Cargando…

Hough Transform Implementation For Event-Based Systems: Concepts and Challenges

Hough transform (HT) is one of the most well-known techniques in computer vision that has been the basis of many practical image processing algorithms. HT however is designed to work for frame-based systems such as conventional digital cameras. Recently, event-based systems such as Dynamic Vision Se...

Descripción completa

Detalles Bibliográficos
Autores principales: Seifozzakerini, Sajjad, Yau, Wei-Yun, Mao, Kezhi, Nejati, Hossein
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6308381/
https://www.ncbi.nlm.nih.gov/pubmed/30622466
http://dx.doi.org/10.3389/fncom.2018.00103
_version_ 1783383174702694400
author Seifozzakerini, Sajjad
Yau, Wei-Yun
Mao, Kezhi
Nejati, Hossein
author_facet Seifozzakerini, Sajjad
Yau, Wei-Yun
Mao, Kezhi
Nejati, Hossein
author_sort Seifozzakerini, Sajjad
collection PubMed
description Hough transform (HT) is one of the most well-known techniques in computer vision that has been the basis of many practical image processing algorithms. HT however is designed to work for frame-based systems such as conventional digital cameras. Recently, event-based systems such as Dynamic Vision Sensor (DVS) cameras, has become popular among researchers. Event-based cameras have a significantly high temporal resolution (1 μs), but each pixel can only detect change and not color. As such, the conventional image processing algorithms cannot be readily applied to event-based output streams. Therefore, it is necessary to adapt the conventional image processing algorithms for event-based cameras. This paper provides a systematic explanation, starting from extending conventional HT to 3D HT, adaptation to event-based systems, and the implementation of the 3D HT using Spiking Neural Networks (SNNs). Using SNN enables the proposed solution to be easily realized on hardware using FPGA, without requiring CPU or additional memory. In addition, we also discuss techniques for optimal SNN-based implementation using efficient number of neurons for the required accuracy and resolution along each dimension, without increasing the overall computational complexity. We hope that this will help to reduce the gap between event-based and frame-based systems.
format Online
Article
Text
id pubmed-6308381
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-63083812019-01-08 Hough Transform Implementation For Event-Based Systems: Concepts and Challenges Seifozzakerini, Sajjad Yau, Wei-Yun Mao, Kezhi Nejati, Hossein Front Comput Neurosci Neuroscience Hough transform (HT) is one of the most well-known techniques in computer vision that has been the basis of many practical image processing algorithms. HT however is designed to work for frame-based systems such as conventional digital cameras. Recently, event-based systems such as Dynamic Vision Sensor (DVS) cameras, has become popular among researchers. Event-based cameras have a significantly high temporal resolution (1 μs), but each pixel can only detect change and not color. As such, the conventional image processing algorithms cannot be readily applied to event-based output streams. Therefore, it is necessary to adapt the conventional image processing algorithms for event-based cameras. This paper provides a systematic explanation, starting from extending conventional HT to 3D HT, adaptation to event-based systems, and the implementation of the 3D HT using Spiking Neural Networks (SNNs). Using SNN enables the proposed solution to be easily realized on hardware using FPGA, without requiring CPU or additional memory. In addition, we also discuss techniques for optimal SNN-based implementation using efficient number of neurons for the required accuracy and resolution along each dimension, without increasing the overall computational complexity. We hope that this will help to reduce the gap between event-based and frame-based systems. Frontiers Media S.A. 2018-12-21 /pmc/articles/PMC6308381/ /pubmed/30622466 http://dx.doi.org/10.3389/fncom.2018.00103 Text en Copyright © 2018 Seifozzakerini, Yau, Mao and Nejati. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Seifozzakerini, Sajjad
Yau, Wei-Yun
Mao, Kezhi
Nejati, Hossein
Hough Transform Implementation For Event-Based Systems: Concepts and Challenges
title Hough Transform Implementation For Event-Based Systems: Concepts and Challenges
title_full Hough Transform Implementation For Event-Based Systems: Concepts and Challenges
title_fullStr Hough Transform Implementation For Event-Based Systems: Concepts and Challenges
title_full_unstemmed Hough Transform Implementation For Event-Based Systems: Concepts and Challenges
title_short Hough Transform Implementation For Event-Based Systems: Concepts and Challenges
title_sort hough transform implementation for event-based systems: concepts and challenges
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6308381/
https://www.ncbi.nlm.nih.gov/pubmed/30622466
http://dx.doi.org/10.3389/fncom.2018.00103
work_keys_str_mv AT seifozzakerinisajjad houghtransformimplementationforeventbasedsystemsconceptsandchallenges
AT yauweiyun houghtransformimplementationforeventbasedsystemsconceptsandchallenges
AT maokezhi houghtransformimplementationforeventbasedsystemsconceptsandchallenges
AT nejatihossein houghtransformimplementationforeventbasedsystemsconceptsandchallenges