Leveraging mixed data sources for enhanced road segmentation in synthetic aperture radar images

In this study, we tackle the task of road segmentation from Synthetic Aperture Radar (SAR) imagery, which is vital for remote sensing applications including urban planning and disaster management. Despite its significance, SAR-based road segmentation is hindered by the scarcity of high-resolution, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Lan, Tian, He, Shuting, Qing, Yuanyuan, Wen, Bihan
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/180516
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-180516
record_format dspace
spelling sg-ntu-dr.10356-1805162024-10-11T15:40:51Z Leveraging mixed data sources for enhanced road segmentation in synthetic aperture radar images Lan, Tian He, Shuting Qing, Yuanyuan Wen, Bihan School of Electrical and Electronic Engineering Engineering Geographic information Transportation In this study, we tackle the task of road segmentation from Synthetic Aperture Radar (SAR) imagery, which is vital for remote sensing applications including urban planning and disaster management. Despite its significance, SAR-based road segmentation is hindered by the scarcity of high-resolution, annotated SAR datasets and the distinct characteristics of SAR imagery, which differ significantly from more commonly used electro-optical (EO) imagery. To overcome these challenges, we introduce a multi-source data approach, creating the HybridSAR Road Dataset (HSRD). This dataset includes the SpaceNet 6 Road (SN6R) dataset, derived from high-resolution SAR images and OSM road data, as well as the DG-SAR and SN3-SAR datasets, synthesized from existing EO datasets. We adapt an off-the-shelf road segmentation network from the optical to the SAR domain through an enhanced training framework that integrates both real and synthetic data. Our results demonstrate that the HybridSAR Road Dataset and the adapted network significantly enhance the accuracy and robustness of SAR road segmentation, paving the way for future advancements in remote sensing. Published version 2024-10-10T01:05:22Z 2024-10-10T01:05:22Z 2024 Journal Article Lan, T., He, S., Qing, Y. & Wen, B. (2024). Leveraging mixed data sources for enhanced road segmentation in synthetic aperture radar images. Remote Sensing, 16(16), 3024-. https://dx.doi.org/10.3390/rs16163024 2072-4292 https://hdl.handle.net/10356/180516 10.3390/rs16163024 2-s2.0-85202441082 16 16 3024 en Remote Sensing © 2024 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 (https:// creativecommons.org/licenses/by/ 4.0/). application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering
Geographic information
Transportation
spellingShingle Engineering
Geographic information
Transportation
Lan, Tian
He, Shuting
Qing, Yuanyuan
Wen, Bihan
Leveraging mixed data sources for enhanced road segmentation in synthetic aperture radar images
description In this study, we tackle the task of road segmentation from Synthetic Aperture Radar (SAR) imagery, which is vital for remote sensing applications including urban planning and disaster management. Despite its significance, SAR-based road segmentation is hindered by the scarcity of high-resolution, annotated SAR datasets and the distinct characteristics of SAR imagery, which differ significantly from more commonly used electro-optical (EO) imagery. To overcome these challenges, we introduce a multi-source data approach, creating the HybridSAR Road Dataset (HSRD). This dataset includes the SpaceNet 6 Road (SN6R) dataset, derived from high-resolution SAR images and OSM road data, as well as the DG-SAR and SN3-SAR datasets, synthesized from existing EO datasets. We adapt an off-the-shelf road segmentation network from the optical to the SAR domain through an enhanced training framework that integrates both real and synthetic data. Our results demonstrate that the HybridSAR Road Dataset and the adapted network significantly enhance the accuracy and robustness of SAR road segmentation, paving the way for future advancements in remote sensing.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Lan, Tian
He, Shuting
Qing, Yuanyuan
Wen, Bihan
format Article
author Lan, Tian
He, Shuting
Qing, Yuanyuan
Wen, Bihan
author_sort Lan, Tian
title Leveraging mixed data sources for enhanced road segmentation in synthetic aperture radar images
title_short Leveraging mixed data sources for enhanced road segmentation in synthetic aperture radar images
title_full Leveraging mixed data sources for enhanced road segmentation in synthetic aperture radar images
title_fullStr Leveraging mixed data sources for enhanced road segmentation in synthetic aperture radar images
title_full_unstemmed Leveraging mixed data sources for enhanced road segmentation in synthetic aperture radar images
title_sort leveraging mixed data sources for enhanced road segmentation in synthetic aperture radar images
publishDate 2024
url https://hdl.handle.net/10356/180516
_version_ 1814047357367484416