Robust segmentation of moving image sequences

This paper introduces a method for a hierarchical representation of moving image sequences. The basic level of this hierarchy is a spatial segmentation, rich in regions and whose contours are localised very precisely. The next levels are constructed by a motion-based progressive merging of regions. Different levels of this hierarchy are nested. This representation is sufficiently flexible to allow a "logical zoom" in the image content and to provide a scalable bit rate. So the two goals of content manipulation and of image compression can be reached.

[1]  Dominique Barba,et al.  Spatio-temporal segmentation of image sequences for object-oriented low bit-rate image coding , 1996, Signal Process. Image Commun..

[2]  Henri Sanson.  Toward a robust parametric identification of motion on regions of arbitrary shape by nonlinear optimization , 1995, Proceedings., International Conference on Image Processing.

[3]  Henri Nicolas,et al.  Region-based motion estimation using deterministic relaxation schemes for image sequence coding , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.