Showing papers by "Shai Avidan published in 2001"
01 Dec 2001
TL;DR: This work shows results of using a homogeneous quadratic polynomial kernel-SVT for vehicle tracking in image sequences and builds pyramids from the support vectors and uses a coarse-to-fine approach in the classification stage.
Abstract: Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames, we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using a homogeneous quadratic polynomial kernel-SVT for vehicle tracking in image sequences.
554 citations
TL;DR: Applications include recovery of camera ego-motion from a sequence of views, image stabilization across a sequence, and multi-view image based rendering.
Abstract: We present a new function that operates on fundamental matrices across a sequence of views. The operation, we call "threading", connects two consecutive fundamental matrices using the trifocal tensor as the connecting thread. The threading operation guarantees that consecutive camera matrices are consistent with a unique 3D model, without ever recovering a 3D model. Applications include recovery of camera ego-motion from a sequence of views, image stabilization across a sequence, and multi-view image based rendering.
59 citations