Loading…
Motion Estimation for H.264/AVC using Programmable Graphics Hardware
We present an efficient implementation of motion estimation (ME) for H.264/AVC using programmable graphics hardware. The cost function for ME in H.264/AVC depends on the motion vector (MV) predictor which is the median MV of three neighboring coded blocks. Previous implementations assume no dependen...
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 | 2052 |
| container_issue | |
| container_start_page | 2049 |
| container_title | |
| container_volume | |
| creator | Chi-Wang Ho Au, O.C. Gary Chan, S.-H. Shu-Kei Yip Hoi-Ming Wong |
| description | We present an efficient implementation of motion estimation (ME) for H.264/AVC using programmable graphics hardware. The cost function for ME in H.264/AVC depends on the motion vector (MV) predictor which is the median MV of three neighboring coded blocks. Previous implementations assume no dependency among adjacent blocks, which is not true for H.264/AVC, they also perform unsatisfactorily because of their low arithmetic intensity, which is defined as operation per word transferred. To overcome the dependency problem, we introduce a new implementation which performs ME on block-by-block basis. Moreover, we can adjust the arithmetic intensity easily to optimize the performance on different graphics cards. Experimental results show that our implementation is substantially faster (by 10 times) than our SIMD optimized CPU implementation |
| doi_str_mv | 10.1109/ICME.2006.262617 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_4037033</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4037033</ieee_id><sourcerecordid>4037033</sourcerecordid><originalsourceid>FETCH-LOGICAL-i217t-1323249068bdf865d2ae72fd0a8ddb6def15188685462ac1e62a83b741645b7e3</originalsourceid><addsrcrecordid>eNo9T09LwzAcjaLgmL0LXvIFuuWXpPmlx1HrOtjQg4q3kS7pjKzrSCritzeo-A7vvdP7Q8gNsBkAK-eralPPOGNqxhVXgGckK1GD5FIyoRDPyQRKWeSo9evFv0e4IlmM7ywBpSyZmJC7zTD64UjrOPre_NhuCLRJwXK-eKnoR_THPX0Mwz6YvjftwdFlMKc3v4u0McF-muCuyWVnDtFlfzolz_f1U9Xk64flqlqsc88BxxwEFzzVKt3aTqvCcuOQd5YZbW2rrOugAK2VLqTiZgcusRYtSlCyaNGJKbn9zfXOue0ppMXha5suIxNCfAPmqEuu</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Motion Estimation for H.264/AVC using Programmable Graphics Hardware</title><source>IEEE Xplore All Conference Series</source><creator>Chi-Wang Ho ; Au, O.C. ; Gary Chan, S.-H. ; Shu-Kei Yip ; Hoi-Ming Wong</creator><creatorcontrib>Chi-Wang Ho ; Au, O.C. ; Gary Chan, S.-H. ; Shu-Kei Yip ; Hoi-Ming Wong</creatorcontrib><description>We present an efficient implementation of motion estimation (ME) for H.264/AVC using programmable graphics hardware. The cost function for ME in H.264/AVC depends on the motion vector (MV) predictor which is the median MV of three neighboring coded blocks. Previous implementations assume no dependency among adjacent blocks, which is not true for H.264/AVC, they also perform unsatisfactorily because of their low arithmetic intensity, which is defined as operation per word transferred. To overcome the dependency problem, we introduce a new implementation which performs ME on block-by-block basis. Moreover, we can adjust the arithmetic intensity easily to optimize the performance on different graphics cards. Experimental results show that our implementation is substantially faster (by 10 times) than our SIMD optimized CPU implementation</description><identifier>ISSN: 1945-7871</identifier><identifier>EISSN: 1945-788X</identifier><identifier>EISBN: 9781424403677</identifier><identifier>EISBN: 1424403677</identifier><identifier>DOI: 10.1109/ICME.2006.262617</identifier><language>eng</language><publisher>IEEE</publisher><subject>Arithmetic ; Automatic voltage control ; Central Processing Unit ; Cost function ; Graphics ; Hardware ; Motion estimation ; Pipelines ; Rendering (computer graphics) ; Streaming media</subject><ispartof>2006 IEEE International Conference on Multimedia and Expo, 2006, p.2049-2052</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/4037033$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4037033$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chi-Wang Ho</creatorcontrib><creatorcontrib>Au, O.C.</creatorcontrib><creatorcontrib>Gary Chan, S.-H.</creatorcontrib><creatorcontrib>Shu-Kei Yip</creatorcontrib><creatorcontrib>Hoi-Ming Wong</creatorcontrib><title>Motion Estimation for H.264/AVC using Programmable Graphics Hardware</title><title>2006 IEEE International Conference on Multimedia and Expo</title><addtitle>ICME</addtitle><description>We present an efficient implementation of motion estimation (ME) for H.264/AVC using programmable graphics hardware. The cost function for ME in H.264/AVC depends on the motion vector (MV) predictor which is the median MV of three neighboring coded blocks. Previous implementations assume no dependency among adjacent blocks, which is not true for H.264/AVC, they also perform unsatisfactorily because of their low arithmetic intensity, which is defined as operation per word transferred. To overcome the dependency problem, we introduce a new implementation which performs ME on block-by-block basis. Moreover, we can adjust the arithmetic intensity easily to optimize the performance on different graphics cards. Experimental results show that our implementation is substantially faster (by 10 times) than our SIMD optimized CPU implementation</description><subject>Arithmetic</subject><subject>Automatic voltage control</subject><subject>Central Processing Unit</subject><subject>Cost function</subject><subject>Graphics</subject><subject>Hardware</subject><subject>Motion estimation</subject><subject>Pipelines</subject><subject>Rendering (computer graphics)</subject><subject>Streaming media</subject><issn>1945-7871</issn><issn>1945-788X</issn><isbn>9781424403677</isbn><isbn>1424403677</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo9T09LwzAcjaLgmL0LXvIFuuWXpPmlx1HrOtjQg4q3kS7pjKzrSCritzeo-A7vvdP7Q8gNsBkAK-eralPPOGNqxhVXgGckK1GD5FIyoRDPyQRKWeSo9evFv0e4IlmM7ywBpSyZmJC7zTD64UjrOPre_NhuCLRJwXK-eKnoR_THPX0Mwz6YvjftwdFlMKc3v4u0McF-muCuyWVnDtFlfzolz_f1U9Xk64flqlqsc88BxxwEFzzVKt3aTqvCcuOQd5YZbW2rrOugAK2VLqTiZgcusRYtSlCyaNGJKbn9zfXOue0ppMXha5suIxNCfAPmqEuu</recordid><startdate>20060101</startdate><enddate>20060101</enddate><creator>Chi-Wang Ho</creator><creator>Au, O.C.</creator><creator>Gary Chan, S.-H.</creator><creator>Shu-Kei Yip</creator><creator>Hoi-Ming Wong</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20060101</creationdate><title>Motion Estimation for H.264/AVC using Programmable Graphics Hardware</title><author>Chi-Wang Ho ; Au, O.C. ; Gary Chan, S.-H. ; Shu-Kei Yip ; Hoi-Ming Wong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i217t-1323249068bdf865d2ae72fd0a8ddb6def15188685462ac1e62a83b741645b7e3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Arithmetic</topic><topic>Automatic voltage control</topic><topic>Central Processing Unit</topic><topic>Cost function</topic><topic>Graphics</topic><topic>Hardware</topic><topic>Motion estimation</topic><topic>Pipelines</topic><topic>Rendering (computer graphics)</topic><topic>Streaming media</topic><toplevel>online_resources</toplevel><creatorcontrib>Chi-Wang Ho</creatorcontrib><creatorcontrib>Au, O.C.</creatorcontrib><creatorcontrib>Gary Chan, S.-H.</creatorcontrib><creatorcontrib>Shu-Kei Yip</creatorcontrib><creatorcontrib>Hoi-Ming Wong</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 (IEEE/IET 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>Chi-Wang Ho</au><au>Au, O.C.</au><au>Gary Chan, S.-H.</au><au>Shu-Kei Yip</au><au>Hoi-Ming Wong</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Motion Estimation for H.264/AVC using Programmable Graphics Hardware</atitle><btitle>2006 IEEE International Conference on Multimedia and Expo</btitle><stitle>ICME</stitle><date>2006-01-01</date><risdate>2006</risdate><spage>2049</spage><epage>2052</epage><pages>2049-2052</pages><issn>1945-7871</issn><eissn>1945-788X</eissn><eisbn>9781424403677</eisbn><eisbn>1424403677</eisbn><abstract>We present an efficient implementation of motion estimation (ME) for H.264/AVC using programmable graphics hardware. The cost function for ME in H.264/AVC depends on the motion vector (MV) predictor which is the median MV of three neighboring coded blocks. Previous implementations assume no dependency among adjacent blocks, which is not true for H.264/AVC, they also perform unsatisfactorily because of their low arithmetic intensity, which is defined as operation per word transferred. To overcome the dependency problem, we introduce a new implementation which performs ME on block-by-block basis. Moreover, we can adjust the arithmetic intensity easily to optimize the performance on different graphics cards. Experimental results show that our implementation is substantially faster (by 10 times) than our SIMD optimized CPU implementation</abstract><pub>IEEE</pub><doi>10.1109/ICME.2006.262617</doi><tpages>4</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1945-7871 |
| ispartof | 2006 IEEE International Conference on Multimedia and Expo, 2006, p.2049-2052 |
| issn | 1945-7871 1945-788X |
| language | eng |
| recordid | cdi_ieee_primary_4037033 |
| source | IEEE Xplore All Conference Series |
| subjects | Arithmetic Automatic voltage control Central Processing Unit Cost function Graphics Hardware Motion estimation Pipelines Rendering (computer graphics) Streaming media |
| title | Motion Estimation for H.264/AVC using Programmable Graphics Hardware |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T00%3A17%3A55IST&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=Motion%20Estimation%20for%20H.264/AVC%20using%20Programmable%20Graphics%20Hardware&rft.btitle=2006%20IEEE%20International%20Conference%20on%20Multimedia%20and%20Expo&rft.au=Chi-Wang%20Ho&rft.date=2006-01-01&rft.spage=2049&rft.epage=2052&rft.pages=2049-2052&rft.issn=1945-7871&rft.eissn=1945-788X&rft_id=info:doi/10.1109/ICME.2006.262617&rft.eisbn=9781424403677&rft.eisbn_list=1424403677&rft_dat=%3Cieee_CHZPO%3E4037033%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i217t-1323249068bdf865d2ae72fd0a8ddb6def15188685462ac1e62a83b741645b7e3%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=4037033&rfr_iscdi=true |