GPU deformable part model for object recognition
We consider the problem of rapidly detecting objects in static images or videos. The task consists in locating and identifying objects of interest. With the progress of affordable high computing hardware, we propose to analyse and evaluate the deformable part model on the Graphics Processing Unit. W...
Gespeichert in:
| Veröffentlicht in: | Journal of real-time image processing 2018-02, Vol.14 (2), p.279-291 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 291 |
|---|---|
| container_issue | 2 |
| container_start_page | 279 |
| container_title | Journal of real-time image processing |
| container_volume | 14 |
| creator | Gadeski, Etienne Fard, Hamidreza Odabai Le Borgne, Hervé |
| description | We consider the problem of rapidly detecting objects in static images or videos. The task consists in locating and identifying objects of interest. With the progress of affordable high computing hardware, we propose to analyse and evaluate the deformable part model on the Graphics Processing Unit. We do not take any prior assumptions on the scene and location of the objects. We provide a fast implementation and analyse the different modules of the state-of-the-art detector. Our implementation allows to accelerate both training and testing. While maintaining comparable classification performance, we report a speed-up of
×
10.6 using a standard GPU card compared to a baseline implemented in C++ on a single core and
×
5 compared to a multi-core OpenMP (8 threads) implementation. |
| doi_str_mv | 10.1007/s11554-014-0447-5 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_hal_p</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_cea_01820312v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2918675845</sourcerecordid><originalsourceid>FETCH-LOGICAL-c420t-993414b1f6f4999f92a599bd1d9945aa5892743a06704b07a08122558c7e7d493</originalsourceid><addsrcrecordid>eNp1kEFLw0AQhRdRsFZ_gLeAJw_Rmc1uNnMsRVuhoAd7XjbJpqak2bqbCv57t0TqycMww_C9x8xj7BbhAQHUY0CUUqSAsYRQqTxjEyxyTAuOdH6aAS7ZVQhbgFzlmZwwWLytk9o2zu9M2dlkb_yQ7FxtuyTuEldubTUk3lZu07dD6_prdtGYLtib3z5l6-en9_kyXb0uXuazVVoJDkNKlAkUJTZ5I4ioIW4kUVljTSSkMbIgrkRm4h0gSlAGCuRcyqJSVtWCsim7H30_TKf3vt0Z_62dafVyttKVNRowvpMh_8LI3o3s3rvPgw2D3rqD7-N5mlP8XMlCyEjhSFXeheBtc7JF0McQ9RhidI4VQ9RHDR81IbL9xvo_5_9FP_qccEg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2918675845</pqid></control><display><type>article</type><title>GPU deformable part model for object recognition</title><source>ProQuest Central UK/Ireland</source><source>SpringerLink Journals - AutoHoldings</source><source>ProQuest Central</source><creator>Gadeski, Etienne ; Fard, Hamidreza Odabai ; Le Borgne, Hervé</creator><creatorcontrib>Gadeski, Etienne ; Fard, Hamidreza Odabai ; Le Borgne, Hervé</creatorcontrib><description>We consider the problem of rapidly detecting objects in static images or videos. The task consists in locating and identifying objects of interest. With the progress of affordable high computing hardware, we propose to analyse and evaluate the deformable part model on the Graphics Processing Unit. We do not take any prior assumptions on the scene and location of the objects. We provide a fast implementation and analyse the different modules of the state-of-the-art detector. Our implementation allows to accelerate both training and testing. While maintaining comparable classification performance, we report a speed-up of
×
10.6 using a standard GPU card compared to a baseline implemented in C++ on a single core and
×
5 compared to a multi-core OpenMP (8 threads) implementation.</description><identifier>ISSN: 1861-8200</identifier><identifier>EISSN: 1861-8219</identifier><identifier>DOI: 10.1007/s11554-014-0447-5</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Algorithms ; Artificial Intelligence ; Computer Graphics ; Computer Science ; Computer Vision and Pattern Recognition ; Deformation ; Formability ; Graphics processing units ; Image Processing and Computer Vision ; Multimedia ; Multimedia Information Systems ; Object recognition ; Original Research Paper ; Pattern Recognition ; Pedestrians ; Sensors ; Signal,Image and Speech Processing</subject><ispartof>Journal of real-time image processing, 2018-02, Vol.14 (2), p.279-291</ispartof><rights>Springer-Verlag Berlin Heidelberg 2014</rights><rights>Springer-Verlag Berlin Heidelberg 2014.</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c420t-993414b1f6f4999f92a599bd1d9945aa5892743a06704b07a08122558c7e7d493</citedby><cites>FETCH-LOGICAL-c420t-993414b1f6f4999f92a599bd1d9945aa5892743a06704b07a08122558c7e7d493</cites><orcidid>0000-0003-0520-8436</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11554-014-0447-5$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2918675845?pq-origsite=primo$$EHTML$$P50$$Gproquest$$H</linktohtml><link.rule.ids>230,314,780,784,885,21388,27924,27925,33744,41488,42557,43805,51319,64385,64389,72469</link.rule.ids><backlink>$$Uhttps://cea.hal.science/cea-01820312$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Gadeski, Etienne</creatorcontrib><creatorcontrib>Fard, Hamidreza Odabai</creatorcontrib><creatorcontrib>Le Borgne, Hervé</creatorcontrib><title>GPU deformable part model for object recognition</title><title>Journal of real-time image processing</title><addtitle>J Real-Time Image Proc</addtitle><description>We consider the problem of rapidly detecting objects in static images or videos. The task consists in locating and identifying objects of interest. With the progress of affordable high computing hardware, we propose to analyse and evaluate the deformable part model on the Graphics Processing Unit. We do not take any prior assumptions on the scene and location of the objects. We provide a fast implementation and analyse the different modules of the state-of-the-art detector. Our implementation allows to accelerate both training and testing. While maintaining comparable classification performance, we report a speed-up of
×
10.6 using a standard GPU card compared to a baseline implemented in C++ on a single core and
×
5 compared to a multi-core OpenMP (8 threads) implementation.</description><subject>Algorithms</subject><subject>Artificial Intelligence</subject><subject>Computer Graphics</subject><subject>Computer Science</subject><subject>Computer Vision and Pattern Recognition</subject><subject>Deformation</subject><subject>Formability</subject><subject>Graphics processing units</subject><subject>Image Processing and Computer Vision</subject><subject>Multimedia</subject><subject>Multimedia Information Systems</subject><subject>Object recognition</subject><subject>Original Research Paper</subject><subject>Pattern Recognition</subject><subject>Pedestrians</subject><subject>Sensors</subject><subject>Signal,Image and Speech Processing</subject><issn>1861-8200</issn><issn>1861-8219</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp1kEFLw0AQhRdRsFZ_gLeAJw_Rmc1uNnMsRVuhoAd7XjbJpqak2bqbCv57t0TqycMww_C9x8xj7BbhAQHUY0CUUqSAsYRQqTxjEyxyTAuOdH6aAS7ZVQhbgFzlmZwwWLytk9o2zu9M2dlkb_yQ7FxtuyTuEldubTUk3lZu07dD6_prdtGYLtib3z5l6-en9_kyXb0uXuazVVoJDkNKlAkUJTZ5I4ioIW4kUVljTSSkMbIgrkRm4h0gSlAGCuRcyqJSVtWCsim7H30_TKf3vt0Z_62dafVyttKVNRowvpMh_8LI3o3s3rvPgw2D3rqD7-N5mlP8XMlCyEjhSFXeheBtc7JF0McQ9RhidI4VQ9RHDR81IbL9xvo_5_9FP_qccEg</recordid><startdate>20180201</startdate><enddate>20180201</enddate><creator>Gadeski, Etienne</creator><creator>Fard, Hamidreza Odabai</creator><creator>Le Borgne, Hervé</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><general>Springer Verlag</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>1XC</scope><orcidid>https://orcid.org/0000-0003-0520-8436</orcidid></search><sort><creationdate>20180201</creationdate><title>GPU deformable part model for object recognition</title><author>Gadeski, Etienne ; Fard, Hamidreza Odabai ; Le Borgne, Hervé</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c420t-993414b1f6f4999f92a599bd1d9945aa5892743a06704b07a08122558c7e7d493</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Algorithms</topic><topic>Artificial Intelligence</topic><topic>Computer Graphics</topic><topic>Computer Science</topic><topic>Computer Vision and Pattern Recognition</topic><topic>Deformation</topic><topic>Formability</topic><topic>Graphics processing units</topic><topic>Image Processing and Computer Vision</topic><topic>Multimedia</topic><topic>Multimedia Information Systems</topic><topic>Object recognition</topic><topic>Original Research Paper</topic><topic>Pattern Recognition</topic><topic>Pedestrians</topic><topic>Sensors</topic><topic>Signal,Image and Speech Processing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Gadeski, Etienne</creatorcontrib><creatorcontrib>Fard, Hamidreza Odabai</creatorcontrib><creatorcontrib>Le Borgne, Hervé</creatorcontrib><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Hyper Article en Ligne (HAL)</collection><jtitle>Journal of real-time image processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Gadeski, Etienne</au><au>Fard, Hamidreza Odabai</au><au>Le Borgne, Hervé</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>GPU deformable part model for object recognition</atitle><jtitle>Journal of real-time image processing</jtitle><stitle>J Real-Time Image Proc</stitle><date>2018-02-01</date><risdate>2018</risdate><volume>14</volume><issue>2</issue><spage>279</spage><epage>291</epage><pages>279-291</pages><issn>1861-8200</issn><eissn>1861-8219</eissn><abstract>We consider the problem of rapidly detecting objects in static images or videos. The task consists in locating and identifying objects of interest. With the progress of affordable high computing hardware, we propose to analyse and evaluate the deformable part model on the Graphics Processing Unit. We do not take any prior assumptions on the scene and location of the objects. We provide a fast implementation and analyse the different modules of the state-of-the-art detector. Our implementation allows to accelerate both training and testing. While maintaining comparable classification performance, we report a speed-up of
×
10.6 using a standard GPU card compared to a baseline implemented in C++ on a single core and
×
5 compared to a multi-core OpenMP (8 threads) implementation.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s11554-014-0447-5</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0003-0520-8436</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1861-8200 |
| ispartof | Journal of real-time image processing, 2018-02, Vol.14 (2), p.279-291 |
| issn | 1861-8200 1861-8219 |
| language | eng |
| recordid | cdi_hal_primary_oai_HAL_cea_01820312v1 |
| source | ProQuest Central UK/Ireland; SpringerLink Journals - AutoHoldings; ProQuest Central |
| subjects | Algorithms Artificial Intelligence Computer Graphics Computer Science Computer Vision and Pattern Recognition Deformation Formability Graphics processing units Image Processing and Computer Vision Multimedia Multimedia Information Systems Object recognition Original Research Paper Pattern Recognition Pedestrians Sensors Signal,Image and Speech Processing |
| title | GPU deformable part model for object recognition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T01%3A20%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_hal_p&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=GPU%20deformable%20part%20model%20for%20object%20recognition&rft.jtitle=Journal%20of%20real-time%20image%20processing&rft.au=Gadeski,%20Etienne&rft.date=2018-02-01&rft.volume=14&rft.issue=2&rft.spage=279&rft.epage=291&rft.pages=279-291&rft.issn=1861-8200&rft.eissn=1861-8219&rft_id=info:doi/10.1007/s11554-014-0447-5&rft_dat=%3Cproquest_hal_p%3E2918675845%3C/proquest_hal_p%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2918675845&rft_id=info:pmid/&rfr_iscdi=true |