Depth cameras allow to setup reliable solutions for people monitoring and behavior understanding, specially when unstable or poor illumination conditions make unusable common RGB sensors. Therefore, we propose a complete framework for the estimation of the head and shoulder pose based on depth images only. A head detection and localization module is also included, in order to develop a complete...

Depth estimation Single-image depth estimation is a fundamental problem in computer vision, which has found broad applications in scene understanding, 3D modeling, and robotics. The problem is challenging since no reliable depth cues are available. In this task, the algorithms output a depth image based on a single RGB input image. To demonstrate the efficacy of our synthetic data, we compare t...

In this paper, we propose a robust motion estimation algorithm using uncalibrated 3D motion model considering depth discontinuity. Most of the previous direct motion estimation algorithms with 3D motion model compute the depth value through the local smoothing, which result in erroneous results at depth discontinuity. In this paper, we overcome this problem at depth discontinuity by adding disc...