A Novel and Effective Short Track Speed Skating Tracking System
This work made publicly available electronically on June 10, 2012.
Abstract
This dissertation proposes a novel and effective system for tracking high-speed skaters. A novel registration method is employed to automatically discover key frames to build the panorama. Then, the homography between a frame and the real world rink can be generated accordingly. Aimed at several challenging tracking problems of short track skating, a novel multiple-objects tracking approach is proposed which includes: Gaussian mixture models (GMMs), evolving templates, constrained dynamical model, fuzzy model, multiple templates initialization, and evolution. The outputs of the system include spatialtemporal trajectories, velocity analysis, and 2D reconstruction animations. The tracking accuracy is about 10 cm (2 pixels). Such information is invaluable for sports experts. Experimental results demonstrate the effectiveness and robustness of the proposed system.
Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .