Parameterized Modeling and Recognition of Activities

DMCA

Parameterized Modeling and Recognition of Activities (1999)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Yaser Yacoob , Michael Black

Venue:	Computer Vision and Image Understanding
Citations:	203 - 7 self

BibTeX

@ARTICLE{Yacoob99parameterizedmodeling,
    author = {Yaser Yacoob and Michael Black},
    title = {Parameterized Modeling and Recognition of Activities},
    journal = {Computer Vision and Image Understanding},
    year = {1999},
    volume = {73},
    pages = {232--247}
}

OpenURL

Abstract

this paper we consider a class of human activities--atomic activities--which can be represented as a set of measurements over a finite temporal window (e.g., the motion of human body parts during a walking cycle) and which has a relatively small space of variations in performance. A new approach for modeling and recognition of atomic activities that employs principal component analysis and analytical global transformations is proposed. The modeling of sets of exemplar instances of activities that are similar in duration and involve similar body part motions is achieved by parameterizing their representation using principal component analysis. The recognition of variants of modeled activities is achieved by searching the space of admissible parameterized transformations that these activities can undergo. This formulation iteratively refines the recognition of the class to which the observed activity belongs and the transformation parameters that relate it to the mod el in its class. We provide several experiments on recognition of articulated and deformable human motions from image motion parameters. 1999 Academic Press 1.

Keyphrases

principal component analysis mod el image motion parameter finite temporal window similar body part motion deformable human motion human activity atomic activity modeled activity exemplar instance walking cycle human body part new approach admissible parameterized transformation transformation parameter analytical global transformation observed activity belongs small space academic press several experiment

DMCA