Loading…

CoF-Net: A Progressive Coarse-to-Fine Framework for Object Detection in Remote-Sensing Imagery

Object detection in remote-sensing images is a crucial task in the fields of Earth observation and computer vision. Despite impressive progress in modern remote-sensing object detectors, there are still three challenges to overcome: 1) complex background interference, 2) dense and cluttered arrangem...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2023-01, Vol.61, p.1-1
Main Authors: Zhang, Cong, Lam, Kin-Man, Wang, Qi
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c294t-e1c3f2962bc95c98fe373617f8a13312af427c94fa375572173d40d3bf071acf3
cites cdi_FETCH-LOGICAL-c294t-e1c3f2962bc95c98fe373617f8a13312af427c94fa375572173d40d3bf071acf3
container_end_page 1
container_issue
container_start_page 1
container_title IEEE transactions on geoscience and remote sensing
container_volume 61
creator Zhang, Cong
Lam, Kin-Man
Wang, Qi
description Object detection in remote-sensing images is a crucial task in the fields of Earth observation and computer vision. Despite impressive progress in modern remote-sensing object detectors, there are still three challenges to overcome: 1) complex background interference, 2) dense and cluttered arrangement of instances, and 3) large scale variations. These challenges lead to two key deficiencies, namely coarse features and coarse samples, which limit the performance of existing object detectors. To address these issues, in this paper, a novel coarse-to-fine framework (CoF-Net) is proposed for object detection in remote-sensing imagery. CoF-Net mainly consists of two parallel branches, namely coarse-to-fine feature adaptation (CoF-FA) and coarse-to-fine sample assignment (CoF-SA), which aim to progressively enhance feature representation and select stronger training samples, respectively. Specifically, CoF-FA smoothly refines the original coarse features into multi-spectral nonlocal fine features with discriminative spatial-spectral details and semantic relations. Meanwhile, CoF-SA dynamically considers samples from coarse to fine by progressively introducing geometric and classification constraints for sample assignment during training. Comprehensive experiments on three public datasets demonstrate the effectiveness and superiority of the proposed method.
doi_str_mv 10.1109/TGRS.2022.3233881
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TGRS_2022_3233881</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10005072</ieee_id><sourcerecordid>2763818119</sourcerecordid><originalsourceid>FETCH-LOGICAL-c294t-e1c3f2962bc95c98fe373617f8a13312af427c94fa375572173d40d3bf071acf3</originalsourceid><addsrcrecordid>eNpNkEFPwjAYhhujiYj-ABMPTTwX-7Xbunoj0yEJEQN4dSnjKxm6Fduh4d87AgdP7-V53zd5CLkFPgDg-mExms0HggsxkELKNIUz0oM4ThlPouic9DjohIlUi0tyFcKGc4hiUD3ykbmcvWL7SIf0zbu1xxCqH6SZMz4gax3LqwZp7k2Nv85_Uus8nS43WLb0CdsuKtfQqqEzrF2LbI5NqJo1HddmjX5_TS6s-Qp4c8o-ec-fF9kLm0xH42w4YaXQUcsQSmmFTsSy1HGpU4tSyQSUTQ1ICcLYSKhSR9ZIFcdKgJKriK_k0nIFprSyT-6Pu1vvvncY2mLjdr7pLguhEplCCqA7Co5U6V0IHm2x9VVt_L4AXhw0FgeNxUFjcdLYde6OnQoR__Gcx1wJ-Qf3U209</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2763818119</pqid></control><display><type>article</type><title>CoF-Net: A Progressive Coarse-to-Fine Framework for Object Detection in Remote-Sensing Imagery</title><source>IEEE Xplore (Online service)</source><creator>Zhang, Cong ; Lam, Kin-Man ; Wang, Qi</creator><creatorcontrib>Zhang, Cong ; Lam, Kin-Man ; Wang, Qi</creatorcontrib><description>Object detection in remote-sensing images is a crucial task in the fields of Earth observation and computer vision. Despite impressive progress in modern remote-sensing object detectors, there are still three challenges to overcome: 1) complex background interference, 2) dense and cluttered arrangement of instances, and 3) large scale variations. These challenges lead to two key deficiencies, namely coarse features and coarse samples, which limit the performance of existing object detectors. To address these issues, in this paper, a novel coarse-to-fine framework (CoF-Net) is proposed for object detection in remote-sensing imagery. CoF-Net mainly consists of two parallel branches, namely coarse-to-fine feature adaptation (CoF-FA) and coarse-to-fine sample assignment (CoF-SA), which aim to progressively enhance feature representation and select stronger training samples, respectively. Specifically, CoF-FA smoothly refines the original coarse features into multi-spectral nonlocal fine features with discriminative spatial-spectral details and semantic relations. Meanwhile, CoF-SA dynamically considers samples from coarse to fine by progressively introducing geometric and classification constraints for sample assignment during training. Comprehensive experiments on three public datasets demonstrate the effectiveness and superiority of the proposed method.</description><identifier>ISSN: 0196-2892</identifier><identifier>EISSN: 1558-0644</identifier><identifier>DOI: 10.1109/TGRS.2022.3233881</identifier><identifier>CODEN: IGRSD2</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>coarse-to-fine paradigms ; Computer vision ; Detection ; Detectors ; Feature extraction ; geometric constraints ; Geospatial analysis ; Imagery ; Object detection ; Object recognition ; Remote observing ; Remote sensing ; Remote-sensing imagery ; Semantics ; spatial-spectral nonlocal features ; Training</subject><ispartof>IEEE transactions on geoscience and remote sensing, 2023-01, Vol.61, p.1-1</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c294t-e1c3f2962bc95c98fe373617f8a13312af427c94fa375572173d40d3bf071acf3</citedby><cites>FETCH-LOGICAL-c294t-e1c3f2962bc95c98fe373617f8a13312af427c94fa375572173d40d3bf071acf3</cites><orcidid>0000-0002-7028-4956 ; 0000-0003-2745-1656</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10005072$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,54796</link.rule.ids></links><search><creatorcontrib>Zhang, Cong</creatorcontrib><creatorcontrib>Lam, Kin-Man</creatorcontrib><creatorcontrib>Wang, Qi</creatorcontrib><title>CoF-Net: A Progressive Coarse-to-Fine Framework for Object Detection in Remote-Sensing Imagery</title><title>IEEE transactions on geoscience and remote sensing</title><addtitle>TGRS</addtitle><description>Object detection in remote-sensing images is a crucial task in the fields of Earth observation and computer vision. Despite impressive progress in modern remote-sensing object detectors, there are still three challenges to overcome: 1) complex background interference, 2) dense and cluttered arrangement of instances, and 3) large scale variations. These challenges lead to two key deficiencies, namely coarse features and coarse samples, which limit the performance of existing object detectors. To address these issues, in this paper, a novel coarse-to-fine framework (CoF-Net) is proposed for object detection in remote-sensing imagery. CoF-Net mainly consists of two parallel branches, namely coarse-to-fine feature adaptation (CoF-FA) and coarse-to-fine sample assignment (CoF-SA), which aim to progressively enhance feature representation and select stronger training samples, respectively. Specifically, CoF-FA smoothly refines the original coarse features into multi-spectral nonlocal fine features with discriminative spatial-spectral details and semantic relations. Meanwhile, CoF-SA dynamically considers samples from coarse to fine by progressively introducing geometric and classification constraints for sample assignment during training. Comprehensive experiments on three public datasets demonstrate the effectiveness and superiority of the proposed method.</description><subject>coarse-to-fine paradigms</subject><subject>Computer vision</subject><subject>Detection</subject><subject>Detectors</subject><subject>Feature extraction</subject><subject>geometric constraints</subject><subject>Geospatial analysis</subject><subject>Imagery</subject><subject>Object detection</subject><subject>Object recognition</subject><subject>Remote observing</subject><subject>Remote sensing</subject><subject>Remote-sensing imagery</subject><subject>Semantics</subject><subject>spatial-spectral nonlocal features</subject><subject>Training</subject><issn>0196-2892</issn><issn>1558-0644</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNpNkEFPwjAYhhujiYj-ABMPTTwX-7Xbunoj0yEJEQN4dSnjKxm6Fduh4d87AgdP7-V53zd5CLkFPgDg-mExms0HggsxkELKNIUz0oM4ThlPouic9DjohIlUi0tyFcKGc4hiUD3ykbmcvWL7SIf0zbu1xxCqH6SZMz4gax3LqwZp7k2Nv85_Uus8nS43WLb0CdsuKtfQqqEzrF2LbI5NqJo1HddmjX5_TS6s-Qp4c8o-ec-fF9kLm0xH42w4YaXQUcsQSmmFTsSy1HGpU4tSyQSUTQ1ICcLYSKhSR9ZIFcdKgJKriK_k0nIFprSyT-6Pu1vvvncY2mLjdr7pLguhEplCCqA7Co5U6V0IHm2x9VVt_L4AXhw0FgeNxUFjcdLYde6OnQoR__Gcx1wJ-Qf3U209</recordid><startdate>20230101</startdate><enddate>20230101</enddate><creator>Zhang, Cong</creator><creator>Lam, Kin-Man</creator><creator>Wang, Qi</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7UA</scope><scope>8FD</scope><scope>C1K</scope><scope>F1W</scope><scope>FR3</scope><scope>H8D</scope><scope>H96</scope><scope>KR7</scope><scope>L.G</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0002-7028-4956</orcidid><orcidid>https://orcid.org/0000-0003-2745-1656</orcidid></search><sort><creationdate>20230101</creationdate><title>CoF-Net: A Progressive Coarse-to-Fine Framework for Object Detection in Remote-Sensing Imagery</title><author>Zhang, Cong ; Lam, Kin-Man ; Wang, Qi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c294t-e1c3f2962bc95c98fe373617f8a13312af427c94fa375572173d40d3bf071acf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>coarse-to-fine paradigms</topic><topic>Computer vision</topic><topic>Detection</topic><topic>Detectors</topic><topic>Feature extraction</topic><topic>geometric constraints</topic><topic>Geospatial analysis</topic><topic>Imagery</topic><topic>Object detection</topic><topic>Object recognition</topic><topic>Remote observing</topic><topic>Remote sensing</topic><topic>Remote-sensing imagery</topic><topic>Semantics</topic><topic>spatial-spectral nonlocal features</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Cong</creatorcontrib><creatorcontrib>Lam, Kin-Man</creatorcontrib><creatorcontrib>Wang, Qi</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library Online</collection><collection>CrossRef</collection><collection>Water Resources Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy &amp; Non-Living Resources</collection><collection>Civil Engineering Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on geoscience and remote sensing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Cong</au><au>Lam, Kin-Man</au><au>Wang, Qi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>CoF-Net: A Progressive Coarse-to-Fine Framework for Object Detection in Remote-Sensing Imagery</atitle><jtitle>IEEE transactions on geoscience and remote sensing</jtitle><stitle>TGRS</stitle><date>2023-01-01</date><risdate>2023</risdate><volume>61</volume><spage>1</spage><epage>1</epage><pages>1-1</pages><issn>0196-2892</issn><eissn>1558-0644</eissn><coden>IGRSD2</coden><abstract>Object detection in remote-sensing images is a crucial task in the fields of Earth observation and computer vision. Despite impressive progress in modern remote-sensing object detectors, there are still three challenges to overcome: 1) complex background interference, 2) dense and cluttered arrangement of instances, and 3) large scale variations. These challenges lead to two key deficiencies, namely coarse features and coarse samples, which limit the performance of existing object detectors. To address these issues, in this paper, a novel coarse-to-fine framework (CoF-Net) is proposed for object detection in remote-sensing imagery. CoF-Net mainly consists of two parallel branches, namely coarse-to-fine feature adaptation (CoF-FA) and coarse-to-fine sample assignment (CoF-SA), which aim to progressively enhance feature representation and select stronger training samples, respectively. Specifically, CoF-FA smoothly refines the original coarse features into multi-spectral nonlocal fine features with discriminative spatial-spectral details and semantic relations. Meanwhile, CoF-SA dynamically considers samples from coarse to fine by progressively introducing geometric and classification constraints for sample assignment during training. Comprehensive experiments on three public datasets demonstrate the effectiveness and superiority of the proposed method.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TGRS.2022.3233881</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0002-7028-4956</orcidid><orcidid>https://orcid.org/0000-0003-2745-1656</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0196-2892
ispartof IEEE transactions on geoscience and remote sensing, 2023-01, Vol.61, p.1-1
issn 0196-2892
1558-0644
language eng
recordid cdi_crossref_primary_10_1109_TGRS_2022_3233881
source IEEE Xplore (Online service)
subjects coarse-to-fine paradigms
Computer vision
Detection
Detectors
Feature extraction
geometric constraints
Geospatial analysis
Imagery
Object detection
Object recognition
Remote observing
Remote sensing
Remote-sensing imagery
Semantics
spatial-spectral nonlocal features
Training
title CoF-Net: A Progressive Coarse-to-Fine Framework for Object Detection in Remote-Sensing Imagery
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T00%3A05%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=CoF-Net:%20A%20Progressive%20Coarse-to-Fine%20Framework%20for%20Object%20Detection%20in%20Remote-Sensing%20Imagery&rft.jtitle=IEEE%20transactions%20on%20geoscience%20and%20remote%20sensing&rft.au=Zhang,%20Cong&rft.date=2023-01-01&rft.volume=61&rft.spage=1&rft.epage=1&rft.pages=1-1&rft.issn=0196-2892&rft.eissn=1558-0644&rft.coden=IGRSD2&rft_id=info:doi/10.1109/TGRS.2022.3233881&rft_dat=%3Cproquest_cross%3E2763818119%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c294t-e1c3f2962bc95c98fe373617f8a13312af427c94fa375572173d40d3bf071acf3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2763818119&rft_id=info:pmid/&rft_ieee_id=10005072&rfr_iscdi=true