Entropy-based metrics for the analysis of partial and total occlusion in video object tracking

Metrics measuring tracking reliability under occlusion that are based on mutual information and do not resort to ground truth data are proposed. Metrics for both the initialisation of the region to be tracked as well as for measuring the performance of the tracking algorithm are presented. The metrics variations may be interpreted as a quantitative estimate of changes in the tracking region due to occlusion, sudden movement or deformation of the tracked object. Performance metrics based on the Kullback -Leibler distance and normalised correlation were also added for comparison purposes. The proposed approach was tested on an object tracking scheme using multiple feature point correspondences. Experimental results have shown that mutual information can effectively characterise object appearance and reappearance in many computer vision applications.

[1]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[2]  Masud Mansuripur,et al.  Introduction to information theory , 1986 .

[3]  C Tomasi,et al.  Shape and motion from image streams: a factorization method. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Daniel P. Huttenlocher,et al.  Tracking non-rigid objects in complex scenes , 1993, 1993 (4th) International Conference on Computer Vision.

[5]  Edward H. Adelson,et al.  Representing moving images with layers , 1994, IEEE Trans. Image Process..

[6]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[7]  오승준.  [서평]「Digital Video Processing」 , 1996 .

[8]  U. Uenohara,et al.  Geometric invariants for verification in 3-D object tracking , 1996, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96.

[9]  Lalit Kumar,et al.  Object tracking using affine structure for point correspondences , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Anil K. Jain,et al.  Object Tracking Using Deformable Templates , 1998, ICCV.

[11]  Jitendra Malik,et al.  Tracking people with twists and exponential maps , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[12]  Gregory D. Hager,et al.  Efficient Region Tracking With Parametric Models of Geometry and Illumination , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Stan Birchfield,et al.  Depth and motion discontinuities , 1999 .

[14]  Natan Peterfreund,et al.  Robust Tracking of Position and Velocity With Kalman Snakes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Minh N. Do,et al.  Texture similarity measurement using Kullback-Leibler distance on wavelet subbands , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[16]  Bernt Schiele,et al.  Using Mutual Information To Combine Object Models , 2000 .

[17]  Yongmin Kim,et al.  Video object tracking with a sequential hierarchy of template deformations , 2001, IEEE Trans. Circuits Syst. Video Technol..

[18]  A. Murat Tekalp,et al.  Metrics for performance evaluation of video object segmentation and tracking without ground-truth , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[19]  Gregory D. Hager,et al.  Probabilistic Data Association Methods for Tracking Complex Visual Objects , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Zhi-Pei Liang,et al.  A bound on mutual information for image registration , 2001, IEEE Transactions on Medical Imaging.

[21]  A. M. Tekalp,et al.  Multiple camera tracking of interacting and occluded human motion , 2001, Proc. IEEE.

[22]  M. Worring,et al.  Occlusion robust adaptive template tracking , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[23]  Bernt Schiele,et al.  Context-driven model switching for visual tracking , 2001, Robotics Auton. Syst..

[24]  A. Murat Tekalp,et al.  Video object tracking with feedback of performance measures , 2003, IEEE Trans. Circuits Syst. Video Technol..

[25]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[26]  P. K. Chaturvedi,et al.  Communication Systems , 2002, IFIP — The International Federation for Information Processing.

[27]  David J. Fleet,et al.  Performance of optical flow techniques , 1994, International Journal of Computer Vision.