3D Skeleton Extraction Method using Potential Field on OpenCL
Department of Computer Science and Engineering, South China University of Technology, Guangzhou, People’s Republic of China
International Conference on Computer Science and Service System (CSSS 2014), 305
@inproceedings{lu20143d,
title={3D Skeleton Extraction Method using Potential Field on OpenCL},
author={Lu, Lu and Xuewen, Wang},
booktitle={3rd International Conference on Computer Science and Service System},
year={2014},
organization={Atlantis Press}
}
For 3D skeleton extraction, the algorithm based on generalized potential fields, known as the outstandingly flexible and robust method, is suffering from seriously heavy computational burden. In this paper, we put forward a parallel algorithm based on OpenCL heterogeneous parallel framework, which can make full use of the great computing power provided by heterogeneous model of CPU+GPU. This algorithm focuses on computing the potential field of each interior point in parallel, with the goal of cutting down the time of potential field calculation to relieve the whole computational burden of this extraction algorithm. The proposed parallel algorithm was evaluated by using several large 3D object volumes. From the tests, we can find that the whole calculation time can be reduced up to 5 to 10 times, without affecting the extraction’s accuracy.
June 9, 2014 by hgpu
