Title :
Commentary Paper 3 on Visual Players Detection and Tracking in Soccer Matches
Author_Institution :
Electr. & Comput. Eng. Dept., Univ. of Michigan-Dearborn, Dearborn, MI, USA
Abstract :
This manuscript presents object detection and tracking in video clips of soccer matches. Background subtraction based framework on pixel energy is proposed to detect objects in the input video clip with varying light conditions, high frame rates, and real-time processing. Unsupervised clustering is then used classify detected objects into various classes. A stochastic approach based on maximum a posteriori probability (MAP) is proposed for object tracking.
Keywords :
maximum likelihood estimation; object detection; pattern clustering; sport; unsupervised learning; video signal processing; background subtraction; maximum a posteriori probability; object detection; object tracking; player tracking; soccer matches; stochastic approach; unsupervised clustering; visual players detection; Computer vision; Equations; Games; Object detection; Parameter estimation; Performance analysis; Power engineering and energy; Stochastic processes; Surveillance; Videoconference;
Conference_Titel :
Advanced Video and Signal Based Surveillance, 2008. AVSS '08. IEEE Fifth International Conference on
Conference_Location :
Santa Fe, NM
Print_ISBN :
978-0-7695-3341-4
Electronic_ISBN :
978-0-7695-3422-0
DOI :
10.1109/AVSS.2008.79
