Robust region merging for spatio-temporal segmentation

A region merging technique for spatio-temporal segmentation of scenes is presented. The proposed technique is a bottom-up method and expects an initial set of regions. These regions are compared on the basis of a similarity measure that integrates both spatial and temporal information. The unsupervised merging procedure is based on a weighted, directed graph that is updated dynamically. Two graph based clustering rules are presented. These rules are used to cluster regions into ensembles that represent meaningful objects present in the scene. Experimental results demonstrate the efficiency of the proposed method.