Skip navigation
Skip navigation

Monocular and Stereo Methods for AAM Learning from Video

Saragih, Jason; Goecke, Roland

Description

The active appearance model (AAM) is a powerful method for modeling deformable visual objects. One of the major drawbacks of the AAM is that it requires a training set of pseudo-dense correspondences over the whole database. In this work, we investigate the utility of stereo constraints for automatic model building from video. First, we propose a new method for automatic correspondence finding in monocular images which is based on an adaptive template tracking paradigm. We then extend this...[Show more]

CollectionsANU Research Publications
Date published: 2007
Type: Conference paper
URI: http://hdl.handle.net/1885/39132
Source: Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR 2007)
DOI: 10.1109/CVPR.2007.383058

Download

File Description SizeFormat Image
01_Saragih_Monocular_and_Stereo_Methods_2007.pdf466 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator