Monocular and Stereo Methods for AAM Learning from Video
-
Altmetric Citations
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]
dc.contributor.author | Saragih, Jason | |
---|---|---|
dc.contributor.author | Goecke, Roland | |
dc.coverage.spatial | Minneapolis USA | |
dc.date.accessioned | 2015-12-10T21:55:46Z | |
dc.date.created | June 18-23 2007 | |
dc.identifier.isbn | 1424411807 | |
dc.identifier.uri | http://hdl.handle.net/1885/39132 | |
dc.description.abstract | 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 method to take the scene geometry into account, proposing three approaches, each accounting for the availability of the fundamental matrix and calibration parameters or the lack thereof. The performance of the monocular method was first evaluated on a pre-annotated database of a talking face. We then compared the monocular method against its three stereo extensions using a stereo database. | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE Inc) | |
dc.relation.ispartofseries | Computer Vision and Pattern Recognition Conference (CVPR 2007) | |
dc.source | Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR 2007) | |
dc.source.uri | http://cvpr.cv.ri.cmu.edu/ | |
dc.subject | Keywords: Database systems; Learning systems; Mathematical models; Parameter estimation; Set theory; Active appearance model (AAM); Calibration parameters; Fundamental matrix; Stereo vision | |
dc.title | Monocular and Stereo Methods for AAM Learning from Video | |
dc.type | Conference paper | |
local.description.notes | Imported from ARIES | |
local.description.refereed | Yes | |
dc.date.issued | 2007 | |
local.identifier.absfor | 080104 - Computer Vision | |
local.identifier.ariespublication | u3357961xPUB172 | |
local.type.status | Published Version | |
local.contributor.affiliation | Saragih, Jason, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Goecke, Roland, College of Engineering and Computer Science, ANU | |
local.description.embargo | 2037-12-31 | |
local.bibliographicCitation.startpage | 1 | |
local.bibliographicCitation.lastpage | 8 | |
local.identifier.doi | 10.1109/CVPR.2007.383058 | |
dc.date.updated | 2015-12-09T07:31:46Z | |
local.identifier.scopusID | 2-s2.0-34948907356 | |
Collections | ANU Research Publications |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Saragih_Monocular_and_Stereo_Methods_2007.pdf | 466 kB | Adobe PDF | Request a copy |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator