Authors:
Ngoc-Trung Tran
1
;
Fakhreddine Ababsa
2
and
Maurice Charbit
3
Affiliations:
1
Telecom ParisTECH and University of Evry, France
;
2
University of Evry, France
;
3
Telecom ParisTECH, France
Keyword(s):
3D Face Tracking, 3D Pose Tracking, Rigid Tracking, Non-rigid Tracking, Face Matching, Synthesized Face, Face Matching.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Human-Computer Interaction
;
Methodologies and Methods
;
Motion and Tracking
;
Motion, Tracking and Stereo Vision
;
Pattern Recognition
;
Physiological Computing Systems
Abstract:
The non-rigid face tracking has been achieved many advances in recent years, but most of empirical experiments are restricted at near-frontal face. This report introduces a robust framework for pose-free tracking of non-rigid face. Our method consists of two phases: training and tracking. In the training phase, a large offline synthesized database is built to train landmark appearance models using linear Support Vector Machine (SVM). In the tracking phase, a two-step approach is proposed: the first step, namely initialization, benefits 2D SIFT matching between the current frame and a set of adaptive keyframes to estimate the rigid parameters. The second step obtains the whole set of parameters (rigid and non-rigid) using a heuristic method via pose-wise SVMs. The combination of these aspects makes our method work robustly up to 90° of vertical axial rotation. Moreover, our method appears to be robust even in the presence of fast movements and tracking losses. Comparing to other publ
ished algorithms, our method offers a very good compromise of rigid and non-rigid parameter accuracies. This study gives a promising perspective because of the good results in terms of pose estimation (average error is less than 4°on BUFT dataset) and landmark tracking precision (5.8 pixel error compared to 6.8 of one state-of-the-art method on Talking Face video). These results highlight the potential of using synthetic data to track non-rigid face in unconstrained poses.
(More)