Oriented Road Marking Detection in MLS Point Cloud Intensity Images Using Channel and Spatial Attention

Accurate detection of road markings is critically important in fields such as autonomous driving technology, high-precision mapping, and intelligent transportation systems. Unlike traditional object detection tasks, road marking detection faces many challenges, including significant direction change...

Full description

Saved in:
Bibliographic Details
Main Authors: Dehui Li, Tao Liu, Ping Du, Yi He, Shuangtong Liu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10985801/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714428464857088
author Dehui Li
Tao Liu
Ping Du
Yi He
Shuangtong Liu
author_facet Dehui Li
Tao Liu
Ping Du
Yi He
Shuangtong Liu
author_sort Dehui Li
collection DOAJ
description Accurate detection of road markings is critically important in fields such as autonomous driving technology, high-precision mapping, and intelligent transportation systems. Unlike traditional object detection tasks, road marking detection faces many challenges, including significant direction changes, complex backgrounds, and diverse types of road markings. To address these issues, this article proposes a deep learning approach based on mobile laser scanning point cloud intensity images to accurately detect road markings with arbitrary orientations. First, we employ an oriented bounding box to precisely represent the direction and location of road markings, thereby improving detection accuracy. Additionally, the channel semantic enhanced module (SEM) is designed to enhance the feature representation capacity of the backbone network, effectively reducing the impact of complex backgrounds on foreground targets. Finally, the spatial SEM is introduced to enhance the feature pyramid network's ability to capture contextual information. The module consists of the large selective kernel network (LSKNet) and the SEM. LSKNet extracts contextual information around the target by adaptively selecting receptive fields of various scales, while SEM, a lightweight semantic segmentation branch, further strengthens the feature representation ability of this information by incorporating a semantic supervision mechanism. The proposed method achieves an mAP of 84.7% on Test Set I, representing a 3.2% improvement over the baseline model, while maintaining high efficiency, offering a robust and reliable solution for real-time road marking detection tasks.
format Article
id doaj-art-bc7e97ef656647b38452a3babe0ff858
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-bc7e97ef656647b38452a3babe0ff8582025-08-20T03:13:42ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118125881260210.1109/JSTARS.2025.356699810985801Oriented Road Marking Detection in MLS Point Cloud Intensity Images Using Channel and Spatial AttentionDehui Li0https://orcid.org/0009-0005-3459-9765Tao Liu1https://orcid.org/0000-0003-0202-0032Ping Du2Yi He3https://orcid.org/0000-0003-4017-0488Shuangtong Liu4https://orcid.org/0009-0004-6183-8680Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, Gansu, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, Gansu, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, Gansu, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, Gansu, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, Gansu, ChinaAccurate detection of road markings is critically important in fields such as autonomous driving technology, high-precision mapping, and intelligent transportation systems. Unlike traditional object detection tasks, road marking detection faces many challenges, including significant direction changes, complex backgrounds, and diverse types of road markings. To address these issues, this article proposes a deep learning approach based on mobile laser scanning point cloud intensity images to accurately detect road markings with arbitrary orientations. First, we employ an oriented bounding box to precisely represent the direction and location of road markings, thereby improving detection accuracy. Additionally, the channel semantic enhanced module (SEM) is designed to enhance the feature representation capacity of the backbone network, effectively reducing the impact of complex backgrounds on foreground targets. Finally, the spatial SEM is introduced to enhance the feature pyramid network's ability to capture contextual information. The module consists of the large selective kernel network (LSKNet) and the SEM. LSKNet extracts contextual information around the target by adaptively selecting receptive fields of various scales, while SEM, a lightweight semantic segmentation branch, further strengthens the feature representation ability of this information by incorporating a semantic supervision mechanism. The proposed method achieves an mAP of 84.7% on Test Set I, representing a 3.2% improvement over the baseline model, while maintaining high efficiency, offering a robust and reliable solution for real-time road marking detection tasks.https://ieeexplore.ieee.org/document/10985801/Channel and spatial attentionmobile laser scanning (MLS) point cloudsoriented road markingssemantic enhancement
spellingShingle Dehui Li
Tao Liu
Ping Du
Yi He
Shuangtong Liu
Oriented Road Marking Detection in MLS Point Cloud Intensity Images Using Channel and Spatial Attention
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Channel and spatial attention
mobile laser scanning (MLS) point clouds
oriented road markings
semantic enhancement
title Oriented Road Marking Detection in MLS Point Cloud Intensity Images Using Channel and Spatial Attention
title_full Oriented Road Marking Detection in MLS Point Cloud Intensity Images Using Channel and Spatial Attention
title_fullStr Oriented Road Marking Detection in MLS Point Cloud Intensity Images Using Channel and Spatial Attention
title_full_unstemmed Oriented Road Marking Detection in MLS Point Cloud Intensity Images Using Channel and Spatial Attention
title_short Oriented Road Marking Detection in MLS Point Cloud Intensity Images Using Channel and Spatial Attention
title_sort oriented road marking detection in mls point cloud intensity images using channel and spatial attention
topic Channel and spatial attention
mobile laser scanning (MLS) point clouds
oriented road markings
semantic enhancement
url https://ieeexplore.ieee.org/document/10985801/
work_keys_str_mv AT dehuili orientedroadmarkingdetectioninmlspointcloudintensityimagesusingchannelandspatialattention
AT taoliu orientedroadmarkingdetectioninmlspointcloudintensityimagesusingchannelandspatialattention
AT pingdu orientedroadmarkingdetectioninmlspointcloudintensityimagesusingchannelandspatialattention
AT yihe orientedroadmarkingdetectioninmlspointcloudintensityimagesusingchannelandspatialattention
AT shuangtongliu orientedroadmarkingdetectioninmlspointcloudintensityimagesusingchannelandspatialattention