3D face and motion from feature points using adaptive constrained minima

This paper presents a novel method for reconstructing 3D geometry of camera motion and human-face model from a video sequence. The approach combines the concepts of Powell's line minimization with gradient descent. We adapted the line minimization with bracketing used in Powell's minimizat...

Full description

Saved in:
Bibliographic Details
Main Authors: Chouvatut,V., Madarasmi,S., Tucerya,M.
Format: Article
Published: Maruzen Co., Ltd/Maruzen Kabushikikaisha 2015
Subjects:
Online Access:http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=80155164016&origin=inward
http://cmuir.cmu.ac.th/handle/6653943832/38604
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-38604
record_format dspace
spelling th-cmuir.6653943832-386042015-06-16T07:53:33Z 3D face and motion from feature points using adaptive constrained minima Chouvatut,V. Madarasmi,S. Tucerya,M. Computer Graphics and Computer-Aided Design Applied Mathematics Electrical and Electronic Engineering Signal Processing This paper presents a novel method for reconstructing 3D geometry of camera motion and human-face model from a video sequence. The approach combines the concepts of Powell's line minimization with gradient descent. We adapted the line minimization with bracketing used in Powell's minimization to our method. However, instead of bracketing and searching deep down a direction for the minimum point along that direction as done in their line minimization, we achieve minimization by bracketing and searching for the direction in the bracket which provides a lower energy than the previous iteration. Thus, we do not need a large memory as required by Powell's algorithm. The approach to moving in a better direction is similar to classical gradient descent except that the derivative calculation and a good starting point are not needed. The system's constraints are also used to control the bracketing direction. The reconstructed solution is further improved using the Levenberg Marquardt algorithm. No average face model or known-coordinate markers are needed. Feature points defining the human face are tracked using the active appearance model. Occluded points, even in the case of self occlusion, do not pose a problem. The reconstructed space is normalized where the origin can be arbitrarily placed. To use the obtained reconstruction, one can rescale the computed volume to a known scale and transform the coordinate system to any other desired coordinates. This is relatively easy since the 3D geometry of the facial points and the camera parameters of all frames are explicitly computed. Robustness to noise and lens distortion, and 3D accuracy are also demonstrated. All experiments were conducted with an off-the-shelf digital camera carried by a person walking without using any dolly to demonstrate the robustness and practicality of the method. Our method does not require a large memory or the use of any particular, expensive equipment. Copyright © 2011 The Institute of Electronics, Information and Communication Engineers. 2015-06-16T07:53:33Z 2015-06-16T07:53:33Z 2011-11-01 Article 09168508 2-s2.0-80155164016 10.1587/transfun.E94.A.2207 http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=80155164016&origin=inward http://cmuir.cmu.ac.th/handle/6653943832/38604 Maruzen Co., Ltd/Maruzen Kabushikikaisha
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
topic Computer Graphics and Computer-Aided Design
Applied Mathematics
Electrical and Electronic Engineering
Signal Processing
spellingShingle Computer Graphics and Computer-Aided Design
Applied Mathematics
Electrical and Electronic Engineering
Signal Processing
Chouvatut,V.
Madarasmi,S.
Tucerya,M.
3D face and motion from feature points using adaptive constrained minima
description This paper presents a novel method for reconstructing 3D geometry of camera motion and human-face model from a video sequence. The approach combines the concepts of Powell's line minimization with gradient descent. We adapted the line minimization with bracketing used in Powell's minimization to our method. However, instead of bracketing and searching deep down a direction for the minimum point along that direction as done in their line minimization, we achieve minimization by bracketing and searching for the direction in the bracket which provides a lower energy than the previous iteration. Thus, we do not need a large memory as required by Powell's algorithm. The approach to moving in a better direction is similar to classical gradient descent except that the derivative calculation and a good starting point are not needed. The system's constraints are also used to control the bracketing direction. The reconstructed solution is further improved using the Levenberg Marquardt algorithm. No average face model or known-coordinate markers are needed. Feature points defining the human face are tracked using the active appearance model. Occluded points, even in the case of self occlusion, do not pose a problem. The reconstructed space is normalized where the origin can be arbitrarily placed. To use the obtained reconstruction, one can rescale the computed volume to a known scale and transform the coordinate system to any other desired coordinates. This is relatively easy since the 3D geometry of the facial points and the camera parameters of all frames are explicitly computed. Robustness to noise and lens distortion, and 3D accuracy are also demonstrated. All experiments were conducted with an off-the-shelf digital camera carried by a person walking without using any dolly to demonstrate the robustness and practicality of the method. Our method does not require a large memory or the use of any particular, expensive equipment. Copyright © 2011 The Institute of Electronics, Information and Communication Engineers.
format Article
author Chouvatut,V.
Madarasmi,S.
Tucerya,M.
author_facet Chouvatut,V.
Madarasmi,S.
Tucerya,M.
author_sort Chouvatut,V.
title 3D face and motion from feature points using adaptive constrained minima
title_short 3D face and motion from feature points using adaptive constrained minima
title_full 3D face and motion from feature points using adaptive constrained minima
title_fullStr 3D face and motion from feature points using adaptive constrained minima
title_full_unstemmed 3D face and motion from feature points using adaptive constrained minima
title_sort 3d face and motion from feature points using adaptive constrained minima
publisher Maruzen Co., Ltd/Maruzen Kabushikikaisha
publishDate 2015
url http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=80155164016&origin=inward
http://cmuir.cmu.ac.th/handle/6653943832/38604
_version_ 1681421503764103168