Comparing discrimination and CFA for selecting tracking features

The ability of a tracker to isolate the foreground target from the background of an image is crucially dependent on the set of features selected for tracking. Collins & Liu [2] propose an on-line, adaptive approach to selecting the set of features based on the insight that the set of features that best discriminate between target and background classes is the best set to use for tracking. In previous work [10], we have proposed an approach based on Combinatorial Fusion Analysis for selecting features for Real-Time tracking. We discuss the relative merits of the two methods and motivate their combination to produce an improved tracking system. We show several results from a difficult tracking sequence with human targets to demonstrate the effectiveness of the combined system.

[1]  D. Frank Hsu,et al.  Consensus Scoring Criteria for Improving Enrichment in Virtual Screening , 2005, J. Chem. Inf. Model..

[2]  D. Frank Hsu,et al.  Combinatorial Fusion Analysis: Methods and Practices of Combining Multiple Scoring Systems , 2006 .

[3]  Damian M. Lyons,et al.  A dynamic pruning and feature selection strategy for real-time tracking , 2005, 19th International Conference on Advanced Information Networking and Applications (AINA'05) Volume 1 (AINA papers).

[4]  Touradj Ebrahimi,et al.  Combination of video-based camera trackers using a dynamically adapted particle filter , 2007, VISAPP.

[5]  R. Collins,et al.  On-line selection of discriminative tracking features , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  Pramod K. Varshney,et al.  Sensor Fusion for Video Surveillance , 2004 .

[7]  Yanxi Liu,et al.  Online Selection of Discriminative Tracking Features , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Larry S. Davis,et al.  Non-parametric Model for Background Subtraction , 2000, ECCV.

[9]  D. Frank Hsu,et al.  Comparing Rank and Score Combination Methods for Data Fusion in Information Retrieval , 2005, Information Retrieval.

[10]  Damian M. Lyons,et al.  Rank-based multisensory fusion in multitarget video tracking , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..

[11]  Hui-Huang Hsu,et al.  Advanced Data Mining Technologies in Bioinformatics , 2006 .

[12]  Ingemar J. Cox,et al.  An efficient implementation and evaluation of Reid's multiple hypothesis tracking algorithm for visual tracking , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[13]  Jake K. Aggarwal,et al.  Physics-based integration of multiple sensing modalities for scene interpretation , 1997 .

[14]  Jacques Verly,et al.  The State of the Art in Multiple Object Tracking Under Occlusion in Video Sequences , 2003 .

[15]  Damian M. Lyons,et al.  Feature selection for real-time tracking , 2006, SPIE Defense + Commercial Sensing.