序列图象运动检测的预处理技术
摘要
本文主要讨论运动距离自动检测的问题。要自动地、准确地检测出运动距离，能否检测出真实的运动即成为一个关键的问题。图象的变化通常是多种因素综合作用的结果，显而易见，消除运动以外的其它因素(如光照，噪声等)引起的变化就成为必不可少的一步。本文给出的方法以散射图去除光照影响和静止背景，用噪声的中位数直接估计其方差，从而去除噪声，检测出由运动引起的变动，最后自动检测运动距离。
This thesis makes a discussion on auto-detection of motion displacement. Change detection thus becomes the key issue. Conventional simple image subtraction detects all difference regardless of their source and is problematic to use. So, it is necessary to isolate the local difference due to the motion from the global difference due to the illumination variations. Scattergram is used to resolve this problem. Then the noise is removed by means of the variance that is estimated directly from the median of the noise. Finally, an auto-detection is made for the motion displacement from the difference image undergone the above pre-processings.
This thesis makes a discussion on auto-detection of motion displacement. Change detection thus becomes the key issue. Conventional simple image subtraction detects all difference regardless of their source and is problematic to use. So, it is necessary to isolate the local difference due to the motion from the global difference due to the illumination variations. Scattergram is used to resolve this problem. Then the noise is removed by means of the variance that is estimated directly from the median of the noise. Finally, an auto-detection is made for the motion displacement from the difference image undergone the above pre-processings.
引文
[1]S.C.Brofferio. An object-background image model for predictive video coding. IEEE Trans. Communications, 37:1391-1394,1989.
[2]Y.H.Yang and M.D.Levine. The background primal sketch: An approach for tracking moving objects. Machine Vision and Application .5:17-34, 1992
[3]I.Dinstein.A new technique for visual motion alarm. Pattern Recognition Letters, 8:347-345, 1998
[4]S.C.Brofferio. An object-background image model for predicted video coding. IEEE Trans. Communications. 37:1391-1394, 1989.
[5]D. Murray and A. Basu, Motion Tracking with an Active Camera, IEEE Trans. Pattern Analysis and Machine Intell ,16(5), 1994,449-459
[6]T. F.Knoll, L.L. Brinkley, and E.J.Delp. Difference picture algorithms for the analysis of extracellar components of histological images.J.Histochem. Cytochem., 33:261-267,1985.
[7]Chen Shapen. Spatio-temporal Demension for Earth Observing with Remote Sensing[J]. Journal of Remote Sensing, 1997,1(3): 161-169.
[8]A.Singh. Digital change detection techniques using remotely-sensed data. Int.J.Remote Sensing, 10:989-1003,1989.
[9]"Advanced Video-Based Surveillance Systems,"ed.C.S.Regazzoni, G.Fabri, and G.Vernazza,Kluwer Academic Publishers(1999)
[10]E.Stringa and C.S.Regazzoni, "Real Time Video-shot Detection for Scene Surveillance Applications". IEEE Transactions on Image Processing, Vol.9,No.1,January 2000
[11]J.D.Courtney, "Automatic video Indexing via Object Motion Analysis," Pattern Recognition, Vol.30,No.4,pp.607-625.
[12]lim H,Tan K C, TanBTG, New methods for restoring motion-blurred images derived from edge error consideration [J].CVGIP, 1991,53:419-490.
[13]P.L. Rosin, Threshiolding for change detection. Technical Report ISTR-97-01. Brunel University, 1997.
[14]柳海峰，姚郁．Kalman滤波抗野值方法研究．计算机自动测量与控制，2001．9(6)
[15]颜东等．基于辨识ARMA模型的野值剔除方法与卡尔曼滤波修正算法．信息与控制，Vol．24，No．3 1995．
[16]Jiawei Han & Micheline Kamber Data Mining:Concept and Techniques. Morgan Kaufmann Publishers,Inc.
[17]刘政凯 瞿建雄；数字图象恢复与重建，合肥：中国科技大学出版社，1989，PP．148-174．
[18]Bassevile M, Nike forov IV. Detection of Abrupt changes: Theory and Application. Prentice Hall Infor & Syst. Sci Series John Wiley &Sons ,1996
[19]Bassevile M. Detection changes in signals and systems-a survey Automation, 1988,24(3):309-326
[20]Kerr TH. Detection lized filtering and redundanvy management for multisensor navigation IEEE T Electronic Systems, 1987. AES_23;83-119
[21]傅京孙著；程民德等译，模式识别应用 北京：北京大学出版社
[22]Faitakis YE, Kantor J C. Residual generation and Fault detection for discrete time systems using and L technique. Int J Control ,1996,64(1) 155-174
[23]Bassevile M, Nikiforov I. A unifield frame work for statistical change detection .Proc. 30th IEEE conference on Decision and Control, Brighton, UK, 1991
[24]Patton R J,etal Fault diagnos is in dynamic system -theory and application, International series in systems and Control Engineering ,Prentic Hall International ,London, UK, 1989.
[25]第一届全国智能视觉监控学术会议论文集 2002年5月，北京．
[26]H.Voorhees and T. Poggio. Detecting textons and texture boundaries in natural images. In Int. Conf. Computer Vision,pages 250-258,1987.
[27]P.L. Rosin, Threshiolding for change detection. Technical Report ISTR-97-01. Brunel University, 1997.
[28]Y.Z. Hsu, H.H. Nagel, and G. Rekers. New likelihood test methods for change
detection in image sequences. Computer Vision, Graphics, and Image Processing, 26: 373-106, 1984
[29]H.J. Eghbali, K-S test for detecting changes from Landsat imagery data. IEEE Trans. on Systems, Man, and Cybernetics, 9: 17-23, 1979
[30]H.J. Eghbali, K-S test for detecting changes from Landsat imagery data. IEEE Trans. on Systems, Man, and Cybernetics, 9:17-23, 1979
[31]B.Chanda, "Application of Binary Mathematical Morphology to Separate Overlapped Objects". Pattern Recognition Letters, September 1992.
[32]P.L. Rosin and T. Ellis, Image difference threshold strategies and shadow detection .In British Machine Vision Conf., pages 347-356,1995.
[33]P.A. Bromiley, N.A.Tracker, and P. Countney. "Non-parametric image subtraction using grey level scattergrams". In 11th British Machine Vision Conference, British Machine Vision Association, Bristol, UK, 2000.
[34]郑捷文；基于对流方程和Hough变换的运动模糊图象恢复[D]，广州：暨南大学计算机科学系，2002．
[35]CAI Li-Dong. "Traveling Wave Equations and Restoration of Motion-Blurred Images". 自动化学报，Vol.29. No.3 466-471 2003.5.
[2]Y.H.Yang and M.D.Levine. The background primal sketch: An approach for tracking moving objects. Machine Vision and Application .5:17-34, 1992
[3]I.Dinstein.A new technique for visual motion alarm. Pattern Recognition Letters, 8:347-345, 1998
[4]S.C.Brofferio. An object-background image model for predicted video coding. IEEE Trans. Communications. 37:1391-1394, 1989.
[5]D. Murray and A. Basu, Motion Tracking with an Active Camera, IEEE Trans. Pattern Analysis and Machine Intell ,16(5), 1994,449-459
[6]T. F.Knoll, L.L. Brinkley, and E.J.Delp. Difference picture algorithms for the analysis of extracellar components of histological images.J.Histochem. Cytochem., 33:261-267,1985.
[7]Chen Shapen. Spatio-temporal Demension for Earth Observing with Remote Sensing[J]. Journal of Remote Sensing, 1997,1(3): 161-169.
[8]A.Singh. Digital change detection techniques using remotely-sensed data. Int.J.Remote Sensing, 10:989-1003,1989.
[9]"Advanced Video-Based Surveillance Systems,"ed.C.S.Regazzoni, G.Fabri, and G.Vernazza,Kluwer Academic Publishers(1999)
[10]E.Stringa and C.S.Regazzoni, "Real Time Video-shot Detection for Scene Surveillance Applications". IEEE Transactions on Image Processing, Vol.9,No.1,January 2000
[11]J.D.Courtney, "Automatic video Indexing via Object Motion Analysis," Pattern Recognition, Vol.30,No.4,pp.607-625.
[12]lim H,Tan K C, TanBTG, New methods for restoring motion-blurred images derived from edge error consideration [J].CVGIP, 1991,53:419-490.
[13]P.L. Rosin, Threshiolding for change detection. Technical Report ISTR-97-01. Brunel University, 1997.
[14]柳海峰，姚郁．Kalman滤波抗野值方法研究．计算机自动测量与控制，2001．9(6)
[15]颜东等．基于辨识ARMA模型的野值剔除方法与卡尔曼滤波修正算法．信息与控制，Vol．24，No．3 1995．
[16]Jiawei Han & Micheline Kamber Data Mining:Concept and Techniques. Morgan Kaufmann Publishers,Inc.
[17]刘政凯 瞿建雄；数字图象恢复与重建，合肥：中国科技大学出版社，1989，PP．148-174．
[18]Bassevile M, Nike forov IV. Detection of Abrupt changes: Theory and Application. Prentice Hall Infor & Syst. Sci Series John Wiley &Sons ,1996
[19]Bassevile M. Detection changes in signals and systems-a survey Automation, 1988,24(3):309-326
[20]Kerr TH. Detection lized filtering and redundanvy management for multisensor navigation IEEE T Electronic Systems, 1987. AES_23;83-119
[21]傅京孙著；程民德等译，模式识别应用 北京：北京大学出版社
[22]Faitakis YE, Kantor J C. Residual generation and Fault detection for discrete time systems using and L technique. Int J Control ,1996,64(1) 155-174
[23]Bassevile M, Nikiforov I. A unifield frame work for statistical change detection .Proc. 30th IEEE conference on Decision and Control, Brighton, UK, 1991
[24]Patton R J,etal Fault diagnos is in dynamic system -theory and application, International series in systems and Control Engineering ,Prentic Hall International ,London, UK, 1989.
[25]第一届全国智能视觉监控学术会议论文集 2002年5月，北京．
[26]H.Voorhees and T. Poggio. Detecting textons and texture boundaries in natural images. In Int. Conf. Computer Vision,pages 250-258,1987.
[27]P.L. Rosin, Threshiolding for change detection. Technical Report ISTR-97-01. Brunel University, 1997.
[28]Y.Z. Hsu, H.H. Nagel, and G. Rekers. New likelihood test methods for change
detection in image sequences. Computer Vision, Graphics, and Image Processing, 26: 373-106, 1984
[29]H.J. Eghbali, K-S test for detecting changes from Landsat imagery data. IEEE Trans. on Systems, Man, and Cybernetics, 9: 17-23, 1979
[30]H.J. Eghbali, K-S test for detecting changes from Landsat imagery data. IEEE Trans. on Systems, Man, and Cybernetics, 9:17-23, 1979
[31]B.Chanda, "Application of Binary Mathematical Morphology to Separate Overlapped Objects". Pattern Recognition Letters, September 1992.
[32]P.L. Rosin and T. Ellis, Image difference threshold strategies and shadow detection .In British Machine Vision Conf., pages 347-356,1995.
[33]P.A. Bromiley, N.A.Tracker, and P. Countney. "Non-parametric image subtraction using grey level scattergrams". In 11th British Machine Vision Conference, British Machine Vision Association, Bristol, UK, 2000.
[34]郑捷文；基于对流方程和Hough变换的运动模糊图象恢复[D]，广州：暨南大学计算机科学系，2002．
[35]CAI Li-Dong. "Traveling Wave Equations and Restoration of Motion-Blurred Images". 自动化学报，Vol.29. No.3 466-471 2003.5.