Browse by author
Lookup NU author(s): Teymoor Ali, Dr Deepayan BhowmikORCiD
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
© 2023, The Author(s). Image processing algorithms on FPGAs have increasingly become more pervasive in real-time vision applications. Such algorithms are computationally complex and memory intensive, which can be severely limited by available hardware resources. Optimisations are therefore necessary to achieve better performance and efficiency. We hypothesise that, unlike generic computing optimisations, domain-specific image processing optimisations can improve performance significantly. In this paper, we propose three domain-specific optimisation strategies that can be applied to many image processing algorithms. The optimisations are tested on popular image-processing algorithms and convolution neural networks on CPU/GPU/FPGA and the impact on performance, accuracy and power are measured. Experimental results show major improvements over the baseline non-optimised versions for both convolution neural networks (MobileNetV2 & ResNet50), Scale-Invariant Feature Transform (SIFT) and filter algorithms. Additionally, the optimised FPGA version of SIFT significantly outperformed an optimised GPU implementation when energy consumption statistics are taken into account.
Author(s): Ali T, Bhowmik D, Nicol R
Publication type: Article
Publication status: Published
Journal: Journal of Signal Processing Systems
Year: 2023
Volume: 95
Pages: 1167–1179
Online publication date: 09/09/2023
Acceptance date: 28/07/2023
Date deposited: 18/09/2023
ISSN (print): 1939-8018
ISSN (electronic): 1939-8115
Publisher: Springer Nature
URL: https://doi.org/10.1007/s11265-023-01888-2
DOI: 10.1007/s11265-023-01888-2
Data Access Statement: The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
Altmetrics provided by Altmetric
