Low-Power, Real-Time Object-Recognition Processors for Mobile Vision Systems
A new low-power object-recognition processor achieves real-time robust recognition, satisfying modern mobile vision systems' requirements. The authors introduce an attention-based object-recognition algorithm for energy efficiency, a heterogeneous multicore architecture for data- and thread-lev...
Gespeichert in:
| Veröffentlicht in: | IEEE MICRO 2012-11, Vol.32 (6), p.38-50 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 50 |
|---|---|
| container_issue | 6 |
| container_start_page | 38 |
| container_title | IEEE MICRO |
| container_volume | 32 |
| creator | Oh, Jinwook Kim, Gyeonghoon Hong, Injoon Park, Junyoung Lee, Seungjin Kim, Joo-Young Woo, Jeong-Ho Yoo, Hoi-Jun |
| description | A new low-power object-recognition processor achieves real-time robust recognition, satisfying modern mobile vision systems' requirements. The authors introduce an attention-based object-recognition algorithm for energy efficiency, a heterogeneous multicore architecture for data- and thread-level parallelism, and a network on a chip for high on-chip bandwidth. The fabricated chip achieves 30 frames/second throughput and an average 320 mW power consumption on test 720p video sequences, yielding 640 GOPS/W and 10.5 NJ/pixel energy efficiency. |
| doi_str_mv | 10.1109/MM.2012.90 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_6353416</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6353416</ieee_id><sourcerecordid>1671432356</sourcerecordid><originalsourceid>FETCH-LOGICAL-c312t-2ae96031debe2e4ab75e51e23222bd7febb99b1f64e3dca7f4691c2de6dea5b93</originalsourceid><addsrcrecordid>eNpd0M9LwzAUB_AgCs7pxauXghcRO_Or6XKU4S9o2ZjTa0jSV8loG006xv57OyYePL3D-_DlvS9ClwRPCMHyviwnFBM6kfgIjYhkecoJZ8dohGlOU5IzeorOYlxjjDOKpyNUFH6bLvwWwl2yBN2kK9dCMjdrsH26BOs_O9c73yWL4C3E6ENMah-S0hvXQPLh4n75tos9tPEcndS6iXDxO8fo_elxNXtJi_nz6-yhSC0jtE-pBikwIxUYoMC1yTPICFBGKTVVXoMxUhpSCw6ssjqvuZDE0gpEBTozko3RzSH3K_jvDcRetS5aaBrdgd9ERUQ-fE1ZJgZ6_Y-u_SZ0w3WKUDHNM8H5PvD2oGzwMQao1VdwrQ47RbDaF6vKUu2LVRIP-OqAHQD8QcEyxolgP9pvczU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1268756449</pqid></control><display><type>article</type><title>Low-Power, Real-Time Object-Recognition Processors for Mobile Vision Systems</title><source>IEEE Electronic Library (IEL)</source><creator>Oh, Jinwook ; Kim, Gyeonghoon ; Hong, Injoon ; Park, Junyoung ; Lee, Seungjin ; Kim, Joo-Young ; Woo, Jeong-Ho ; Yoo, Hoi-Jun</creator><creatorcontrib>Oh, Jinwook ; Kim, Gyeonghoon ; Hong, Injoon ; Park, Junyoung ; Lee, Seungjin ; Kim, Joo-Young ; Woo, Jeong-Ho ; Yoo, Hoi-Jun</creatorcontrib><description>A new low-power object-recognition processor achieves real-time robust recognition, satisfying modern mobile vision systems' requirements. The authors introduce an attention-based object-recognition algorithm for energy efficiency, a heterogeneous multicore architecture for data- and thread-level parallelism, and a network on a chip for high on-chip bandwidth. The fabricated chip achieves 30 frames/second throughput and an average 320 mW power consumption on test 720p video sequences, yielding 640 GOPS/W and 10.5 NJ/pixel energy efficiency.</description><identifier>ISSN: 0272-1732</identifier><identifier>EISSN: 1937-4143</identifier><identifier>DOI: 10.1109/MM.2012.90</identifier><identifier>CODEN: IEMIDZ</identifier><language>eng</language><publisher>Los Alamitos: IEEE</publisher><subject>attention ; attention-based object recognition ; Chip formation ; Chips ; Computer architecture ; Decision support systems ; Energy efficiency ; Energy management ; heterogeneous multicore ; Low power electronics ; Multicore processing ; multicore processor ; Network-on-a-chip ; network-on-chip ; Object recognition ; object-recognition pipeline ; Power consumption ; Processors ; Real time ; Robustness ; scale invariant feature transform ; SIFT ; Vision systems</subject><ispartof>IEEE MICRO, 2012-11, Vol.32 (6), p.38-50</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Nov/Dec 2012</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c312t-2ae96031debe2e4ab75e51e23222bd7febb99b1f64e3dca7f4691c2de6dea5b93</citedby><cites>FETCH-LOGICAL-c312t-2ae96031debe2e4ab75e51e23222bd7febb99b1f64e3dca7f4691c2de6dea5b93</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6353416$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6353416$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Oh, Jinwook</creatorcontrib><creatorcontrib>Kim, Gyeonghoon</creatorcontrib><creatorcontrib>Hong, Injoon</creatorcontrib><creatorcontrib>Park, Junyoung</creatorcontrib><creatorcontrib>Lee, Seungjin</creatorcontrib><creatorcontrib>Kim, Joo-Young</creatorcontrib><creatorcontrib>Woo, Jeong-Ho</creatorcontrib><creatorcontrib>Yoo, Hoi-Jun</creatorcontrib><title>Low-Power, Real-Time Object-Recognition Processors for Mobile Vision Systems</title><title>IEEE MICRO</title><addtitle>MM</addtitle><description>A new low-power object-recognition processor achieves real-time robust recognition, satisfying modern mobile vision systems' requirements. The authors introduce an attention-based object-recognition algorithm for energy efficiency, a heterogeneous multicore architecture for data- and thread-level parallelism, and a network on a chip for high on-chip bandwidth. The fabricated chip achieves 30 frames/second throughput and an average 320 mW power consumption on test 720p video sequences, yielding 640 GOPS/W and 10.5 NJ/pixel energy efficiency.</description><subject>attention</subject><subject>attention-based object recognition</subject><subject>Chip formation</subject><subject>Chips</subject><subject>Computer architecture</subject><subject>Decision support systems</subject><subject>Energy efficiency</subject><subject>Energy management</subject><subject>heterogeneous multicore</subject><subject>Low power electronics</subject><subject>Multicore processing</subject><subject>multicore processor</subject><subject>Network-on-a-chip</subject><subject>network-on-chip</subject><subject>Object recognition</subject><subject>object-recognition pipeline</subject><subject>Power consumption</subject><subject>Processors</subject><subject>Real time</subject><subject>Robustness</subject><subject>scale invariant feature transform</subject><subject>SIFT</subject><subject>Vision systems</subject><issn>0272-1732</issn><issn>1937-4143</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2012</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpd0M9LwzAUB_AgCs7pxauXghcRO_Or6XKU4S9o2ZjTa0jSV8loG006xv57OyYePL3D-_DlvS9ClwRPCMHyviwnFBM6kfgIjYhkecoJZ8dohGlOU5IzeorOYlxjjDOKpyNUFH6bLvwWwl2yBN2kK9dCMjdrsH26BOs_O9c73yWL4C3E6ENMah-S0hvXQPLh4n75tos9tPEcndS6iXDxO8fo_elxNXtJi_nz6-yhSC0jtE-pBikwIxUYoMC1yTPICFBGKTVVXoMxUhpSCw6ssjqvuZDE0gpEBTozko3RzSH3K_jvDcRetS5aaBrdgd9ERUQ-fE1ZJgZ6_Y-u_SZ0w3WKUDHNM8H5PvD2oGzwMQao1VdwrQ47RbDaF6vKUu2LVRIP-OqAHQD8QcEyxolgP9pvczU</recordid><startdate>20121101</startdate><enddate>20121101</enddate><creator>Oh, Jinwook</creator><creator>Kim, Gyeonghoon</creator><creator>Hong, Injoon</creator><creator>Park, Junyoung</creator><creator>Lee, Seungjin</creator><creator>Kim, Joo-Young</creator><creator>Woo, Jeong-Ho</creator><creator>Yoo, Hoi-Jun</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>20121101</creationdate><title>Low-Power, Real-Time Object-Recognition Processors for Mobile Vision Systems</title><author>Oh, Jinwook ; Kim, Gyeonghoon ; Hong, Injoon ; Park, Junyoung ; Lee, Seungjin ; Kim, Joo-Young ; Woo, Jeong-Ho ; Yoo, Hoi-Jun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c312t-2ae96031debe2e4ab75e51e23222bd7febb99b1f64e3dca7f4691c2de6dea5b93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2012</creationdate><topic>attention</topic><topic>attention-based object recognition</topic><topic>Chip formation</topic><topic>Chips</topic><topic>Computer architecture</topic><topic>Decision support systems</topic><topic>Energy efficiency</topic><topic>Energy management</topic><topic>heterogeneous multicore</topic><topic>Low power electronics</topic><topic>Multicore processing</topic><topic>multicore processor</topic><topic>Network-on-a-chip</topic><topic>network-on-chip</topic><topic>Object recognition</topic><topic>object-recognition pipeline</topic><topic>Power consumption</topic><topic>Processors</topic><topic>Real time</topic><topic>Robustness</topic><topic>scale invariant feature transform</topic><topic>SIFT</topic><topic>Vision systems</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Oh, Jinwook</creatorcontrib><creatorcontrib>Kim, Gyeonghoon</creatorcontrib><creatorcontrib>Hong, Injoon</creatorcontrib><creatorcontrib>Park, Junyoung</creatorcontrib><creatorcontrib>Lee, Seungjin</creatorcontrib><creatorcontrib>Kim, Joo-Young</creatorcontrib><creatorcontrib>Woo, Jeong-Ho</creatorcontrib><creatorcontrib>Yoo, Hoi-Jun</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>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><jtitle>IEEE MICRO</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Oh, Jinwook</au><au>Kim, Gyeonghoon</au><au>Hong, Injoon</au><au>Park, Junyoung</au><au>Lee, Seungjin</au><au>Kim, Joo-Young</au><au>Woo, Jeong-Ho</au><au>Yoo, Hoi-Jun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Low-Power, Real-Time Object-Recognition Processors for Mobile Vision Systems</atitle><jtitle>IEEE MICRO</jtitle><stitle>MM</stitle><date>2012-11-01</date><risdate>2012</risdate><volume>32</volume><issue>6</issue><spage>38</spage><epage>50</epage><pages>38-50</pages><issn>0272-1732</issn><eissn>1937-4143</eissn><coden>IEMIDZ</coden><abstract>A new low-power object-recognition processor achieves real-time robust recognition, satisfying modern mobile vision systems' requirements. The authors introduce an attention-based object-recognition algorithm for energy efficiency, a heterogeneous multicore architecture for data- and thread-level parallelism, and a network on a chip for high on-chip bandwidth. The fabricated chip achieves 30 frames/second throughput and an average 320 mW power consumption on test 720p video sequences, yielding 640 GOPS/W and 10.5 NJ/pixel energy efficiency.</abstract><cop>Los Alamitos</cop><pub>IEEE</pub><doi>10.1109/MM.2012.90</doi><tpages>13</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0272-1732 |
| ispartof | IEEE MICRO, 2012-11, Vol.32 (6), p.38-50 |
| issn | 0272-1732 1937-4143 |
| language | eng |
| recordid | cdi_ieee_primary_6353416 |
| source | IEEE Electronic Library (IEL) |
| subjects | attention attention-based object recognition Chip formation Chips Computer architecture Decision support systems Energy efficiency Energy management heterogeneous multicore Low power electronics Multicore processing multicore processor Network-on-a-chip network-on-chip Object recognition object-recognition pipeline Power consumption Processors Real time Robustness scale invariant feature transform SIFT Vision systems |
| title | Low-Power, Real-Time Object-Recognition Processors for Mobile Vision Systems |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T08%3A22%3A55IST&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=Low-Power,%20Real-Time%20Object-Recognition%20Processors%20for%20Mobile%20Vision%20Systems&rft.jtitle=IEEE%20MICRO&rft.au=Oh,%20Jinwook&rft.date=2012-11-01&rft.volume=32&rft.issue=6&rft.spage=38&rft.epage=50&rft.pages=38-50&rft.issn=0272-1732&rft.eissn=1937-4143&rft.coden=IEMIDZ&rft_id=info:doi/10.1109/MM.2012.90&rft_dat=%3Cproquest_RIE%3E1671432356%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=1268756449&rft_id=info:pmid/&rft_ieee_id=6353416&rfr_iscdi=true |