Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/36495
Appears in Collections:Psychology Conference Papers and Proceedings
Peer Review Status: Refereed
Author(s): Ali, Teymoor
Rainey, James
Lau, Sook Yen
Gheorghiu, Elena
Maier, Patrick
Appiah, Kofi
Bhowmick, Deepayan
Contact Email: elena.gheorghiu@stir.ac.uk
Title: An FPGA-based neuromorphic vision system accelerator
Editor(s): Bouma, Henri
Prabhu, Radhakrishna
Yitzhaky, Yitzhak
Kuijf, Hugo J
Citation: Ali T, Rainey J, Lau SY, Gheorghiu E, Maier P, Appiah K & Bhowmick D (2024) An FPGA-based neuromorphic vision system accelerator. In: Bouma H, Prabhu R, Yitzhaky Y & Kuijf HJ (eds.) <i>Artificial Intelligence for Security and Defence Applications II</i>. Proceedings of SPIE, 13206. SPIE "Artificial Intelligence for Security and Defence Applications II, Edinburgh, 16.09.2024-20.09.2024. SPIE.
Issue Date: 2024
Date Deposited: 25-Sep-2024
Series/Report no.: Proceedings of SPIE, 13206
Conference Name: SPIE "Artificial Intelligence for Security and Defence Applications II
Conference Dates: 2024-09-16 - 2024-09-20
Conference Location: Edinburgh
Abstract: Rapid reaction to a specific event is a critical feature for an embedded computer vision system to ensure reliable and secure interaction with the environment in resource-limited real-time applications. This requires highlevel scene understanding with ultra-fast processing capabilities and the ability to operate at extremely low power. Existing vision systems, which rely on traditional computation techniques, including deep learning-based approaches, are limited by the compute capabilities due to large power dissipation and slow off-chip memory access. These challenges are evident in environments with constrained power, bandwidth and hardware resources, such as in the applications of drones and robot navigation in expansive areas. A new NEuromorphic Vision System (NEVIS) is proposed to address the limitations of existing computer vision systems for many resource-limited real-time applications. NEVIS mimics the efficiency of the human visual system by encoding visual signals into spikes, which are processed by neurons with synaptic connections. The potential of NEVIS is explored through an FPGA-based accelerator implementation on a Xilinx Kria board that achieved 40× speed up compared to a Raspberry Pi 4B CPU. This work informs the future potential of NEVIS in embedded computer vision system development.
Status: AM - Accepted Manuscript
Rights: Publisher allows this work to be made available in this repository. Published in Proceedings of SPIE with the following policy: SPIE grants to authors (and their employers) of papers, posters, and presentation recordings published in Proceedings of SPIE the right to post an author-prepared version or the officially published version (preferred) on an internal or external repository controlled exclusively by the author/employer, or the entity funding the research, provided that (a) such posting is noncommercial and the publication is made available to users without charge; (b) an appropriate SPIE attribution and citation appear with the publication; and (c) a DOI link to SPIE’s official online version of the publication is provided. Please cite as: Ali T, Rainey J, Lau SY, Gheorghiu E, Maier P, Appiah K & Bhowmick D (2024) An FPGA-based neuromorphic vision system accelerator. In: <i>Artificial Intelligence for Security and Defence Applications II</i>. Proceedings of SPIE, 13206. SPIE "Artificial Intelligence for Security and Defence Applications II, Edinburgh, 16.09.2024-20.09.2024. SPIE.
Licence URL(s): http://creativecommons.org/licenses/by-nc/4.0/

Files in This Item:
File Description SizeFormat 
SPIE_2024_NEVIS_FPGA_FINAL.pdfFulltext - Accepted Version408.29 kBAdobe PDFView/Open



This item is protected by original copyright



A file in this item is licensed under a Creative Commons License Creative Commons

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved https://creativecommons.org/publicdomain/zero/1.0/

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.