Real-time identification and localization of body parts from depth images
We deal with the problem of detecting and identifying body parts in depth images at video frame rates. Our solution involves a novel interest point detector for mesh and range data that is particularly well suited for analyzing human shape. The interest points, which are based on identifying geodesi...
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 | 3113 |
---|---|
container_issue | |
container_start_page | 3108 |
container_title | |
container_volume | |
creator | Plagemann, Christian Ganapathi, Varun Koller, Daphne Thrun, Sebastian |
description | We deal with the problem of detecting and identifying body parts in depth images at video frame rates. Our solution involves a novel interest point detector for mesh and range data that is particularly well suited for analyzing human shape. The interest points, which are based on identifying geodesic extrema on the surface mesh, coincide with salient points of the body, which can be classified as, e.g., hand, foot or head using local shape descriptors. Our approach also provides a natural way of estimating a 3D orientation vector for a given interest point. This can be used to normalize the local shape descriptors to simplify the classification problem as well as to directly estimate the orientation of body parts in space. Experiments involving ground truth labels acquired via an active motion capture system show that our interest points in conjunction with a boosted patch classifier are significantly better in detecting body parts in depth images than state-of-the-art sliding-window based detectors. |
doi_str_mv | 10.1109/ROBOT.2010.5509559 |
format | Conference Proceeding |
fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5509559</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5509559</ieee_id><sourcerecordid>5509559</sourcerecordid><originalsourceid>FETCH-LOGICAL-c290t-eaeed194fe0c1ebb826be5474166e0f340d66ca229d26d4eaaabd9f548d190653</originalsourceid><addsrcrecordid>eNotUNtKw0AUXG9gWvsD-rI_sPXsNdlHLVULhUCp4FvZZM_qSm4kealfb6B5GmaGmYEh5JHDmnOwz4f8NT-uBUxca7Ba2yuy4EoopUGBvCaJ0GnKIEu_bsjKptnsyYzfkoSDBqZSYe_JYhh-AUBKYxKyO6Cr2BhrpNFjM8YQSzfGtqGu8bRqS1fFv4vQBlq0_kw7148DDX1bU4_d-ENj7b5xeCB3wVUDrmZcks-37XHzwfb5-27zsmelsDAydIieWxUQSo5FkQlToFap4sYgBKnAG1M6IawXxit0zhXeBq2yKQVGyyV5uvRGRDx1_bTen0_zJfIfX11SCQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Real-time identification and localization of body parts from depth images</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Plagemann, Christian ; Ganapathi, Varun ; Koller, Daphne ; Thrun, Sebastian</creator><creatorcontrib>Plagemann, Christian ; Ganapathi, Varun ; Koller, Daphne ; Thrun, Sebastian</creatorcontrib><description>We deal with the problem of detecting and identifying body parts in depth images at video frame rates. Our solution involves a novel interest point detector for mesh and range data that is particularly well suited for analyzing human shape. The interest points, which are based on identifying geodesic extrema on the surface mesh, coincide with salient points of the body, which can be classified as, e.g., hand, foot or head using local shape descriptors. Our approach also provides a natural way of estimating a 3D orientation vector for a given interest point. This can be used to normalize the local shape descriptors to simplify the classification problem as well as to directly estimate the orientation of body parts in space. Experiments involving ground truth labels acquired via an active motion capture system show that our interest points in conjunction with a boosted patch classifier are significantly better in detecting body parts in depth images than state-of-the-art sliding-window based detectors.</description><identifier>ISSN: 1050-4729</identifier><identifier>ISBN: 9781424450381</identifier><identifier>ISBN: 1424450381</identifier><identifier>EISSN: 2577-087X</identifier><identifier>EISBN: 1424450403</identifier><identifier>EISBN: 9781424450404</identifier><identifier>DOI: 10.1109/ROBOT.2010.5509559</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Detectors ; Head ; Humans ; Image sensors ; Layout ; Motion detection ; Shape ; Skeleton ; USA Councils</subject><ispartof>2010 IEEE International Conference on Robotics and Automation, 2010, p.3108-3113</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c290t-eaeed194fe0c1ebb826be5474166e0f340d66ca229d26d4eaaabd9f548d190653</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5509559$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5509559$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Plagemann, Christian</creatorcontrib><creatorcontrib>Ganapathi, Varun</creatorcontrib><creatorcontrib>Koller, Daphne</creatorcontrib><creatorcontrib>Thrun, Sebastian</creatorcontrib><title>Real-time identification and localization of body parts from depth images</title><title>2010 IEEE International Conference on Robotics and Automation</title><addtitle>ROBOT</addtitle><description>We deal with the problem of detecting and identifying body parts in depth images at video frame rates. Our solution involves a novel interest point detector for mesh and range data that is particularly well suited for analyzing human shape. The interest points, which are based on identifying geodesic extrema on the surface mesh, coincide with salient points of the body, which can be classified as, e.g., hand, foot or head using local shape descriptors. Our approach also provides a natural way of estimating a 3D orientation vector for a given interest point. This can be used to normalize the local shape descriptors to simplify the classification problem as well as to directly estimate the orientation of body parts in space. Experiments involving ground truth labels acquired via an active motion capture system show that our interest points in conjunction with a boosted patch classifier are significantly better in detecting body parts in depth images than state-of-the-art sliding-window based detectors.</description><subject>Cameras</subject><subject>Detectors</subject><subject>Head</subject><subject>Humans</subject><subject>Image sensors</subject><subject>Layout</subject><subject>Motion detection</subject><subject>Shape</subject><subject>Skeleton</subject><subject>USA Councils</subject><issn>1050-4729</issn><issn>2577-087X</issn><isbn>9781424450381</isbn><isbn>1424450381</isbn><isbn>1424450403</isbn><isbn>9781424450404</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotUNtKw0AUXG9gWvsD-rI_sPXsNdlHLVULhUCp4FvZZM_qSm4kealfb6B5GmaGmYEh5JHDmnOwz4f8NT-uBUxca7Ba2yuy4EoopUGBvCaJ0GnKIEu_bsjKptnsyYzfkoSDBqZSYe_JYhh-AUBKYxKyO6Cr2BhrpNFjM8YQSzfGtqGu8bRqS1fFv4vQBlq0_kw7148DDX1bU4_d-ENj7b5xeCB3wVUDrmZcks-37XHzwfb5-27zsmelsDAydIieWxUQSo5FkQlToFap4sYgBKnAG1M6IawXxit0zhXeBq2yKQVGyyV5uvRGRDx1_bTen0_zJfIfX11SCQ</recordid><startdate>201005</startdate><enddate>201005</enddate><creator>Plagemann, Christian</creator><creator>Ganapathi, Varun</creator><creator>Koller, Daphne</creator><creator>Thrun, Sebastian</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201005</creationdate><title>Real-time identification and localization of body parts from depth images</title><author>Plagemann, Christian ; Ganapathi, Varun ; Koller, Daphne ; Thrun, Sebastian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c290t-eaeed194fe0c1ebb826be5474166e0f340d66ca229d26d4eaaabd9f548d190653</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Cameras</topic><topic>Detectors</topic><topic>Head</topic><topic>Humans</topic><topic>Image sensors</topic><topic>Layout</topic><topic>Motion detection</topic><topic>Shape</topic><topic>Skeleton</topic><topic>USA Councils</topic><toplevel>online_resources</toplevel><creatorcontrib>Plagemann, Christian</creatorcontrib><creatorcontrib>Ganapathi, Varun</creatorcontrib><creatorcontrib>Koller, Daphne</creatorcontrib><creatorcontrib>Thrun, Sebastian</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Plagemann, Christian</au><au>Ganapathi, Varun</au><au>Koller, Daphne</au><au>Thrun, Sebastian</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Real-time identification and localization of body parts from depth images</atitle><btitle>2010 IEEE International Conference on Robotics and Automation</btitle><stitle>ROBOT</stitle><date>2010-05</date><risdate>2010</risdate><spage>3108</spage><epage>3113</epage><pages>3108-3113</pages><issn>1050-4729</issn><eissn>2577-087X</eissn><isbn>9781424450381</isbn><isbn>1424450381</isbn><eisbn>1424450403</eisbn><eisbn>9781424450404</eisbn><abstract>We deal with the problem of detecting and identifying body parts in depth images at video frame rates. Our solution involves a novel interest point detector for mesh and range data that is particularly well suited for analyzing human shape. The interest points, which are based on identifying geodesic extrema on the surface mesh, coincide with salient points of the body, which can be classified as, e.g., hand, foot or head using local shape descriptors. Our approach also provides a natural way of estimating a 3D orientation vector for a given interest point. This can be used to normalize the local shape descriptors to simplify the classification problem as well as to directly estimate the orientation of body parts in space. Experiments involving ground truth labels acquired via an active motion capture system show that our interest points in conjunction with a boosted patch classifier are significantly better in detecting body parts in depth images than state-of-the-art sliding-window based detectors.</abstract><pub>IEEE</pub><doi>10.1109/ROBOT.2010.5509559</doi><tpages>6</tpages></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1050-4729 |
ispartof | 2010 IEEE International Conference on Robotics and Automation, 2010, p.3108-3113 |
issn | 1050-4729 2577-087X |
language | eng |
recordid | cdi_ieee_primary_5509559 |
source | IEEE Electronic Library (IEL) Conference Proceedings |
subjects | Cameras Detectors Head Humans Image sensors Layout Motion detection Shape Skeleton USA Councils |
title | Real-time identification and localization of body parts from depth images |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T20%3A40%3A14IST&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=Real-time%20identification%20and%20localization%20of%20body%20parts%20from%20depth%20images&rft.btitle=2010%20IEEE%20International%20Conference%20on%20Robotics%20and%20Automation&rft.au=Plagemann,%20Christian&rft.date=2010-05&rft.spage=3108&rft.epage=3113&rft.pages=3108-3113&rft.issn=1050-4729&rft.eissn=2577-087X&rft.isbn=9781424450381&rft.isbn_list=1424450381&rft_id=info:doi/10.1109/ROBOT.2010.5509559&rft_dat=%3Cieee_6IE%3E5509559%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1424450403&rft.eisbn_list=9781424450404&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5509559&rfr_iscdi=true |