Loading…
Pyramidal Fisher Motion for Multiview Gait Recognition
The goal of this paper is to identify individuals by analyzing their gait. Instead of using binary silhouettes as input data (as done in many previous works) we propose and evaluate the use of motion descriptors based on densely sampled short-term trajectories. We take advantage of state-of-the-art...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 1697 |
| container_issue | |
| container_start_page | 1692 |
| container_title | |
| container_volume | |
| creator | Castro, Francisco M. Marin-Jimenez, Manuel J. Medina-Carnicer, Rafael |
| description | The goal of this paper is to identify individuals by analyzing their gait. Instead of using binary silhouettes as input data (as done in many previous works) we propose and evaluate the use of motion descriptors based on densely sampled short-term trajectories. We take advantage of state-of-the-art people detectors to define custom spatial configurations of the descriptors around the target person. Thus, obtaining a pyramidal representation of the gait motion. The local motion features (described by the Divergence-Curl-Shear descriptor [1]) extracted on the different spatial areas of the person are combined into a single high-level gait descriptor by using the Fisher Vector encoding [2]. The proposed approach, coined Pyramidal Fisher Motion, is experimentally validated on the recent 'AVA Multiview Gait' dataset [3]. The results show that this new approach achieves promising results in the problem of gait recognition. |
| doi_str_mv | 10.1109/ICPR.2014.298 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_6977009</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6977009</ieee_id><sourcerecordid>6977009</sourcerecordid><originalsourceid>FETCH-LOGICAL-i214t-e87457e4e03901ab8655aae1d05035a5dc8b679c015c76f266658c1918d738ff3</originalsourceid><addsrcrecordid>eNotjNFKwzAUQKMoWOceffIlP9B6b5Kb5D5KcXMwcQx9HmmbaqBbpa3K_l5Fn86BA0eIa4QCEfh2VW62hQI0hWJ_Ii7ROGZSwHQqMuU15s44OhMZAmFuLOGFmI9jqkBZZ43WnAm7OQ5hn5rQyUUa3-IgH_sp9QfZ9j_60U3pM8UvuQxpkttY96-H9JuvxHkbujHO_zkTL4v75_IhXz8tV-XdOk8KzZRH7wy5aCJoBgyVt0QhRGyAQFOgpvaVdVwDUu1sq6y15Gtk9I3Tvm31TNz8fVOMcfc-pH0YjjvLzgGw_gabb0ZN</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Pyramidal Fisher Motion for Multiview Gait Recognition</title><source>IEEE Xplore All Conference Series</source><creator>Castro, Francisco M. ; Marin-Jimenez, Manuel J. ; Medina-Carnicer, Rafael</creator><creatorcontrib>Castro, Francisco M. ; Marin-Jimenez, Manuel J. ; Medina-Carnicer, Rafael</creatorcontrib><description>The goal of this paper is to identify individuals by analyzing their gait. Instead of using binary silhouettes as input data (as done in many previous works) we propose and evaluate the use of motion descriptors based on densely sampled short-term trajectories. We take advantage of state-of-the-art people detectors to define custom spatial configurations of the descriptors around the target person. Thus, obtaining a pyramidal representation of the gait motion. The local motion features (described by the Divergence-Curl-Shear descriptor [1]) extracted on the different spatial areas of the person are combined into a single high-level gait descriptor by using the Fisher Vector encoding [2]. The proposed approach, coined Pyramidal Fisher Motion, is experimentally validated on the recent 'AVA Multiview Gait' dataset [3]. The results show that this new approach achieves promising results in the problem of gait recognition.</description><identifier>ISSN: 1051-4651</identifier><identifier>EISSN: 2831-7475</identifier><identifier>EISBN: 1479952095</identifier><identifier>EISBN: 9781479952090</identifier><identifier>DOI: 10.1109/ICPR.2014.298</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Encoding ; Feature extraction ; Fisher Vectors ; Gait ; Gait recognition ; motion ; Training ; Trajectory ; Vectors</subject><ispartof>2014 22nd International Conference on Pattern Recognition, 2014, p.1692-1697</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6977009$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23929,23930,25139,27924,54554,54931</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6977009$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Castro, Francisco M.</creatorcontrib><creatorcontrib>Marin-Jimenez, Manuel J.</creatorcontrib><creatorcontrib>Medina-Carnicer, Rafael</creatorcontrib><title>Pyramidal Fisher Motion for Multiview Gait Recognition</title><title>2014 22nd International Conference on Pattern Recognition</title><addtitle>ICPR</addtitle><description>The goal of this paper is to identify individuals by analyzing their gait. Instead of using binary silhouettes as input data (as done in many previous works) we propose and evaluate the use of motion descriptors based on densely sampled short-term trajectories. We take advantage of state-of-the-art people detectors to define custom spatial configurations of the descriptors around the target person. Thus, obtaining a pyramidal representation of the gait motion. The local motion features (described by the Divergence-Curl-Shear descriptor [1]) extracted on the different spatial areas of the person are combined into a single high-level gait descriptor by using the Fisher Vector encoding [2]. The proposed approach, coined Pyramidal Fisher Motion, is experimentally validated on the recent 'AVA Multiview Gait' dataset [3]. The results show that this new approach achieves promising results in the problem of gait recognition.</description><subject>Cameras</subject><subject>Encoding</subject><subject>Feature extraction</subject><subject>Fisher Vectors</subject><subject>Gait</subject><subject>Gait recognition</subject><subject>motion</subject><subject>Training</subject><subject>Trajectory</subject><subject>Vectors</subject><issn>1051-4651</issn><issn>2831-7475</issn><isbn>1479952095</isbn><isbn>9781479952090</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2014</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjNFKwzAUQKMoWOceffIlP9B6b5Kb5D5KcXMwcQx9HmmbaqBbpa3K_l5Fn86BA0eIa4QCEfh2VW62hQI0hWJ_Ii7ROGZSwHQqMuU15s44OhMZAmFuLOGFmI9jqkBZZ43WnAm7OQ5hn5rQyUUa3-IgH_sp9QfZ9j_60U3pM8UvuQxpkttY96-H9JuvxHkbujHO_zkTL4v75_IhXz8tV-XdOk8KzZRH7wy5aCJoBgyVt0QhRGyAQFOgpvaVdVwDUu1sq6y15Gtk9I3Tvm31TNz8fVOMcfc-pH0YjjvLzgGw_gabb0ZN</recordid><startdate>20141204</startdate><enddate>20141204</enddate><creator>Castro, Francisco M.</creator><creator>Marin-Jimenez, Manuel J.</creator><creator>Medina-Carnicer, Rafael</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20141204</creationdate><title>Pyramidal Fisher Motion for Multiview Gait Recognition</title><author>Castro, Francisco M. ; Marin-Jimenez, Manuel J. ; Medina-Carnicer, Rafael</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i214t-e87457e4e03901ab8655aae1d05035a5dc8b679c015c76f266658c1918d738ff3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Cameras</topic><topic>Encoding</topic><topic>Feature extraction</topic><topic>Fisher Vectors</topic><topic>Gait</topic><topic>Gait recognition</topic><topic>motion</topic><topic>Training</topic><topic>Trajectory</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Castro, Francisco M.</creatorcontrib><creatorcontrib>Marin-Jimenez, Manuel J.</creatorcontrib><creatorcontrib>Medina-Carnicer, Rafael</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 Xplore</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>Castro, Francisco M.</au><au>Marin-Jimenez, Manuel J.</au><au>Medina-Carnicer, Rafael</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Pyramidal Fisher Motion for Multiview Gait Recognition</atitle><btitle>2014 22nd International Conference on Pattern Recognition</btitle><stitle>ICPR</stitle><date>2014-12-04</date><risdate>2014</risdate><spage>1692</spage><epage>1697</epage><pages>1692-1697</pages><issn>1051-4651</issn><eissn>2831-7475</eissn><eisbn>1479952095</eisbn><eisbn>9781479952090</eisbn><coden>IEEPAD</coden><abstract>The goal of this paper is to identify individuals by analyzing their gait. Instead of using binary silhouettes as input data (as done in many previous works) we propose and evaluate the use of motion descriptors based on densely sampled short-term trajectories. We take advantage of state-of-the-art people detectors to define custom spatial configurations of the descriptors around the target person. Thus, obtaining a pyramidal representation of the gait motion. The local motion features (described by the Divergence-Curl-Shear descriptor [1]) extracted on the different spatial areas of the person are combined into a single high-level gait descriptor by using the Fisher Vector encoding [2]. The proposed approach, coined Pyramidal Fisher Motion, is experimentally validated on the recent 'AVA Multiview Gait' dataset [3]. The results show that this new approach achieves promising results in the problem of gait recognition.</abstract><pub>IEEE</pub><doi>10.1109/ICPR.2014.298</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1051-4651 |
| ispartof | 2014 22nd International Conference on Pattern Recognition, 2014, p.1692-1697 |
| issn | 1051-4651 2831-7475 |
| language | eng |
| recordid | cdi_ieee_primary_6977009 |
| source | IEEE Xplore All Conference Series |
| subjects | Cameras Encoding Feature extraction Fisher Vectors Gait Gait recognition motion Training Trajectory Vectors |
| title | Pyramidal Fisher Motion for Multiview Gait Recognition |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T20%3A55%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Pyramidal%20Fisher%20Motion%20for%20Multiview%20Gait%20Recognition&rft.btitle=2014%2022nd%20International%20Conference%20on%20Pattern%20Recognition&rft.au=Castro,%20Francisco%20M.&rft.date=2014-12-04&rft.spage=1692&rft.epage=1697&rft.pages=1692-1697&rft.issn=1051-4651&rft.eissn=2831-7475&rft.coden=IEEPAD&rft_id=info:doi/10.1109/ICPR.2014.298&rft.eisbn=1479952095&rft.eisbn_list=9781479952090&rft_dat=%3Cieee_CHZPO%3E6977009%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i214t-e87457e4e03901ab8655aae1d05035a5dc8b679c015c76f266658c1918d738ff3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6977009&rfr_iscdi=true |