A Multisource Dynamic Fusion Network for Urban Functional Zone Identification on Remote Sensing, POI, and Building Footprint

Urban functional zones (UFZ) identification with remote sensing imagery (RSI) is attracting increasing attention in urban planning and resource allocation in urban areas, etc. The UFZ is a comprehensive unit comprising geographical, how to effectively integrate the RSI and points of interest (POI) w...

Full description

Saved in:
Bibliographic Details
Main Authors: Hangfeng Qiao, Huiping Jiang, Gang Yang, Faming Jing, Weiwei Sun, Chenyang Lu, Xiangchao Meng
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10542987/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850219426617491456
author Hangfeng Qiao
Huiping Jiang
Gang Yang
Faming Jing
Weiwei Sun
Chenyang Lu
Xiangchao Meng
author_facet Hangfeng Qiao
Huiping Jiang
Gang Yang
Faming Jing
Weiwei Sun
Chenyang Lu
Xiangchao Meng
author_sort Hangfeng Qiao
collection DOAJ
description Urban functional zones (UFZ) identification with remote sensing imagery (RSI) is attracting increasing attention in urban planning and resource allocation in urban areas, etc. The UFZ is a comprehensive unit comprising geographical, how to effectively integrate the RSI and points of interest (POI) with different physical and socioeconomic characteristics is important and promising. However, there are two challenges for the UFZ identification. On one hand, the UFZ is closely related to buildings, and most current methods lack an in-depth understanding of building semantics. Therefore, an efficient integration of building footprint (FT) data deserves further investigation. On the other hand, these RSI, POI, and FT data are heterogeneous; how to effectively leverage complementary information among these highly heterogeneous modalities to enhance the comprehensive understanding of urban. To solve the above challenges, this article introduces an end-to-end deep learning-based multisource dynamic fusion network for UFZ identification on RSI, POI, and FT. In the proposed method, an adaptive weight interactive fusion module is designed to comprehensively integrate the complementary information among the heterogeneous RSI, POI, and FT data sources. In addition, a multiscale feature focus module is proposed to extract multiscale image features and emphasize critical characteristics. This method was applied to UFZ classification in Ningbo, Zhejiang Province, China, and the experimental results demonstrate the competitive performance.
format Article
id doaj-art-a9ef8eb02a8947b99a01fbe21fcabb09
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-a9ef8eb02a8947b99a01fbe21fcabb092025-08-20T02:07:23ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-0117105831059910.1109/JSTARS.2024.340409410542987A Multisource Dynamic Fusion Network for Urban Functional Zone Identification on Remote Sensing, POI, and Building FootprintHangfeng Qiao0https://orcid.org/0009-0009-6506-8958Huiping Jiang1https://orcid.org/0000-0001-9539-1662Gang Yang2https://orcid.org/0000-0002-7001-2037Faming Jing3Weiwei Sun4https://orcid.org/0000-0003-3399-7858Chenyang Lu5https://orcid.org/0000-0002-5565-7689Xiangchao Meng6https://orcid.org/0000-0002-7405-3143Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaKey Laboratory of Regional Sustainable Development Modeling, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, ChinaDepartment of Geography and Spatial Information Techniques, Ningbo University, Ningbo, ChinaNingbo Institute of Surveying Mapping and Remote Sensing, Ningbo, ChinaDepartment of Geography and Spatial Information Techniques, Ningbo University, Ningbo, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaUrban functional zones (UFZ) identification with remote sensing imagery (RSI) is attracting increasing attention in urban planning and resource allocation in urban areas, etc. The UFZ is a comprehensive unit comprising geographical, how to effectively integrate the RSI and points of interest (POI) with different physical and socioeconomic characteristics is important and promising. However, there are two challenges for the UFZ identification. On one hand, the UFZ is closely related to buildings, and most current methods lack an in-depth understanding of building semantics. Therefore, an efficient integration of building footprint (FT) data deserves further investigation. On the other hand, these RSI, POI, and FT data are heterogeneous; how to effectively leverage complementary information among these highly heterogeneous modalities to enhance the comprehensive understanding of urban. To solve the above challenges, this article introduces an end-to-end deep learning-based multisource dynamic fusion network for UFZ identification on RSI, POI, and FT. In the proposed method, an adaptive weight interactive fusion module is designed to comprehensively integrate the complementary information among the heterogeneous RSI, POI, and FT data sources. In addition, a multiscale feature focus module is proposed to extract multiscale image features and emphasize critical characteristics. This method was applied to UFZ classification in Ningbo, Zhejiang Province, China, and the experimental results demonstrate the competitive performance.https://ieeexplore.ieee.org/document/10542987/Deep learning (DL)multimodal data fusionremote sensing imagery (RSI)social sensing dataurban functional zone (UFZ)
spellingShingle Hangfeng Qiao
Huiping Jiang
Gang Yang
Faming Jing
Weiwei Sun
Chenyang Lu
Xiangchao Meng
A Multisource Dynamic Fusion Network for Urban Functional Zone Identification on Remote Sensing, POI, and Building Footprint
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning (DL)
multimodal data fusion
remote sensing imagery (RSI)
social sensing data
urban functional zone (UFZ)
title A Multisource Dynamic Fusion Network for Urban Functional Zone Identification on Remote Sensing, POI, and Building Footprint
title_full A Multisource Dynamic Fusion Network for Urban Functional Zone Identification on Remote Sensing, POI, and Building Footprint
title_fullStr A Multisource Dynamic Fusion Network for Urban Functional Zone Identification on Remote Sensing, POI, and Building Footprint
title_full_unstemmed A Multisource Dynamic Fusion Network for Urban Functional Zone Identification on Remote Sensing, POI, and Building Footprint
title_short A Multisource Dynamic Fusion Network for Urban Functional Zone Identification on Remote Sensing, POI, and Building Footprint
title_sort multisource dynamic fusion network for urban functional zone identification on remote sensing poi and building footprint
topic Deep learning (DL)
multimodal data fusion
remote sensing imagery (RSI)
social sensing data
urban functional zone (UFZ)
url https://ieeexplore.ieee.org/document/10542987/
work_keys_str_mv AT hangfengqiao amultisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT huipingjiang amultisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT gangyang amultisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT famingjing amultisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT weiweisun amultisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT chenyanglu amultisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT xiangchaomeng amultisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT hangfengqiao multisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT huipingjiang multisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT gangyang multisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT famingjing multisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT weiweisun multisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT chenyanglu multisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint
AT xiangchaomeng multisourcedynamicfusionnetworkforurbanfunctionalzoneidentificationonremotesensingpoiandbuildingfootprint