基于多传感器信息融合的同步定位与地图创建研究
|
摘要
随着社会信息化技术的发展,工业、农业、科研、国防等各个领域越来越需要高性能的自动化系统。特别是在机器人与自动化领域,更是引起了很多人的兴趣。当前世界各地的机器人公司和科研机构正加紧开发研制各种智能移动服务机器人来代替人类工作,例如开发研制各种自主车辆系统,用于安全驾驶或者军事。在所有这些应用中,机器人自主导航是一个最基本的需求,而机器人定位又是自主导航的最基本内容,并且现代定位方法是结合内、外部传感器的基于环境地图的定位方法。换言之,定位和地图创建是研究未知环境下移动机器人导航技术所涉及的两个主要内容。它们之间并非相互独立,在考虑到所有传感器信息都具有不确定性的情况下,单独考虑其中一个问题是不符合实际情况的。
本文主要研究基于不确定信息的自主移动机器人(Autonomous Mobile Robot, AMR)同步定位与地图创建(Simultaneous Localization and Mapping,SLAM)问题,旨在构建一个完整的系统,使得机器人在未知结构化环境下实现“自主”定位与地图开发的能力。首先对不同的传感器进行了分析与比较;其次,分析了单个机器人在未知环境下同步定位与地图创建问题。在环境的特征提取中,采用了一种基于新的多尺度几何分析工具——Ridgelet进行线段特征的提取,并采用小波变换阈值法去除干扰点的方法。由于Ridgelet在检测直线奇异性,以及小波在检测点状奇异性上的优势,本方法能提取到更为准确的特征;最后,在回顾和总结目前存在的移动机器人同步定位与地图创建方法的基础上,提出了一种基于多传感器信息融合的扩展卡尔曼滤波(Extended Kalman Filter, EKF)方法,实现了机器人的高精度定位,并将定位结果应用于地图创建,从而构成了完整的SLAM系统。室内结构化环境下的仿真实验结果证明,系统准确性高而且具有较好的实时性和鲁棒性,达到了设计要求。仿真结果证明了作者提出方法的有效性。
Autonomous system is required increasingly in the fields of industry, agriculture, scientific research and national defence along with the development to information technology. More and more research is focused on robot and robotization robot company and research institute are developing various service robots to work instead of human and developing autonomous land vehicle for the sake of safe drive or military affairs. Autonomous navigation is necessary, and localization is a funda- mental problem for autonomous navigation and modern localization method is based on environment map with interoceptive and exteroceptive sensor. In other words, mobile robot navigation in unknown environment involves two important components: localization and mapping. They are not independent mutually considering that all sensor information is uncertainty. So dealing with only one of them does not agree with the physical world.
This paper focused on Simultaneous Localization and Mapping (SLAM) of Autonomous Mobile Robots (AMR) based on uncertainty environmental information, in order to build a complete system that makes robots have the ability of autonomous map development in unknown structural environment. Firstly various kinds of sensors are compared and analyzed, secondly the single mobile robot simultaneous 1ocalization and mapping(SLAM) under unknown environment is deeply investigated. For the feature extraction from environment, we proposed a ridgelet based method for straight line feature and then used wavelet thresholding to smooth away the disturbance points, which combines the superiority of ridgelet in detecting linear singularities and wavelet in detecting point-like singularities together to get more accurate features. At last, we also realize precise localization using Extended Kalman Filter (EKF) based on multi-sensor fusion, and apply localization results to map building to form complete SLAM system. The indoor experimental results demonstrate the accuracy, real-time, and robustness of SLAM system, and fulfills the design requires completely.
本文主要研究基于不确定信息的自主移动机器人(Autonomous Mobile Robot, AMR)同步定位与地图创建(Simultaneous Localization and Mapping,SLAM)问题,旨在构建一个完整的系统,使得机器人在未知结构化环境下实现“自主”定位与地图开发的能力。首先对不同的传感器进行了分析与比较;其次,分析了单个机器人在未知环境下同步定位与地图创建问题。在环境的特征提取中,采用了一种基于新的多尺度几何分析工具——Ridgelet进行线段特征的提取,并采用小波变换阈值法去除干扰点的方法。由于Ridgelet在检测直线奇异性,以及小波在检测点状奇异性上的优势,本方法能提取到更为准确的特征;最后,在回顾和总结目前存在的移动机器人同步定位与地图创建方法的基础上,提出了一种基于多传感器信息融合的扩展卡尔曼滤波(Extended Kalman Filter, EKF)方法,实现了机器人的高精度定位,并将定位结果应用于地图创建,从而构成了完整的SLAM系统。室内结构化环境下的仿真实验结果证明,系统准确性高而且具有较好的实时性和鲁棒性,达到了设计要求。仿真结果证明了作者提出方法的有效性。
Autonomous system is required increasingly in the fields of industry, agriculture, scientific research and national defence along with the development to information technology. More and more research is focused on robot and robotization robot company and research institute are developing various service robots to work instead of human and developing autonomous land vehicle for the sake of safe drive or military affairs. Autonomous navigation is necessary, and localization is a funda- mental problem for autonomous navigation and modern localization method is based on environment map with interoceptive and exteroceptive sensor. In other words, mobile robot navigation in unknown environment involves two important components: localization and mapping. They are not independent mutually considering that all sensor information is uncertainty. So dealing with only one of them does not agree with the physical world.
This paper focused on Simultaneous Localization and Mapping (SLAM) of Autonomous Mobile Robots (AMR) based on uncertainty environmental information, in order to build a complete system that makes robots have the ability of autonomous map development in unknown structural environment. Firstly various kinds of sensors are compared and analyzed, secondly the single mobile robot simultaneous 1ocalization and mapping(SLAM) under unknown environment is deeply investigated. For the feature extraction from environment, we proposed a ridgelet based method for straight line feature and then used wavelet thresholding to smooth away the disturbance points, which combines the superiority of ridgelet in detecting linear singularities and wavelet in detecting point-like singularities together to get more accurate features. At last, we also realize precise localization using Extended Kalman Filter (EKF) based on multi-sensor fusion, and apply localization results to map building to form complete SLAM system. The indoor experimental results demonstrate the accuracy, real-time, and robustness of SLAM system, and fulfills the design requires completely.
引文
[1]王耀南.机器人智能控制技术工程[M].北京:科学出版社,2004.
[2] Nilsson N J. A mobile automation: An application of artificial intelligence techniques[C]. Proceedings of the 1st Int. Joint Conference on Artificial Intelligence,Washington D.C. 1969 509-520.
[3] Shhaidi R, Shayman M, Krishnaprasad P S. Mobile robot navigation using potential functions[C]. In Proc. IEEE International Conference on Robotics and Automation, New York,1991: 2047- 2053.
[4] Borenstein J, Koren Y. Real-time obstacle avoidance for fast mobile robots in clustered environments[J]. IEEE Transactions on Systems. Man. and Cybernetics, 1989, 19(5):1179-1187.
[5] Koren Y, Borenstein J. Potential field methods and their inherent limitations for mobile robot navigation[C]. In Proc. IEEE International Conference on Robotics and Automation, California, 1991: 1398-1404.
[6] H F Durrant-Whyte. Where am I? A tutorial on mobile vehicle localization[J]. Industrial Robot, 21(2) :11-16,1994.
[7] J Guivant, E Nebot, and S Baiker. High accuracy navigation using laser angles sensors in out door applications[C]. IEEE International Conference on Robotics and Automation, 2000, 2:2512- 2517.
[8] J Guivant, E Nebot and S Baiker. Localization and map building using laser range sensors in out door applications[J]. Journal of Robotic Systems, 2000,1: 565-583.
[9] E M Nebot, H F Durrant-Whyte, and S Scheding. Frequency domain modeling of aided GPS for vehicle navigation systems. Journal of Robotics and Autonomous Systems, 1998(25): 73-82 .
[10] E M Nebot, S Scheding, and H F Durrant-Whyte. Kalman Filtering design techniques for aided GPS land navigation applications. Proceedings 1st Australian Data Fusion Symposium, 1996, pp .83-89.
[11]杨毅,智能机器人的研究与开发[D].河北工业大学硕士论文,2004, 3.
[12]何克忠,郭木河.智能移动机器人技术研究[J].机器人技术与应用, 1996.
[13]张朋飞,何克忠,欧阳正柱等.多功能室外智能移动机器人实验平台—THRM-V[J].机器人,2002,24(2):97-101.
[14]田宇,吴镇炜,柳长春.开放式三自由度全方位移动机器人实验平台[J].机器人,200,224(2): 102-111.
[15]孙振平,安向京,贺汉根. CITAVT-Ⅳ—视觉导航的自主车[J].机器人,2002,24(2):115-121.
[16]张纯刚,席裕庚.动态未知环境中移动机器人的滚动路径规划[J].机器人,2002,24(1):69-75.
[17]郭琦,洪炳熔.基于人工神经网络实现智能机器人的避障轨迹控制[J].机器人,2002,2(6):508-512.
[18] Csorba M. Simultaneous localization and map building[D]. Oxford: University of Oxford, 1997.
[19] Smith R, Self M, Chesseman P. Estimating uncertain spatial relationships in robotics[A]. Proceedings of Conference on Uncertainty in Artificial Intelligence[C]. Amsterdam: North- holland, 1988, 435-461.
[20]王璐,蔡智兴.未知环境中移动机器人并发建图与定位(CLM)的研究进展[J].机器人,2004,26(4):380-384.
[21] Elefs A, Moravec H. High resolution maps from wide angle sonar [C]//Proc of the IEEE 1nt Conf. on Robots and Automation. St. Louis MO: IEEE Press, 1985: 116-121.
[22] Borenstein J, Everett H R, Feng L, et al. Mobile robot positioning: sensors and techniques [J]. J of robotic System, Special Issue on Mobile Robots,1997,4(4): 231-249.
[23]王耀南,余洪山.未知环境下移动机器人同步地图创建与定位研究进展[J].控制理论与应用, 2008, 25(1): 57-65.
[24] Chatterjee, Matsuno A, Jadavpur F, Kolkata. Improving EKF-based solutions for SLAM problems in Mobile Robots employing Neuro-Fuzzy Supervision [J]. Intelligent Systems, 2006 3rd International IEEE Conf., 2006, 683-689.
[25]罗荣华,洪炳镕.移动机器人同时定位与地图创建研究进展[J].机器人, 2004, 26 (2):182-186.
[26]罗荣华,洪炳镕.基于信息融合的同时定位与地图创建研究[J].哈尔滨工业大学学报,2004,36(5):566-569.
[27]蔡自兴,贺汉根,陈虹.未知环境中移动机器人导航控制研究的若干问题[J].控制与决策, 2002, 17(4):385-390.
[28] J J Leonard, H F Durrant-Whyte. Mobile Robot Localization by Tracking Geometric Beacons [J]. IEEE Transactions on Robotics and Automation, 1991,7(3):376-382.
[29] Barshan, B Durrant-Whyte, H F. Evaluation of a solid-state gyroscope for robotics applications [J]. IEEE Instrumentation and Measurement, 1995, 44(1): 61-67.
[30] S Thrun. Robotic mapping: a survey [M]. CMU-CS-02-111 School of Computer Science, Carnegie Mellon University Pittsburgh, 2002, 2.
[31]迟健男,徐心和.移动机器人即时定位与地图创建问题研究[J].机器人, 2004, 26(1): 92-96.
[32] Durrant-Whyte H, Bailey T. Simultaneous Localization and Mapping(SLAM):Part I[J].IEEE Robotics and Automation Magazine, 2006, 13(2): 99-110.
[33] Leonard J.J., Durrant-whyte H.F. Simultaneous map building and localization for an autonomous mobile robot [J]. Intelligent Robots and Systems' 91. 'Intelligence for Mechanical Systems, Proceedings IROS'91. IEEE/RSJ International Workshop on: 1442–1447.
[34] Thrun S, Burgard W and Fox D. A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots[J]. Machine Learning, 1998, 31(5): 29-53.
[35]殷波.移动机器人同时定位与地图创建方法研究[D].中国海洋大学博士论文,2006, 6.
[36]孙华,陈俊风,吴林.多传感器信息融合及其在机器人中的应用[J].传感器技术,2003.22 (9): 1-4.
[37]何友,王国宏,彭应宁等.多传感器信息融合及应用(第二版)[M].北京:电子工业出版社, 2007:1-68.
[38] Lawrence A Klenin著;戴亚平,刘征,郁光辉泽.多传感器数据融合理论及应用(第二版)[M].北京:北京理工大学出版社,2004.
[39]刘同明,夏祖勋,解洪成.数据融合技术及应用[M].北京:国防工业出版社, 2000.
[40]杨万海等.多传感器数据融合及应用[M].西安:西安电子科技大学出版社, 2004.
[41]张毅,罗元,郑太雄.移动机器人技术及其应用[M].北京:电子工业出版社,2007.
[42]周金祥.多传感器数据融合及其在移动机器人中的应用[D].北方工业大学硕士论文, 2006.
[43] H Evers and G Kasties. Differential GPS in a real-time and vehicle environment-satellite based van carrier location system. IEEE Aero space and Electrical Systems Magazine, 1994,9(8):26- 32.
[44] Chatila R. Mobile robot navigation: Space modeling and decisional processes. Proc. of 3rd International Symposium on Robotics Research , pp .373-378,Gouvieux,France,1985.
[45] Elfes A. Occupancy grids: A probabilistic frame work for robot perception and navigation[D]. Pittsburgh: Department of Electrical and Computer Engineering, Carnegie Mellon University, 1989.
[46] Ulrichl, Noubrkahsh I. Appearnace-based place recognition for topological localization. In Proceedings of the IEEE. International Conference on Robotics and Automation. 2000, 2: 1023-1029.
[47] Thurn S. Learning metric-topological maps for indoor mobile robot navigation[J]. Artificial Intelligence, 1998, 99(l), 21-71.
[48] Hoppen P, Knieriemen T and von Putkamer, E. Laser-radar based mapping and navigation for an autonomous mobile Robot. Proc. of the IEEE International Conference on Robotics and Automation,2 :948-953.1990.
[49] Buchberger, M. Laser radar and sonar based world mode ling and motion control for fast obstacle avoidance of an autonomous robot. Proc. of the IEEE International Conference on Robotic and Automation,,1993, 1:534-540.
[50] Thrun S, Fox D, Burgard W. Monte Carlo localization with mixture proposal distribution[C], Proc. of the 7th National Conf on Artificial Intelligence. Austin, TX: AAAI Press, 2000: 859-865.
[51] O Aycard, F Charpillet, D Fohr etc. Place learning and recognition using hidden markov models. In IEEE International Conference on Intelligent Robots and Systems, pages 1741–1746, 1997.
[52]王卫华,陈卫东.移动机器人地图创建中的不确定传感信息处理[J].自动化学报,2003, 29(2):56-63.
[53] C Harris and M J Stephens. A combined corner and edge detector. In Alvey Vision Conference, 1988, 147-152.
[54] Jianbo Shi, Tomasi C. Good Features to Track[C]. IEEE Conference on Computer Vision and Pattern Recognition, 1994, 593-600.
[55] Lindeberg T. Detecting salient blob-like image structures and their scales with a scale-space primal sketch: a method for focus-of attention. International Journal of Computer Vision, 1993(11), 283-318.
[56] A Shokoufandeh, I Marsic, and S J Dickinson. View-based object recognition using saliency maps.Image and Vision Computing, 1999 (17) :445-460 .
[57] D. G. Lowe. Object recognition from local scale-invariant features[C]. International Conference on Computer Vision, Corfu, Greece. 1999, 1150-1157.
[58] Mikolajczyk Krystian, Schmid Cordelia. Scale & affine invariant interest point detectors[J].International Journal of Computer Vision, 2004, 60(1): 63-86.
[59] E J Candes. Ridgelets: Theory and applications [M], ph. D. dissertation, Dept. Statistics, Stanford Univ., Stanford, CA, 1998.
[60] E J Cande and D L Donoho. Ridgelets: A key to higher-dimensional intermittency? [J], Phil. Trans. R. Soc. Lond. A., 1999, pp. 2495-2509.
[61]张友民,戴冠中,张洪才.卡尔曼滤波计算方法研究进展[J].控制理论与应用,1995,12(5): 529-538.
[2] Nilsson N J. A mobile automation: An application of artificial intelligence techniques[C]. Proceedings of the 1st Int. Joint Conference on Artificial Intelligence,Washington D.C. 1969 509-520.
[3] Shhaidi R, Shayman M, Krishnaprasad P S. Mobile robot navigation using potential functions[C]. In Proc. IEEE International Conference on Robotics and Automation, New York,1991: 2047- 2053.
[4] Borenstein J, Koren Y. Real-time obstacle avoidance for fast mobile robots in clustered environments[J]. IEEE Transactions on Systems. Man. and Cybernetics, 1989, 19(5):1179-1187.
[5] Koren Y, Borenstein J. Potential field methods and their inherent limitations for mobile robot navigation[C]. In Proc. IEEE International Conference on Robotics and Automation, California, 1991: 1398-1404.
[6] H F Durrant-Whyte. Where am I? A tutorial on mobile vehicle localization[J]. Industrial Robot, 21(2) :11-16,1994.
[7] J Guivant, E Nebot, and S Baiker. High accuracy navigation using laser angles sensors in out door applications[C]. IEEE International Conference on Robotics and Automation, 2000, 2:2512- 2517.
[8] J Guivant, E Nebot and S Baiker. Localization and map building using laser range sensors in out door applications[J]. Journal of Robotic Systems, 2000,1: 565-583.
[9] E M Nebot, H F Durrant-Whyte, and S Scheding. Frequency domain modeling of aided GPS for vehicle navigation systems. Journal of Robotics and Autonomous Systems, 1998(25): 73-82 .
[10] E M Nebot, S Scheding, and H F Durrant-Whyte. Kalman Filtering design techniques for aided GPS land navigation applications. Proceedings 1st Australian Data Fusion Symposium, 1996, pp .83-89.
[11]杨毅,智能机器人的研究与开发[D].河北工业大学硕士论文,2004, 3.
[12]何克忠,郭木河.智能移动机器人技术研究[J].机器人技术与应用, 1996.
[13]张朋飞,何克忠,欧阳正柱等.多功能室外智能移动机器人实验平台—THRM-V[J].机器人,2002,24(2):97-101.
[14]田宇,吴镇炜,柳长春.开放式三自由度全方位移动机器人实验平台[J].机器人,200,224(2): 102-111.
[15]孙振平,安向京,贺汉根. CITAVT-Ⅳ—视觉导航的自主车[J].机器人,2002,24(2):115-121.
[16]张纯刚,席裕庚.动态未知环境中移动机器人的滚动路径规划[J].机器人,2002,24(1):69-75.
[17]郭琦,洪炳熔.基于人工神经网络实现智能机器人的避障轨迹控制[J].机器人,2002,2(6):508-512.
[18] Csorba M. Simultaneous localization and map building[D]. Oxford: University of Oxford, 1997.
[19] Smith R, Self M, Chesseman P. Estimating uncertain spatial relationships in robotics[A]. Proceedings of Conference on Uncertainty in Artificial Intelligence[C]. Amsterdam: North- holland, 1988, 435-461.
[20]王璐,蔡智兴.未知环境中移动机器人并发建图与定位(CLM)的研究进展[J].机器人,2004,26(4):380-384.
[21] Elefs A, Moravec H. High resolution maps from wide angle sonar [C]//Proc of the IEEE 1nt Conf. on Robots and Automation. St. Louis MO: IEEE Press, 1985: 116-121.
[22] Borenstein J, Everett H R, Feng L, et al. Mobile robot positioning: sensors and techniques [J]. J of robotic System, Special Issue on Mobile Robots,1997,4(4): 231-249.
[23]王耀南,余洪山.未知环境下移动机器人同步地图创建与定位研究进展[J].控制理论与应用, 2008, 25(1): 57-65.
[24] Chatterjee, Matsuno A, Jadavpur F, Kolkata. Improving EKF-based solutions for SLAM problems in Mobile Robots employing Neuro-Fuzzy Supervision [J]. Intelligent Systems, 2006 3rd International IEEE Conf., 2006, 683-689.
[25]罗荣华,洪炳镕.移动机器人同时定位与地图创建研究进展[J].机器人, 2004, 26 (2):182-186.
[26]罗荣华,洪炳镕.基于信息融合的同时定位与地图创建研究[J].哈尔滨工业大学学报,2004,36(5):566-569.
[27]蔡自兴,贺汉根,陈虹.未知环境中移动机器人导航控制研究的若干问题[J].控制与决策, 2002, 17(4):385-390.
[28] J J Leonard, H F Durrant-Whyte. Mobile Robot Localization by Tracking Geometric Beacons [J]. IEEE Transactions on Robotics and Automation, 1991,7(3):376-382.
[29] Barshan, B Durrant-Whyte, H F. Evaluation of a solid-state gyroscope for robotics applications [J]. IEEE Instrumentation and Measurement, 1995, 44(1): 61-67.
[30] S Thrun. Robotic mapping: a survey [M]. CMU-CS-02-111 School of Computer Science, Carnegie Mellon University Pittsburgh, 2002, 2.
[31]迟健男,徐心和.移动机器人即时定位与地图创建问题研究[J].机器人, 2004, 26(1): 92-96.
[32] Durrant-Whyte H, Bailey T. Simultaneous Localization and Mapping(SLAM):Part I[J].IEEE Robotics and Automation Magazine, 2006, 13(2): 99-110.
[33] Leonard J.J., Durrant-whyte H.F. Simultaneous map building and localization for an autonomous mobile robot [J]. Intelligent Robots and Systems' 91. 'Intelligence for Mechanical Systems, Proceedings IROS'91. IEEE/RSJ International Workshop on: 1442–1447.
[34] Thrun S, Burgard W and Fox D. A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots[J]. Machine Learning, 1998, 31(5): 29-53.
[35]殷波.移动机器人同时定位与地图创建方法研究[D].中国海洋大学博士论文,2006, 6.
[36]孙华,陈俊风,吴林.多传感器信息融合及其在机器人中的应用[J].传感器技术,2003.22 (9): 1-4.
[37]何友,王国宏,彭应宁等.多传感器信息融合及应用(第二版)[M].北京:电子工业出版社, 2007:1-68.
[38] Lawrence A Klenin著;戴亚平,刘征,郁光辉泽.多传感器数据融合理论及应用(第二版)[M].北京:北京理工大学出版社,2004.
[39]刘同明,夏祖勋,解洪成.数据融合技术及应用[M].北京:国防工业出版社, 2000.
[40]杨万海等.多传感器数据融合及应用[M].西安:西安电子科技大学出版社, 2004.
[41]张毅,罗元,郑太雄.移动机器人技术及其应用[M].北京:电子工业出版社,2007.
[42]周金祥.多传感器数据融合及其在移动机器人中的应用[D].北方工业大学硕士论文, 2006.
[43] H Evers and G Kasties. Differential GPS in a real-time and vehicle environment-satellite based van carrier location system. IEEE Aero space and Electrical Systems Magazine, 1994,9(8):26- 32.
[44] Chatila R. Mobile robot navigation: Space modeling and decisional processes. Proc. of 3rd International Symposium on Robotics Research , pp .373-378,Gouvieux,France,1985.
[45] Elfes A. Occupancy grids: A probabilistic frame work for robot perception and navigation[D]. Pittsburgh: Department of Electrical and Computer Engineering, Carnegie Mellon University, 1989.
[46] Ulrichl, Noubrkahsh I. Appearnace-based place recognition for topological localization. In Proceedings of the IEEE. International Conference on Robotics and Automation. 2000, 2: 1023-1029.
[47] Thurn S. Learning metric-topological maps for indoor mobile robot navigation[J]. Artificial Intelligence, 1998, 99(l), 21-71.
[48] Hoppen P, Knieriemen T and von Putkamer, E. Laser-radar based mapping and navigation for an autonomous mobile Robot. Proc. of the IEEE International Conference on Robotics and Automation,2 :948-953.1990.
[49] Buchberger, M. Laser radar and sonar based world mode ling and motion control for fast obstacle avoidance of an autonomous robot. Proc. of the IEEE International Conference on Robotic and Automation,,1993, 1:534-540.
[50] Thrun S, Fox D, Burgard W. Monte Carlo localization with mixture proposal distribution[C], Proc. of the 7th National Conf on Artificial Intelligence. Austin, TX: AAAI Press, 2000: 859-865.
[51] O Aycard, F Charpillet, D Fohr etc. Place learning and recognition using hidden markov models. In IEEE International Conference on Intelligent Robots and Systems, pages 1741–1746, 1997.
[52]王卫华,陈卫东.移动机器人地图创建中的不确定传感信息处理[J].自动化学报,2003, 29(2):56-63.
[53] C Harris and M J Stephens. A combined corner and edge detector. In Alvey Vision Conference, 1988, 147-152.
[54] Jianbo Shi, Tomasi C. Good Features to Track[C]. IEEE Conference on Computer Vision and Pattern Recognition, 1994, 593-600.
[55] Lindeberg T. Detecting salient blob-like image structures and their scales with a scale-space primal sketch: a method for focus-of attention. International Journal of Computer Vision, 1993(11), 283-318.
[56] A Shokoufandeh, I Marsic, and S J Dickinson. View-based object recognition using saliency maps.Image and Vision Computing, 1999 (17) :445-460 .
[57] D. G. Lowe. Object recognition from local scale-invariant features[C]. International Conference on Computer Vision, Corfu, Greece. 1999, 1150-1157.
[58] Mikolajczyk Krystian, Schmid Cordelia. Scale & affine invariant interest point detectors[J].International Journal of Computer Vision, 2004, 60(1): 63-86.
[59] E J Candes. Ridgelets: Theory and applications [M], ph. D. dissertation, Dept. Statistics, Stanford Univ., Stanford, CA, 1998.
[60] E J Cande and D L Donoho. Ridgelets: A key to higher-dimensional intermittency? [J], Phil. Trans. R. Soc. Lond. A., 1999, pp. 2495-2509.
[61]张友民,戴冠中,张洪才.卡尔曼滤波计算方法研究进展[J].控制理论与应用,1995,12(5): 529-538.