line with screen (1).Video camera (2) captures the image on screen (1), is transferred to host (3), host (3)
The image transmitted to video camera (2) calculates, and result of calculation is transferred to screen (1) display.
Fig. 1 is a kind of schematic diagram of method improving touch-control system tracking precision proposed by the present invention, and video camera (2) is caught
The image for catching previous frame and present frame of each contact on screen (1), is transferred to the host (3), and the host (3) receives
The image that the video camera (2) is transmitted, is detected contact track, tracks, wherein the contact of previous frame be a1, a2, a3,
A4, a5, the contact of present frame are b1, b2, b3, b4, in previous frame image the area of each contact be respectively area11,
Area12, area13, area14, area15, in current frame image the area of each contact be respectively area21, area22,
Area23, area24, in previous frame image the coordinate of each contact be respectively (x11, y11), (x12, y12), (x13,
Y13), (x14, y14), (x15, y15), in current frame image the coordinate of each contact be respectively (x21, y21), (x22,
Y22), (x23, y23), (x24, y24), the long axis of each contact is respectively Long axis11, Long in previous frame image
Axis12, Long axis13, Long axis14, Long axis15, short axle is respectively minor axis11, minor
Axis12, minor axis13, minor axis14, minor axis15, the long axis of each contact point in current frame image
Not Wei Long axis21, Long axis22, Long axis23, Long axis24, short axle is respectively minor axis21,
Minor axis22, minor axis23, minor axis24, the host (3) calculate previous frame according to above-mentioned tracking result
In image in each contact and current frame image each contact area matched degree, long axis matching degree, short axle matching degree and coordinate
The calculation formula of matching degree, area matched degree isThe calculation formula of long axis matching degree isThe calculation formula of short axle matching degree isFirst preset one
Then distance threshold d1 goes to determine the distance threshold d finally used, coordinate matching degree by testing and acquiring a large amount of data
Calculation formula beAll area matched degree form area matched degree matrix
, all long axis matching degrees composition long axis matching degree matrixesAll short axle matching degree compositions are short
Axis matching degree matrixAll seats
It marks matching degree and forms coordinate matching degree matrix
The host (3) sets area matched degree weight K1, long axis matching degree according to above-mentioned result of calculation by acquiring mass data
Weight K2, short axle matching degree weight K3 and coordinate matching degree weight K4, under normal circumstances, K2=K3, long axis matching degree and short axle
Matching degree can combine measurement outline matching degree, and then calculate total matching degree matrix, and total matching degree Matrix Computation Formulas is Then the value of the total matching degree of each of total matching degree matrix is sorted,
Total matching maximum two points of angle value are optimal match points, then by the columns and rows in the matrix where maximum total matching angle value
Remove, continue to sort to remaining total matching angle value, this total matching maximum two point of angle value is matched, with such
It pushes away, the track of all points is all matched, while this result of calculation is transferred to screen (1), the screen (1) receives master
The result of calculation that machine (3) transmits, and show.
In conclusion a kind of method improving touch-control system tracking precision proposed by the present invention, by a variety of matching process
Combined by weight, solve the deficiency for going to matching track by one-side evaluation criterion well, is subsequent rail
Mark tracking provides a kind of with reference to solution.
Above embodiment is the preferred embodiment of the present invention, is not intended to limit the patent protection model of the present invention
It encloses.Those skilled in the art belonging to any present invention, in the premise for not departing from spirit and scope disclosed in this invention
Under, the transformation of the equivalent structure and equivalent steps that done to present disclosure each falls within claimed the scope of the claims
Within.
Claims (13)
1. a kind of method improving touch-control system tracking precision, the touch-control system includes screen (1), video camera (2) and master
Machine (3), video camera (2) are connect with host (3) by data line, and host (3) is connect with screen (1) by video line, feature
It is, steps are as follows:
S1:Video camera (2) captures the image of previous frame and present frame of each contact on screen (1), is transferred to the host
(3);
S2:The host (3) receives the image that the video camera (2) is transmitted, and is detected, tracks to contact track, wherein
The area of each contact is respectively area11, area12, area13 ... in previous frame image, area1n, wherein n=1, and 2,
3 ..., n represent the serial number of contact in previous frame image;The area of each contact is respectively area21 in current frame image,
Area22, area23 ..., area2m, wherein m=1,2,3 ..., m represent the serial number of contact in current frame image;In previous frame
The coordinate of each contact is respectively (x11, y11), (x12, y12), (x13, y13) ..., (x1n, y1n), in present frame in image
The coordinate of each contact is respectively (x21, y21), (x22, y22), (x23, y23) ..., (x2m, y2m), in previous frame in image
The long axis of each contact is respectively Long axis11, Long axis12, Long axis13 ..., Long axis1n in image,
Short axle is respectively minor axis11, minor axis12, minor axis13 ..., minor axis1n, in current frame image
In the long axis of each contact be respectively Long axis21, Long axis22, Long axis23 ..., Long axis2m, short axle
Respectively minor axis21, minor axis22, minor axis23 ..., minor axis2m;
S3:The host (3) calculates each contact and present frame figure in previous frame image according to the tracking result of above-mentioned steps S2
Area matched degree, long axis matching degree, short axle matching degree and the coordinate matching degree of each contact as in, all area matched degree compositions
Area matched degree matrix, all long axis matching degrees form long axis matching degree matrix, and all short axle matching degrees form short axle matching degree
Matrix, all coordinate matching degree form coordinate matching degree matrix;
S4:The host (3) calculates total matching degree matrix according to the result of calculation of above-mentioned steps S3, will be in total matching degree matrix
The value sequence of each total matching degree, matches the track of each contact according to ranking results, and result of calculation is transferred to
Screen (1);
S5:The result of calculation that screen (1) receiving host (3) is transmitted, and show.
2. a kind of method improving touch-control system tracking precision according to claim 1, which is characterized in that the step
The calculation formula of area matched degree is in S3
3. a kind of method improving touch-control system tracking precision according to claim 2, which is characterized in that the step
Area matched degree matrix is in S3
4. a kind of method improving touch-control system tracking precision according to claim 1, which is characterized in that the step
The calculation formula of long axis matching degree is in S3
5. a kind of method improving touch-control system tracking precision according to claim 1, which is characterized in that the step
The calculation formula of S3 short-and-medium axle matching degrees is
6. a kind of method improving touch-control system tracking precision according to claim 4, which is characterized in that the step
Long axis matching degree matrix is in S3
7. a kind of method improving touch-control system tracking precision according to claim 5, which is characterized in that the step
S3 short-and-medium axle matching degree matrixes are
8. a kind of method improving touch-control system tracking precision according to claim 1, which is characterized in that the step
It further include the setting of distance threshold d in S3.
9. a kind of method improving touch-control system tracking precision according to claim 8, which is characterized in that the step
The calculation formula of coordinate matching degree is in S3
10. a kind of method improving touch-control system tracking precision according to claim 9, which is characterized in that the step
Coordinate matching degree matrix is in rapid S3
11. a kind of method improving touch-control system tracking precision according to claim 1, which is characterized in that the step
Further include area matched degree weight K1, long axis matching degree weight K2, short axle matching degree weight K3 and coordinate matching degree power in rapid S4
The setting of weight K4.
12. a kind of method improving touch-control system tracking precision according to claim 11, which is characterized in that the K2
=K3.
13. a kind of method improving touch-control system tracking precision according to claim 12, which is characterized in that the step
The calculation formula of total matching degree matrix is in rapid S4
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610873002.0A CN106354333B (en) | 2016-09-30 | 2016-09-30 | A method of improving touch-control system tracking precision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610873002.0A CN106354333B (en) | 2016-09-30 | 2016-09-30 | A method of improving touch-control system tracking precision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106354333A CN106354333A (en) | 2017-01-25 |
CN106354333B true CN106354333B (en) | 2018-10-16 |
Family
ID=57866086
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610873002.0A Active CN106354333B (en) | 2016-09-30 | 2016-09-30 | A method of improving touch-control system tracking precision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106354333B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109669567B (en) * | 2017-10-13 | 2020-10-16 | 华为技术有限公司 | Control method and terminal |
US11216116B2 (en) | 2017-10-13 | 2022-01-04 | Huawei Technologies Co., Ltd. | Control method and terminal |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202472604U (en) * | 2012-03-15 | 2012-10-03 | 郝宏贤 | Computer screen touch control identification system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011013299A1 (en) * | 2009-07-31 | 2011-02-03 | パナソニック株式会社 | Mobile body detection apparatus and mobile body detection method |
-
2016
- 2016-09-30 CN CN201610873002.0A patent/CN106354333B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202472604U (en) * | 2012-03-15 | 2012-10-03 | 郝宏贤 | Computer screen touch control identification system |
Also Published As
Publication number | Publication date |
---|---|
CN106354333A (en) | 2017-01-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108986037B (en) | Monocular vision odometer positioning method and positioning system based on semi-direct method | |
CN103458977B (en) | Sensing device and sensing method used for virtual golf simulation device | |
CN106650701B (en) | Binocular vision-based obstacle detection method and device in indoor shadow environment | |
CN104408725A (en) | Target recapture system and method based on TLD optimization algorithm | |
CN106845330A (en) | A kind of training method of the two-dimension human face identification model based on depth convolutional neural networks | |
CN104299243B (en) | Target tracking method based on Hough forests | |
CN107543530B (en) | Method, system, and non-transitory computer-readable recording medium for measuring rotation of ball | |
CN108955718A (en) | A kind of visual odometry and its localization method, robot and storage medium | |
CN103227888B (en) | A kind of based on empirical mode decomposition with the video stabilization method of multiple interpretational criteria | |
CN107146239A (en) | Satellite video moving target detecting method and system | |
CN101930628A (en) | Monocular-camera and multiplane mirror catadioptric device-based motion capturing method | |
CN110648362B (en) | Binocular stereo vision badminton positioning identification and posture calculation method | |
CN106354333B (en) | A method of improving touch-control system tracking precision | |
CN112966571B (en) | Standing long jump flight height measurement method based on machine vision | |
CN105279771A (en) | Method for detecting moving object on basis of online dynamic background modeling in video | |
CN108171728A (en) | Unmarked moving object pose recovery method and device based on Hybrid camera system | |
CN105242568A (en) | Tobacco leaf accurate rejecting control method based on digital image processing | |
CN106767833A (en) | A kind of robot localization method of fusion RGBD depth transducers and encoder | |
CN106595601A (en) | Camera six-degree-of-freedom pose accurate repositioning method without hand eye calibration | |
CN107480678A (en) | A kind of chessboard recognition methods and identifying system | |
CN113393524B (en) | Target pose estimation method combining deep learning and contour point cloud reconstruction | |
CN107564037A (en) | A kind of multirobot detection and tracking based on local feature | |
CN105046691A (en) | Method for camera self-calibration based on orthogonal vanishing points | |
CN111062968A (en) | Robot path skeleton extraction method based on edge scanning and centerline extraction | |
CN104715482B (en) | A kind of RANSAC calculates point thresholding automatic setting method in fundamental matrix |
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 |