A non-iterative greedy algorithm for multi-frame point correspondence

We present a framework for finding point correspondences in monocular image sequences over multiple frames. The general problem of multiframe point correspondence is NP hard for three or more frames. A polynomial time algorithm for a restriction of this problem is presented, and is used as the basis of proposed greedy algorithm for the general problem. The greedy nature of the proposed algorithm allows it to be used in real time systems for tracking and surveillance etc. In addition, the proposed algorithm deals with the problems of occlusion, missed detections, and false positives, by using a single noniterative greedy optimization scheme, and hence, reduces the complexity of the overall algorithm as compared to most existing approaches, where multiple heuristics are used for the same purpose. While most greedy algorithms for point tracking do not allow for entry and exit of points from the scene, this is not a limitation for the proposed algorithm. Experiments with real and synthetic data show that the proposed algorithm outperforms the existing techniques and is applicable in more general settings.

[1]  J. Todd.  Visual information about rigid and nonrigid motion: a geometric analysis. , 1982, Journal of experimental psychology. Human perception and performance.

[2]  Aubrey B. Poore,et al.  Computational experiences with hot starts for a moving window implementation of track maintenance , 1998, Defense, Security, and Sensing.

[3]  E. Reed.  The Ecological Approach to Visual Perception , 1989 .

[4]  Kathryn Fraughnaugh,et al.  Introduction to graph theory , 1973, Mathematical Gazette.

[5]  H. Barlow.  Vision: A computational investigation into the human representation and processing of visual information: David Marr. San Francisco: W. H. Freeman, 1982. pp. xvi + 397 , 1983 .

[6]  Minoru Asada,et al.  Representation of three-dimensional motion in dynamic scenes , 1982, Comput. Vis. Graph. Image Process..

[7]  Ingemar J. Cox,et al.  A review of statistical data association techniques for motion correspondence , 1993, International Journal of Computer Vision.

[8]  Richard M. Karp,et al.  A n^5/2 Algorithm for Maximum Matchings in Bipartite Graphs , 1971, SWAT.

[9]  M. Dawson,et al.  The how and why of what went where in apparent motion: modeling solutions to the motion correspondence problem. , 1991, Psychological review.

[10]  Cor J. Veenman,et al.  Resolving Motion Correspondence for Densely Moving Points , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

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

[12]  J. Gibson.  The Ecological Approach to Visual Perception , 1979 .

[13]  William B. Thompson,et al.  Disparity Analysis of Images , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Richard M. Karp,et al.  A n^5/2 Algorithm for Maximum Matchings in Bipartite Graphs , 1971, SWAT.

[15]  Y. Bar-Shalom,et al.  A generalized S-D assignment algorithm for multisensor-multitarget state estimation , 1997, IEEE Transactions on Aerospace and Electronic Systems.

[16]  James F. Gimpel,et al.  Covering Points of a Digraph with Point-Disjoint Paths and Its Application to Code Optimization , 1977, JACM.

[17]  Ishwar K. Sethi,et al.  Finding Trajectories of Feature Points in a Monocular Image Sequence , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Dmitry Chetverikov,et al.  Feature Point Tracking for Incomplete Trajectories , 1999, Computing.

[19]  Dmitry Chetverikov,et al.  Experimental Comparative Evaluation of Feature Point Tracking Algorithms , 1998, Theoretical Foundations of Computer Vision.

[20]  C. Trevarthen.  Review: Cognition and Reality: Principles and Implications of Cognitive Psychology , 1977 .

[21]  Thomas S. Huang,et al.  Uniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects with Curved Surfaces , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  S. Ullman.  The Interpretation of Visual Motion , 1979 .

[23]  Michael Jenkin,et al.  Tracking three-dimensional moving light displays , 1986, Workshop on Motion.

[24]  Yaakov Bar-Shalom,et al.  Sonar tracking of multiple targets using joint probabilistic data association , 1983 .

[25]  Mubarak Shah,et al.  Tracking across multiple cameras with disjoint views , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[26]  Ingemar J. Cox,et al.  On Finding Ranked Assignments With Application to Multi-Target Tracking and Motion Correspondence , 1995 .

[27]  Minoru Asada,et al.  Automatic Analysis of Moving Images , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  R. Danchick,et al.  A fast method for finding the exact N-best hypotheses for multitarget tracking , 1993 .

[29]  Mubarak Shah,et al.  Establishing motion correspondence , 1991, CVGIP Image Underst..

[30]  Mubarak Shah,et al.  Tracking and Object Classification for Automated Surveillance , 2002, ECCV.

[31]  Ingemar J. Cox,et al.  An Efficient Implementation of Reid's Multiple Hypothesis Tracking Algorithm and Its Evaluation for the Purpose of Visual Tracking , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  R. F. Rashid,et al.  Towards a system for the interpretation of moving light displays , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  G Johansson,et al.  Spatio-temporal differentiation and integration in visual motion perception , 1976, Psychological research.

[34]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[35]  Aubrey B. Poore,et al.  Multidimensional Assignments and Multitarget Tracking , 1993, Partitioning Data Sets.

[36]  Ishwar K. Sethi,et al.  Feature Point Correspondence in the Presence of Occlusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..