International Journal of Computer Vision

, Volume 31, Issue 1, pp 31-50

First online:

Structure and Motion Estimation from Dynamic Silhouettes under Perspective Projection

  • Tanuja JoshiAffiliated withMicrosoft Corporation, One Microsoft Way
  • , Narendra AhujaAffiliated withBeckman Institute, University of Illinois
  • , Jean PonceAffiliated withBeckman Institute, University of Illinois

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access


We address the problem of estimating the structure and motion of a smooth curved object from its silhouettes observed over time by a trinocular stereo rig under perspective projection. 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 time instants. The algorithm tracks certain surface features (parabolic points) and image features (silhouette inflections and frontier points) which are used to bootstrap the motion estimation process. The entire silhouettes along with the reconstructed local structure are then used to refine the initial motion estimate. We have implemented the proposed approach and report results on real images.

motion estimation 3D structure estimation silhouettes occluding contours trinocular stereo frontier points epipolar curves