Header logo is ps

Parameterized modeling and recognition of activities




In 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 model in its class. We provide several experiments on recognition of articulated and deformable human motions from image motion parameters.

Author(s): Yacoob, Y. and Black, M. J.
Journal: Computer Vision and Image Understanding
Volume: 73
Number (issue): 2
Pages: 232--247
Year: 1999

Department(s): Perceiving Systems
Bibtex Type: Article (article)
Paper Type: Journal

DOI: 10.1006/cviu.1998.0726

Links: pdf
pdf from publisher


  title = {Parameterized modeling and recognition of activities},
  author = {Yacoob, Y. and Black, M. J.},
  journal = {Computer Vision and Image Understanding},
  volume = {73},
  number = {2},
  pages = {232--247},
  year = {1999}