Learning and Classification of Trajectories in Dynamic Scenes: A General Framework for Live Video Analysis
This paper presents a general framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature of object trajectories is used to build a topographical scene description where node...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 161 |
|---|---|
| container_issue | |
| container_start_page | 154 |
| container_title | |
| container_volume | |
| creator | Morris, B.T. Trivedi, M.M. |
| description | This paper presents a general framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature of object trajectories is used to build a topographical scene description where nodes are points of interest (POT) and the edges correspond to activity paths (AP). The POI are learned through as a mixture of Gaussians and AP by clustering trajectories. The paths are probabilistically represented by hidden Markov models and adapt to temporal variations using online maximum likelihood regression (MLLR) and through a periodic batch update. Using the scene graph, new trajectories can be analyzed in online fashion to categorize past and present activity, predict future behavior, and detect abnormalities. |
| doi_str_mv | 10.1109/AVSS.2008.65 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4730406</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4730406</ieee_id><sourcerecordid>4730406</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-538ce46b07767e144a48160188242625e5edf7fdefced2754d23271ae67007d13</originalsourceid><addsrcrecordid>eNotjMFKAzEURSNS0Nbu3LnJD7S-vGSSjLuhahUGXLR0W-LkRVKnGUmK0r-3Uu_mnguHy9itgLkQUN83m9VqjgB2rqsLNq2NBaPrSipEuGTj85BK2BEb_2k11srqKzYtZQenVGgQ8ZrtWnI5xfTBXfJ80btSYoidO8Qh8SHwdXY76g5DjlR4TPzxmNw-dnzVUaLywBu-PEF2PX_Obk8_Q_7kYci8jd_EN9HTwJvk-mOJ5YaNgusLTf97wtbPT-vFy6x9W74umnYWazjMKmk7UvodjNGGhFJOWaFBWIsKNVZUkQ8meAodeTSV8ijRCEfaABgv5ITdnW8jEW2_cty7fNwqI0GBlr_CaVky</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Learning and Classification of Trajectories in Dynamic Scenes: A General Framework for Live Video Analysis</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Morris, B.T. ; Trivedi, M.M.</creator><creatorcontrib>Morris, B.T. ; Trivedi, M.M.</creatorcontrib><description>This paper presents a general framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature of object trajectories is used to build a topographical scene description where nodes are points of interest (POT) and the edges correspond to activity paths (AP). The POI are learned through as a mixture of Gaussians and AP by clustering trajectories. The paths are probabilistically represented by hidden Markov models and adapt to temporal variations using online maximum likelihood regression (MLLR) and through a periodic batch update. Using the scene graph, new trajectories can be analyzed in online fashion to categorize past and present activity, predict future behavior, and detect abnormalities.</description><identifier>ISBN: 0769533418</identifier><identifier>ISBN: 9780769533414</identifier><identifier>EISBN: 9780769534220</identifier><identifier>EISBN: 0769534228</identifier><identifier>DOI: 10.1109/AVSS.2008.65</identifier><identifier>LCCN: 2008929486</identifier><language>eng</language><publisher>IEEE</publisher><subject>abnormality detection ; activity prediction ; Cameras ; Computer vision ; Laboratories ; Layout ; live activity analysis ; Monitoring ; Robot vision systems ; Signal analysis ; Surveillance ; trajectory learning ; Video compression ; Videoconference</subject><ispartof>2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance, 2008, p.154-161</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4730406$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,2052,27906,54901</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4730406$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Morris, B.T.</creatorcontrib><creatorcontrib>Trivedi, M.M.</creatorcontrib><title>Learning and Classification of Trajectories in Dynamic Scenes: A General Framework for Live Video Analysis</title><title>2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance</title><addtitle>avss</addtitle><description>This paper presents a general framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature of object trajectories is used to build a topographical scene description where nodes are points of interest (POT) and the edges correspond to activity paths (AP). The POI are learned through as a mixture of Gaussians and AP by clustering trajectories. The paths are probabilistically represented by hidden Markov models and adapt to temporal variations using online maximum likelihood regression (MLLR) and through a periodic batch update. Using the scene graph, new trajectories can be analyzed in online fashion to categorize past and present activity, predict future behavior, and detect abnormalities.</description><subject>abnormality detection</subject><subject>activity prediction</subject><subject>Cameras</subject><subject>Computer vision</subject><subject>Laboratories</subject><subject>Layout</subject><subject>live activity analysis</subject><subject>Monitoring</subject><subject>Robot vision systems</subject><subject>Signal analysis</subject><subject>Surveillance</subject><subject>trajectory learning</subject><subject>Video compression</subject><subject>Videoconference</subject><isbn>0769533418</isbn><isbn>9780769533414</isbn><isbn>9780769534220</isbn><isbn>0769534228</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotjMFKAzEURSNS0Nbu3LnJD7S-vGSSjLuhahUGXLR0W-LkRVKnGUmK0r-3Uu_mnguHy9itgLkQUN83m9VqjgB2rqsLNq2NBaPrSipEuGTj85BK2BEb_2k11srqKzYtZQenVGgQ8ZrtWnI5xfTBXfJ80btSYoidO8Qh8SHwdXY76g5DjlR4TPzxmNw-dnzVUaLywBu-PEF2PX_Obk8_Q_7kYci8jd_EN9HTwJvk-mOJ5YaNgusLTf97wtbPT-vFy6x9W74umnYWazjMKmk7UvodjNGGhFJOWaFBWIsKNVZUkQ8meAodeTSV8ijRCEfaABgv5ITdnW8jEW2_cty7fNwqI0GBlr_CaVky</recordid><startdate>200809</startdate><enddate>200809</enddate><creator>Morris, B.T.</creator><creator>Trivedi, M.M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200809</creationdate><title>Learning and Classification of Trajectories in Dynamic Scenes: A General Framework for Live Video Analysis</title><author>Morris, B.T. ; Trivedi, M.M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-538ce46b07767e144a48160188242625e5edf7fdefced2754d23271ae67007d13</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>abnormality detection</topic><topic>activity prediction</topic><topic>Cameras</topic><topic>Computer vision</topic><topic>Laboratories</topic><topic>Layout</topic><topic>live activity analysis</topic><topic>Monitoring</topic><topic>Robot vision systems</topic><topic>Signal analysis</topic><topic>Surveillance</topic><topic>trajectory learning</topic><topic>Video compression</topic><topic>Videoconference</topic><toplevel>online_resources</toplevel><creatorcontrib>Morris, B.T.</creatorcontrib><creatorcontrib>Trivedi, M.M.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Morris, B.T.</au><au>Trivedi, M.M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Learning and Classification of Trajectories in Dynamic Scenes: A General Framework for Live Video Analysis</atitle><btitle>2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance</btitle><stitle>avss</stitle><date>2008-09</date><risdate>2008</risdate><spage>154</spage><epage>161</epage><pages>154-161</pages><isbn>0769533418</isbn><isbn>9780769533414</isbn><eisbn>9780769534220</eisbn><eisbn>0769534228</eisbn><abstract>This paper presents a general framework for live video analysis. The activities of surveillance subjects are described using a spatio-temporal vocabulary learned from recurrent motion patterns. The repetitive nature of object trajectories is used to build a topographical scene description where nodes are points of interest (POT) and the edges correspond to activity paths (AP). The POI are learned through as a mixture of Gaussians and AP by clustering trajectories. The paths are probabilistically represented by hidden Markov models and adapt to temporal variations using online maximum likelihood regression (MLLR) and through a periodic batch update. Using the scene graph, new trajectories can be analyzed in online fashion to categorize past and present activity, predict future behavior, and detect abnormalities.</abstract><pub>IEEE</pub><doi>10.1109/AVSS.2008.65</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 0769533418 |
| ispartof | 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance, 2008, p.154-161 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_4730406 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | abnormality detection activity prediction Cameras Computer vision Laboratories Layout live activity analysis Monitoring Robot vision systems Signal analysis Surveillance trajectory learning Video compression Videoconference |
| title | Learning and Classification of Trajectories in Dynamic Scenes: A General Framework for Live Video Analysis |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T09%3A56%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Learning%20and%20Classification%20of%20Trajectories%20in%20Dynamic%20Scenes:%20A%20General%20Framework%20for%20Live%20Video%20Analysis&rft.btitle=2008%20IEEE%20Fifth%20International%20Conference%20on%20Advanced%20Video%20and%20Signal%20Based%20Surveillance&rft.au=Morris,%20B.T.&rft.date=2008-09&rft.spage=154&rft.epage=161&rft.pages=154-161&rft.isbn=0769533418&rft.isbn_list=9780769533414&rft_id=info:doi/10.1109/AVSS.2008.65&rft_dat=%3Cieee_6IE%3E4730406%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9780769534220&rft.eisbn_list=0769534228&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4730406&rfr_iscdi=true |