Title :
Iterative motion-based segmentation for object-based video coding
Author :
Csillag, Péter ; Böröczky, Lilla
Author_Institution :
KFKI Res. Inst. for Meas. & Comput. Tech., Budapest, Hungary
Abstract :
In this paper a new iterative motion-based segmentation algorithm is presented for object-based video coding. At first, dense motion fields between image pairs are obtained by a multiresolution motion estimation algorithm. Based on these motion fields a set of global motion vectors are determined by an iterative vector quantisation procedure. Using the global motion vectors, the images are segmented into homogenous regions. Covered and uncovered areas of the background and objects are properly recognized by examining two consecutive motion fields. Experimental results for artificial as well for real-life video have shown that the proposed algorithm results in good quality segmentation label fields while it requires only moderate computations
Keywords :
image segmentation; image sequences; iterative methods; motion estimation; vector quantisation; video coding; artificial video; covered areas; dense motion fields; global motion vectors; homogenous regions; image pairs; image segmentation; iterative motion-based segmentation; iterative vector quantisation; multiresolution motion estimation algorithm; object-based video coding; real-life video; segmentation label fields; uncovered areas; Computational complexity; Image resolution; Image segmentation; Image sequences; Iterative algorithms; Motion estimation; Spatial resolution; Spatiotemporal phenomena; Vector quantization; Video coding;
Conference_Titel :
Image Processing, 1997. Proceedings., International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8183-7
DOI :
10.1109/ICIP.1997.647387
