Title :
Motion segmentation by fuzzy clustering with automatic determination of the number of motions
Author :
Duc, Benoît ; Schroeter, Philippe ; Bigün, Josef
Author_Institution :
Signal Process. Lab., Swiss Federal Inst. of Technol., Lausanne, Switzerland
Abstract :
A layered motion estimation scheme using fuzzy clustering is introduced in this paper. Once motion estimation is performed a modified objective criterion is applied to discard non significant classes
Keywords :
fuzzy set theory; image recognition; image segmentation; motion estimation; automatic determination; fuzzy clustering; layered motion estimation scheme; modified objective criterion; motion segmentation; Computer vision; Eigenvalues and eigenfunctions; Equations; Image processing; Image sequences; Laboratories; Motion estimation; Motion segmentation; Optical computing; Signal processing;
Conference_Titel :
Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-8186-7282-X
DOI :
10.1109/ICPR.1996.547449
