Perceiving Systems Conference Paper 1998

A Probabilistic framework for matching temporal trajectories: Condensation-based recognition of gestures and expressions

pdf
Thumb ticker sm headshot2021
Perceiving Systems
Director
no image
Perceiving Systems
Bildschirmfoto 2013 01 14 um 09.29.19

The recognition of human gestures and facial expressions in image sequences is an important and challenging problem that enables a host of human-computer interaction applications. This paper describes a framework for incremental recognition of human motion that extends the “Condensation” algorithm proposed by Isard and Blake (ECCV’96). Human motions are modeled as temporal trajectories of some estimated parameters over time. The Condensation algorithm uses random sampling techniques to incrementally match the trajectory models to the multi-variate input data. The recognition framework is demonstrated with two examples. The first example involves an augmented office whiteboard with which a user can make simple hand gestures to grab regions of the board, print them, save them, etc. The second example illustrates the recognition of human facial expressions using the estimated parameters of a learned model of mouth motion.

Author(s): Black, M. J. and Jepson, A. D.
Links:
Book Title: European Conf. on Computer Vision, ECCV-98
Pages: 909-924
Year: 1998
Bibtex Type: Conference Paper (inproceedings)
Address: Freiburg, Germany
Electronic Archiving: grant_archive

BibTex

@inproceedings{Black:ECCV:1998,
  title = {A Probabilistic framework for matching temporal trajectories: Condensation-based recognition of gestures and expressions},
  booktitle = {European Conf. on Computer Vision, ECCV-98},
  abstract = {The recognition of human gestures and facial expressions in image sequences is an important and challenging problem that enables a host of human-computer interaction applications. This paper describes a framework for incremental recognition of human motion that extends the “Condensation” algorithm proposed by Isard and Blake (ECCV’96). Human motions are modeled as temporal trajectories of some estimated parameters over time. The Condensation algorithm uses random sampling techniques to incrementally match the trajectory models to the multi-variate input data. The recognition framework is demonstrated with two examples. The first example involves an augmented office whiteboard with which a user can make simple hand gestures to grab regions of the board, print them, save them, etc. The second example illustrates the recognition of human facial expressions using the estimated parameters of a learned model of mouth motion.},
  pages = {909-924},
  address = {Freiburg, Germany},
  year = {1998},
  slug = {black-eccv-1998},
  author = {Black, M. J. and Jepson, A. D.}
}