In this paper, we present a new scheme to robustly estimate the head pose from either video sequence or individual images. Developed from ISOMAP, we learn a person-independent and nonlinear embedding space (we call it a 2-D feature space) for different poses. A nonlinear interpolation is proposed to map new sequences or images into the 2-D feature space. Especially for video sequences, we propose an adaptive local fitting technique to filter unreasonable mappings. By exploring the intrinsic characteristics, we further estimate the head pose of that sequence or image. Experiments reported in this paper showed robust results.
Head pose estimation by non-linear embedding and mapping
01.01.2005
456629 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Head Pose Estimation by Non-Linear Embedding and Mapping
| British Library Conference Proceedings | 2005
Multi-camera head pose estimation
| British Library Online Contents | 2012
Driver Head Pose Estimation by Regression
| Springer Verlag | 2015
Head pose estimation for driver monitoring
| IEEE | 2004
Head Pose Estimation for Driver Monitoring
| British Library Conference Proceedings | 2004