People detection method using graphics processing units for a mobile robot with an omnidirectional camera
Chung-Ang University, Graduate School of Advanced Imaging, Science, Multimedia and Film, Department of Imaging Science and Arts, 221 Huksuk-dong, Dongjak-ku, Seoul, 156-756, Republic of Korea
Optical Engineering, Volume 50, Issue 12, 2011
@article{kang2011people,
title={People detection method using graphics processing units for a mobile robot with an omnidirectional camera},
author={Kang, S. and Roh, A. and Nam, B. and Hong, H.},
journal={Optical Engineering},
volume={50},
number={12},
pages={127204},
year={2011}
}
This paper presents a novel vision system for people detection using an omnidirectional camera mounted on a mobile robot. In order to determine regions of interest (ROI), we compute a dense optical flow map using graphics processing units, which enable us to examine compliance with the ego-motion of the robot in a dynamic environment. Shape-based classification algorithms are employed to sort ROIs into human beings and nonhumans. The experimental results show that the proposed system detects people more precisely than previous methods.
January 10, 2012 by hgpu
