Robust real-time face tracking and modeling from video

Authors:
Ronghua Liang;Chun Chen;Zhigeng Pan;Jiajun Bu
Affiliations:
College of Computer Science, Zhejiang University, Hangzhou, P.R. China and Institute of VR and Multimedia, Hangzhou Inst. of Electronics Engineering, Hangzhou, P.R. China;College of Computer Science, Zhejiang University, Hangzhou, P.R. China;State Key Lab of CAD&CG, Zhejiang University, Hangzhou, P.R. China;College of Computer Science, Zhejiang University, Hangzhou, P.R. China
Venue:
ICCSA'03 Proceedings of the 2003 international conference on Computational science and its applications: PartI
Year:
2003

Citing 5
Cited 0

A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry

Artificial Intelligence - Special volume on computer vision
Motion texture: a two-level statistical model for character motion synthesis

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Motion graphs

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Interactive control of avatars animated with human motion data

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Real-Time Physically-Based Facial Expression Animation Using Mass-Spring System

CGI '01 Computer Graphics International 2001

Quantified Score

Hi-index	0.00

Visualization

Abstract

Real-time face tracking and 3D reconstruction from video is a challenge in computer graphics and computer vision. We develop a system to track face by integrating image pyramid algorithm and Kalman filter. First, Facial features of the first frame are acquired automatically by Plessey corner detector according to FDP in MPEG-4 and FACS based on anatomical knowledge and general 3D model. And then corner disparity is obtained by image pyramid algorithm and Kalman filter. Kalman filter is employed to resolve the tracking speed and occlusion problems. Finally, 3D model is reconstructed by SfM (Structure from motion). Experimental results show the high prospect of this algorithm, and the two issues of real-time face tracking and modeling are resolved in our algorithm.