Multi-resolution Tracking in Space and Time

This paper proposes efficient and robust methods for tracking a moving object at multiple spatial and temporal resolution levels. The efficiency comes from optimising the amounts of spatial and temporal data processed. The robustness results from multi-level coarse-to-fine statespace searching. Tracking across resolution levels incurs a accuracy-versus-speed trade-off. For example, tracking at higher resolutions incurs greater processing cost, while maintaining higher accuracy in estimating the position of the moving object. We propose a novel spatial multi-scale tracker that tracks at the optimal accuracy-versus-speed operating point. Next, we relax this requirement to propose a multi-resolution tracker that operates at a minimum acceptable performance level. Finally, we extend these ideas to a multi-resolution spatio-temporal tracker. We show results of extensive experimentation in support of the proposed approaches.

• Type: Conference
• Year: 2008
• Where: ICVGIP
• Authors: Sumantra Dutta Roy, Son Dinh Tran, Larry S. Davis, B. Sreenivasa Vikram
• Keywords: Computer Vision, ICVGIP 2008, Multi-resolution Spatio-temporal Tracker, Resolution Levels, Temporal Resolution Levels