Title :
Motion segmentation by SCC on the hopkins 155 database
Author :
Chen, Guangliang ; Lerman, Gilad
Author_Institution :
Sch. of Math., Univ. of Minnesota, Minneapolis, MN, USA
fDate :
Sept. 27 2009-Oct. 4 2009
Abstract :
We apply the Spectral Curvature Clustering (SCC) algorithm to a benchmark database of 155 motion sequences, and show that it outperforms all other state-of-the-art methods. The average misclassification rate by SCC is 1.41% for sequences having two motions and 4.85% for three motions.
Keywords :
image classification; image motion analysis; image segmentation; image sequences; pattern clustering; Hopkins 155 database; misclassification rate; motion segmentation; motion sequences; spectral curvature clustering; Computer vision; Conferences; Databases; Motion segmentation;
Conference_Titel :
Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4244-4442-7
Electronic_ISBN :
978-1-4244-4441-0
DOI :
10.1109/ICCVW.2009.5457626
