Abstract
Reliable and accurate car driver head pose estimation is an important function for the next generation of Advanced Driver Assistance Systems that need to consider the driver state in their analysis. For optimal performance, head pose estimation needs to be non-invasive, calibration-free and accurate for varying driving and illumination conditions. In this pilot study we investigate a 3D head pose estimation system that automatically fits a statistical 3D face model to measurements of a driver's face, acquired with a low-cost depth sensor on challenging real-world data. We evaluate the results of our sensor-independent, driver-adaptive approach to those of a state-of-the-art camera-based 2D face tracking system as well as a non-adaptive 3D model relative to own ground-truth data, and compare to other 3D benchmarks. We find large accuracy benefits of the adaptive 3D approach. Our system shows a median error of 5.99 mm for position and 2.12° for rotation while delivering a full 6-DOF pose with very little degradation from strong illumination changes or out-of-plane rotations of more than 50°. In terms of accuracy, 95% of all our results have a position error of less than 9.50 mm, and a rotation error of less than 4.41°. Compared to the 2D method, this represents a 59.7% reduction of the 95% rotation accuracy threshold, and a 56.1% reduction of the median rotation error.
Original document
The different versions of the original document can be found in:
Document information
Published on 01/01/2016
Volume 2016, 2016
DOI: 10.1109/itsc.2016.7795719
Licence: CC BY-NC-SA license
Share this document
Keywords
claim authorship
Are you one of the authors of this document?