基于自适应门控的双路激光雷达三维车道线检测 Article Swipe

PDF

Jie Hu , 陈楠 Chen Nan , 徐文才 Xu Wencai , 昌敏杰 Chang Minjie , 徐博远 Xu Boyuan , 王占彬 Wang Zhanbin , 郭启翔 Guo Qixiang ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.3788/cjl230456

局部和全局特征提取在车道线检测任务中扮演着重要的角色。针对现有的基于激光雷达的车道线检测算法局部特征提取层次单一和全局特征利用不充分的问题，提出一种基于自适应门控的双路激光雷达三维车道线检测算法。首先，通过全局特征金字塔结构，使网络提取具有全局相关性的多层次车道线特征；其次，引入双路结构，其中辅助通路将底层高分辨率纹理特征压缩到高级抽象语义特征从而降低计算复杂度，压缩的语义特征用作另一个构建的主通路的先验信息，帮助学习更加精细的底层纹理细节，并借助高效移动卷积模块，在缓解注意力窗口效应的同时产生更好的下采样特征；最后，设计一种自适应多阶门控模块来更好地利用上下文信息，使网络自适应捕捉车道线更具代表性的全局纹理及语义特征。在K-Lane数据集上的实验表明，所提算法F1分数较主流模型提升2.6个百分点，在不良光照、严重遮挡条件下分别提升2.7个百分点和3.5个百分点。将算法部署在实车平台实现在线检测，验证了算法的工程实用价值。

Related Topics

Computer Science

Concepts

Computer science

Metadata

Type: article
Language: ja
Landing Page: https://doi.org/10.3788/cjl230456
PDF: https://www.opticsjournal.net/Articles/GetArticlePDF/OJ96be999cf00fb099
OA Status: bronze
Cited By: 5
References: 46
OpenAlex ID: https://openalex.org/W4389108027

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4389108027

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.3788/cjl230456

Digital Object Identifier
Title: 基于自适应门控的双路激光雷达三维车道线检测

Work title
Type: article

OpenAlex work type
Language: ja

Primary language
Publication year: 2023

Year of publication
Publication date: 2023-01-01

Full publication date if available
Authors: Jie Hu, 陈楠 Chen Nan, 徐文才 Xu Wencai, 昌敏杰 Chang Minjie, 徐博远 Xu Boyuan, 王占彬 Wang Zhanbin, 郭启翔 Guo Qixiang

List of authors in order
Landing page: https://doi.org/10.3788/cjl230456

Publisher landing page
PDF URL: https://www.opticsjournal.net/Articles/GetArticlePDF/OJ96be999cf00fb099

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: bronze

Open access status per OpenAlex
OA URL: https://www.opticsjournal.net/Articles/GetArticlePDF/OJ96be999cf00fb099

Direct OA link when available
Concepts: Computer science

Top concepts (fields/topics) attached by OpenAlex
Cited by: 5

Total citation count in OpenAlex
Citations by year (recent): 2025: 2, 2024: 3

Per-year citation counts (last 5 years)
References (count): 46

Number of works referenced by this work

Full payload

id	https://openalex.org/W4389108027
doi	https://doi.org/10.3788/cjl230456
ids.doi	https://doi.org/10.3788/cjl230456
ids.openalex	https://openalex.org/W4389108027
fwci	2.28577285
type	article
title	基于自适应门控的双路激光雷达三维车道线检测
biblio.issue	22
biblio.volume	50
biblio.last_page	2210001
biblio.first_page	2210001
topics[0].id	https://openalex.org/T12153
topics[0].field.id	https://openalex.org/fields/31
topics[0].field.display_name	Physics and Astronomy
topics[0].score	0.996999979019165
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/3105
topics[0].subfield.display_name	Instrumentation
topics[0].display_name	Advanced Optical Sensing Technologies
topics[1].id	https://openalex.org/T12549
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9760000109672546
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1707
topics[1].subfield.display_name	Computer Vision and Pattern Recognition
topics[1].display_name	Image and Object Detection Techniques
topics[2].id	https://openalex.org/T11164
topics[2].field.id	https://openalex.org/fields/23
topics[2].field.display_name	Environmental Science
topics[2].score	0.9679999947547913
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/2305
topics[2].subfield.display_name	Environmental Engineering
topics[2].display_name	Remote Sensing and LiDAR Applications
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.2685999274253845
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.2685999274253845
keywords[0].display_name	Computer science
language	ja
locations[0].id	doi:10.3788/cjl230456
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4210218867
locations[0].source.issn	0258-7025
locations[0].source.type	journal
locations[0].source.is_oa	False
locations[0].source.issn_l	0258-7025
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	Chinese Journal of Lasers
locations[0].source.host_organization	https://openalex.org/P4310319982
locations[0].source.host_organization_name	Science Press
locations[0].source.host_organization_lineage	https://openalex.org/P4310319982
locations[0].license
locations[0].pdf_url	https://www.opticsjournal.net/Articles/GetArticlePDF/OJ96be999cf00fb099
locations[0].version	publishedVersion
locations[0].raw_type	journal-article
locations[0].license_id
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Chinese Journal of Lasers
locations[0].landing_page_url	https://doi.org/10.3788/cjl230456
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5029178842
authorships[0].author.orcid	https://orcid.org/0000-0003-0713-3458
authorships[0].author.display_name	Jie Hu
authorships[0].author_position	first
authorships[0].raw_author_name	胡杰 Hu Jie
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5082858614
authorships[1].author.orcid
authorships[1].author.display_name	陈楠 Chen Nan
authorships[1].author_position	middle
authorships[1].raw_author_name	陈楠 Chen Nan
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5067826181
authorships[2].author.orcid
authorships[2].author.display_name	徐文才 Xu Wencai
authorships[2].author_position	middle
authorships[2].raw_author_name	徐文才 Xu Wencai
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5093365112
authorships[3].author.orcid
authorships[3].author.display_name	昌敏杰 Chang Minjie
authorships[3].author_position	middle
authorships[3].raw_author_name	昌敏杰 Chang Minjie
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5093365113
authorships[4].author.orcid
authorships[4].author.display_name	徐博远 Xu Boyuan
authorships[4].author_position	middle
authorships[4].raw_author_name	徐博远 Xu Boyuan
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5093365114
authorships[5].author.orcid
authorships[5].author.display_name	王占彬 Wang Zhanbin
authorships[5].author_position	middle
authorships[5].raw_author_name	王占彬 Wang Zhanbin
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5093365115
authorships[6].author.orcid
authorships[6].author.display_name	郭启翔 Guo Qixiang
authorships[6].author_position	last
authorships[6].raw_author_name	郭启翔 Guo Qixiang
authorships[6].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://www.opticsjournal.net/Articles/GetArticlePDF/OJ96be999cf00fb099
open_access.oa_status	bronze
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	基于自适应门控的双路激光雷达三维车道线检测
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T12153
primary_topic.field.id	https://openalex.org/fields/31
primary_topic.field.display_name	Physics and Astronomy
primary_topic.score	0.996999979019165
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/3105
primary_topic.subfield.display_name	Instrumentation
primary_topic.display_name	Advanced Optical Sensing Technologies
cited_by_count	5
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	2
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	3
locations_count	1
best_oa_location.id	doi:10.3788/cjl230456
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4210218867
best_oa_location.source.issn	0258-7025
best_oa_location.source.type	journal
best_oa_location.source.is_oa	False
best_oa_location.source.issn_l	0258-7025
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	Chinese Journal of Lasers
best_oa_location.source.host_organization	https://openalex.org/P4310319982
best_oa_location.source.host_organization_name	Science Press
best_oa_location.source.host_organization_lineage	https://openalex.org/P4310319982
best_oa_location.license
best_oa_location.pdf_url	https://www.opticsjournal.net/Articles/GetArticlePDF/OJ96be999cf00fb099
best_oa_location.version	publishedVersion
best_oa_location.raw_type	journal-article
best_oa_location.license_id
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Chinese Journal of Lasers
best_oa_location.landing_page_url	https://doi.org/10.3788/cjl230456
primary_location.id	doi:10.3788/cjl230456
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4210218867
primary_location.source.issn	0258-7025
primary_location.source.type	journal
primary_location.source.is_oa	False
primary_location.source.issn_l	0258-7025
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	Chinese Journal of Lasers
primary_location.source.host_organization	https://openalex.org/P4310319982
primary_location.source.host_organization_name	Science Press
primary_location.source.host_organization_lineage	https://openalex.org/P4310319982
primary_location.license
primary_location.pdf_url	https://www.opticsjournal.net/Articles/GetArticlePDF/OJ96be999cf00fb099
primary_location.version	publishedVersion
primary_location.raw_type	journal-article
primary_location.license_id
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Chinese Journal of Lasers
primary_location.landing_page_url	https://doi.org/10.3788/cjl230456
publication_date	2023-01-01
publication_year	2023
referenced_works	https://openalex.org/W4221143432, https://openalex.org/W2905537262, https://openalex.org/W3160905021, https://openalex.org/W3132570553, https://openalex.org/W6785766105, https://openalex.org/W3021107981, https://openalex.org/W4381515369, https://openalex.org/W2133026742, https://openalex.org/W2116484457, https://openalex.org/W3094398790, https://openalex.org/W1673310716, https://openalex.org/W6757826844, https://openalex.org/W3118490488, https://openalex.org/W4292829054, https://openalex.org/W4306801739, https://openalex.org/W2774996270, https://openalex.org/W6687483927, https://openalex.org/W2565639579, https://openalex.org/W4362502944, https://openalex.org/W3085282765, https://openalex.org/W4221162820, https://openalex.org/W3138516171, https://openalex.org/W3168825659, https://openalex.org/W4362502814, https://openalex.org/W4285205127, https://openalex.org/W6811173682, https://openalex.org/W4288804646, https://openalex.org/W2979983945, https://openalex.org/W6743731764, https://openalex.org/W2734349601, https://openalex.org/W2286929393, https://openalex.org/W4213345160, https://openalex.org/W3119586106, https://openalex.org/W4309845474, https://openalex.org/W4226272139, https://openalex.org/W2963400571, https://openalex.org/W2963840672, https://openalex.org/W4385346076, https://openalex.org/W2194775991, https://openalex.org/W3203848864, https://openalex.org/W4366352791, https://openalex.org/W4301860726, https://openalex.org/W4385245566, https://openalex.org/W4308068964, https://openalex.org/W2909761845, https://openalex.org/W3034552520
referenced_works_count	46
abstract_inverted_index.局部和全局特征提取在车道线检测任务中扮演着重要的角色。针对现有的基于激光雷达的车道线检测算法局部特征提取层次单一和全局特征利用不充分的问题，提出一种基于自适应门控的双路激光雷达三维车道线检测算法。首先，通过全局特征金字塔结构，使网络提取具有全局相关性的多层次车道线特征；其次，引入双路结构，其中辅助通路将底层高分辨率纹理特征压缩到高级抽象语义特征从而降低计算复杂度，压缩的语义特征用作另一个构建的主通路的先验信息，帮助学习更加精细的底层纹理细节，并借助高效移动卷积模块，在缓解注意力窗口效应的同时产生更好的下采样特征；最后，设计一种自适应多阶门控模块来更好地利用上下文信息，使网络自适应捕捉车道线更具代表性的全局纹理及语义特征。在K-Lane数据集上的实验表明，所提算法F1分数较主流模型提升2.6个百分点，在不良光照、严重遮挡条件下分别提升2.7个百分点和3.5个百分点。将算法部署在实车平台实现在线检测，验证了算法的工程实用价值。	0
cited_by_percentile_year.max	97
cited_by_percentile_year.min	95
countries_distinct_count	0
institutions_distinct_count	7
citation_normalized_percentile.value	0.91394837
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False