基于双目视觉的多介质空间运动目标跟踪定位技术研究
|
摘要
应用双目视觉技术对目标进行三维测量以及动态跟踪定位是当今计算机视觉领域的研究热点,它已经广泛应用于军事视觉制导、机器人视觉导航、交通管理以及工业检测等领域。由于受环境、设备等的影响,如何提高测量精度,并且能够在多介质情况下对多目标进行正确的动态跟踪识别成为实际应用中面临的难点问题。
论文以双目视觉技术为基础,设计开发了多介质空间运动目标跟踪定位系统。论文首先以张正友摄像机标定原理为基础,设计了新型的标定板及配套的标定板检测算法,将检测精度提高到亚像素级别,进而提高了标定精度；其次,在运动目标的检测与跟踪方面,论文重点解决了传统的Mean-Shift算法容易产生的跟踪丢失问题,结合Kalman算法,研究了融合运动目标位置预测的跟踪算法,有效提高了多目标动态跟踪识别的准确度；最后,论文依据光线在临界面的折射原理,结合空间几何理论,研究了多介质情况下目标的视觉测量理论,建立了数学模型并对其进行了测试。
实验数据表明,本系统测量精度较高,稳定性好,能够实现在多介质情况下对多目标进行实时的动态跟踪及定位,满足实际工程的要求,具有很好的应用和推广价值。
The application of binocular vision techniques on three-dimensional measurement and the moving object tracking and locating is a hot research topic in computer vision, which has been used widely in the military vision-guided, robot visual navigation, traffic management and industrial inspection and other fields. Due to the impact of environment and equipment, how to improve the measuring accuracy, track and identify dynamic objects correctly in multi-media is a difficult problem for practical applications at present.
Based on the principle of binocular vision, a system for tracking and locating moving objects in multi-media space is designed in the paper. Firstly, the calibration board and corresponding detection algorithm is designed based on Zhang Zhengyou binocular camera calibration principle, which improves detection accuracy up to sub-pixel level, thus the accuracy of calibration is improved; On moving objects detecting and tracking, since Mean-Shift algorithm doesn't contain object's motion information in the process of object tracking, it easily fails to track the objects, an improved algorithm combined with Kalman filtering is proposed in the paper, which improves the accuracy of detecting and tracking moving objects effectively; Then, Combined the refraction theory of light in the critical surface with the spatial geometry theory, the principle of visual measurement in multi-media is researched, and a mathematical model is constructed and tested in the paper.
Finally, the whole system is set up and tested, experiment result shows that this system is precise and stable, and it can realize tracking and extracting 3D coordinates of moving objects in multi-media, meet practical requirements, and it is worthy for using and promoting.
论文以双目视觉技术为基础,设计开发了多介质空间运动目标跟踪定位系统。论文首先以张正友摄像机标定原理为基础,设计了新型的标定板及配套的标定板检测算法,将检测精度提高到亚像素级别,进而提高了标定精度；其次,在运动目标的检测与跟踪方面,论文重点解决了传统的Mean-Shift算法容易产生的跟踪丢失问题,结合Kalman算法,研究了融合运动目标位置预测的跟踪算法,有效提高了多目标动态跟踪识别的准确度；最后,论文依据光线在临界面的折射原理,结合空间几何理论,研究了多介质情况下目标的视觉测量理论,建立了数学模型并对其进行了测试。
实验数据表明,本系统测量精度较高,稳定性好,能够实现在多介质情况下对多目标进行实时的动态跟踪及定位,满足实际工程的要求,具有很好的应用和推广价值。
The application of binocular vision techniques on three-dimensional measurement and the moving object tracking and locating is a hot research topic in computer vision, which has been used widely in the military vision-guided, robot visual navigation, traffic management and industrial inspection and other fields. Due to the impact of environment and equipment, how to improve the measuring accuracy, track and identify dynamic objects correctly in multi-media is a difficult problem for practical applications at present.
Based on the principle of binocular vision, a system for tracking and locating moving objects in multi-media space is designed in the paper. Firstly, the calibration board and corresponding detection algorithm is designed based on Zhang Zhengyou binocular camera calibration principle, which improves detection accuracy up to sub-pixel level, thus the accuracy of calibration is improved; On moving objects detecting and tracking, since Mean-Shift algorithm doesn't contain object's motion information in the process of object tracking, it easily fails to track the objects, an improved algorithm combined with Kalman filtering is proposed in the paper, which improves the accuracy of detecting and tracking moving objects effectively; Then, Combined the refraction theory of light in the critical surface with the spatial geometry theory, the principle of visual measurement in multi-media is researched, and a mathematical model is constructed and tested in the paper.
Finally, the whole system is set up and tested, experiment result shows that this system is precise and stable, and it can realize tracking and extracting 3D coordinates of moving objects in multi-media, meet practical requirements, and it is worthy for using and promoting.
引文
[1]杨剑.大尺寸视觉测量精度的理论和实验研究[D].北京：北京邮电大.2010
[2]徐德,谭民,李原.机器人视觉测量与控制[M].北京：国防工业出版社.2008
[3]Asada M, Tanaka T, Hosoda K. Visual tracking of unknown moving object by adaptive binocular visual servoing[C].International Conference on Multi-sensor Fusion and Integration for Intelligent System,Taiwan,China,1999:249-254
[4]Okada K, Inaba M, Inoue H. Integration of real-time binocular stereo vision and whole body information for dynamic walking navigation of humanoid robot[C]. International Conference on Multi-sensor Fusion and Integration for Intelligent System, Tokyo, Japan, 2003:131-136
[5]Olson C F, Abi-Rached H, Ming Y, et al. Wide-baseline stereo vision for Mars rovers [C].International Conference on Intelligent Robots and Systems, Nevada, USA,2003: 1302-1307
[6]Kim Hong-Jae, You Bum-Jae, etai. Three-dimensional pose determination for a humanoid robot using binocular head system[A].IEEE International Conference on Intelligent Robots and Systems[C]. Institute of Electrical and Electronics Engineers Inc, 1999:1204-1209
[7]高庆吉,洪炳熔,阮玉峰.基于异构双目视觉的全自主足球机器人导航[J].哈尔滨工业大学学报.2003,35(9)
[8]管业鹏,童林夙,陈娜.基于双目立体视觉的偏转线圈测量方法研究[J].电子学报.2003,09
[9]张春森.序列立体图像三维运动物体定位与跟踪[D].武汉：武汉大学.2004
[10]张广军.视觉测量[M].北京：科学出版社.2008
[11]吴亚鹏.基于双目视觉的运动目标跟踪与三维测量[D].西安：西北大学.2008
[12]李伟,吕晓旭.基于平面模版的摄像机标定方法比较[J].激光杂志.2006
[13]R.Y.Tsai. An efficient and accurate camera calibration technique for 3D machine vision, Proceedings of IEEE Conference On Computer Vision and Pattern Recognition.1986
[14]Zhengyou Zhang. A Flexible New Technique for Camera Calibration[J], IEEE Transactions on Pattern Analysis and Machine Intelligence.2000
[15]唐志豪.基于双目立体视觉的测量技术研究[D].江苏大学.2006
[16]Lourakis, I. A. A Brief Description of the Levenberg-Marquardt Algorithm Implemented by levmar[J]. Institute of Computer Science Foundation for Research and Technology.2005
[17]马颂德,张正友.计算机视觉[M].北京：科学出版社.1998
[18]张广军.机器视觉[M].北京：科学出版社.2005
[19]赵文彬,张艳宁.角点检测技术综述[J].计算机应用研究.2006
[20]郭海霞,解凯.角点检测技术的研究[J].哈尔滨师范大学自然科学学报.2007
[21]Canny J F. A computational approach to edge detection[J]. IEEE Transaction on Pattern Anlysis and Machine Intelligence,1986,8(6):679-698
[22]Xi'ang, Liu, et al. Cocoon edge detection based on self-adaptive Canny operator[J]. Computer Science and Software Engineering,2008
[23]黄桂平.圆形标志中心子像素定位方法的研究与实现[J].武汉大学学报.2005
[24]贾云得.机器视觉[M].北京：北京科学出版社.2000
[25]刘书桂,李蓬,那永林.基于最小二乘原理的平面任意位置椭圆的评价[J].计量学报.2002.10
[26]张娟,毛晓波,陈铁军.运动目标跟踪算法研究综述[J].计算机应用研究.2009
[27]Gary Bradski, Adrain Kaebler. Learning OpenCV[M]. the United States of America: O'Reilly Media, Inc.2008
[28]Fukunage K. Hostetler L. D. The estimation of the gradient of a density function with application in pattern recognition[J]. IEEE Trans. Information Theory,1975
[29]Cheng Y. Mean Shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8)
[30]朱胜利.MeanShift及相关算法在视频跟踪中的研究[D].浙江大学.2006
[31]常发亮,刘雪,王华杰.基于均值漂移与卡尔曼滤波的目标跟踪算法[J].计算机工程与应用.2007
[32]Swain, M.J. and D.H.Ball. Color Indexing[J]. International journal of computer vision. 1991
[33]朱凤茹.运动物体跟踪方法研究及应用[D].中山大学.2007
[34]汪颖进.目标跟踪过程中的遮挡问题研究[D].华中科技大学.2004
[35]韩振军.视频目标跟踪中的特征评估算法研究[D].中国科学院研究生院.2009
[36]D. Comaniciu, V. Ramesh, and P. Meer. Real-Time Tracking of Non-Rigid Objects Using Mean Shift [J]. Computer Vision and Pattern Recognition.2000
[37]Michael J. Swain and Dana H. Ballard. Color Indexing[J]. International Journal of Computer Vision.1991
[38]崔宇巍.运动目标检测与跟踪中有关问题的研究[D].西北大学.2005
[39]Smithanik J R. Optimal vision-based position estimation of an underwater space simulation vehicle[J]. University of Maryland, College Park,2004
[40]Smithanik J R, Atkins E M, and Sanner R M. Visual positioning system for an underwater space simulation environment[J]. Journal of Guidance, Control, and Dynamics,2006,29(4):858-869
[41]Peasco R S. A vision-based underwater three dimensional positioning system[J]. University of Maryland, College Park,2002
[42]Rosendall P E. Enhanced algorithms for an underwater visual positioning system[J]. 45th AIAA Aerospace Sciences Meeting and Exhibit.2007
[43]王俊,朱战霞,贾国华,张旭阳.基于视觉系统的双介质下目标定位[J].科学技术与工程.2010.11
[2]徐德,谭民,李原.机器人视觉测量与控制[M].北京：国防工业出版社.2008
[3]Asada M, Tanaka T, Hosoda K. Visual tracking of unknown moving object by adaptive binocular visual servoing[C].International Conference on Multi-sensor Fusion and Integration for Intelligent System,Taiwan,China,1999:249-254
[4]Okada K, Inaba M, Inoue H. Integration of real-time binocular stereo vision and whole body information for dynamic walking navigation of humanoid robot[C]. International Conference on Multi-sensor Fusion and Integration for Intelligent System, Tokyo, Japan, 2003:131-136
[5]Olson C F, Abi-Rached H, Ming Y, et al. Wide-baseline stereo vision for Mars rovers [C].International Conference on Intelligent Robots and Systems, Nevada, USA,2003: 1302-1307
[6]Kim Hong-Jae, You Bum-Jae, etai. Three-dimensional pose determination for a humanoid robot using binocular head system[A].IEEE International Conference on Intelligent Robots and Systems[C]. Institute of Electrical and Electronics Engineers Inc, 1999:1204-1209
[7]高庆吉,洪炳熔,阮玉峰.基于异构双目视觉的全自主足球机器人导航[J].哈尔滨工业大学学报.2003,35(9)
[8]管业鹏,童林夙,陈娜.基于双目立体视觉的偏转线圈测量方法研究[J].电子学报.2003,09
[9]张春森.序列立体图像三维运动物体定位与跟踪[D].武汉：武汉大学.2004
[10]张广军.视觉测量[M].北京：科学出版社.2008
[11]吴亚鹏.基于双目视觉的运动目标跟踪与三维测量[D].西安：西北大学.2008
[12]李伟,吕晓旭.基于平面模版的摄像机标定方法比较[J].激光杂志.2006
[13]R.Y.Tsai. An efficient and accurate camera calibration technique for 3D machine vision, Proceedings of IEEE Conference On Computer Vision and Pattern Recognition.1986
[14]Zhengyou Zhang. A Flexible New Technique for Camera Calibration[J], IEEE Transactions on Pattern Analysis and Machine Intelligence.2000
[15]唐志豪.基于双目立体视觉的测量技术研究[D].江苏大学.2006
[16]Lourakis, I. A. A Brief Description of the Levenberg-Marquardt Algorithm Implemented by levmar[J]. Institute of Computer Science Foundation for Research and Technology.2005
[17]马颂德,张正友.计算机视觉[M].北京：科学出版社.1998
[18]张广军.机器视觉[M].北京：科学出版社.2005
[19]赵文彬,张艳宁.角点检测技术综述[J].计算机应用研究.2006
[20]郭海霞,解凯.角点检测技术的研究[J].哈尔滨师范大学自然科学学报.2007
[21]Canny J F. A computational approach to edge detection[J]. IEEE Transaction on Pattern Anlysis and Machine Intelligence,1986,8(6):679-698
[22]Xi'ang, Liu, et al. Cocoon edge detection based on self-adaptive Canny operator[J]. Computer Science and Software Engineering,2008
[23]黄桂平.圆形标志中心子像素定位方法的研究与实现[J].武汉大学学报.2005
[24]贾云得.机器视觉[M].北京：北京科学出版社.2000
[25]刘书桂,李蓬,那永林.基于最小二乘原理的平面任意位置椭圆的评价[J].计量学报.2002.10
[26]张娟,毛晓波,陈铁军.运动目标跟踪算法研究综述[J].计算机应用研究.2009
[27]Gary Bradski, Adrain Kaebler. Learning OpenCV[M]. the United States of America: O'Reilly Media, Inc.2008
[28]Fukunage K. Hostetler L. D. The estimation of the gradient of a density function with application in pattern recognition[J]. IEEE Trans. Information Theory,1975
[29]Cheng Y. Mean Shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8)
[30]朱胜利.MeanShift及相关算法在视频跟踪中的研究[D].浙江大学.2006
[31]常发亮,刘雪,王华杰.基于均值漂移与卡尔曼滤波的目标跟踪算法[J].计算机工程与应用.2007
[32]Swain, M.J. and D.H.Ball. Color Indexing[J]. International journal of computer vision. 1991
[33]朱凤茹.运动物体跟踪方法研究及应用[D].中山大学.2007
[34]汪颖进.目标跟踪过程中的遮挡问题研究[D].华中科技大学.2004
[35]韩振军.视频目标跟踪中的特征评估算法研究[D].中国科学院研究生院.2009
[36]D. Comaniciu, V. Ramesh, and P. Meer. Real-Time Tracking of Non-Rigid Objects Using Mean Shift [J]. Computer Vision and Pattern Recognition.2000
[37]Michael J. Swain and Dana H. Ballard. Color Indexing[J]. International Journal of Computer Vision.1991
[38]崔宇巍.运动目标检测与跟踪中有关问题的研究[D].西北大学.2005
[39]Smithanik J R. Optimal vision-based position estimation of an underwater space simulation vehicle[J]. University of Maryland, College Park,2004
[40]Smithanik J R, Atkins E M, and Sanner R M. Visual positioning system for an underwater space simulation environment[J]. Journal of Guidance, Control, and Dynamics,2006,29(4):858-869
[41]Peasco R S. A vision-based underwater three dimensional positioning system[J]. University of Maryland, College Park,2002
[42]Rosendall P E. Enhanced algorithms for an underwater visual positioning system[J]. 45th AIAA Aerospace Sciences Meeting and Exhibit.2007
[43]王俊,朱战霞,贾国华,张旭阳.基于视觉系统的双介质下目标定位[J].科学技术与工程.2010.11