Deep learning-based detection and evaluation of building changes in rail transit protection zones

Rapid urbanization in China exacerbates risks to rail transit protection zones, necessitating high-precision building change detection. Existing research primarily focuses on algorithm optimization and overlooks the construction of scene-specific datasets. Focusing on protected areas of 16 rail tran...

Full description

Saved in:
Bibliographic Details
Main Authors: Cai Jia, Long Zhao, Chengyang Qian, Yu Zhang, Zini Cao, Xiaoqiang Zhu
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Geocarto International
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/10106049.2025.2521835
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850157053718298624
author Cai Jia
Long Zhao
Chengyang Qian
Yu Zhang
Zini Cao
Xiaoqiang Zhu
author_facet Cai Jia
Long Zhao
Chengyang Qian
Yu Zhang
Zini Cao
Xiaoqiang Zhu
author_sort Cai Jia
collection DOAJ
description Rapid urbanization in China exacerbates risks to rail transit protection zones, necessitating high-precision building change detection. Existing research primarily focuses on algorithm optimization and overlooks the construction of scene-specific datasets. Focusing on protected areas of 16 rail transit lines in Beijing, this study constructs a dedicated training sample set and conducts change detection using Mask R-CNN. The results show that the dedicated training sample set achieves 92.45%, 93.28%, 92.86%, and 86.38% in precision, recall, F1 score, and IOU, respectively, which are significantly improved over common datasets. Compared with the EGRCNN, precision, F1 score, and IOU are improved by 1.04%, 3.62%, and 5.81%, respectively, despite a marginally lower recall. The study demonstrates that a dedicated training sample set enhances the accuracy of building change detection. It emphasizes a shift from pure algorithm optimization toward dataset specialization, offering methodological and practical value for infrastructure safety and sustainable urban development.
format Article
id doaj-art-9a32f7f5014843d686b806bb48aeac12
institution OA Journals
issn 1010-6049
1752-0762
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Geocarto International
spelling doaj-art-9a32f7f5014843d686b806bb48aeac122025-08-20T02:24:17ZengTaylor & Francis GroupGeocarto International1010-60491752-07622025-12-0140110.1080/10106049.2025.2521835Deep learning-based detection and evaluation of building changes in rail transit protection zonesCai Jia0Long Zhao1Chengyang Qian2Yu Zhang3Zini Cao4Xiaoqiang Zhu5School of Geography and Tourism, Anhui Normal University, Wuhu, ChinaSchool of Geography and Tourism, Anhui Normal University, Wuhu, ChinaJiangsu Geospatial Artificial Intelligence Engineering Research Center, Suzhou, ChinaSIPSG Information Technology Co. Ltd, Suzhou, ChinaSchool of Geography and Tourism, Anhui Normal University, Wuhu, ChinaSchool of Geography and Tourism, Anhui Normal University, Wuhu, ChinaRapid urbanization in China exacerbates risks to rail transit protection zones, necessitating high-precision building change detection. Existing research primarily focuses on algorithm optimization and overlooks the construction of scene-specific datasets. Focusing on protected areas of 16 rail transit lines in Beijing, this study constructs a dedicated training sample set and conducts change detection using Mask R-CNN. The results show that the dedicated training sample set achieves 92.45%, 93.28%, 92.86%, and 86.38% in precision, recall, F1 score, and IOU, respectively, which are significantly improved over common datasets. Compared with the EGRCNN, precision, F1 score, and IOU are improved by 1.04%, 3.62%, and 5.81%, respectively, despite a marginally lower recall. The study demonstrates that a dedicated training sample set enhances the accuracy of building change detection. It emphasizes a shift from pure algorithm optimization toward dataset specialization, offering methodological and practical value for infrastructure safety and sustainable urban development.https://www.tandfonline.com/doi/10.1080/10106049.2025.2521835Remote sensing technologyrail transit protection zonededicated training sample setbuilding change detectionevaluation indicators
spellingShingle Cai Jia
Long Zhao
Chengyang Qian
Yu Zhang
Zini Cao
Xiaoqiang Zhu
Deep learning-based detection and evaluation of building changes in rail transit protection zones
Geocarto International
Remote sensing technology
rail transit protection zone
dedicated training sample set
building change detection
evaluation indicators
title Deep learning-based detection and evaluation of building changes in rail transit protection zones
title_full Deep learning-based detection and evaluation of building changes in rail transit protection zones
title_fullStr Deep learning-based detection and evaluation of building changes in rail transit protection zones
title_full_unstemmed Deep learning-based detection and evaluation of building changes in rail transit protection zones
title_short Deep learning-based detection and evaluation of building changes in rail transit protection zones
title_sort deep learning based detection and evaluation of building changes in rail transit protection zones
topic Remote sensing technology
rail transit protection zone
dedicated training sample set
building change detection
evaluation indicators
url https://www.tandfonline.com/doi/10.1080/10106049.2025.2521835
work_keys_str_mv AT caijia deeplearningbaseddetectionandevaluationofbuildingchangesinrailtransitprotectionzones
AT longzhao deeplearningbaseddetectionandevaluationofbuildingchangesinrailtransitprotectionzones
AT chengyangqian deeplearningbaseddetectionandevaluationofbuildingchangesinrailtransitprotectionzones
AT yuzhang deeplearningbaseddetectionandevaluationofbuildingchangesinrailtransitprotectionzones
AT zinicao deeplearningbaseddetectionandevaluationofbuildingchangesinrailtransitprotectionzones
AT xiaoqiangzhu deeplearningbaseddetectionandevaluationofbuildingchangesinrailtransitprotectionzones