GPU based extraction of moving objects without shadows under intensity changes
Faculty of Education, Aichi University
Evolutionary Computation, 2008. CEC 2008. (IEEE World Congress on Computational Intelligence). IEEE Congress on In Evolutionary Computation, 2008. CEC 2008. (IEEE World Congress on Computational Intelligence). IEEE Congress on (2008), pp. 4165-4172
@conference{fukui2008gpu,
title={GPU based extraction of moving objects without shadows under intensity changes},
author={Fukui, S. and Iwahori, Y. and Woodham, R.J.},
booktitle={Evolutionary Computation, 2008. CEC 2008.(IEEE World Congress on Computational Intelligence). IEEE Congress on},
pages={4165–4172},
year={2008},
organization={IEEE}
}
This paper proposes a GPU based algorithm for extracting moving objects in real time. The whole process of the proposed approach is handled on GPU. GPU is used for acceleration and the proposed approach increases processing speed dramatically. The method uses a* component and b* component of CIELAB color space without extracting shadow areas as moving objects. It is robust to intensity changes because an estimated background image is generated and moving objects are extracted using background subtraction of the estimated background image and the observed image. The proposed method reduces the times for transferring calculation results from GPU into CPU and the opposite transfer. Reducing the transfer times contributes to speeding up of the proposed method. Results are demonstrated with experiments on real data.
December 8, 2010 by hgpu
