Feature Detection and Description using a Harris-Hessian/FREAK Combination on an Embedded GPU

Max Danielsson, Thomas Sievert, Håkan Grahn, Jim Rasmusson

2016

Abstract

GPUs in embedded platforms are reaching performance levels comparable to desktop hardware, thus it becomes interesting to apply Computer Vision techniques. We propose, implement, and evaluate a novel feature detector and descriptor combination, i.e., we combine the Harris-Hessian detector with the FREAK binary descriptor. The implementation is done in OpenCL, and we evaluate the execution time and classification performance. We compare our approach with two other methods, FAST/BRISK and ORB. Performance data is presented for the mobile device Xperia Z3 and the desktop Nvidia GTX 660. Our results indicate that the execution times on the Xperia Z3 are insufficient for real-time applications while desktop execution shows future potential. Classification performance of Harris-Hessian/FREAK indicates that the solution is sensitive to rotation, but superior in scale variant images.

Paper Citation

in Harvard Style

Danielsson M., Sievert T., Grahn H. and Rasmusson J. (2016). Feature Detection and Description using a Harris-Hessian/FREAK Combination on an Embedded GPU . In Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-173-1, pages 517-525. DOI: 10.5220/0005662005170525

in Bibtex Style

@conference{icpram16,
author={Max Danielsson and Thomas Sievert and Håkan Grahn and Jim Rasmusson},
title={Feature Detection and Description using a Harris-Hessian/FREAK Combination on an Embedded GPU},
booktitle={Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2016},
pages={517-525},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005662005170525},
isbn={978-989-758-173-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Feature Detection and Description using a Harris-Hessian/FREAK Combination on an Embedded GPU
SN - 978-989-758-173-1
AU - Danielsson M.
AU - Sievert T.
AU - Grahn H.
AU - Rasmusson J.
PY - 2016
SP - 517
EP - 525
DO - 10.5220/0005662005170525