Title :
Region-based affine motion segmentation using color information
Author :
Eren, Erhan P. ; Altunbasak, Yucel ; Tekalp, Murat A.
Author_Institution :
Dept. of Electr. Eng., Rochester Univ., NY, USA
Abstract :
This paper presents region-based affine motion parameter clustering methods by motion-vector and intensity matching to provide improved robustness and alignment of motion boundaries with real object boundaries. Regions may be formed as fixed- or variable-size rectangular blocks, triangular patches, or arbitrary-shaped areas defined by color or texture uniformity. A particular combination of these affine clustering methods is then proposed to obtain the best segmentation results on a variety of image sequences. Experimental results showing the benefits of the proposed scheme are provided
Keywords :
edge detection; image colour analysis; image matching; image segmentation; image sequences; image texture; motion estimation; affine clustering methods; alignment; arbitrary-shaped areas; color; color information; image sequences; intensity matching; motion boundaries; motion-vector; object boundaries; rectangular blocks; region-based affine motion parameter clustering methods; region-based affine motion segmentation; robustness; texture; triangular patches; Bayesian methods; Clustering methods; Computer vision; Deformable models; Estimation error; Image segmentation; Image sequences; Motion estimation; Motion segmentation; Robustness;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on
Conference_Location :
Munich
Print_ISBN :
0-8186-7919-0
DOI :
10.1109/ICASSP.1997.595424
