Paper Info
Title
Real-time 3D human pose recognition from reconstructed volume via voxel classifiers
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.
Year
DOI
Venue
2014
10.1117/12.2037152
Proceedings of SPIE
Keywords
Field
DocType
Volume Decomposition,Ray-casting,Volume Reconstruction,Human Pose Recognition
Voxel,Computer vision,Decision tree,Pattern recognition,Stereo display,Ray casting,Artificial intelligence,Virtual fitting,Volumetric data,Volume reconstruction,Physics,Bayesian probability
Conference
Volume
ISSN
Citations 
9013
0277-786X
0
PageRank 
References 
Authors
0.34
7
8
Name
Order
Citations
PageRank
ByungIn Yoo1365.52
Changkyu Choi215914.99
Jae-Joon Han3181.40
changkyo lee400.34
Wonjun Kim530126.50
Sungjoo Suh6272.89
Du Sik Park724629.09
Junmo Kim847642.50