We propose to use a state-of-the-art visual odometry technique for the purpose of head pose estimation. We demonstrate that with small adaptation this algorithm allows to achieve more accurate head pose estimation from an RGBD sensor than all the methods published to date. We also propose a novel methodology to automatically assess the accuracy of a tracking algorithm without the need to manual...

In this paper we propose a performance criterion for the depth estimation of an active vision system. It is well-known that the linear velocity of the camera must satisfy some constraints for a success of the depth estimation. However, these constraints cannot ensure a good convergence performance of the depth estimation. Our criterion is an extension from an estimation result of a linear syste...