Authors:
Yuanyuan Liu
1
;
Jingying Chen
2
;
Leyuan Liu
2
;
Yujiao Gong
3
and
Nan Luo
3
Affiliations:
1
Central China Normal University, Collaborative & Innovative Center for Educational Technology (CICET) and Huazhong University of Science and Technology Wenhua College, China
;
2
Central China Normal University and Collaborative & Innovative Center for Educational Technology (CICET), China
;
3
Central China Normal University, China
Keyword(s):
Dirichlet-tree distribution enhanced random forests. Head pose estimation. Gaussion mixture model. Positive patch extraction.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Gaussian Processes
;
Geometry and Modeling
;
ICA, PCA, CCA and other Linear Models
;
Image-Based Modeling
;
Incremental Learning
;
Learning and Adaptive Control
;
Multiclassifier Fusion
;
Object Recognition
;
Pattern Recognition
;
Software Engineering
;
Theory and Methods
Abstract:
Head pose estimation is important in human-machine interfaces. However, illumination variation, occlusion
and low image resolution make the estimation task difficult. Hence, a Dirichlet-tree distribution enhanced
Random Forests approach (D-RF) is proposed in this paper to estimate head pose efficiently and robustly under
various conditions. First, Gabor features of the facial positive patches are extracted to eliminate the influence
of occlusion and noise. Then, the D-RF is proposed to estimate the head pose in a coarse-to-fine way. In order
to improve the discrimination capability of the approach, an adaptive Gaussian mixture model is introduced
in the tree distribution. The proposed method has been evaluated with different data sets spanning from -90º
to 90º in vertical and horizontal directions under various conditions.The experimental results demonstrate the
approach’s robustness and efficiency.