Detection and classification of football players with automatic generation of models

作者：Gomez Jorge R^*; Herrero Jaraba Elias; Angel Montanes Miguel; Martinez Contreras Francisco; Orrite Urunuela Carlos

来源：Optical Engineering, 2010, 49(1): 017005.

DOI：10.1117/1.3294885

• automatic segmentation
• SOM
• clustering algorithm

We focus on the automatic detection and classification of players in a football match. Our approach is not based on any a priori knowledge of the outfits, but on the assumption that the two main uniforms detected correspond to the two football teams. The algorithm is designed to be able to operate in real time, once it has been trained, and is able to detect partially occluded players and update the color of the kits to cope with some gradual illumination changes through time. Our method, evaluated from real sequences, gave better detection and classification results than those obtained by a system using a manual selection of samples to compute a Gaussian mixture model.

• 出版日期2010-1