基于全向视觉的足球机器人定位的研究
|
摘要
机器人足球是目前机器人控制、机器视觉、人工智能等领域研究的一个热点。本论文以自主移动机器人为研究平台,以RoboCup中型组机器人足球赛为应用背景,选择并实现了一套由全向反射镜和图像处理软件组成的全向视觉系统,并在此基础上重点进行基于全向视觉的机器人自定位方法的研究。该系统能实时采集较为理想的全景图像,并对之进行分割和处理,使机器人能够精确的获取自身工作环境,根据图像提取的特征进行机器人的自定位和目标识别,从而基本满足比赛的实时性和精确性的要求。
论文的主要研究内容如下:介绍了几种常用的全向反射镜,并根据比赛对视觉系统的各种要求,选用了一套适用于RoboCup中型组比赛的全景视觉系统。针对全景图像设计了图像处理算法,能够快速实现图像分割和特征提取,完成目标识别,在此基础上,针对根据图像提取的特征进行机器人的自定位。根据对机器人运动机构和和全景视觉系统的工作原理的分析,提出一种基于扩展卡尔曼滤波(EKF)的算法将码盘信息和视觉系统采集的数据进行融合,从而完成机器人的自定位。
论文最后对全文进行了总结,说明了研究的主要成果,同时指出自己的不足和有待进一步改进的地方。
Robot soccer is a researchful hotspot of robot control, machine vision and artificial intelligence presently. The thesis designs and implements a novel Omni-vision system for the application in the middle-size league of RoboCup-The World Cup of Soccer Robots and for the platform of autonomous robot, which composed of a camera and a mirror generated with a surface of revolution, and does research on the robot’s self-localization methods based on the Omni-vision system. The system can capture the rather perfect panoramic image real timely, and process and segmentation image, which made robot can get the working environment of itself exactly, and complete robot’s self-localization and recognization of target from the extraction of features, to satisfy the requirement of real time and accuracy of compete.
This paper works over the following contents: introduce several Omni-mirror in common use, and choose a suit of Omni-vision system which is the same with the middle-size league of RoboCup according diversified requirement of compete for vision system. Design a image processing algorithm for the panoramic image, which can segment the image by color, extract the features of image fast and effectively and complete the recognization of target, and then realize the robot’s self-localization based on the character of the imaging. Put forward an extend kalman filter(EKF) arithmetic based on the analysis of robot sport framework and theory of panorama vision system, which amalgamation the data information from mile meter and vision system, and then complete robot’s self-localization.
Lastly, the thesis summarizes the whole paper, make out the main researchful fruit, at the same time point out the deficiency and places need to be improved.
论文的主要研究内容如下:介绍了几种常用的全向反射镜,并根据比赛对视觉系统的各种要求,选用了一套适用于RoboCup中型组比赛的全景视觉系统。针对全景图像设计了图像处理算法,能够快速实现图像分割和特征提取,完成目标识别,在此基础上,针对根据图像提取的特征进行机器人的自定位。根据对机器人运动机构和和全景视觉系统的工作原理的分析,提出一种基于扩展卡尔曼滤波(EKF)的算法将码盘信息和视觉系统采集的数据进行融合,从而完成机器人的自定位。
论文最后对全文进行了总结,说明了研究的主要成果,同时指出自己的不足和有待进一步改进的地方。
Robot soccer is a researchful hotspot of robot control, machine vision and artificial intelligence presently. The thesis designs and implements a novel Omni-vision system for the application in the middle-size league of RoboCup-The World Cup of Soccer Robots and for the platform of autonomous robot, which composed of a camera and a mirror generated with a surface of revolution, and does research on the robot’s self-localization methods based on the Omni-vision system. The system can capture the rather perfect panoramic image real timely, and process and segmentation image, which made robot can get the working environment of itself exactly, and complete robot’s self-localization and recognization of target from the extraction of features, to satisfy the requirement of real time and accuracy of compete.
This paper works over the following contents: introduce several Omni-mirror in common use, and choose a suit of Omni-vision system which is the same with the middle-size league of RoboCup according diversified requirement of compete for vision system. Design a image processing algorithm for the panoramic image, which can segment the image by color, extract the features of image fast and effectively and complete the recognization of target, and then realize the robot’s self-localization based on the character of the imaging. Put forward an extend kalman filter(EKF) arithmetic based on the analysis of robot sport framework and theory of panorama vision system, which amalgamation the data information from mile meter and vision system, and then complete robot’s self-localization.
Lastly, the thesis summarizes the whole paper, make out the main researchful fruit, at the same time point out the deficiency and places need to be improved.
引文
[1]李实,徐旭明,叶榛等.国家机器人足球比赛及相关技术.机器人robot, 2000,5: 420-426.
[2] Akira Motomura, TaReshi Matsuoka, Tsutomu Hasegawa, Self-localization Method Using Two Landmarks and Dead Reckoning for Autonomous Mobile soccer Robots. RoboCup 2003:526-533
[3]卢绍芳,刘大维.自主式移动机器人导航研究现状及相关技术.农业机械学报2002,33(2):112-116
[4]于秀芬.轮式移动机器人视觉定位与目标跟踪:[南京航空航天大学硕士论文].南京:南京航空航天大学,2004
[5]曾大幸.中型组足球机器人的视觉识别与视觉定位研究:[燕山大学硕士论文].秦皇岛:燕山大学,2004
[6]王亮.智能移动机器人定位技术研究:[哈尔滨工程大学硕士论文].哈尔滨:哈尔滨工程大学,2003
[7]董再励,王光辉.自主移动机器人激光全局定位系统研究.机器人,2000
[8]崔峰.基于GPS|GZS|GSM的移动机器人定位技术研究.河北工业大学,2004
[9]张毅,罗元,郑太雄等.移动机器人技术及应用.北京:电子工业出版社,2007
[10] Stroupea, Sikosiki K, Balch T. Constraint-Based Lardmark Localization. RoboCup 2002. Heidelberg springer-Verlag. 2002:8-24
[11] Yingjie Ye, Yirung Yang. Li T. Full autonomous middle size soccer robot. IEEE International Conference on Intelligent Robots and systems, 2005, 451-456
[12]田梦倩,罗翔,黄惟一.视觉伺服机器人对运动目标操作的研究.机器人,2003,25(6):549-554
[13] Simon BaRer and shree K. Nayar, A theory of catadioptric image formation. submitted to IJCV, 1997, Also appears in ICCV98, and exists as TR CUCS-015-97, and it was presented in Darpa Iuw1997.
[14] R.A.HicRs, R. Bajcsy, Reflective Surfaces as Computational Sensors. IEEE Workshop on Perception for Mobile Agents, 1999, 15(2):165-170
[15] H.Ishiguro. Development of Low-Cost and Compact Omni-directional Vision Secsors and their Applications. In: Proc of Int Conf.Information systems analysis and synthesis, 1998, 5:433-439
[16] Zeng Jiyong, Su Xianyu. Hyperboloidal catadioptric Omni-directional imaging system. Acta Optica sinica, 2003, 23(9):1138-1142
[17] Sun Tien-Lung. Conics enhanced vision approach for easy and low-cost 3D tracking. Pattern Recognition, 2004, 37(7):1441-1450
[18] Yang M, Li G, Wang Hetai. Vision-Based Real-Time Vehicle Guidance on THMR-V. Prceedings of the International Symposium on Test and Measurement, 2001, 2:1371-1375
[19]陶霖密,徐光祐.机器视觉中的颜色问题及应用.科学通报,2001年03期
[20]邵丹,韩家伟.YUV与RGB之间的转换.长春大学学报,2004,14(4):51-53
[21]沈庭芝,方子文.数字图像处理及模式识别.北京:北京理工大学出版社,1998:152-159
[22]闫成新.基于区域的图像分割技术研究.武汉:华中科技大学,2004
[23]刘文萍,吴立德.图像分割中阈值选取方法比较研究.模式识别与人工智能,1997,10(3):329-335
[24]左奇,史忠科.一种基于直方图评价函数的快速图像分割方法.计算机工程与应用,2003,39(19):5-6,20
[25] Thrun S. Probabilistic Algorithms in Robotics .AI Magazine, 2000, 21(4):93-109
[26] Kai-Tai Song, Chao-Wu Wang. Self-Localization and Control of an Omni- Directional Mobile Robot Based on an Omni-Directional Camera. In: Proc of the 7th Asian Control Conference. Hong Kong, 2009, 899-90
[27]何友,王国宏,彭应宁.多传感信息融合及应用.北京:电子工业出版社,2000:21-86
[28]王仲民,岳宏,刘继岩.移动机器人多传感器信息融合技术述评.传感器技术,2005,24(4):5-7
[29]刘瑜,朱世强,金波.移动机器人Markov定位算法的研究.浙江大学学报,2005,39(3):339-341
[30]厉茂海,洪炳熔.移动机器人的概率定位方法研究进展.机器人, 2005, 27(4): 380-383
[31]王文学,王强,孙萍.卡尔曼滤波在机器人足球比赛系统中的应用.机器人,2006,28(4):410-414
[32] Arnau Ramisa, Adriana Tapus. Mobile Robot Localization using Panoramic Vision and Combinations of Feature Region Detectors. In: Proc of Int Conf on Robotics and Automation, Pasadena, CA, USA, 2008, 538-543
[33]张德丰. MATLAB数字图像处理机械.北京:工业出版社, 2009
[34]殷国军,秦莉.图像分割方法研究综述.河北工程技术高等专科学校学报, 2009, (2): 9-11?
[2] Akira Motomura, TaReshi Matsuoka, Tsutomu Hasegawa, Self-localization Method Using Two Landmarks and Dead Reckoning for Autonomous Mobile soccer Robots. RoboCup 2003:526-533
[3]卢绍芳,刘大维.自主式移动机器人导航研究现状及相关技术.农业机械学报2002,33(2):112-116
[4]于秀芬.轮式移动机器人视觉定位与目标跟踪:[南京航空航天大学硕士论文].南京:南京航空航天大学,2004
[5]曾大幸.中型组足球机器人的视觉识别与视觉定位研究:[燕山大学硕士论文].秦皇岛:燕山大学,2004
[6]王亮.智能移动机器人定位技术研究:[哈尔滨工程大学硕士论文].哈尔滨:哈尔滨工程大学,2003
[7]董再励,王光辉.自主移动机器人激光全局定位系统研究.机器人,2000
[8]崔峰.基于GPS|GZS|GSM的移动机器人定位技术研究.河北工业大学,2004
[9]张毅,罗元,郑太雄等.移动机器人技术及应用.北京:电子工业出版社,2007
[10] Stroupea, Sikosiki K, Balch T. Constraint-Based Lardmark Localization. RoboCup 2002. Heidelberg springer-Verlag. 2002:8-24
[11] Yingjie Ye, Yirung Yang. Li T. Full autonomous middle size soccer robot. IEEE International Conference on Intelligent Robots and systems, 2005, 451-456
[12]田梦倩,罗翔,黄惟一.视觉伺服机器人对运动目标操作的研究.机器人,2003,25(6):549-554
[13] Simon BaRer and shree K. Nayar, A theory of catadioptric image formation. submitted to IJCV, 1997, Also appears in ICCV98, and exists as TR CUCS-015-97, and it was presented in Darpa Iuw1997.
[14] R.A.HicRs, R. Bajcsy, Reflective Surfaces as Computational Sensors. IEEE Workshop on Perception for Mobile Agents, 1999, 15(2):165-170
[15] H.Ishiguro. Development of Low-Cost and Compact Omni-directional Vision Secsors and their Applications. In: Proc of Int Conf.Information systems analysis and synthesis, 1998, 5:433-439
[16] Zeng Jiyong, Su Xianyu. Hyperboloidal catadioptric Omni-directional imaging system. Acta Optica sinica, 2003, 23(9):1138-1142
[17] Sun Tien-Lung. Conics enhanced vision approach for easy and low-cost 3D tracking. Pattern Recognition, 2004, 37(7):1441-1450
[18] Yang M, Li G, Wang Hetai. Vision-Based Real-Time Vehicle Guidance on THMR-V. Prceedings of the International Symposium on Test and Measurement, 2001, 2:1371-1375
[19]陶霖密,徐光祐.机器视觉中的颜色问题及应用.科学通报,2001年03期
[20]邵丹,韩家伟.YUV与RGB之间的转换.长春大学学报,2004,14(4):51-53
[21]沈庭芝,方子文.数字图像处理及模式识别.北京:北京理工大学出版社,1998:152-159
[22]闫成新.基于区域的图像分割技术研究.武汉:华中科技大学,2004
[23]刘文萍,吴立德.图像分割中阈值选取方法比较研究.模式识别与人工智能,1997,10(3):329-335
[24]左奇,史忠科.一种基于直方图评价函数的快速图像分割方法.计算机工程与应用,2003,39(19):5-6,20
[25] Thrun S. Probabilistic Algorithms in Robotics .AI Magazine, 2000, 21(4):93-109
[26] Kai-Tai Song, Chao-Wu Wang. Self-Localization and Control of an Omni- Directional Mobile Robot Based on an Omni-Directional Camera. In: Proc of the 7th Asian Control Conference. Hong Kong, 2009, 899-90
[27]何友,王国宏,彭应宁.多传感信息融合及应用.北京:电子工业出版社,2000:21-86
[28]王仲民,岳宏,刘继岩.移动机器人多传感器信息融合技术述评.传感器技术,2005,24(4):5-7
[29]刘瑜,朱世强,金波.移动机器人Markov定位算法的研究.浙江大学学报,2005,39(3):339-341
[30]厉茂海,洪炳熔.移动机器人的概率定位方法研究进展.机器人, 2005, 27(4): 380-383
[31]王文学,王强,孙萍.卡尔曼滤波在机器人足球比赛系统中的应用.机器人,2006,28(4):410-414
[32] Arnau Ramisa, Adriana Tapus. Mobile Robot Localization using Panoramic Vision and Combinations of Feature Region Detectors. In: Proc of Int Conf on Robotics and Automation, Pasadena, CA, USA, 2008, 538-543
[33]张德丰. MATLAB数字图像处理机械.北京:工业出版社, 2009
[34]殷国军,秦莉.图像分割方法研究综述.河北工程技术高等专科学校学报, 2009, (2): 9-11?