Enhancing Building Segmentation With Shadow-Aware Edge Perception

Accurate building semantic segmentation in remote sensing imagery is essential for urban planning, environmental monitoring, and map creation. While deep learning has achieved significant advancements in this field, precisely segmenting building edges and shadows in complex scenarios remains challen...

Full description

Saved in:
Bibliographic Details
Main Authors: Ying Yu, Chunping Wang, Renke Kou, Huiying Wang, Boxiong Yang, Jinhui Xu, Qiang Fu
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/10713904/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267890693963776
author Ying Yu
Chunping Wang
Renke Kou
Huiying Wang
Boxiong Yang
Jinhui Xu
Qiang Fu
author_facet Ying Yu
Chunping Wang
Renke Kou
Huiying Wang
Boxiong Yang
Jinhui Xu
Qiang Fu
author_sort Ying Yu
collection DOAJ
description Accurate building semantic segmentation in remote sensing imagery is essential for urban planning, environmental monitoring, and map creation. While deep learning has achieved significant advancements in this field, precisely segmenting building edges and shadows in complex scenarios remains challenging. Shadows often introduce boundary ambiguities, affecting the local shape and texture information of buildings. Current methods do not fully perceive or utilize shadows. To address these challenges, we propose an advanced high-resolution image segmentation network, high-resolution network, integrated with a shadow-inclusive edge perception module. Our approach involves introducing a shadow-inclusive contour transition module (SCTM) during the feature extraction stage to enhance the features of blurry boundaries. The proposed SCTM and shadow-aware attention module significantly enhance attention maps, improve responses in blurry boundary regions, and increase consistency between predictions and ground truth, setting a new benchmark for building semantic segmentation in remote sensing imagery. This enriched information is then fed into an attention module that concurrently focuses on boundary and channel features, surpassing traditional semantic segmentation methods. We validated our method on three datasets: Massachusetts, WHU, and Inria. Our approach outperformed state-of-the-art methods on the WHU Building Dataset across all metrics, including mIoU, Accuracy, Kappa, and Dice coefficient.
format Article
id doaj-art-d4a4c56b5c954955b2856cb6f0241864
institution OA Journals
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-d4a4c56b5c954955b2856cb6f02418642025-08-20T01:53:36ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-011811210.1109/JSTARS.2024.347907310713904Enhancing Building Segmentation With Shadow-Aware Edge PerceptionYing Yu0https://orcid.org/0000-0001-7840-9891Chunping Wang1Renke Kou2https://orcid.org/0000-0001-5893-3127Huiying Wang3https://orcid.org/0009-0004-0346-3585Boxiong Yang4Jinhui Xu5Qiang Fu6https://orcid.org/0000-0002-3831-9856Shijiazhuang campus, Army Engineering University of PLA, Shijiazhuang, ChinaShijiazhuang campus, Army Engineering University of PLA, Shijiazhuang, ChinaSchool of Aviation Engineering, Air Force Engineering University, Xi'an, ChinaShijiazhuang campus, Army Engineering University of PLA, Shijiazhuang, ChinaSchool of Information and Intelligent Engineering, University of Sanya, Sanya, ChinaSchool of Information and Intelligent Engineering, University of Sanya, Sanya, ChinaShijiazhuang campus, Army Engineering University of PLA, Shijiazhuang, ChinaAccurate building semantic segmentation in remote sensing imagery is essential for urban planning, environmental monitoring, and map creation. While deep learning has achieved significant advancements in this field, precisely segmenting building edges and shadows in complex scenarios remains challenging. Shadows often introduce boundary ambiguities, affecting the local shape and texture information of buildings. Current methods do not fully perceive or utilize shadows. To address these challenges, we propose an advanced high-resolution image segmentation network, high-resolution network, integrated with a shadow-inclusive edge perception module. Our approach involves introducing a shadow-inclusive contour transition module (SCTM) during the feature extraction stage to enhance the features of blurry boundaries. The proposed SCTM and shadow-aware attention module significantly enhance attention maps, improve responses in blurry boundary regions, and increase consistency between predictions and ground truth, setting a new benchmark for building semantic segmentation in remote sensing imagery. This enriched information is then fed into an attention module that concurrently focuses on boundary and channel features, surpassing traditional semantic segmentation methods. We validated our method on three datasets: Massachusetts, WHU, and Inria. Our approach outperformed state-of-the-art methods on the WHU Building Dataset across all metrics, including mIoU, Accuracy, Kappa, and Dice coefficient.https://ieeexplore.ieee.org/document/10713904/Buildings segmentationremote sensingsemantic segmentationshadow-aware attention moduleshadow-inclusive contour transition module (SCTM)
spellingShingle Ying Yu
Chunping Wang
Renke Kou
Huiying Wang
Boxiong Yang
Jinhui Xu
Qiang Fu
Enhancing Building Segmentation With Shadow-Aware Edge Perception
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Buildings segmentation
remote sensing
semantic segmentation
shadow-aware attention module
shadow-inclusive contour transition module (SCTM)
title Enhancing Building Segmentation With Shadow-Aware Edge Perception
title_full Enhancing Building Segmentation With Shadow-Aware Edge Perception
title_fullStr Enhancing Building Segmentation With Shadow-Aware Edge Perception
title_full_unstemmed Enhancing Building Segmentation With Shadow-Aware Edge Perception
title_short Enhancing Building Segmentation With Shadow-Aware Edge Perception
title_sort enhancing building segmentation with shadow aware edge perception
topic Buildings segmentation
remote sensing
semantic segmentation
shadow-aware attention module
shadow-inclusive contour transition module (SCTM)
url https://ieeexplore.ieee.org/document/10713904/
work_keys_str_mv AT yingyu enhancingbuildingsegmentationwithshadowawareedgeperception
AT chunpingwang enhancingbuildingsegmentationwithshadowawareedgeperception
AT renkekou enhancingbuildingsegmentationwithshadowawareedgeperception
AT huiyingwang enhancingbuildingsegmentationwithshadowawareedgeperception
AT boxiongyang enhancingbuildingsegmentationwithshadowawareedgeperception
AT jinhuixu enhancingbuildingsegmentationwithshadowawareedgeperception
AT qiangfu enhancingbuildingsegmentationwithshadowawareedgeperception