Title :
Attributed hypergraph representations for dynamic vision
Author :
Rong, L. ; Wong, A.K.C.
Author_Institution :
Pattern Analysis & Machine Intell. Group, Waterloo Univ., Ont., Canada
Abstract :
Investigates the use of an attributed hypergraph (AH) as a generic and hierarchical representation for dynamic vision, and examines its mathematical perspective in the framework of category theory. As shown in Kass et al. (1988), attributed hypergraph representation (AHR) is able to render a direct, general and flexible representation for describing objects/models with geometrical and physical features. With this representation, analysis and synthesis of structural/visual patterns can be carried out at different resolution levels. This paper presents the application of AHR in motion analysis and automatic morphing
Keywords :
category theory; computer vision; graph theory; motion estimation; attributed hypergraph representations; automatic morphing; category theory; dynamic vision; flexible representation; geometrical features; hierarchical representation; motion analysis; physical features; structural/visual patterns; Animation; Automation; Deformable models; Machine intelligence; Machine vision; Motion analysis; Optimization methods; Pattern analysis; Psychology; Solid modeling;
Conference_Titel :
Systems, Man, and Cybernetics, 1996., IEEE International Conference on
Print_ISBN :
0-7803-3280-6
DOI :
10.1109/ICSMC.1996.569842
