CN102729250A - Chess opening chessman-placing system and method - Google Patents
Chess opening chessman-placing system and method Download PDFInfo
- Publication number
- CN102729250A CN102729250A CN2011100837506A CN201110083750A CN102729250A CN 102729250 A CN102729250 A CN 102729250A CN 2011100837506 A CN2011100837506 A CN 2011100837506A CN 201110083750 A CN201110083750 A CN 201110083750A CN 102729250 A CN102729250 A CN 102729250A
- Authority
- CN
- China
- Prior art keywords
- image
- chess
- robot
- specific marker
- chessman
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Manipulator (AREA)
Abstract
The invention discloses a chess opening chessman-placing system and a method. The system mainly comprises a robot carrier, an image collection system, an image processing system, chessmen (6) and a chessboard (8). The robot carrier comprises an arm robot (1) and a chessman grabbing paw (7). The image collection system comprises a colorful camera (2), a data transmission line (3), an image data collection card (4) and a terminal computer (5). Image data is collected by the colorful camera (2), and data information is transmitted to the image data collection card (4) mounted on the computer (5) through the data transmission line (3). The image processing system is responsible for processing and analyzing the collected image information, distinguishing the chessmen of two sides according to colors and implementing grey processing. The chessmen (6) are distinguished and the coordinates of the chessmen (6) are located through an SIFI algorithm. And finally the chessman grabbing paw (7) is controlled by the robot to place the chessmen (6). The chess opening chessman-placing system has a modularized and reliable structure, and can be conveniently mounted and used according to different robot carriers, thus really realizing the automation of the chessman-placing process.
Description
Technical field
The present invention relates to the Robotics field, the digital picture recognition technology that beginning pendulum chess method in particularly a kind of robot system of playing chess, this system are based on the SIFT algorithm realizes the system and method for chess piece identification and location pendulum chess.
Background technology
Present Chinese chess robot adopts two kinds of patterns basically aspect the identification of chess game: a kind of is to discern chess piece with chessboard as sensor; A kind of is to have adopted machine vision technique, adopts vision sensor combining image treatment technology to discern chessboard and chess piece.Along with the development of machine vision and image processing techniques, machine vision technique is (replacement) chessboard mode sensor progressively.
Image recognition technology is as one of the core of Chinese chess robot vision identification and navigation system and basic technology; Be the forward position and the focus of present Chinese chess robot vision area research; This technology is just obtaining application more and more widely in concrete practices such as the chess piece perception of Chinese chess robot, chess piece location, the behavior of carrying chess piece, its image matching algorithm-SIFT algorithm is also adopted by people gradually.
The SIFT algorithm is a kind of algorithm that extracts local feature, seeks extreme point, extracting position, yardstick, rotational invariants at metric space.The SIFT characteristic point vector that utilization SIFT algorithm extracts has following advantage: the SIFT characteristic is the local feature of image; Rotation, scale, brightness are changed the voltinism that remains unchanged, visual angle change, affine transformation, noise are also kept stability to a certain degree; Unique good, information content is abundant, is applicable in the magnanimity property data base and matees fast and accurately; Volume property is even several objects of minority also can produce a large amount of SIFT characteristic vectors.
At present, the Chinese chess robot vision is applied in the process of playing chess, but on beginning pendulum chess process, because the randomness of chess piece placement location is not also seen relevant beginning pendulum chess patent system.Therefore, present Chinese chess robot mostly adopts manual work to arrange the chess pieces, and is only robot oneself next period then, and the next period efficient of such Chinese chess robot is low, needs human intervention, is unfavorable for the versatility and the popularization of Chinese chess robot.
Summary of the invention
According to background technology; The objective of the invention is to avoid above-mentioned deficiency, a kind of Chinese chess robot beginning pendulum game system based on the image recognition technology of improving the SIFT algorithm is provided, this system can realize the autonomous pendulum chess of Chinese chess robot; Needn't human intervention; Raise the efficiency, reduce match time greatly, really realize automatically playing chess of Chinese chess robot.
To achieve these goals, the present invention realizes through following technical scheme:
A kind of Chinese chess beginning pendulum game system comprises robot carrier, image capturing system, image processing system, chess piece (6) and chessboard (8) composition, and wherein: robot carrier comprises arm robot (1) and grabs chess player's pawl (7); Image capturing system comprises colour imagery shot (2), data line (3), image data acquiring card (4), terminal control computer (5), also will add light source in case of necessity; Image processing system comprises SIFT identification chess piece program and terminal control computer (5); Colour imagery shot (2) is fixed on the arm robot (1), and colour imagery shot (2) is connected with image data acquiring card (4) on the terminal control computer (5) through data line (3).
Digital picture recognition technology based on the SIFT algorithm realizes chess piece identification and location pendulum chess method, and it comprises the following step:
(1) robot is carried out IMAQ at initial position to specific marker scenery, obtain containing the original image of specific marker image;
The specific marker original image that (2) will obtain is handled, according to color differentiating both sides chess piece;
The specific marker original image that (3) will obtain carries out gray scale to be handled, and obtains the gray scale picture of specific marker image;
(4) utilization SIFT algorithm is handled the image to be identified that obtains, the chess piece on the identification picture;
(5) chess piece that identifies is calculated the coordinate on its relative picture, according to the relation of image coordinate and actual coordinate, its Coordinate Conversion is become actual coordinate again;
(6) will calculate the chess piece actual coordinate that calculates and send to terminal control computer, chess piece is put by terminal control computer control robot.
Described specific marker is the image that robot is taken at initial position;
Described SIFT algorithm is a yardstick invariant features mapping algorithm.
Owing to adopted technique scheme, the present invention to have following advantage and effect:
1, the present invention has realized the automation of beginning pendulum chess of Chinese chess, has broken through the shortcoming that Chinese chess robot in the past can not put chess automatically, does not need artificially to put the intervention of chess, has realized real pendulum chess automation;
2, the present invention utilizes the visual identity technology, need therefore not have no specific (special) requirements to chessboard and chess piece, highly versatile with sensor as means of identification;
3, the present invention utilizes the SIFT algorithm, need not to cut apart more accurately comprising specific marker Background, as long as comprise the image of specific marker in the specific marker background image;
4, the present invention can effectively discern the specific marker that complex background, inclination, deformation, dirt, partial occlusion, light change; Match time is short, is fit to very much the real-time requirement that the Chinese chess robot plays chess;
5, image capturing system of the present invention and image processing system can be transplanted on other Chinese chess robot carriers easily, and the platform of Chinese chess robot is not had specific (special) requirements, and be strong to the adaptability of environment, mobility is strong;
6, the present invention utilizes the corresponding relation of image coordinate and actual coordinate, has realized Chinese chess robot vision location.
Description of drawings
Fig. 1 is the modular structure sketch map of system of the present invention
Fig. 2 connects sketch map for the structure of system of the present invention
Fig. 3 is visual identity, the positioning flow figure that the present invention is based on the SIFT algorithm.
The specific embodiment
By Fig. 1 the system module of realizing chess piece identification and location pendulum chess based on the digital picture recognition technology of SIFT algorithm is shown, it comprises three modules: robot carrier 1, image capturing system 2 and image processing system 3.Image capturing system 2 is low with 3 pairs of robot carriers of image processing system, 1 module dependence, can transplant according to the difference of robot.
The structure that system of the present invention is shown by Fig. 2 connects sketch map, and Chinese chess beginning pendulum game system comprises robot carrier, image capturing system, image processing system, chess piece 6 and chessboard 8, and wherein: robot carrier comprises arm robot 1 and grabs chess player's pawl 7; Image capturing system comprises colour imagery shot 2, data line 3, image data acquiring card 4, terminal control computer 5, also will add light source in case of necessity; Image processing system comprises SIFT identification chess piece program and terminal control computer 5; Colour imagery shot 2 is fixed on the arm robot 1, and colour imagery shot 2 is connected with image data acquiring card 4 on the terminal control computer 5 through data line 3.
Fig. 3 is for the present invention is based on visual identity, the positioning flow figure of SIFT algorithm (yardstick invariant features mapping algorithm), and the key step of pendulum chess is following:
(1) robot is carried out IMAQ at initial position to specific marker scenery, obtain containing the original image of specific marker image;
The specific marker that (2) will obtain, promptly robot handles at the original image of initial position shooting, and is different according to the color of Chinese chess both sides chess piece, at first distinguishes both sides' chess piece through color;
The specific marker original image that (3) will obtain carries out gray scale to be handled; Obtain the gray scale picture of specific marker image; Because the SIFT algorithm can only be discerned the gray scale picture, can not handle colour picture, simultaneously in order to improve real-time; Handle so carry out gray scale, colour picture is processed into the gray scale picture;
(4) utilization SIFT algorithm is handled the image to be identified that obtains; Through detect yardstick spatial extrema point, accurately locate extreme point, describe after these several steps of generation of chess piece for each key point assigned direction parameter and key point; Extract rotation, scale, brightness are changed the SIFT characteristic vector that maintains the invariance; And be stored in the Computer Database, Target Photo is carried out matching treatment, discern the chess piece on the picture;
(5) chess piece that identifies is calculated the coordinate on its relative picture, according to the relation of image coordinate and actual coordinate, its Coordinate Conversion is become actual coordinate again, for robot pendulum chess provides foundation;
(6) the chess piece actual coordinate that calculates is sent to terminal control computer, the chess player's pawl 7 of grabbing of terminal control computer control robot carrier 1 is put chess piece.
In practical application, can be applied to widely in the Chinese chess robot, that realizes the Chinese chess robot puts chess piece fast.The present invention simultaneously is that the chess piece of putting with robot is a platform, realizes the fusion of key technologies such as IMAQ, processing, identification, location, can expand to each application easily.Have very high practical value and commercial value.
Claims (5)
1. Chinese chess beginning pendulum game system comprises robot carrier, image capturing system, image processing system, chess piece (6) and chessboard (8) composition, and wherein: robot carrier comprises arm robot (1) and grabs chess player's pawl (7); Image capturing system comprises colour imagery shot (2), data line (3), image data acquiring card (4), terminal control computer (5); Image processing system comprises SIFT identification chess piece program and terminal control computer (5); Colour imagery shot (2) is fixed on the arm robot (1), and colour imagery shot (2) is connected with image data acquiring card (4) on the terminal control computer (5) through data line (3).
2. Chinese chess beginning pendulum game system according to claim 1, it is characterized in that: image capturing system (2) adds light source.
3. the chess method is put in Chinese chess beginning, and key step is following:
(1) robot is carried out IMAQ at initial position to specific marker scenery, obtain containing the original image of specific marker image;
(2) the specific marker original image that obtains is handled, according to color differentiating both sides chess piece;
(3) the specific marker original image that obtains is carried out gray scale and handle, obtain the gray scale picture of specific marker image;
(4) utilization SIFT algorithm is handled the image to be identified that obtains, and identifies the chess piece on the picture;
(5) chess piece that identifies is calculated the coordinate on its relative picture, according to the relation of image coordinate and actual coordinate, its Coordinate Conversion is become actual coordinate again;
(6) the chess piece actual coordinate that calculates is sent to terminal control computer, chess piece is put by terminal control computer control robot.
4. Chinese chess beginning pendulum chess method according to claim 3, it is characterized in that: described specific marker is the image that robot is taken at initial position.
5. Chinese chess beginning pendulum chess method according to claim 3, it is characterized in that: described SIFT algorithm is a yardstick invariant features mapping algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011100837506A CN102729250A (en) | 2011-04-02 | 2011-04-02 | Chess opening chessman-placing system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011100837506A CN102729250A (en) | 2011-04-02 | 2011-04-02 | Chess opening chessman-placing system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102729250A true CN102729250A (en) | 2012-10-17 |
Family
ID=46985902
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011100837506A Pending CN102729250A (en) | 2011-04-02 | 2011-04-02 | Chess opening chessman-placing system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102729250A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106067025A (en) * | 2016-05-10 | 2016-11-02 | 浙江理工大学 | A kind of recognition methods of Chinese chess beginning in kind |
CN106529531A (en) * | 2016-10-31 | 2017-03-22 | 华南理工大学 | Chinese chess identification system and method based on image processing |
CN107598920A (en) * | 2017-08-23 | 2018-01-19 | 深圳果力智能科技有限公司 | A kind of manipulator of view-based access control model control |
CN107737448A (en) * | 2017-09-30 | 2018-02-27 | 杭州科技职业技术学院 | Automatic Chinese chess machine |
CN107875625A (en) * | 2017-11-23 | 2018-04-06 | 东华大学 | A kind of voice-based Chinese chess is played chess device |
CN108671534A (en) * | 2018-05-21 | 2018-10-19 | 湖南大学 | A kind of robot Chinese chess beginning pendulum chess method and system based on objective contour and framework characteristic |
CN109045676A (en) * | 2018-07-23 | 2018-12-21 | 西安交通大学 | A kind of Chinese chess identification learning algorithm and the robot intelligence dynamicization System and method for based on the algorithm |
CN111738443A (en) * | 2019-05-20 | 2020-10-02 | 北京京东尚科信息技术有限公司 | Data processing method, device, system and computer readable storage medium |
CN113878579A (en) * | 2021-09-30 | 2022-01-04 | 北京市商汤科技开发有限公司 | Chess playing method and device, chess playing robot and computer storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2527324Y (en) * | 2002-03-26 | 2002-12-25 | 龙建 | Chess set distinguished and operated by machine |
CN1448884A (en) * | 2003-04-24 | 2003-10-15 | 上海交通大学 | Chessboard identification system based on visual sensation |
CN101556647A (en) * | 2009-05-20 | 2009-10-14 | 哈尔滨理工大学 | mobile robot visual orientation method based on improved SIFT algorithm |
CN101732852A (en) * | 2008-11-25 | 2010-06-16 | 北京新岸线移动多媒体技术有限公司 | Chess control device and method |
CN202028163U (en) * | 2011-04-02 | 2011-11-09 | 北京石油化工学院 | Chinese chess opening placing system |
-
2011
- 2011-04-02 CN CN2011100837506A patent/CN102729250A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2527324Y (en) * | 2002-03-26 | 2002-12-25 | 龙建 | Chess set distinguished and operated by machine |
CN1448884A (en) * | 2003-04-24 | 2003-10-15 | 上海交通大学 | Chessboard identification system based on visual sensation |
CN101732852A (en) * | 2008-11-25 | 2010-06-16 | 北京新岸线移动多媒体技术有限公司 | Chess control device and method |
CN101556647A (en) * | 2009-05-20 | 2009-10-14 | 哈尔滨理工大学 | mobile robot visual orientation method based on improved SIFT algorithm |
CN202028163U (en) * | 2011-04-02 | 2011-11-09 | 北京石油化工学院 | Chinese chess opening placing system |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106067025A (en) * | 2016-05-10 | 2016-11-02 | 浙江理工大学 | A kind of recognition methods of Chinese chess beginning in kind |
CN106529531A (en) * | 2016-10-31 | 2017-03-22 | 华南理工大学 | Chinese chess identification system and method based on image processing |
CN107598920A (en) * | 2017-08-23 | 2018-01-19 | 深圳果力智能科技有限公司 | A kind of manipulator of view-based access control model control |
CN107737448A (en) * | 2017-09-30 | 2018-02-27 | 杭州科技职业技术学院 | Automatic Chinese chess machine |
CN107737448B (en) * | 2017-09-30 | 2023-12-19 | 杭州科技职业技术学院 | automatic chess machine |
CN107875625A (en) * | 2017-11-23 | 2018-04-06 | 东华大学 | A kind of voice-based Chinese chess is played chess device |
CN108671534A (en) * | 2018-05-21 | 2018-10-19 | 湖南大学 | A kind of robot Chinese chess beginning pendulum chess method and system based on objective contour and framework characteristic |
CN108671534B (en) * | 2018-05-21 | 2020-10-02 | 湖南大学 | Robot chess opening and placing method and system based on target contour and skeleton characteristics |
CN109045676A (en) * | 2018-07-23 | 2018-12-21 | 西安交通大学 | A kind of Chinese chess identification learning algorithm and the robot intelligence dynamicization System and method for based on the algorithm |
CN111738443A (en) * | 2019-05-20 | 2020-10-02 | 北京京东尚科信息技术有限公司 | Data processing method, device, system and computer readable storage medium |
CN113878579A (en) * | 2021-09-30 | 2022-01-04 | 北京市商汤科技开发有限公司 | Chess playing method and device, chess playing robot and computer storage medium |
CN113878579B (en) * | 2021-09-30 | 2023-08-18 | 北京市商汤科技开发有限公司 | Chess playing method, device, chess playing robot and computer storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102729250A (en) | Chess opening chessman-placing system and method | |
CN104463108B (en) | A kind of monocular real time target recognitio and pose measuring method | |
CN101537618B (en) | Visual system for ball picking robot in stadium | |
KR101633359B1 (en) | Marker-less augmented reality system using projective invariant and method the same | |
CN110084243B (en) | File identification and positioning method based on two-dimensional code and monocular camera | |
CN108109174A (en) | A kind of robot monocular bootstrap technique sorted at random for part at random and system | |
CN109461184B (en) | Automatic positioning method for grabbing point for grabbing object by robot mechanical arm | |
CN110443898A (en) | A kind of AR intelligent terminal target identification system and method based on deep learning | |
CN111462154B (en) | Target positioning method and device based on depth vision sensor and automatic grabbing robot | |
CN114952809B (en) | Workpiece identification and pose detection method, system and mechanical arm grabbing control method | |
CN106934833A (en) | A kind of stacking material pick device and method at random | |
CN104766345B (en) | Body scan data and motion capture method based on garment features point | |
CN103093191A (en) | Object recognition method with three-dimensional point cloud data and digital image data combined | |
CN101441769A (en) | Real time vision positioning method of monocular camera | |
CN101556647A (en) | mobile robot visual orientation method based on improved SIFT algorithm | |
CN109045676B (en) | Chinese chess recognition learning algorithm and robot intelligent system and method based on algorithm | |
CN112906797A (en) | Plane grabbing detection method based on computer vision and deep learning | |
CN110089350A (en) | A kind of Mushroom Picking Robot system and picking method | |
CN106422223A (en) | Intelligent robot system for spherical object recycling and method | |
CN107909889B (en) | Gobang man-machine playing experiment teaching system based on visual guidance | |
CN110852186A (en) | Visual identification and picking sequence planning method for citrus on tree and simulation system thereof | |
CN202028163U (en) | Chinese chess opening placing system | |
CN111399634B (en) | Method and device for recognizing gesture-guided object | |
CN111080685A (en) | Airplane sheet metal part three-dimensional reconstruction method and system based on multi-view stereoscopic vision | |
CN204036474U (en) | Industrial robot sorting system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20121017 |