Title :
Feature grouping in moving objects
Author_Institution :
NEC Res. Inst., Princeton, NJ, USA
Abstract :
We address the problem of grouping points or features common to a single object. In this paper we consider the processing of a sequence of two-dimensional orthogonal projections of a three-dimensional scene containing an unknown number of independently-moving rigid objects. We describe a computationally inexpensive algorithm that can determine the number of bodies and which points belong to which body
Keywords :
feature extraction; motion estimation; computationally inexpensive algorithm; feature grouping; independently-moving rigid objects; moving objects; three-dimensional scene; two-dimensional orthogonal projections; Cameras; Clustering algorithms; Data mining; Gears; Independent component analysis; Layout; Matrix decomposition; National electric code; Performance analysis; Singular value decomposition;
Conference_Titel :
Motion of Non-Rigid and Articulated Objects, 1994., Proceedings of the 1994 IEEE Workshop on
Conference_Location :
Austin, TX
Print_ISBN :
0-8186-6435-5
DOI :
10.1109/MNRAO.1994.346233
