Real-Time Posture Reconstruction for Microsoft Kinect

Real-Time Posture Reconstruction for Microsoft Kinect

Abstract

The recent advancement of motion recognition using Microsoft Kinect stimulates many new ideas in motion capture and virtual reality applications. Utilizing a pattern recognition algorithm, Kinect can determine the positions of different body parts from the user. However, due to the use of a single depth camera, recognition accuracy drops significantly when the parts are occluded. This hugely limits the usability of applications that involves interaction with external objects, such as sport training or exercising systems. The problem becomes more critical when Kinect incorrectly perceives the body parts. This is because applications have limited information about the recognition correctness, and using those parts to synthesize a body postures would result in serious visual artifacts. In this paper, we propose a new method to reconstruct valid movement from incomplete and noisy postures captured by Kinect. We first design a set of measurements that objectively evaluates the degree of reliability on each tracked body part. By incorporating the reliability estimation into a motion database query during run-time, we obtain a set of similar postures that are kinematically valid. These postures are used to construct a latent space, which is known as the natural posture space in our system, with local Principle Component Analysis (PCA). We finally apply frame-based optimization in the space to synthesize a new posture that closely resembles the true user posture while satisfying kinematic constraints. Experimental results show that our method can significantly improve the quality of the recognized posture under severely occluded environments, such as a person exercising with a basketball or moving in a small room.

Publication

Hubert P. H. Shum, Edmond S. L. Ho, Yang Jiang and Shu Takagi,
"Real-Time Posture Reconstruction for Microsoft Kinect",
IEEE Transactions on Cybernetics (TCyb)

Citation=100## IF=8.803#

# Impact factor from the Journal Citation Reports as of 2017
## Citation count from Google Scholar as of 2018

Downloads

YouTube

References

BibTeX

@article{shum13realtime,
 author={Shum, Hubert P. H. and Ho, Edmond S. L. and Jiang, Yang and Takagi, Shu},
 journal={IEEE Transactions on Cybernetics},
 title={Real-Time Posture Reconstruction for Microsoft Kinect},
 year={2013},
 volume={43},
 number={5},
 pages={1357--1369},
 numpages={13},
 doi={10.1109/TCYB.2013.2275945},
 issn={2168-2267},
 publisher={IEEE},
}

EndNote/RefMan

TY  - JOUR
AU  - Shum, Hubert P. H.
AU  - Ho, Edmond S. L.
AU  - Jiang, Yang
AU  - Takagi, Shu
T2  - IEEE Transactions on Cybernetics
TI  - Real-Time Posture Reconstruction for Microsoft Kinect
PY  - 2013
VL  - 43
IS  - 5
SP  - 1357
EP  - 1369
DO  - 10.1109/TCYB.2013.2275945
SN  - 2168-2267
PB  - IEEE
ER  - 

Plain Text

Hubert P. H. Shum, Edmond S. L. Ho, Yang Jiang and Shu Takagi, "Real-Time Posture Reconstruction for Microsoft Kinect," IEEE Transactions on Cybernetics, vol. 43, no. 5, pp. 1357-1369, IEEE, 2013.

Similar Research

 

         

Last update: 14/01/2019