DocumentCode
2783305
Title
Active Appearance Models for Automatic Fitting of 3D Morphable Models
Author
Faggian, Nathan ; Paplinski, Andrew P. ; Sherrah, Jamie
Author_Institution
Monash University, Australia
fYear
2006
fDate
Nov. 2006
Firstpage
90
Lastpage
90
Abstract
This paper presents a fast fitting method for 3D Morphable Models (3DMMs). In most cases fitting a Morphable Model to an image is done using slow non-linear optimization processes. We avoid this by introducing a relationship to Active Appearance Models (AAMs) that can be used to linearize the non-linear optimization problem of 3DMM fitting. Using the combination of a constrained AAM and closed form 2D-3D fitting method for 3DMMs we show that a perceptually close 3D shape can be extracted from the AAM fittings. We show preliminary results of the method and a simplified exterior orientation solution. Finally we conclude with a tracking algorithm that is based on the combination of the AAM and 3DMM, presenting the tracking and reconstruction errors.
Keywords
Active appearance model; Eigenvalues and eigenfunctions; Equations; Face; Fitting; Head; Humans; Image texture analysis; Principal component analysis; Shape;
fLanguage
English
Publisher
ieee
Conference_Titel
Video and Signal Based Surveillance, 2006. AVSS '06. IEEE International Conference on
Conference_Location
Sydney, Australia
Print_ISBN
0-7695-2688-8
Type
conf
DOI
10.1109/AVSS.2006.16
Filename
4020749
Link To Document