View Alignment with Dynamically Updated Affine Tracking

We propose a framework for fast view alignment using adaptive affine tracking. We address the issue of modelling both shape and texture information in eigenspace for view alignment. We present an effective bootstrapping process based on colour segmentation and selective attention. We recover affine parameters with dynamic updates to the eigenspace using most recent history and perform predictions in parameter space. Experimental results are given to illustrate our approach.

• Type: Conference
• Year: 1998
• Where: FGR
• Authors: Fernando De la Torre, Shaogang Gong, Stephen J. McKenna
• Keywords: Adaptive Affine Tracking, Biometrics, Fast View Alignment, FGR 1998, View Alignment