Title :
Parameterized modeling and recognition of activities
Author :
Yacoob, Yaser ; Black, Michael J.
Author_Institution :
Comput. Vision Lab., Maryland Univ., College Park, MD, USA
Abstract :
A framework for modeling and recognition of temporal activities is proposed. The modeling of sets of exemplar activities is achieved by parameterizing their representation in the form of principal components. Recognition of spatio-temporal variants of modeled activities is achieved by parameterizing the search in the space of admissible transformations that the activities can undergo. Experiments on recognition of articulated and deformable object motion from image motion parameters are presented
Keywords :
image sequences; motion estimation; activities recognition; admissible transformations; articulated object motion; deformable object motion; exemplar activities; image motion parameters; parameterized modeling; recognition; spatio-temporal variants; Cameras; Computer vision; Foot; Humans; Image recognition; Image sequences; Laboratories; Principal component analysis; Thigh; Torso;
Conference_Titel :
Computer Vision, 1998. Sixth International Conference on
Conference_Location :
Bombay
Print_ISBN :
81-7319-221-9
DOI :
10.1109/ICCV.1998.710709
