In this paper a coarse-to-fine system framework for analyzing the head gesture is presented. We discuss several important modules from computer vision aspects, including the pose-invariant face detection, face tracking, pose determination and high-resolution image reconstruction for eye pupils detection. Visual cues using intensity images obtained from in-car cameras are explored. A pose-invariant face detection algorithm is used to get the initial face area; afterwards face tracking and validation step is proposed to segment the face region for pose determination. The algorithm is tested on the drivers images under natural driving conditions. Experimental results show that the algorithm is robust to the head pose changes as well as the illumination changes. In this system framework, we propose that when coarse analysis utilizing the head pose alone is not sufficient for driver's behavior analysis, a finer analysis based on the eye gaze tracking is used, which requires images with sufficient resolution. A novel super-resolution reconstruction algorithm is proposed to help reveal more facial details, so as to facilitate the pupil detection. Experiment on the synthesis data shows the effectiveness of the super-resolution reconstruction algorithm.
Visual Modules for Head Gesture Analysis in Intelligent Vehicle Systems
2006-01-01
18597549 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Visual Modules for Head Gesture Analysis in Intelligent Vehicle Systems
British Library Conference Proceedings | 2006
|Learning Visual Behavior for Gesture Analysis
British Library Conference Proceedings | 1995
|Head gesture recognition for hands-free control of an intelligent wheelchair
Tema Archiv | 2007
|Eye Gesture Analysis with Head Movement for Advanced Driver Assistance Systems
BASE | 2012
|