全向视频运动目标检测与跟踪
|
摘要
全向视频是虚拟现实和计算机视觉中一种重要的场景表示方法,它指的是在垂直方向180°和水平方向360°的图像视图。与传统视频相比,全向视频的优点在于其360°的宽广视野感知范围,全向摄像机的运动估计比传统摄像机更加稳定,因为传统摄像机视野小,运动估计对摄像机的方向很敏感,而且其水平方向上平移产生的运动与绕垂直轴旋转产生的运动十分相似,难以区分,而全景摄像机特有的360°视野能避免这些问题。正是由于具有这些优势,基于全向视频的目标检测与跟踪已经在一些领域开始得到越来越多的研究,例如视频监控、机器人导航和智能驾驶等领域。
本文在分析全向图像特点的基础上,针对经典目标检测与跟踪算法运用于全向视频的不足,分别对目标检测算法和目标跟踪算法加以改进,论文的研究成果主要包括以下几个方面:
(1)在分析马尔可夫随机场图像运动检测原理的基础上,根据全向图像的分辨率和邻域特点,提出一种新的折反射全向图像邻域定义方法。
(2)在分析卡尔曼滤波器图像运动目标跟踪原理的基础上,针对目标沿直线运动时在折反射全向图像上的成像轨迹是二次曲线的问题,修改卡尔曼滤波器,提高折反射全向视频卡尔曼滤波目标跟踪时的状态预测精度。
结合以上方法,通过多个实验视频来验证算法的鲁棒性和准确性,其实验结果令人满意。
Omni-directional video is an important representation for scenes of virtual reality and computer vision, which refers to the image of vertical 180°and horizontal 360°view. Compared with traditional video, the advantages of the omni-directional video lies in its 360°field of vision sensing range. The motion estimation based on omni-directional camera is more stable than traditional cameras. The traditional cameras has a small vision, so motion estimation is very sensitive to the direction of the camera, and its movement of horizontal translation and rotation around the vertical axis is so similar that it is difficult to distinguish. Because the unique omni-directional camera 360°field of vision can avoid these problems, target detection and tracking based on omni-directional video has been researched in a number of areas, such as video surveillance, robot navigation, and smart driving.
This paper analyzes the characteristics of omni-directional image, improves the target detection and tracking algorithm respectively, for the inadequate of classical target detection and tracking algorithm applied to omni-directional images. Research includes the following aspects:
(1) Based on the analysis of Markov random field image motion detection principle and the characteristics of omni-directional image resolution and neighborhood, the paper presents a new neighborhood definition method for catadioptric omni-directional image.
(2) Based on the analysis of kalman filter image motion tracking theory and the phenomenon that imaging trajectory is conic in the catadioptric omni-directional image when target moves along the straight-line, the paper modifies the kalman filter to improve the state prediction accuracy of target tracking on the catadioptric omni-directional image.
Combination of the above methods, the paper verifies the robustness and correctness of algorithms through many experiment videos, and the results are satisfactory.
本文在分析全向图像特点的基础上,针对经典目标检测与跟踪算法运用于全向视频的不足,分别对目标检测算法和目标跟踪算法加以改进,论文的研究成果主要包括以下几个方面:
(1)在分析马尔可夫随机场图像运动检测原理的基础上,根据全向图像的分辨率和邻域特点,提出一种新的折反射全向图像邻域定义方法。
(2)在分析卡尔曼滤波器图像运动目标跟踪原理的基础上,针对目标沿直线运动时在折反射全向图像上的成像轨迹是二次曲线的问题,修改卡尔曼滤波器,提高折反射全向视频卡尔曼滤波目标跟踪时的状态预测精度。
结合以上方法,通过多个实验视频来验证算法的鲁棒性和准确性,其实验结果令人满意。
Omni-directional video is an important representation for scenes of virtual reality and computer vision, which refers to the image of vertical 180°and horizontal 360°view. Compared with traditional video, the advantages of the omni-directional video lies in its 360°field of vision sensing range. The motion estimation based on omni-directional camera is more stable than traditional cameras. The traditional cameras has a small vision, so motion estimation is very sensitive to the direction of the camera, and its movement of horizontal translation and rotation around the vertical axis is so similar that it is difficult to distinguish. Because the unique omni-directional camera 360°field of vision can avoid these problems, target detection and tracking based on omni-directional video has been researched in a number of areas, such as video surveillance, robot navigation, and smart driving.
This paper analyzes the characteristics of omni-directional image, improves the target detection and tracking algorithm respectively, for the inadequate of classical target detection and tracking algorithm applied to omni-directional images. Research includes the following aspects:
(1) Based on the analysis of Markov random field image motion detection principle and the characteristics of omni-directional image resolution and neighborhood, the paper presents a new neighborhood definition method for catadioptric omni-directional image.
(2) Based on the analysis of kalman filter image motion tracking theory and the phenomenon that imaging trajectory is conic in the catadioptric omni-directional image when target moves along the straight-line, the paper modifies the kalman filter to improve the state prediction accuracy of target tracking on the catadioptric omni-directional image.
Combination of the above methods, the paper verifies the robustness and correctness of algorithms through many experiment videos, and the results are satisfactory.
引文
[1] Haritacglu I, Harwood D, Davis L. W4:Real-time surveillance of people and their activities[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8):809-830.
[2] Pavlidis I, Morellas V, Tsiamyrtzis P, Harp S. Urban surveillance system: From the laboratory to the commercial world[C]. Proceedings of the IEEE, 2001, 89(10):1478-1497.
[3] Collins R, Lipton A, Kanade T, Fujiyoshi H, Duggins D, Tsin Y, Tolliver D, Enomoto N, Hasegawa O, Burt P, Wixson L. A system for video surveillance and monitoring[C]. VSAM final report, Carnegie Mellon University: Technical Report CMU-RI-TR-00-12,2000.
[4] Collins R, Lipton A, Fujiyoshi H, Kanade T. Algorithms for cooperative multi-sensor surveillance[C]. Proceedings of the IEEE, 2001,89(10):1456-1477.
[5] Bogaert M, Chleq N, Cornez P, Regazzoni C S, Teschioni A, T honnat M. The PASSWORDS project[C]. Proceedings of IEEE International Conference on Image Processing. Switzerland: Lausanne, 1996,3:675-678.
[6] Wren C R, Azarbayejani A, Darrell T, Pentland A P. Pfinder: Real-time tracking of the human body[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(7):780-785.
[7] S. Nayar. Catadioptric Omnidirectional Camera[C]. In Proc. Of IEEE Conf. on Computer Vision and Pattern Recognition, 1997: 482-488.
[8] Baker S,Nayar S. A theory of single-viewpoint catadioptric image formation[C].International Journal of Computer Vision.1999,35(2):237-251.
[9] R. Benosman and S. B. Kang. Panoramic Vision: Sensors, Theory, and Applications. Springer, 2001.
[10] Gluckman J, Nayar S. Ego-motion and omnidirectional cameras[C]. In Proc. of the International Conference on Computer Vision, 1998: 999-1005.
[11]曾吉勇,苏显渝.折反射全景成像系统[J]. LASER JOURNAL, 2004, 25(6):62-64.
[12]蒋苏蓉,王松,冯刚.基于图像的全景视图的实现技术.计算机应用[J]. 2002, 22(6):86-87.
[13] Kim C. Ng, H. Ishiguro, M. Trivedi, T. Sogo. An integrated surveillance system-human tracking and view synthesis using multiple omni-directional vision sensors[J]. Image and Vision Computing, 2004, 22(7):551–561.
[14] T.E. Boult, X. Gao, R. Micheals, M. Eckmann. Omni-directional visual surveillance[J]. Image and Vision Computing, 2004, 22(7):515–534.
[15] Y Onoe, K Yamazawa, N Yokoya, H Takemura. Visual surveillance and monitoring system using an omnidirectional video camera[C]. In Proc. IEEE International Conference on Pattern Recognition, 1998:588-592
[16] Hiroshi Koyasu, Jun Miura, and Yoshiaki Shirai Realtime Omnidirectional Stereo for Obstacle Detection and Tracking in Dynamic Environments[C]. Proc IEEE/RSJ Int Conf. on Intelligent Robots and Systems,2001,PP: 31-36
[17] T. E. Boult, R. Michaels, X. Gao, P. Lewis, C. Power, W. Yin, and A. Erkan, Frame-rate ominidirectional surveillance and tracking of camouflaged and occluded targets[J]. Proc. of 2nd IEEE Workshop on Visual Surveillance , 1999, 48-55.
[18] Marin Kobilarov, Gaurav Sukhatme, People tracking and following with mobile robot using an omnidirectional camera and a laser[C]. Proceedings of the 2006 IEEE International Conference on Robotics and Automation.
[19] Frank Wallhoff, Martin Zobl, and Gerhard Rigoll Face Tracking in Meeting Room Scenarios Using Omnidirectional Views[C]. IEEE International Conference on Pattern Recognition, 2004.
[20] Tarak Gandhi, Mohan M. Trivedi. Motion Analysis for vent Detection and Tracking with a Mobile OmniDirectional Camera[C] ACM Multimedia Systems Journal, Special Issue on Video Surveillance, 2004
[21] Tarak Gandhi, Mohan Trivedi. Parametric ego-motion estimation for vehicle surround analysis using an omnidirectional camera[J]. Machine Vision and Applications, 2005, 16(2): 85–95.
[22] Tarak Gandhi, Mohan M. Trivedi. Dynamic Panoramic Surround Map: Motivation and Omni Video Based Approach[J]. In Proc. of the Workshop on Machine Vision for Intelligent Vehicles, CVPR, 2005.
[23] Kohsia S. Huang, Mohan M. Trivedi, and Tarak Gandhi. Driver’s View and Vehicle Surround Estimation using Omnidirectional Video Stream[C]. IEEE Intelligent Vehicles Symposium, Columbus, OH, USA, 2003,444-449.
[24] G. Scotti, L. Marcenaro, C. Coelho, et al. Dual camera intelligent sensor for high definition 360 degrees surveillance[C], IEE Proc.-Vis. Image Signal Process., 2005 April, Vol.152, No.2.
[25] Yi Yao, Besma Abidi, Mongi Abidi. Fusion of Omnidirectional and PTZ Cameras for Accurate Cooperative Tracking[C]. IEEE International Conference on Video and Signal Based Surveillance (AVSS'06)
[26] Tarak Gandhi,Mohan Manubhai Trivedi. Person tracking and reidentification: Introducing Panoramic Appearance Map (PAM) for feature representation. Machine Vision and Applications (2007) 18:207–220
[27] T. Gandhi, M. M. Trivedi. Vehicle surround capture: Survey of techniques and a novel omni-video-based approach for dynamic panoramic surround maps[C]. IEEETransactions on Intelligent Transportation Systems, 2006, 7(3): 293-308
[28] S. Shimizu, K. Yamamoto, C. Wang, et al. Moving object detection by mobile Stereo Omni-directional System (SOS) using spherical depth image[J]. Pattern Analysis & Applications, 2006, 9(2): 113-126
[29]卢惠民,刘斐,郑志强.一种新的用于足球机器人的全向视觉系统[J].中国图象图形学报. 2007, 12(7):1243-1248.
[30] Cielniak, Miladinovic G., Hammarin M. et al., Appearance-based Tracking of Persons with an Omnidirectional Vision Sensor[J]. In Proceedings of Computer Vision and Pattern Recognition Workshop, 2003.pp:84-89.
[31] Boult T.E., Gao X., Micheal R., et al. Omni-directional visual surveillance[J]. Image and Vision Computing In Visual Surveillance, Vol. 22, No. 7. (01 July 2004), pp. 515-534.
[32] Kazumasa Yamazawa and Naokazu Yokoya Detecting Moving Objects with an omnidirectional Camera Based on Adaptive Background Subtraction[C]. SCIA 2003, LNCS 2749, pp. 969?974.
[33] Akari Matsumura,Yoshio Iwai, Masahiko Yachida. Tracking people by using color information from omnidirectional images[C]. SICE 2002 Aug.5-7, Osaka.
[34] Raju Patil, Paul E. Rybski, Takeo Kanade, Manuela M. Veloso. People Detection and Tracking in High Resolution Panoramic Video Mosaic[C]. Proceed of 2004 IEEE/RSJ Internationa Conference on Intelligent Robots and Systems.September 28-October 2,2004,Sendai,Japan.
[35] Hiroshi Koyasu, Jun Miura, and Yoshiaki Shirai. Recognizing Moving Obstacles for Robot Navigation using Real-time Omnidirectional Stereo Vision[J]. J. of Robotics and Mechatronics, Vol. 14, No. 2, pp. 147-156, 2002.
[36] Huei-Yung Lin, Ming-Liang Wang, Chi-Chang Huang. A Robust Visual Surveillance System Based on an Omnidirectional Vision Sensor[J],Journal of Computers Vol.19, No.3, 2008, pp:3-14.
[37] Mei C., Benhimane S., Malis E., et al. Homography-based Tracking for Central Catadioptric Cameras[C]. In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006, pp: 669-674.
[38] Liu, H.Y., Javed O., Taylor, G., et al. Omni-Directional Surveillance for Unmanned Water Vehicles[C]. In Proceedings of the Eighth International Workshop on Visual Surveillance, 2008.
[39] Ikoma N., Ryuichi Yamaguchi, Kawano H., Tracking of Multiple Moving Objects in Dynamic Image of Omni-Directional Camera Using PHD Filter[J]. Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.12 No.1, 2008, pp:167-180.
[40]王宇,王涌天,刘越.一种基于全向视觉的运动物体检测算法[J],模式识别与人工智能, 2008, 04.
[41]周家至.应用全方位影像与光流技术于运动估测[D].中国台湾国立中山大学机械与机电工程学系. 2006.7.
[42] Yang Shu-Ying, Ge WeiMin, Zhang Cheng,Tracking unknown moving targets on omnidirectional vision[J]. Vision Research, 49 (2009) , pp:362–367.
[43]皮文凯,刘宏,查红彬.基于自适应背景模型的全方位视觉人体运动检测[J].北京大学学报(自然科学版), 2004 .40(3):458-464.
[44] Karmann K and Brandt A. Moving object recognition using an adaptive background memory[J]. In: V Cappellini, Time-varying Image Processing and Moving Object Recognition. 2. Elsevier, Amsterdam, The Netherlands, 1990.
[45] Stauffer C and Crimson W. Adaptive background mixture models for real-time tracking[C]. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, 1999, 2: 246-252.
[46] McKenna S et al. Tracking groups of people[J]. Computer Vision and Image Understanding, 2000, 80 (1):42-56.
[47] Lipton A, Fujiyoshi H and Patil R. Moving target classification and tracking from real-time video[J]. In: Proc IEEE Workshop on Applications of Computer Vision, Princeton, NJ, 1998, 8-14
[48] Anderson C, Bert P and Vander Wal G. Change detection and tracking using pyramids transformation techniques[C]. In: Proc SPIE Conference on Intelligent Robots and Computer Vision, Cambridge, M A, 1985, 579:72 -78.
[49] Barron J, Fleet D and Beauchemin S. Performance of optical flow techniques [J]. International Journal of Computer Vision, 1994, 12(1):42 -77.
[50] Meyer D, Denzler J and Niemann H. Model based extraction of articulated objects in image sequences for gait analysis[C]. In: Proc IEEE International Conference on Image Processing, Santa Barbara, California 1997, 78-81.
[51] Friedman N and Russell S. Image segmentation in video sequences: a probabilistic approach[C]. In: Proc the Thirteenth Conference on Uncertainty in Artificial Intelligence, Rhode Island, USA, 1997.
[52] Stringa E. Morphological change detection algorithms for surveillance applications[C]. In: British Machine Vision Conference, Bristol, UK, 2000, 402-411.
[53] Kass M, Witkin A and Terzopoulos D. Snakes: Active Contour Models[C]. The 1st International Conference of Computer Vision, London, 1987:259-268.
[54]智利丁.智能视频监控中多运动对象的检测与跟踪[D].国防科学技术大学2007,11.
[55] Kalman, R. E. 1960. A New Approach to Linear Filtering and Prediction Problems. ansaction of the ASME[J]. Journal of Basic Engineering, pp. 35-45 (March 1960).
[56] Cedric Demonceaux, Pascal Vasseur, Markov random fields for catadioptric image processing[J], Pattern Recognition Letters , 27 (2006): 1957-1967.
[57] Demonceaux C., Vasseur P., Markov random fields for catadioptric image processing[J], Pattern Recognition Letters, 27 (2006): 1957-1967.
[58] Daniilidis, K., Makadia, A., Blow, T Image processing in catadioptric planes: Spatiotemporal derivatives and optical flow computation[C]. In: IEEE Workshop on Omnidirectional Vision (OMNIVIS02), Copenhagen, Denmark, 2002, pp. 3-10.
[59] Strauss O, Comby F, Variable structuring element based fuzzy morphological operations for single viewpoint omnidirectional images[J], Pattern Recognition, 40(2007):3578-3596.
[60] Jacquey F., Comby F., Strauss O. Fuzzy edge detection for omnidirectional images[J]. Fuzzy Sets and Systems, 159 (2008): 1991-2010.
[61] Ieng S., Benosman R., Devars J., An efficient dynamic multi-angular feature points matcher for catadioptric views[C]. Proceedings of Omnivis 2003, Workshop on Omnidirectional Vision and Camera Networks, Madison, USA, 2003.
[62] Svoboda, T., Pajdla, T. Matching in catadioptric images with appropriate windows, and outliers removal[C]. In: Internat. Conf. On Computer Analysis of Images and Patterns (CAIP01), Warsaw, Poland, 2001,pp. 733-740.
[63] Baker, S., Nayar, S.K.. A theory of single-viewpoint catadioptric image formation[J]. Internt. J. Comput. Vision (IJCV) , 1999, 35 (N2): 175-196.
[64] Geyer, C., Daniilidis, K.. Catadioptric projective geometry[J]. Internat. J. Comput. Vision (IJCV) , 2001, 45 (N3): 223-243.
[65] Barreto J. P. , Araujo H. Geometric Properties of Central Catadioptric Line Images and Their Application in Calibration[C]. IEEE Transactions on Pattern Analysis and Machine intellegence, 27(8)(2005):1327-1333.
[66] Mei C., Rives P., Single View Point Omnidirectional Camera Calibration from Planar Grids[C]. In: Proceedings of IEEE International Conference on Robotics and Automation (2007), pp. 3945-3950.
[67] Barreto P. and Araujo H.,Geometric Properties of Central Catadioptric Line Images and Their Application in Calibration[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8),2005, pp:1327-1333.
[68]刘传才,图像理解与计算机视觉[M],厦门大学出版社, 2002.
[69]邓小明,吴福朝,段福庆,吴毅红,胡占义.基于一维标定物的反射折射摄像机标定方法[J].计算机学报. 2007,30(5):737-747.
[70] Aliaga D G. Accurate catadioptric calibration for real-time pose estimation in room size environments[C]. Proceedings of the 8th International Conferenee on Computer Vision. Vancouver, BC, 2001, 1:127-134.
[71] Vasseur P, M ouaddib E1 M. Central catadioptric line detection[C]. Proceedings ofthe British Machine Vision Conference. Kingston University, London, 2004.
[72] Geyer C, Daniilids K. Paracatadioptric camera calibration[J]. IEEE Transactions on Pattern Analysis and M aehine Intelligence, 2002, 24(5): 687-695.
[73] Barreto J P, Araujo H. Geometry properties of central catadioptric line images and application in calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(8):1327-1333.
[74] Ying X, Hu Z. Catadioptrie camera calibration using geometric invariants[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(10) :1260-1271.
[75] Kang S B. Catadioptric self-calibration[C]. Proceedings of the IEEE Conference on Co mputer Vision and Pattern Recognition. Hilton H ead Island, SC, U SA, 2000, 1:201-207.
[76] Mei, C. Malis, E., Fast Central Catadioptric Line Extraction[C]. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006, pp: 4774-4779.
[77] Toriia A., Imiya A., The randomized-Hough-transform-based method for great-circle detection on sphere[J]. Pattern Recognition Letters. Volume 28, Issue 10, 2007, pp:1186-1192.
[2] Pavlidis I, Morellas V, Tsiamyrtzis P, Harp S. Urban surveillance system: From the laboratory to the commercial world[C]. Proceedings of the IEEE, 2001, 89(10):1478-1497.
[3] Collins R, Lipton A, Kanade T, Fujiyoshi H, Duggins D, Tsin Y, Tolliver D, Enomoto N, Hasegawa O, Burt P, Wixson L. A system for video surveillance and monitoring[C]. VSAM final report, Carnegie Mellon University: Technical Report CMU-RI-TR-00-12,2000.
[4] Collins R, Lipton A, Fujiyoshi H, Kanade T. Algorithms for cooperative multi-sensor surveillance[C]. Proceedings of the IEEE, 2001,89(10):1456-1477.
[5] Bogaert M, Chleq N, Cornez P, Regazzoni C S, Teschioni A, T honnat M. The PASSWORDS project[C]. Proceedings of IEEE International Conference on Image Processing. Switzerland: Lausanne, 1996,3:675-678.
[6] Wren C R, Azarbayejani A, Darrell T, Pentland A P. Pfinder: Real-time tracking of the human body[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(7):780-785.
[7] S. Nayar. Catadioptric Omnidirectional Camera[C]. In Proc. Of IEEE Conf. on Computer Vision and Pattern Recognition, 1997: 482-488.
[8] Baker S,Nayar S. A theory of single-viewpoint catadioptric image formation[C].International Journal of Computer Vision.1999,35(2):237-251.
[9] R. Benosman and S. B. Kang. Panoramic Vision: Sensors, Theory, and Applications. Springer, 2001.
[10] Gluckman J, Nayar S. Ego-motion and omnidirectional cameras[C]. In Proc. of the International Conference on Computer Vision, 1998: 999-1005.
[11]曾吉勇,苏显渝.折反射全景成像系统[J]. LASER JOURNAL, 2004, 25(6):62-64.
[12]蒋苏蓉,王松,冯刚.基于图像的全景视图的实现技术.计算机应用[J]. 2002, 22(6):86-87.
[13] Kim C. Ng, H. Ishiguro, M. Trivedi, T. Sogo. An integrated surveillance system-human tracking and view synthesis using multiple omni-directional vision sensors[J]. Image and Vision Computing, 2004, 22(7):551–561.
[14] T.E. Boult, X. Gao, R. Micheals, M. Eckmann. Omni-directional visual surveillance[J]. Image and Vision Computing, 2004, 22(7):515–534.
[15] Y Onoe, K Yamazawa, N Yokoya, H Takemura. Visual surveillance and monitoring system using an omnidirectional video camera[C]. In Proc. IEEE International Conference on Pattern Recognition, 1998:588-592
[16] Hiroshi Koyasu, Jun Miura, and Yoshiaki Shirai Realtime Omnidirectional Stereo for Obstacle Detection and Tracking in Dynamic Environments[C]. Proc IEEE/RSJ Int Conf. on Intelligent Robots and Systems,2001,PP: 31-36
[17] T. E. Boult, R. Michaels, X. Gao, P. Lewis, C. Power, W. Yin, and A. Erkan, Frame-rate ominidirectional surveillance and tracking of camouflaged and occluded targets[J]. Proc. of 2nd IEEE Workshop on Visual Surveillance , 1999, 48-55.
[18] Marin Kobilarov, Gaurav Sukhatme, People tracking and following with mobile robot using an omnidirectional camera and a laser[C]. Proceedings of the 2006 IEEE International Conference on Robotics and Automation.
[19] Frank Wallhoff, Martin Zobl, and Gerhard Rigoll Face Tracking in Meeting Room Scenarios Using Omnidirectional Views[C]. IEEE International Conference on Pattern Recognition, 2004.
[20] Tarak Gandhi, Mohan M. Trivedi. Motion Analysis for vent Detection and Tracking with a Mobile OmniDirectional Camera[C] ACM Multimedia Systems Journal, Special Issue on Video Surveillance, 2004
[21] Tarak Gandhi, Mohan Trivedi. Parametric ego-motion estimation for vehicle surround analysis using an omnidirectional camera[J]. Machine Vision and Applications, 2005, 16(2): 85–95.
[22] Tarak Gandhi, Mohan M. Trivedi. Dynamic Panoramic Surround Map: Motivation and Omni Video Based Approach[J]. In Proc. of the Workshop on Machine Vision for Intelligent Vehicles, CVPR, 2005.
[23] Kohsia S. Huang, Mohan M. Trivedi, and Tarak Gandhi. Driver’s View and Vehicle Surround Estimation using Omnidirectional Video Stream[C]. IEEE Intelligent Vehicles Symposium, Columbus, OH, USA, 2003,444-449.
[24] G. Scotti, L. Marcenaro, C. Coelho, et al. Dual camera intelligent sensor for high definition 360 degrees surveillance[C], IEE Proc.-Vis. Image Signal Process., 2005 April, Vol.152, No.2.
[25] Yi Yao, Besma Abidi, Mongi Abidi. Fusion of Omnidirectional and PTZ Cameras for Accurate Cooperative Tracking[C]. IEEE International Conference on Video and Signal Based Surveillance (AVSS'06)
[26] Tarak Gandhi,Mohan Manubhai Trivedi. Person tracking and reidentification: Introducing Panoramic Appearance Map (PAM) for feature representation. Machine Vision and Applications (2007) 18:207–220
[27] T. Gandhi, M. M. Trivedi. Vehicle surround capture: Survey of techniques and a novel omni-video-based approach for dynamic panoramic surround maps[C]. IEEETransactions on Intelligent Transportation Systems, 2006, 7(3): 293-308
[28] S. Shimizu, K. Yamamoto, C. Wang, et al. Moving object detection by mobile Stereo Omni-directional System (SOS) using spherical depth image[J]. Pattern Analysis & Applications, 2006, 9(2): 113-126
[29]卢惠民,刘斐,郑志强.一种新的用于足球机器人的全向视觉系统[J].中国图象图形学报. 2007, 12(7):1243-1248.
[30] Cielniak, Miladinovic G., Hammarin M. et al., Appearance-based Tracking of Persons with an Omnidirectional Vision Sensor[J]. In Proceedings of Computer Vision and Pattern Recognition Workshop, 2003.pp:84-89.
[31] Boult T.E., Gao X., Micheal R., et al. Omni-directional visual surveillance[J]. Image and Vision Computing In Visual Surveillance, Vol. 22, No. 7. (01 July 2004), pp. 515-534.
[32] Kazumasa Yamazawa and Naokazu Yokoya Detecting Moving Objects with an omnidirectional Camera Based on Adaptive Background Subtraction[C]. SCIA 2003, LNCS 2749, pp. 969?974.
[33] Akari Matsumura,Yoshio Iwai, Masahiko Yachida. Tracking people by using color information from omnidirectional images[C]. SICE 2002 Aug.5-7, Osaka.
[34] Raju Patil, Paul E. Rybski, Takeo Kanade, Manuela M. Veloso. People Detection and Tracking in High Resolution Panoramic Video Mosaic[C]. Proceed of 2004 IEEE/RSJ Internationa Conference on Intelligent Robots and Systems.September 28-October 2,2004,Sendai,Japan.
[35] Hiroshi Koyasu, Jun Miura, and Yoshiaki Shirai. Recognizing Moving Obstacles for Robot Navigation using Real-time Omnidirectional Stereo Vision[J]. J. of Robotics and Mechatronics, Vol. 14, No. 2, pp. 147-156, 2002.
[36] Huei-Yung Lin, Ming-Liang Wang, Chi-Chang Huang. A Robust Visual Surveillance System Based on an Omnidirectional Vision Sensor[J],Journal of Computers Vol.19, No.3, 2008, pp:3-14.
[37] Mei C., Benhimane S., Malis E., et al. Homography-based Tracking for Central Catadioptric Cameras[C]. In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006, pp: 669-674.
[38] Liu, H.Y., Javed O., Taylor, G., et al. Omni-Directional Surveillance for Unmanned Water Vehicles[C]. In Proceedings of the Eighth International Workshop on Visual Surveillance, 2008.
[39] Ikoma N., Ryuichi Yamaguchi, Kawano H., Tracking of Multiple Moving Objects in Dynamic Image of Omni-Directional Camera Using PHD Filter[J]. Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.12 No.1, 2008, pp:167-180.
[40]王宇,王涌天,刘越.一种基于全向视觉的运动物体检测算法[J],模式识别与人工智能, 2008, 04.
[41]周家至.应用全方位影像与光流技术于运动估测[D].中国台湾国立中山大学机械与机电工程学系. 2006.7.
[42] Yang Shu-Ying, Ge WeiMin, Zhang Cheng,Tracking unknown moving targets on omnidirectional vision[J]. Vision Research, 49 (2009) , pp:362–367.
[43]皮文凯,刘宏,查红彬.基于自适应背景模型的全方位视觉人体运动检测[J].北京大学学报(自然科学版), 2004 .40(3):458-464.
[44] Karmann K and Brandt A. Moving object recognition using an adaptive background memory[J]. In: V Cappellini, Time-varying Image Processing and Moving Object Recognition. 2. Elsevier, Amsterdam, The Netherlands, 1990.
[45] Stauffer C and Crimson W. Adaptive background mixture models for real-time tracking[C]. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, 1999, 2: 246-252.
[46] McKenna S et al. Tracking groups of people[J]. Computer Vision and Image Understanding, 2000, 80 (1):42-56.
[47] Lipton A, Fujiyoshi H and Patil R. Moving target classification and tracking from real-time video[J]. In: Proc IEEE Workshop on Applications of Computer Vision, Princeton, NJ, 1998, 8-14
[48] Anderson C, Bert P and Vander Wal G. Change detection and tracking using pyramids transformation techniques[C]. In: Proc SPIE Conference on Intelligent Robots and Computer Vision, Cambridge, M A, 1985, 579:72 -78.
[49] Barron J, Fleet D and Beauchemin S. Performance of optical flow techniques [J]. International Journal of Computer Vision, 1994, 12(1):42 -77.
[50] Meyer D, Denzler J and Niemann H. Model based extraction of articulated objects in image sequences for gait analysis[C]. In: Proc IEEE International Conference on Image Processing, Santa Barbara, California 1997, 78-81.
[51] Friedman N and Russell S. Image segmentation in video sequences: a probabilistic approach[C]. In: Proc the Thirteenth Conference on Uncertainty in Artificial Intelligence, Rhode Island, USA, 1997.
[52] Stringa E. Morphological change detection algorithms for surveillance applications[C]. In: British Machine Vision Conference, Bristol, UK, 2000, 402-411.
[53] Kass M, Witkin A and Terzopoulos D. Snakes: Active Contour Models[C]. The 1st International Conference of Computer Vision, London, 1987:259-268.
[54]智利丁.智能视频监控中多运动对象的检测与跟踪[D].国防科学技术大学2007,11.
[55] Kalman, R. E. 1960. A New Approach to Linear Filtering and Prediction Problems. ansaction of the ASME[J]. Journal of Basic Engineering, pp. 35-45 (March 1960).
[56] Cedric Demonceaux, Pascal Vasseur, Markov random fields for catadioptric image processing[J], Pattern Recognition Letters , 27 (2006): 1957-1967.
[57] Demonceaux C., Vasseur P., Markov random fields for catadioptric image processing[J], Pattern Recognition Letters, 27 (2006): 1957-1967.
[58] Daniilidis, K., Makadia, A., Blow, T Image processing in catadioptric planes: Spatiotemporal derivatives and optical flow computation[C]. In: IEEE Workshop on Omnidirectional Vision (OMNIVIS02), Copenhagen, Denmark, 2002, pp. 3-10.
[59] Strauss O, Comby F, Variable structuring element based fuzzy morphological operations for single viewpoint omnidirectional images[J], Pattern Recognition, 40(2007):3578-3596.
[60] Jacquey F., Comby F., Strauss O. Fuzzy edge detection for omnidirectional images[J]. Fuzzy Sets and Systems, 159 (2008): 1991-2010.
[61] Ieng S., Benosman R., Devars J., An efficient dynamic multi-angular feature points matcher for catadioptric views[C]. Proceedings of Omnivis 2003, Workshop on Omnidirectional Vision and Camera Networks, Madison, USA, 2003.
[62] Svoboda, T., Pajdla, T. Matching in catadioptric images with appropriate windows, and outliers removal[C]. In: Internat. Conf. On Computer Analysis of Images and Patterns (CAIP01), Warsaw, Poland, 2001,pp. 733-740.
[63] Baker, S., Nayar, S.K.. A theory of single-viewpoint catadioptric image formation[J]. Internt. J. Comput. Vision (IJCV) , 1999, 35 (N2): 175-196.
[64] Geyer, C., Daniilidis, K.. Catadioptric projective geometry[J]. Internat. J. Comput. Vision (IJCV) , 2001, 45 (N3): 223-243.
[65] Barreto J. P. , Araujo H. Geometric Properties of Central Catadioptric Line Images and Their Application in Calibration[C]. IEEE Transactions on Pattern Analysis and Machine intellegence, 27(8)(2005):1327-1333.
[66] Mei C., Rives P., Single View Point Omnidirectional Camera Calibration from Planar Grids[C]. In: Proceedings of IEEE International Conference on Robotics and Automation (2007), pp. 3945-3950.
[67] Barreto P. and Araujo H.,Geometric Properties of Central Catadioptric Line Images and Their Application in Calibration[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8),2005, pp:1327-1333.
[68]刘传才,图像理解与计算机视觉[M],厦门大学出版社, 2002.
[69]邓小明,吴福朝,段福庆,吴毅红,胡占义.基于一维标定物的反射折射摄像机标定方法[J].计算机学报. 2007,30(5):737-747.
[70] Aliaga D G. Accurate catadioptric calibration for real-time pose estimation in room size environments[C]. Proceedings of the 8th International Conferenee on Computer Vision. Vancouver, BC, 2001, 1:127-134.
[71] Vasseur P, M ouaddib E1 M. Central catadioptric line detection[C]. Proceedings ofthe British Machine Vision Conference. Kingston University, London, 2004.
[72] Geyer C, Daniilids K. Paracatadioptric camera calibration[J]. IEEE Transactions on Pattern Analysis and M aehine Intelligence, 2002, 24(5): 687-695.
[73] Barreto J P, Araujo H. Geometry properties of central catadioptric line images and application in calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(8):1327-1333.
[74] Ying X, Hu Z. Catadioptrie camera calibration using geometric invariants[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(10) :1260-1271.
[75] Kang S B. Catadioptric self-calibration[C]. Proceedings of the IEEE Conference on Co mputer Vision and Pattern Recognition. Hilton H ead Island, SC, U SA, 2000, 1:201-207.
[76] Mei, C. Malis, E., Fast Central Catadioptric Line Extraction[C]. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006, pp: 4774-4779.
[77] Toriia A., Imiya A., The randomized-Hough-transform-based method for great-circle detection on sphere[J]. Pattern Recognition Letters. Volume 28, Issue 10, 2007, pp:1186-1192.