ORGM: Occlusion Relational Graphical Model for Human Pose Estimation
Articulated human pose estimation from monocular image is a challenging problem in computer vision. Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structured models. The tree structured model is simple and convenient for exact inference, but short i...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on image processing 2017-02, Vol.26 (2), p.927-941 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 941 |
|---|---|
| container_issue | 2 |
| container_start_page | 927 |
| container_title | IEEE transactions on image processing |
| container_volume | 26 |
| creator | Fu, Lianrui Zhang, Junge Huang, Kaiqi |
| description | Articulated human pose estimation from monocular image is a challenging problem in computer vision. Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structured models. The tree structured model is simple and convenient for exact inference, but short in modeling the occlusion coherence especially in the case of self-occlusion. We propose an occlusion relational graphical model, which is able to model both self-occlusion and occlusion by the other objects simultaneously. The proposed model can encode the interactions between human body parts and objects, and enables it to learn occlusion coherence from data discriminatively. We evaluate our model on several public benchmarks for human pose estimation, including challenging subsets featuring significant occlusion. The experimental results show that our method is superior to the previous state-of-the-arts, and is robust to occlusion for 2D human pose estimation. |
| doi_str_mv | 10.1109/TIP.2016.2639441 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_miscellaneous_1861614306</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7782843</ieee_id><sourcerecordid>1861614306</sourcerecordid><originalsourceid>FETCH-LOGICAL-c385t-c465eadaefc601766ddb5e9663be1feab609f64b1441e8f0d14aa3eba0cd4e4e3</originalsourceid><addsrcrecordid>eNo9kEFPwkAQRjdGI4jeTUxMj15aZ7rbbevNIAIJBELwvNlup7GmpdhtD_57F0FO8yXzZjLzGLtHCBAhfd7O10EIKINQ8lQIvGBDTAX6ACK8dBmi2I9RpAN2Y-0XAIoI5TUbhAki5yiH7G21mS5fvJUxVW_LZudtqNKdC7rypq3ef5bGpWWTU-UVTevN-lrvvHVjyZvYrqz_2Ft2VejK0t2pjtjH-2Q7nvmL1XQ-fl34hidR5xshI9K5psJIwFjKPM8iSqXkGWFBOpOQFlJk6D6hpIAchdacMg0mFySIj9jTce--bb57sp2qS2uoqvSOmt4qTCRKFBykQ-GImraxtqVC7Vt3bfujENTBnXLu1MGdOrlzI4-n7X1WU34e-JflgIcjUBLRuR3HSZgIzn8BTw5yeQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1861614306</pqid></control><display><type>article</type><title>ORGM: Occlusion Relational Graphical Model for Human Pose Estimation</title><source>IEEE Electronic Library (IEL)</source><creator>Fu, Lianrui ; Zhang, Junge ; Huang, Kaiqi</creator><creatorcontrib>Fu, Lianrui ; Zhang, Junge ; Huang, Kaiqi</creatorcontrib><description>Articulated human pose estimation from monocular image is a challenging problem in computer vision. Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structured models. The tree structured model is simple and convenient for exact inference, but short in modeling the occlusion coherence especially in the case of self-occlusion. We propose an occlusion relational graphical model, which is able to model both self-occlusion and occlusion by the other objects simultaneously. The proposed model can encode the interactions between human body parts and objects, and enables it to learn occlusion coherence from data discriminatively. We evaluate our model on several public benchmarks for human pose estimation, including challenging subsets featuring significant occlusion. The experimental results show that our method is superior to the previous state-of-the-arts, and is robust to occlusion for 2D human pose estimation.</description><identifier>ISSN: 1057-7149</identifier><identifier>EISSN: 1941-0042</identifier><identifier>DOI: 10.1109/TIP.2016.2639441</identifier><identifier>PMID: 28113316</identifier><identifier>CODEN: IIPRE4</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Biological system modeling ; Cognition ; Coherence ; Computational modeling ; Data models ; graphical model ; Graphical models ; mixture ; Occlusion ; Pose estimation ; spacial relationship</subject><ispartof>IEEE transactions on image processing, 2017-02, Vol.26 (2), p.927-941</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c385t-c465eadaefc601766ddb5e9663be1feab609f64b1441e8f0d14aa3eba0cd4e4e3</citedby><cites>FETCH-LOGICAL-c385t-c465eadaefc601766ddb5e9663be1feab609f64b1441e8f0d14aa3eba0cd4e4e3</cites><orcidid>0000-0002-2677-9273</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7782843$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27903,27904,54737</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7782843$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/28113316$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Fu, Lianrui</creatorcontrib><creatorcontrib>Zhang, Junge</creatorcontrib><creatorcontrib>Huang, Kaiqi</creatorcontrib><title>ORGM: Occlusion Relational Graphical Model for Human Pose Estimation</title><title>IEEE transactions on image processing</title><addtitle>TIP</addtitle><addtitle>IEEE Trans Image Process</addtitle><description>Articulated human pose estimation from monocular image is a challenging problem in computer vision. Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structured models. The tree structured model is simple and convenient for exact inference, but short in modeling the occlusion coherence especially in the case of self-occlusion. We propose an occlusion relational graphical model, which is able to model both self-occlusion and occlusion by the other objects simultaneously. The proposed model can encode the interactions between human body parts and objects, and enables it to learn occlusion coherence from data discriminatively. We evaluate our model on several public benchmarks for human pose estimation, including challenging subsets featuring significant occlusion. The experimental results show that our method is superior to the previous state-of-the-arts, and is robust to occlusion for 2D human pose estimation.</description><subject>Biological system modeling</subject><subject>Cognition</subject><subject>Coherence</subject><subject>Computational modeling</subject><subject>Data models</subject><subject>graphical model</subject><subject>Graphical models</subject><subject>mixture</subject><subject>Occlusion</subject><subject>Pose estimation</subject><subject>spacial relationship</subject><issn>1057-7149</issn><issn>1941-0042</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kEFPwkAQRjdGI4jeTUxMj15aZ7rbbevNIAIJBELwvNlup7GmpdhtD_57F0FO8yXzZjLzGLtHCBAhfd7O10EIKINQ8lQIvGBDTAX6ACK8dBmi2I9RpAN2Y-0XAIoI5TUbhAki5yiH7G21mS5fvJUxVW_LZudtqNKdC7rypq3ef5bGpWWTU-UVTevN-lrvvHVjyZvYrqz_2Ft2VejK0t2pjtjH-2Q7nvmL1XQ-fl34hidR5xshI9K5psJIwFjKPM8iSqXkGWFBOpOQFlJk6D6hpIAchdacMg0mFySIj9jTce--bb57sp2qS2uoqvSOmt4qTCRKFBykQ-GImraxtqVC7Vt3bfujENTBnXLu1MGdOrlzI4-n7X1WU34e-JflgIcjUBLRuR3HSZgIzn8BTw5yeQ</recordid><startdate>201702</startdate><enddate>201702</enddate><creator>Fu, Lianrui</creator><creator>Zhang, Junge</creator><creator>Huang, Kaiqi</creator><general>IEEE</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-2677-9273</orcidid></search><sort><creationdate>201702</creationdate><title>ORGM: Occlusion Relational Graphical Model for Human Pose Estimation</title><author>Fu, Lianrui ; Zhang, Junge ; Huang, Kaiqi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c385t-c465eadaefc601766ddb5e9663be1feab609f64b1441e8f0d14aa3eba0cd4e4e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Biological system modeling</topic><topic>Cognition</topic><topic>Coherence</topic><topic>Computational modeling</topic><topic>Data models</topic><topic>graphical model</topic><topic>Graphical models</topic><topic>mixture</topic><topic>Occlusion</topic><topic>Pose estimation</topic><topic>spacial relationship</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fu, Lianrui</creatorcontrib><creatorcontrib>Zhang, Junge</creatorcontrib><creatorcontrib>Huang, Kaiqi</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>MEDLINE - Academic</collection><jtitle>IEEE transactions on image processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Fu, Lianrui</au><au>Zhang, Junge</au><au>Huang, Kaiqi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ORGM: Occlusion Relational Graphical Model for Human Pose Estimation</atitle><jtitle>IEEE transactions on image processing</jtitle><stitle>TIP</stitle><addtitle>IEEE Trans Image Process</addtitle><date>2017-02</date><risdate>2017</risdate><volume>26</volume><issue>2</issue><spage>927</spage><epage>941</epage><pages>927-941</pages><issn>1057-7149</issn><eissn>1941-0042</eissn><coden>IIPRE4</coden><abstract>Articulated human pose estimation from monocular image is a challenging problem in computer vision. Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structured models. The tree structured model is simple and convenient for exact inference, but short in modeling the occlusion coherence especially in the case of self-occlusion. We propose an occlusion relational graphical model, which is able to model both self-occlusion and occlusion by the other objects simultaneously. The proposed model can encode the interactions between human body parts and objects, and enables it to learn occlusion coherence from data discriminatively. We evaluate our model on several public benchmarks for human pose estimation, including challenging subsets featuring significant occlusion. The experimental results show that our method is superior to the previous state-of-the-arts, and is robust to occlusion for 2D human pose estimation.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>28113316</pmid><doi>10.1109/TIP.2016.2639441</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0002-2677-9273</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1057-7149 |
| ispartof | IEEE transactions on image processing, 2017-02, Vol.26 (2), p.927-941 |
| issn | 1057-7149 1941-0042 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1861614306 |
| source | IEEE Electronic Library (IEL) |
| subjects | Biological system modeling Cognition Coherence Computational modeling Data models graphical model Graphical models mixture Occlusion Pose estimation spacial relationship |
| title | ORGM: Occlusion Relational Graphical Model for Human Pose Estimation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T03%3A13%3A23IST&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=ORGM:%20Occlusion%20Relational%20Graphical%20Model%20for%20Human%20Pose%20Estimation&rft.jtitle=IEEE%20transactions%20on%20image%20processing&rft.au=Fu,%20Lianrui&rft.date=2017-02&rft.volume=26&rft.issue=2&rft.spage=927&rft.epage=941&rft.pages=927-941&rft.issn=1057-7149&rft.eissn=1941-0042&rft.coden=IIPRE4&rft_id=info:doi/10.1109/TIP.2016.2639441&rft_dat=%3Cproquest_RIE%3E1861614306%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=1861614306&rft_id=info:pmid/28113316&rft_ieee_id=7782843&rfr_iscdi=true |