Suitability of recent hardware accelerators (DSPs, FPGAs, and GPUs) for computer vision and image processing algorithms

作者：

Highlights：

•

• Important considerations when selecting hardware accelerators are discussed.

• Practical information about state-of-the-art DSPs, FPGAs, and GPUs are presented.

• Relative advantages and disadvantages of DSPs, FPGAs, and GPUs are explained.

• Several recent examples from the literature are reviewed and compared.

摘要

•Important considerations when selecting hardware accelerators are discussed.•Practical information about state-of-the-art DSPs, FPGAs, and GPUs are presented.•Relative advantages and disadvantages of DSPs, FPGAs, and GPUs are explained.•Several recent examples from the literature are reviewed and compared.

论文关键词：Review,Computer vision,Image processing,Digital signal processor (DSP),Field programmable gate array (FPGA),Graphics processing unit (GPU)

论文评审过程：Received 14 November 2017, Revised 6 June 2018, Accepted 9 July 2018, Available online 25 July 2018, Version of Record 25 July 2018.

论文官网地址：https://doi.org/10.1016/j.image.2018.07.007