Towards structure and motion estimation from dynamic silhouettes

Tanuja Joshi, Narendra Ahuja, Jean Ponce

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We address the problem of estimating the structure and motion of a smooth curved object from its silhouettes observed over time by a trinocular imagery. We first construct a model for the local structure along the silhouette for each frame in the temporal sequence. The local models are then integrated into a global surface description by estimating the motion between successive frames. The algorithm tracks certain surface and image features (parabolic points and silhouette inflections, frontier points) which are used to bootstrap the motion estimation process. The whole silhouette is then used to refine the initial motion estimate. We have implemented the proposed approach and report preliminary results.

Original languageEnglish (US)
Title of host publicationMotion of Non-Rigid and Articulated Obgects Workshop, Proceedings
PublisherIEEE
Pages166-171
Number of pages6
StatePublished - 1994
EventProceedings of the Workshop on Motion of Non-Rigid and Articulated Objects - Austin, TX, USA
Duration: Nov 11 1994Nov 12 1994

Other

OtherProceedings of the Workshop on Motion of Non-Rigid and Articulated Objects
CityAustin, TX, USA
Period11/11/9411/12/94

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Towards structure and motion estimation from dynamic silhouettes'. Together they form a unique fingerprint.

  • Cite this

    Joshi, T., Ahuja, N., & Ponce, J. (1994). Towards structure and motion estimation from dynamic silhouettes. In Motion of Non-Rigid and Articulated Obgects Workshop, Proceedings (pp. 166-171). IEEE.