In:
PLOS ONE, Public Library of Science (PLoS), Vol. 16, No. 7 ( 2021-7-15), p. e0254521-
Abstract:
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.
Type of Medium:
Online Resource
ISSN:
1932-6203
DOI:
10.1371/journal.pone.0254521
DOI:
10.1371/journal.pone.0254521.g001
DOI:
10.1371/journal.pone.0254521.g002
DOI:
10.1371/journal.pone.0254521.g003
DOI:
10.1371/journal.pone.0254521.g004
DOI:
10.1371/journal.pone.0254521.g005
DOI:
10.1371/journal.pone.0254521.g006
DOI:
10.1371/journal.pone.0254521.g007
DOI:
10.1371/journal.pone.0254521.g008
DOI:
10.1371/journal.pone.0254521.g009
DOI:
10.1371/journal.pone.0254521.g010
DOI:
10.1371/journal.pone.0254521.t001
DOI:
10.1371/journal.pone.0254521.t002
DOI:
10.1371/journal.pone.0254521.t003
DOI:
10.1371/journal.pone.0254521.t004
DOI:
10.1371/journal.pone.0254521.t005
DOI:
10.1371/journal.pone.0254521.t006
DOI:
10.1371/journal.pone.0254521.t007
DOI:
10.1371/journal.pone.0254521.t008
DOI:
10.1371/journal.pone.0254521.t009
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2021
detail.hit.zdb_id:
2267670-3
Permalink