The geometric attention-aware network for lane detection in complex road scenes.

Lane detection in complex road scenes is still a challenging task due to poor lighting conditions, interference of irrelevant road markings or signs, etc. To solve the problem of lane detection in the various complex road scenes, we proposed a geometric attention-aware network (GAAN) for lane detect...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	JianWu Long, ZeRan Yan, Lang Peng, Tong Li
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/5cccc3ac12064f078dcef34b22630a9c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5cccc3ac12064f078dcef34b22630a9c
record_format	dspace
spelling	oai:doaj.org-article:5cccc3ac12064f078dcef34b22630a9c2021-12-02T20:09:12ZThe geometric attention-aware network for lane detection in complex road scenes.1932-620310.1371/journal.pone.0254521https://doaj.org/article/5cccc3ac12064f078dcef34b22630a9c2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0254521https://doaj.org/toc/1932-6203Lane detection in complex road scenes is still a challenging task due to poor lighting conditions, interference of irrelevant road markings or signs, etc. To solve the problem of lane detection in the various complex road scenes, we proposed a geometric attention-aware network (GAAN) for lane detection. The proposed GAAN adopted a multi-task branch architecture, and used the attention information propagation (AIP) module to perform communication between branches, then the geometric attention-aware (GAA) module was used to complete feature fusion. In order to verify the lane detection effect of the proposed model in this paper, the experiments were conducted on the CULane dataset, TuSimple dataset, and BDD100K dataset. The experimental results show that our method performs well compared with the current excellent lane line detection networks.JianWu LongZeRan YanLang PengTong LiPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 7, p e0254521 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q JianWu Long ZeRan Yan Lang Peng Tong Li The geometric attention-aware network for lane detection in complex road scenes.
description	Lane detection in complex road scenes is still a challenging task due to poor lighting conditions, interference of irrelevant road markings or signs, etc. To solve the problem of lane detection in the various complex road scenes, we proposed a geometric attention-aware network (GAAN) for lane detection. The proposed GAAN adopted a multi-task branch architecture, and used the attention information propagation (AIP) module to perform communication between branches, then the geometric attention-aware (GAA) module was used to complete feature fusion. In order to verify the lane detection effect of the proposed model in this paper, the experiments were conducted on the CULane dataset, TuSimple dataset, and BDD100K dataset. The experimental results show that our method performs well compared with the current excellent lane line detection networks.
format	article
author	JianWu Long ZeRan Yan Lang Peng Tong Li
author_facet	JianWu Long ZeRan Yan Lang Peng Tong Li
author_sort	JianWu Long
title	The geometric attention-aware network for lane detection in complex road scenes.
title_short	The geometric attention-aware network for lane detection in complex road scenes.
title_full	The geometric attention-aware network for lane detection in complex road scenes.
title_fullStr	The geometric attention-aware network for lane detection in complex road scenes.
title_full_unstemmed	The geometric attention-aware network for lane detection in complex road scenes.
title_sort	geometric attention-aware network for lane detection in complex road scenes.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/5cccc3ac12064f078dcef34b22630a9c
work_keys_str_mv	AT jianwulong thegeometricattentionawarenetworkforlanedetectionincomplexroadscenes AT zeranyan thegeometricattentionawarenetworkforlanedetectionincomplexroadscenes AT langpeng thegeometricattentionawarenetworkforlanedetectionincomplexroadscenes AT tongli thegeometricattentionawarenetworkforlanedetectionincomplexroadscenes AT jianwulong geometricattentionawarenetworkforlanedetectionincomplexroadscenes AT zeranyan geometricattentionawarenetworkforlanedetectionincomplexroadscenes AT langpeng geometricattentionawarenetworkforlanedetectionincomplexroadscenes AT tongli geometricattentionawarenetworkforlanedetectionincomplexroadscenes
_version_	1718375126146220032

The geometric attention-aware network for lane detection in complex road scenes.

Ejemplares similares