Enhancing Urban Land Utilization Through SegFormer: A Vacant Land Analysis in Chengdu

Urban vacant land (UVL) presents significant environmental and urban planning challenges as cities expand, necessitating effective identification and management strategies. This study proposes an enhanced framework for UVL extraction, based on an improved SegFormer model, which incorporates the dens...

Full description

Saved in:
Bibliographic Details
Main Authors: Xi Cheng, Jieyu Yang, Bin Li, Bin Zhao, Deng Pan, Zhanfeng Shen, Qian Zhu, Miaomiao 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/10873816/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850231338726064128
author Xi Cheng
Jieyu Yang
Bin Li
Bin Zhao
Deng Pan
Zhanfeng Shen
Qian Zhu
Miaomiao Liu
author_facet Xi Cheng
Jieyu Yang
Bin Li
Bin Zhao
Deng Pan
Zhanfeng Shen
Qian Zhu
Miaomiao Liu
author_sort Xi Cheng
collection DOAJ
description Urban vacant land (UVL) presents significant environmental and urban planning challenges as cities expand, necessitating effective identification and management strategies. This study proposes an enhanced framework for UVL extraction, based on an improved SegFormer model, which incorporates the densely connected atrous spatial pyramid pooling module and the progressive feature pyramid network for expanded receptive field and achieve multiscale feature integration. The framework first applies a region-based stratification approach, dividing the study area into the central and expanded areas to handle varying land characteristics in different urban regions. Both pretrained and non-pretrained models were utilized to assess their effectiveness in segmentation accuracy, using high-resolution remote sensing images of Chengdu. The experimental results demonstrate the effectiveness of the framework, with the pretrained model, trained on urbanized area data from Chinese cities, achieving <italic>F</italic>1-scores of 91.34 and 90.05 and IoU values of 84.21 and 81.91 for the central and expanded areas, respectively. In contrast, the non-pretrained model yielded <italic>F</italic>1-scores of 93.08 and 92.32, with corresponding IoU values of 87.16 and 85.74. Ablation studies and robustness tests further confirm the model's stability and precision in complex application scenarios. This framework provides the accurate and efficient tool for UVL identification, contributing to improved urban land utilization and offering valuable insights for future research and urban planning.
format Article
id doaj-art-d29bd4a8346d4328a4f2bf57c00c25f5
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-d29bd4a8346d4328a4f2bf57c00c25f52025-08-20T02:03:34ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01186070608510.1109/JSTARS.2025.353892010873816Enhancing Urban Land Utilization Through SegFormer: A Vacant Land Analysis in ChengduXi Cheng0https://orcid.org/0000-0002-0587-8651Jieyu Yang1https://orcid.org/0009-0001-1969-2559Bin Li2Bin Zhao3Deng Pan4Zhanfeng Shen5https://orcid.org/0000-0002-8651-7435Qian Zhu6Miaomiao Liu7https://orcid.org/0009-0004-2814-5372College of Geophysics, Chengdu University of Technology, Chengdu, ChinaCollege of Geophysics, Chengdu University of Technology, Chengdu, ChinaCollege of Geophysics, Chengdu University of Technology, Chengdu, ChinaCollege of Geophysics, Chengdu University of Technology, Chengdu, ChinaCollege of Geophysics, Chengdu University of Technology, Chengdu, ChinaNational Engineering Research Center for Geomatics, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaCollege of Geophysics, Chengdu University of Technology, Chengdu, ChinaCollege of Geophysics, Chengdu University of Technology, Chengdu, ChinaUrban vacant land (UVL) presents significant environmental and urban planning challenges as cities expand, necessitating effective identification and management strategies. This study proposes an enhanced framework for UVL extraction, based on an improved SegFormer model, which incorporates the densely connected atrous spatial pyramid pooling module and the progressive feature pyramid network for expanded receptive field and achieve multiscale feature integration. The framework first applies a region-based stratification approach, dividing the study area into the central and expanded areas to handle varying land characteristics in different urban regions. Both pretrained and non-pretrained models were utilized to assess their effectiveness in segmentation accuracy, using high-resolution remote sensing images of Chengdu. The experimental results demonstrate the effectiveness of the framework, with the pretrained model, trained on urbanized area data from Chinese cities, achieving <italic>F</italic>1-scores of 91.34 and 90.05 and IoU values of 84.21 and 81.91 for the central and expanded areas, respectively. In contrast, the non-pretrained model yielded <italic>F</italic>1-scores of 93.08 and 92.32, with corresponding IoU values of 87.16 and 85.74. Ablation studies and robustness tests further confirm the model's stability and precision in complex application scenarios. This framework provides the accurate and efficient tool for UVL identification, contributing to improved urban land utilization and offering valuable insights for future research and urban planning.https://ieeexplore.ieee.org/document/10873816/Chengduhigh-resolution remote sensingSegFormer modelsemantic segmentationvacant land identification
spellingShingle Xi Cheng
Jieyu Yang
Bin Li
Bin Zhao
Deng Pan
Zhanfeng Shen
Qian Zhu
Miaomiao Liu
Enhancing Urban Land Utilization Through SegFormer: A Vacant Land Analysis in Chengdu
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Chengdu
high-resolution remote sensing
SegFormer model
semantic segmentation
vacant land identification
title Enhancing Urban Land Utilization Through SegFormer: A Vacant Land Analysis in Chengdu
title_full Enhancing Urban Land Utilization Through SegFormer: A Vacant Land Analysis in Chengdu
title_fullStr Enhancing Urban Land Utilization Through SegFormer: A Vacant Land Analysis in Chengdu
title_full_unstemmed Enhancing Urban Land Utilization Through SegFormer: A Vacant Land Analysis in Chengdu
title_short Enhancing Urban Land Utilization Through SegFormer: A Vacant Land Analysis in Chengdu
title_sort enhancing urban land utilization through segformer a vacant land analysis in chengdu
topic Chengdu
high-resolution remote sensing
SegFormer model
semantic segmentation
vacant land identification
url https://ieeexplore.ieee.org/document/10873816/
work_keys_str_mv AT xicheng enhancingurbanlandutilizationthroughsegformeravacantlandanalysisinchengdu
AT jieyuyang enhancingurbanlandutilizationthroughsegformeravacantlandanalysisinchengdu
AT binli enhancingurbanlandutilizationthroughsegformeravacantlandanalysisinchengdu
AT binzhao enhancingurbanlandutilizationthroughsegformeravacantlandanalysisinchengdu
AT dengpan enhancingurbanlandutilizationthroughsegformeravacantlandanalysisinchengdu
AT zhanfengshen enhancingurbanlandutilizationthroughsegformeravacantlandanalysisinchengdu
AT qianzhu enhancingurbanlandutilizationthroughsegformeravacantlandanalysisinchengdu
AT miaomiaoliu enhancingurbanlandutilizationthroughsegformeravacantlandanalysisinchengdu