Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on image processing 2021, Vol.30, p.1925-1934 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1934 |
|---|---|
| container_issue | |
| container_start_page | 1925 |
| container_title | IEEE transactions on image processing |
| container_volume | 30 |
| creator | Hu, Xiaowei Wang, Tianyu Fu, Chi-Wing Jiang, Yitong Wang, Qiong Heng, Pheng-Ann |
| description | Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations. |
| doi_str_mv | 10.1109/TIP.2021.3049331 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_pubmed_primary_33428570</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9319520</ieee_id><sourcerecordid>2477263180</sourcerecordid><originalsourceid>FETCH-LOGICAL-c347t-b6520502db43cad795a8ee6e60cb28e19f3deb5089d38ef8e7a80215de8f10393</originalsourceid><addsrcrecordid>eNpdkMtLxDAQh4Movu-CIAEvXrpOXk3ibV2fICo-8FjSdqrVbrM2XR__vVl29eBpBuabYX4fITsMBoyBPXy4vB1w4GwgQFoh2BJZZ1ayBEDy5diD0olm0q6RjRBeAZhULF0la0JIbpSGdXJ2hx91qPu6fab3L670n_QEeyz62rdHdEiv8ZMeY1u8jF33Rk9c7wL2tPIdHfnxpMEv-uS7ptwiK5VrAm4v6iZ5PDt9GF0kVzfnl6PhVVIIqfskTxUHBbzMpShcqa1yBjHFFIqcG2S2EiXmCowthcHKoHYmxlMlmoqBsGKTHMzvTjr_PsXQZ-M6FNg0rkU_DRmXWvNUMAMR3f-Hvvpp18bvZpQ1xmipIgVzquh8CB1W2aSrY9bvjEE2c5xFx9nMcbZwHFf2Foen-RjLv4VfqRHYnQM1Iv6NrWA2phc_txV9yg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2479888745</pqid></control><display><type>article</type><title>Revisiting Shadow Detection: A New Benchmark Dataset for Complex World</title><source>IEEE Electronic Library (IEL)</source><creator>Hu, Xiaowei ; Wang, Tianyu ; Fu, Chi-Wing ; Jiang, Yitong ; Wang, Qiong ; Heng, Pheng-Ann</creator><creatorcontrib>Hu, Xiaowei ; Wang, Tianyu ; Fu, Chi-Wing ; Jiang, Yitong ; Wang, Qiong ; Heng, Pheng-Ann</creatorcontrib><description>Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations.</description><identifier>ISSN: 1057-7149</identifier><identifier>EISSN: 1941-0042</identifier><identifier>DOI: 10.1109/TIP.2021.3049331</identifier><identifier>PMID: 33428570</identifier><identifier>CODEN: IIPRE4</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>benchmark dataset ; Benchmark testing ; Benchmarks ; Buildings ; complex ; Complexity ; Complexity theory ; Datasets ; deep neural network ; Feature extraction ; Roads ; Shadow detection ; Shadows ; Solid modeling ; Training</subject><ispartof>IEEE transactions on image processing, 2021, Vol.30, p.1925-1934</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c347t-b6520502db43cad795a8ee6e60cb28e19f3deb5089d38ef8e7a80215de8f10393</citedby><cites>FETCH-LOGICAL-c347t-b6520502db43cad795a8ee6e60cb28e19f3deb5089d38ef8e7a80215de8f10393</cites><orcidid>0000-0002-0835-3770 ; 0000-0002-5708-7018 ; 0000-0003-3055-5034</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9319520$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,4024,27923,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9319520$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33428570$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Hu, Xiaowei</creatorcontrib><creatorcontrib>Wang, Tianyu</creatorcontrib><creatorcontrib>Fu, Chi-Wing</creatorcontrib><creatorcontrib>Jiang, Yitong</creatorcontrib><creatorcontrib>Wang, Qiong</creatorcontrib><creatorcontrib>Heng, Pheng-Ann</creatorcontrib><title>Revisiting Shadow Detection: A New Benchmark Dataset for Complex World</title><title>IEEE transactions on image processing</title><addtitle>TIP</addtitle><addtitle>IEEE Trans Image Process</addtitle><description>Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations.</description><subject>benchmark dataset</subject><subject>Benchmark testing</subject><subject>Benchmarks</subject><subject>Buildings</subject><subject>complex</subject><subject>Complexity</subject><subject>Complexity theory</subject><subject>Datasets</subject><subject>deep neural network</subject><subject>Feature extraction</subject><subject>Roads</subject><subject>Shadow detection</subject><subject>Shadows</subject><subject>Solid modeling</subject><subject>Training</subject><issn>1057-7149</issn><issn>1941-0042</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkMtLxDAQh4Movu-CIAEvXrpOXk3ibV2fICo-8FjSdqrVbrM2XR__vVl29eBpBuabYX4fITsMBoyBPXy4vB1w4GwgQFoh2BJZZ1ayBEDy5diD0olm0q6RjRBeAZhULF0la0JIbpSGdXJ2hx91qPu6fab3L670n_QEeyz62rdHdEiv8ZMeY1u8jF33Rk9c7wL2tPIdHfnxpMEv-uS7ptwiK5VrAm4v6iZ5PDt9GF0kVzfnl6PhVVIIqfskTxUHBbzMpShcqa1yBjHFFIqcG2S2EiXmCowthcHKoHYmxlMlmoqBsGKTHMzvTjr_PsXQZ-M6FNg0rkU_DRmXWvNUMAMR3f-Hvvpp18bvZpQ1xmipIgVzquh8CB1W2aSrY9bvjEE2c5xFx9nMcbZwHFf2Foen-RjLv4VfqRHYnQM1Iv6NrWA2phc_txV9yg</recordid><startdate>2021</startdate><enddate>2021</enddate><creator>Hu, Xiaowei</creator><creator>Wang, Tianyu</creator><creator>Fu, Chi-Wing</creator><creator>Jiang, Yitong</creator><creator>Wang, Qiong</creator><creator>Heng, Pheng-Ann</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>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-0835-3770</orcidid><orcidid>https://orcid.org/0000-0002-5708-7018</orcidid><orcidid>https://orcid.org/0000-0003-3055-5034</orcidid></search><sort><creationdate>2021</creationdate><title>Revisiting Shadow Detection: A New Benchmark Dataset for Complex World</title><author>Hu, Xiaowei ; Wang, Tianyu ; Fu, Chi-Wing ; Jiang, Yitong ; Wang, Qiong ; Heng, Pheng-Ann</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c347t-b6520502db43cad795a8ee6e60cb28e19f3deb5089d38ef8e7a80215de8f10393</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>benchmark dataset</topic><topic>Benchmark testing</topic><topic>Benchmarks</topic><topic>Buildings</topic><topic>complex</topic><topic>Complexity</topic><topic>Complexity theory</topic><topic>Datasets</topic><topic>deep neural network</topic><topic>Feature extraction</topic><topic>Roads</topic><topic>Shadow detection</topic><topic>Shadows</topic><topic>Solid modeling</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hu, Xiaowei</creatorcontrib><creatorcontrib>Wang, Tianyu</creatorcontrib><creatorcontrib>Fu, Chi-Wing</creatorcontrib><creatorcontrib>Jiang, Yitong</creatorcontrib><creatorcontrib>Wang, Qiong</creatorcontrib><creatorcontrib>Heng, Pheng-Ann</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 (IEL)</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on image processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hu, Xiaowei</au><au>Wang, Tianyu</au><au>Fu, Chi-Wing</au><au>Jiang, Yitong</au><au>Wang, Qiong</au><au>Heng, Pheng-Ann</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Revisiting Shadow Detection: A New Benchmark Dataset for Complex World</atitle><jtitle>IEEE transactions on image processing</jtitle><stitle>TIP</stitle><addtitle>IEEE Trans Image Process</addtitle><date>2021</date><risdate>2021</risdate><volume>30</volume><spage>1925</spage><epage>1934</epage><pages>1925-1934</pages><issn>1057-7149</issn><eissn>1941-0042</eissn><coden>IIPRE4</coden><abstract>Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>33428570</pmid><doi>10.1109/TIP.2021.3049331</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0002-0835-3770</orcidid><orcidid>https://orcid.org/0000-0002-5708-7018</orcidid><orcidid>https://orcid.org/0000-0003-3055-5034</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1057-7149 |
| ispartof | IEEE transactions on image processing, 2021, Vol.30, p.1925-1934 |
| issn | 1057-7149 1941-0042 |
| language | eng |
| recordid | cdi_pubmed_primary_33428570 |
| source | IEEE Electronic Library (IEL) |
| subjects | benchmark dataset Benchmark testing Benchmarks Buildings complex Complexity Complexity theory Datasets deep neural network Feature extraction Roads Shadow detection Shadows Solid modeling Training |
| title | Revisiting Shadow Detection: A New Benchmark Dataset for Complex World |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T14%3A46%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Revisiting%20Shadow%20Detection:%20A%20New%20Benchmark%20Dataset%20for%20Complex%20World&rft.jtitle=IEEE%20transactions%20on%20image%20processing&rft.au=Hu,%20Xiaowei&rft.date=2021&rft.volume=30&rft.spage=1925&rft.epage=1934&rft.pages=1925-1934&rft.issn=1057-7149&rft.eissn=1941-0042&rft.coden=IIPRE4&rft_id=info:doi/10.1109/TIP.2021.3049331&rft_dat=%3Cproquest_RIE%3E2477263180%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2479888745&rft_id=info:pmid/33428570&rft_ieee_id=9319520&rfr_iscdi=true |