Depei Bao
ABSTRACT
The image projection has been proven to be an effective method for extracting image features. This paper utilizes multiple facial cues extracted by the projection function for driver vigilance monitoring. To measure vigilance, we calculate two metrics: PERCLOS and PERROTAT from facial state estimation. The main advantage of the presented system in contrast to existing ones is the usage of cheap equipment (only one monocular camera) to achieve a good cost-performance ratio and fast computation time.
- Bachmann, Thomas, BMW and Bujnoch, Stephan. Connecteddrive - driver assistance systems for the future, Technical report, 2002.Google Scholar
- Bekiaris. A. System for effective assessment of driver vigilance and warning according to traffic risk estimation - awake, Technical report, National Center for Research and Technology Hellas (CERTH) Hellenic Institute of Transport (HIT), 2002.Google Scholar
- Feng GC, Yuen PC, Variance projection function and its application to eye detection for human face recognition {J}, Pattern Recognition Letters, 1998. Google ScholarDigital Library
- Ji Qiang: 3D Face pose estimation and tracking from a monocular camera, Image Vision Computing. 20(7): 499--511 (2002).Google ScholarCross Ref
- Saito, S. Does fatigue exist in a quantitative of eye movement? Ergonomics, 35: 607--615, 1992.Google ScholarCross Ref
- Ueno, H., Kaneda, M. & Tsukino, M. (1994) Development of drowsiness detection system. Proceedings of 1994 Vehicle Navigation and Information Systems Conference, Yokohama, Japan, August 1994, pp. 15--20.Google ScholarCross Ref
Index Terms
- Projection function for driver fatigue monitoring with monocular camera
Recommendations
Semi-dense Visual Odometry for a Monocular Camera
ICCV '13: Proceedings of the 2013 IEEE International Conference on Computer VisionWe propose a fundamentally novel approach to real-time visual odometry for a monocular camera. It allows to benefit from the simplicity and accuracy of dense tracking - which does not depend on visual features - while running in real-time on a CPU. The ...
Monocular scene flow estimation via variational method
Scene flow provides the 3D motion field of point clouds, which correspond to image pixels. Current algorithms usually need complex stereo calibration before estimating flow, which has strong restrictions on the position of the camera. This paper ...
3D pedestrian localization fusing via monocular camera
AbstractIn the field of intelligent transportation, autonomous driving technologies, especially visual sensing solutions have attracted increasing attention in recent years. There are still some challenges in pedestrian location based on the monocular ...
Comments