ADAPTIVE SEGMENTATION FOR GYMNASTIC EXERCISES BASED ON CHANGE DETECTION OVER MULTIRESOLUTION COMBINED DIFFERENCES (MA-P4)

Author(s) : José M. Cobo (Universidad Politécnica de Madrid, Spain) Luis Salgado (Universidad Politécnica de Madrid, Spain) Julian Cabrera (Universidad Politécnica de Madrid, Spain)

Abstract : A new adaptive segmentation strategy is proposed to accurately segment gymnasts in sport sequences. It is based on a Markov Random Fields (MRF) change detection analysis operating on a multiresolution combination of static and dynamic image differences. After a morphological analysis of the segmented masks, it incorporates estimated motion information in the area of interest to refine the segmentation process. Besides, segmentation parameters are dynamically modified according to an efficient estimation of the global motion of the scene. Although presented in the particular context of gymnastic exercises, the new segmentation strategy could be applied to other applications where moving objects on a quasi-static background need to be segmented.

Menu