Robust Head Pose Estimation based on Key-Frames for human-machine interaction
Résumé
Human can interact with several kinds of machine (motor vehicle, robots, among others) in different ways. One way is through his/her head pose. In this work we propose a head pose estimation framework that combines 2D and 3D cues using the concept of Key-Frames (KF). KFs are a set frames learned automatically offline that consist: 2D features, encoded through Speeded Up Robust Features (SURF) descriptors; 3D information, captured by Fast Point Feature Histograms (FPFH) descriptors; and target's head orientation (pose) in real world coordinates, which is represented through a 3D facial model. Then, the KF information is re-enforced through a global optimization process that minimizes error in a way similar to bundle adjustment. The KF allows to formulate, in an online process, a hypothesis of the head pose in new images that is then refined through an optimization process, performed by the Iterative Closest Point (ICP) algorithm. This KF-based framework can handle partial occlusions and extreme rotations even with noisy depth data, improving the accuracy of pose estimation and detection rate. We evaluate the proposal using two public benchmarks in state-of-art: (1) BIWI Kinect Head Pose Database, and (2) ICT 3D HeadPose Database. In addition, we evaluate this framework with a small but challenging dataset of our own authorship where the targets perform more complex behaviors, that those in the aforementioned public datasets. We show how our approach outperforms relevant state-of-the-art proposals on all these datasets.
Origine : Fichiers produits par l'(les) auteur(s)