HIERARCHICAL SEGMENTATION OF VIDEO SEQUENCES FOR CONTENT MANIPULATIONAND ADAPTIVE CODING

The problem of unsupervised hierarchical segmentation of video content is discussed. A segmentation approach combining local spatial homogen eity with motion homogeneity is proposed. Motion is the main character istic which allows the decomposition of video sequences into a nested hierarchy of representation levels, each of them corresponding to a sp ecified quality of motion compensation in terms of a proposed criterio n. Two strategies of construction of such a hierarchy are studied. The first, a purely bottom-up approach, favours local motion homogeneity and constructs a hierarchical representation starting from the most de tailed (gray-level based) segmentation then progressively merging the region primitives. The second, a cooperative strategy, uses a global m otion analysis to guide the bottom-up approach. Results on test sequen ces MPEG ISO SC29/WG11 show interesting performances of such technique s for an automatic construction of hierarchical representations of tim e-varying images, allowing for flexible access and manipulation of vid eo content. (C) 1998 Elsevier Science B.V. All rights reserved.