Fast k Nearest Neighbor Search using GPU
Universitu de Nice-Sophia Antipolis/CNRS Laboratoire I3S, 2000 route des Lucioles, 06903, France
arXiv:0804.1448v1 [cs.CV] (9 Apr 2008)
@article{garcia2008fast,
title={Fast k nearest neighbor search using gpu},
author={Garcia, V. and Debreuve, E. and Barlaud, M.},
year={2008},
publisher={IEEE}
}
The recent improvements of graphics processing units (GPU) offer to the computer vision community a powerful processing platform. Indeed, a lot of highly-parallelizable computer vision problems can be significantly accelerated using GPU architecture. Among these algorithms, the k nearest neighbor search (KNN) is a well-known problem linked with many applications such as classification, estimation of statistical properties, etc. The main drawback of this task lies in its computation burden, as it grows polynomially with the data size. In this paper, we show that the use of the NVIDIA CUDA API accelerates the search for the KNN up to a factor of 120.
October 27, 2010 by hgpu
