BuildWin-SAM: An Improved SAM-Based Method for Extracting Building Windows From Street View Images

Building facade segmentation provides critical support for urban information management, precise 3D reconstruction, and energy consumption analysis. Window, as a pivotal component of building facades, plays a central role in these applications. However, accurately identifying windows in diverse urba...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhengnan Li, Yizhen Yan, Bo Huang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10955328/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850200223071076352
author Zhengnan Li
Yizhen Yan
Bo Huang
author_facet Zhengnan Li
Yizhen Yan
Bo Huang
author_sort Zhengnan Li
collection DOAJ
description Building facade segmentation provides critical support for urban information management, precise 3D reconstruction, and energy consumption analysis. Window, as a pivotal component of building facades, plays a central role in these applications. However, accurately identifying windows in diverse urban environments poses significant challenges due to dataset limitations and variability in model performance. This study presents two primary contributions: first, we develop the Street View Building Window (SVBW) segmentation dataset, comprising 1,172 images that represent diverse urban contexts and window types, with a total of 50,321 meticulously annotated window instances. This dataset addresses existing gaps in segmenting irregular building facades. Second, we propose BuildWin-SAM, a model for window extraction based on the Segment Anything Model (SAM) architecture, which is trained on the SVBW dataset. Comparative analysis with CNN-based semantic segmentation models and SAM demonstrates that BuildWin-SAM achieves improvements across key evaluation metrics, including Intersection over Union (IoU), F1 score, precision, and recall. Specifically, BuildWin-SAM achieves an IoU of 80.70%, precision of 89.43%, recall of 89.20%, and an F1 score of 88.52%, demonstrating precise window localization and delineation capabilities. To further validate its robustness, we conduct evaluations on three public datasets featuring multi-scale and multi-scene images with building window annotations. BuildWin-SAM achieves Recall rates exceeding 72% and Precision rates mainly above 87% across these datasets. These results demonstrate BuildWin-SAM&#x2019;s potential to significantly enhance building window recognition in diverse urban environments, ultimately contributing to advancements in building information management and other relevant applications. The SVBW dataset will be provided at <uri>https://github.com/zhengnanle/svbw</uri>.
format Article
id doaj-art-5ceba207c90d449fbe8ee4f5c4d9eace
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-5ceba207c90d449fbe8ee4f5c4d9eace2025-08-20T02:12:24ZengIEEEIEEE Access2169-35362025-01-0113616966170710.1109/ACCESS.2025.355673810955328BuildWin-SAM: An Improved SAM-Based Method for Extracting Building Windows From Street View ImagesZhengnan Li0https://orcid.org/0009-0007-3600-9911Yizhen Yan1Bo Huang2https://orcid.org/0000-0002-5063-3522School of Ecology and Environment, Renmin University of China, Beijing, ChinaResearch Institute for Smart Cities, School of Architecture and Urban Planning, Shenzhen University, Shenzhen, ChinaGuangdong-Hong Kong-Macau Joint Laboratory for Smart Cities, Shenzhen, ChinaBuilding facade segmentation provides critical support for urban information management, precise 3D reconstruction, and energy consumption analysis. Window, as a pivotal component of building facades, plays a central role in these applications. However, accurately identifying windows in diverse urban environments poses significant challenges due to dataset limitations and variability in model performance. This study presents two primary contributions: first, we develop the Street View Building Window (SVBW) segmentation dataset, comprising 1,172 images that represent diverse urban contexts and window types, with a total of 50,321 meticulously annotated window instances. This dataset addresses existing gaps in segmenting irregular building facades. Second, we propose BuildWin-SAM, a model for window extraction based on the Segment Anything Model (SAM) architecture, which is trained on the SVBW dataset. Comparative analysis with CNN-based semantic segmentation models and SAM demonstrates that BuildWin-SAM achieves improvements across key evaluation metrics, including Intersection over Union (IoU), F1 score, precision, and recall. Specifically, BuildWin-SAM achieves an IoU of 80.70%, precision of 89.43%, recall of 89.20%, and an F1 score of 88.52%, demonstrating precise window localization and delineation capabilities. To further validate its robustness, we conduct evaluations on three public datasets featuring multi-scale and multi-scene images with building window annotations. BuildWin-SAM achieves Recall rates exceeding 72% and Precision rates mainly above 87% across these datasets. These results demonstrate BuildWin-SAM&#x2019;s potential to significantly enhance building window recognition in diverse urban environments, ultimately contributing to advancements in building information management and other relevant applications. The SVBW dataset will be provided at <uri>https://github.com/zhengnanle/svbw</uri>.https://ieeexplore.ieee.org/document/10955328/Building window datasetsemantic segmentationsegment anythingBaidu street view image
spellingShingle Zhengnan Li
Yizhen Yan
Bo Huang
BuildWin-SAM: An Improved SAM-Based Method for Extracting Building Windows From Street View Images
IEEE Access
Building window dataset
semantic segmentation
segment anything
Baidu street view image
title BuildWin-SAM: An Improved SAM-Based Method for Extracting Building Windows From Street View Images
title_full BuildWin-SAM: An Improved SAM-Based Method for Extracting Building Windows From Street View Images
title_fullStr BuildWin-SAM: An Improved SAM-Based Method for Extracting Building Windows From Street View Images
title_full_unstemmed BuildWin-SAM: An Improved SAM-Based Method for Extracting Building Windows From Street View Images
title_short BuildWin-SAM: An Improved SAM-Based Method for Extracting Building Windows From Street View Images
title_sort buildwin sam an improved sam based method for extracting building windows from street view images
topic Building window dataset
semantic segmentation
segment anything
Baidu street view image
url https://ieeexplore.ieee.org/document/10955328/
work_keys_str_mv AT zhengnanli buildwinsamanimprovedsambasedmethodforextractingbuildingwindowsfromstreetviewimages
AT yizhenyan buildwinsamanimprovedsambasedmethodforextractingbuildingwindowsfromstreetviewimages
AT bohuang buildwinsamanimprovedsambasedmethodforextractingbuildingwindowsfromstreetviewimages