Parallelization Methods of the Template Matching Method on Graphics Accelerators
John von Neumann Faculty of Informatics, Obuda University
16th IEEE International Symposium on Computational Intelligence and Informatics (CINTI 2015), 2015
@article{kertesz2015parallelization,
title={Parallelization Methods of the Template Matching Method on Graphics Accelerators},
author={Kert{‘e}sz, G{‘a}bor and Sz{‘e}n{‘a}si, S{‘a}ndor and V{‘a}mossy, Zolt{‘a}n},
year={2015}
}
Template matching is a classic technique used in image processing for object detection. It is based on multiple matrix-based calculations, where there are no dependencies on partial results, so parallel solutions could be created. In this article two GPU implemented methods are presented and compared to the CPU-based sequential solution.
December 6, 2015 by hgpu
