6 March 2014 Real-time 3D human pose recognition from reconstructed volume via voxel classifiers
Author Affiliations +
Abstract
This paper presents a human pose recognition method which simultaneously reconstructs a human volume based on ensemble of voxel classifiers from a single depth image in real-time. The human pose recognition is a difficult task since a single depth camera can capture only visible surfaces of a human body. In order to recognize invisible (self-occluded) surfaces of a human body, the proposed algorithm employs voxel classifiers trained with multi-layered synthetic voxels. Specifically, ray-casting onto a volumetric human model generates a synthetic voxel, where voxel consists of a 3D position and ID corresponding to the body part. The synthesized volumetric data which contain both visible and invisible body voxels are utilized to train the voxel classifiers. As a result, the voxel classifiers not only identify the visible voxels but also reconstruct the 3D positions and the IDs of the invisible voxels. The experimental results show improved performance on estimating the human poses due to the capability of inferring the invisible human body voxels. It is expected that the proposed algorithm can be applied to many fields such as telepresence, gaming, virtual fitting, wellness business, and real 3D contents control on real 3D displays.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
ByungIn Yoo, Changkyu Choi, Jae-Joon Han, Changkyo Lee, Wonjun Kim, Sungjoo Suh, Dusik Park, Junmo Kim, "Real-time 3D human pose recognition from reconstructed volume via voxel classifiers", Proc. SPIE 9013, Three-Dimensional Image Processing, Measurement (3DIPM), and Applications 2014, 901306 (6 March 2014); doi: 10.1117/12.2037152; https://doi.org/10.1117/12.2037152
PROCEEDINGS
8 PAGES


SHARE
Back to Top