Cargando…

Learning Region-Based Attention Network for Traffic Sign Recognition

Traffic sign recognition in poor environments has always been a challenge in self-driving. Although a few works have achieved good results in the field of traffic sign recognition, there is currently a lack of traffic sign benchmarks containing many complex factors and a robust network. In this pape...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhou, Ke, Zhan, Yufei, Fu, Dongmei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7864033/
https://www.ncbi.nlm.nih.gov/pubmed/33498332
http://dx.doi.org/10.3390/s21030686
_version_ 1783647591738638336
author Zhou, Ke
Zhan, Yufei
Fu, Dongmei
author_facet Zhou, Ke
Zhan, Yufei
Fu, Dongmei
author_sort Zhou, Ke
collection PubMed
description Traffic sign recognition in poor environments has always been a challenge in self-driving. Although a few works have achieved good results in the field of traffic sign recognition, there is currently a lack of traffic sign benchmarks containing many complex factors and a robust network. In this paper, we propose an ice environment traffic sign recognition benchmark (ITSRB) and detection benchmark (ITSDB), marked in the COCO2017 format. The benchmarks include 5806 images with 43,290 traffic sign instances with different climate, light, time, and occlusion conditions. Second, we tested the robustness of the Libra-RCNN and HRNetv2p on the ITSDB compared with Faster-RCNN. The Libra-RCNN performed well and proved that our ITSDB dataset did increase the challenge in this task. Third, we propose an attention network based on high-resolution traffic sign classification (PFANet), and conduct ablation research on the design parallel fusion attention module. Experiments show that our representation reached 93.57% accuracy in ITSRB, and performed as well as the newest and most effective networks in the German traffic sign recognition dataset (GTSRB).
format Online
Article
Text
id pubmed-7864033
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-78640332021-02-06 Learning Region-Based Attention Network for Traffic Sign Recognition Zhou, Ke Zhan, Yufei Fu, Dongmei Sensors (Basel) Article Traffic sign recognition in poor environments has always been a challenge in self-driving. Although a few works have achieved good results in the field of traffic sign recognition, there is currently a lack of traffic sign benchmarks containing many complex factors and a robust network. In this paper, we propose an ice environment traffic sign recognition benchmark (ITSRB) and detection benchmark (ITSDB), marked in the COCO2017 format. The benchmarks include 5806 images with 43,290 traffic sign instances with different climate, light, time, and occlusion conditions. Second, we tested the robustness of the Libra-RCNN and HRNetv2p on the ITSDB compared with Faster-RCNN. The Libra-RCNN performed well and proved that our ITSDB dataset did increase the challenge in this task. Third, we propose an attention network based on high-resolution traffic sign classification (PFANet), and conduct ablation research on the design parallel fusion attention module. Experiments show that our representation reached 93.57% accuracy in ITSRB, and performed as well as the newest and most effective networks in the German traffic sign recognition dataset (GTSRB). MDPI 2021-01-20 /pmc/articles/PMC7864033/ /pubmed/33498332 http://dx.doi.org/10.3390/s21030686 Text en © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhou, Ke
Zhan, Yufei
Fu, Dongmei
Learning Region-Based Attention Network for Traffic Sign Recognition
title Learning Region-Based Attention Network for Traffic Sign Recognition
title_full Learning Region-Based Attention Network for Traffic Sign Recognition
title_fullStr Learning Region-Based Attention Network for Traffic Sign Recognition
title_full_unstemmed Learning Region-Based Attention Network for Traffic Sign Recognition
title_short Learning Region-Based Attention Network for Traffic Sign Recognition
title_sort learning region-based attention network for traffic sign recognition
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7864033/
https://www.ncbi.nlm.nih.gov/pubmed/33498332
http://dx.doi.org/10.3390/s21030686
work_keys_str_mv AT zhouke learningregionbasedattentionnetworkfortrafficsignrecognition
AT zhanyufei learningregionbasedattentionnetworkfortrafficsignrecognition
AT fudongmei learningregionbasedattentionnetworkfortrafficsignrecognition