Loading…
Heterogeneous CPU–GPU tracking–learning–detection (H-TLD) for real-time object tracking
The recently proposed tracking–learning–detection (TLD) method has become a popular visual tracking algorithm as it was shown to provide promising long-term tracking results. On the other hand, the high computational cost of the algorithm prevents it being used at higher resolutions and frame rates....
Saved in:
Published in: | Journal of real-time image processing 2019-04, Vol.16 (2), p.339-353 |
---|---|
Main Authors: | , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c316t-278758f545d5cf0c280a698902d041456e0a5d1784736841e9896fd4bce5ebac3 |
---|---|
cites | cdi_FETCH-LOGICAL-c316t-278758f545d5cf0c280a698902d041456e0a5d1784736841e9896fd4bce5ebac3 |
container_end_page | 353 |
container_issue | 2 |
container_start_page | 339 |
container_title | Journal of real-time image processing |
container_volume | 16 |
creator | Gurcan, Ilker Temizel, Alptekin |
description | The recently proposed tracking–learning–detection (TLD) method has become a popular visual tracking algorithm as it was shown to provide promising long-term tracking results. On the other hand, the high computational cost of the algorithm prevents it being used at higher resolutions and frame rates. In this paper, we describe the design and implementation of a heterogeneous CPU–GPU TLD (H-TLD) solution using OpenMP and CUDA. Leveraging the advantages of the heterogeneous architecture, serial parts are run asynchronously on the CPU while the most computationally costly parts are parallelized and run on the GPU. Design of the solution ensures keeping data transfers between CPU and GPU at a minimum and applying stream compaction and overlapping data transfer with computation whenever such transfers are necessary. The workload is balanced for a uniform work distribution across the GPU multiprocessors. Results show that 10.25 times speed-up is achieved at 1920
×
1080 resolution compared to the baseline TLD. The source code has been made publicly available to download from the following address:
http://gpuresearch.ii.metu.edu.tr/codes/
. |
doi_str_mv | 10.1007/s11554-015-0538-y |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2918675797</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2918675797</sourcerecordid><originalsourceid>FETCH-LOGICAL-c316t-278758f545d5cf0c280a698902d041456e0a5d1784736841e9896fd4bce5ebac3</originalsourceid><addsrcrecordid>eNp1UL1OwzAQthBIlMIDsEVigcFwTuKfjKiUFqkSHdoRWa5zqVLauNjp0I134A15ElwFlYnpvtP3c7qPkGsG9wxAPgTGOM8pME6BZ4ruT0iPKcGoSllxesQA5-QihBWAkCLjPfI2xha9W2KDbheSwXT-_fk1ms6T1hv7XjfLuK7R-KaDZVTbtnZNcjums8nTXVI5n3g0a9rWG0zcYhX5o_mSnFVmHfDqd_bJ_Hk4G4zp5HX0MnicUJsx0dJUKslVxXNecluBTRUYUagC0hJylnOBYHjJpMplJlTOMHKiKvOFRY4LY7M-uelyt9597DC0euV2vokndVrE1yWXhYwq1qmsdyF4rPTW1xvj95qBPrSouxZ1bFEfWtT76Ek7T4jaZon-L_l_0w8J5Hcu</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2918675797</pqid></control><display><type>article</type><title>Heterogeneous CPU–GPU tracking–learning–detection (H-TLD) for real-time object tracking</title><source>Springer Link</source><creator>Gurcan, Ilker ; Temizel, Alptekin</creator><creatorcontrib>Gurcan, Ilker ; Temizel, Alptekin</creatorcontrib><description>The recently proposed tracking–learning–detection (TLD) method has become a popular visual tracking algorithm as it was shown to provide promising long-term tracking results. On the other hand, the high computational cost of the algorithm prevents it being used at higher resolutions and frame rates. In this paper, we describe the design and implementation of a heterogeneous CPU–GPU TLD (H-TLD) solution using OpenMP and CUDA. Leveraging the advantages of the heterogeneous architecture, serial parts are run asynchronously on the CPU while the most computationally costly parts are parallelized and run on the GPU. Design of the solution ensures keeping data transfers between CPU and GPU at a minimum and applying stream compaction and overlapping data transfer with computation whenever such transfers are necessary. The workload is balanced for a uniform work distribution across the GPU multiprocessors. Results show that 10.25 times speed-up is achieved at 1920
×
1080 resolution compared to the baseline TLD. The source code has been made publicly available to download from the following address:
http://gpuresearch.ii.metu.edu.tr/codes/
.</description><identifier>ISSN: 1861-8200</identifier><identifier>EISSN: 1861-8219</identifier><identifier>DOI: 10.1007/s11554-015-0538-y</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Algorithms ; Central processing units ; Computer Graphics ; Computer Science ; CPUs ; Data transfer (computers) ; Graphics processing units ; Image Processing and Computer Vision ; Multimedia Information Systems ; Multiprocessing ; Optical tracking ; Optimization ; Original Research Paper ; Pattern Recognition ; Sensors ; Signal,Image and Speech Processing ; Source code</subject><ispartof>Journal of real-time image processing, 2019-04, Vol.16 (2), p.339-353</ispartof><rights>Springer-Verlag Berlin Heidelberg 2015</rights><rights>Springer-Verlag Berlin Heidelberg 2015.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c316t-278758f545d5cf0c280a698902d041456e0a5d1784736841e9896fd4bce5ebac3</citedby><cites>FETCH-LOGICAL-c316t-278758f545d5cf0c280a698902d041456e0a5d1784736841e9896fd4bce5ebac3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,778,782,27907,27908</link.rule.ids></links><search><creatorcontrib>Gurcan, Ilker</creatorcontrib><creatorcontrib>Temizel, Alptekin</creatorcontrib><title>Heterogeneous CPU–GPU tracking–learning–detection (H-TLD) for real-time object tracking</title><title>Journal of real-time image processing</title><addtitle>J Real-Time Image Proc</addtitle><description>The recently proposed tracking–learning–detection (TLD) method has become a popular visual tracking algorithm as it was shown to provide promising long-term tracking results. On the other hand, the high computational cost of the algorithm prevents it being used at higher resolutions and frame rates. In this paper, we describe the design and implementation of a heterogeneous CPU–GPU TLD (H-TLD) solution using OpenMP and CUDA. Leveraging the advantages of the heterogeneous architecture, serial parts are run asynchronously on the CPU while the most computationally costly parts are parallelized and run on the GPU. Design of the solution ensures keeping data transfers between CPU and GPU at a minimum and applying stream compaction and overlapping data transfer with computation whenever such transfers are necessary. The workload is balanced for a uniform work distribution across the GPU multiprocessors. Results show that 10.25 times speed-up is achieved at 1920
×
1080 resolution compared to the baseline TLD. The source code has been made publicly available to download from the following address:
http://gpuresearch.ii.metu.edu.tr/codes/
.</description><subject>Algorithms</subject><subject>Central processing units</subject><subject>Computer Graphics</subject><subject>Computer Science</subject><subject>CPUs</subject><subject>Data transfer (computers)</subject><subject>Graphics processing units</subject><subject>Image Processing and Computer Vision</subject><subject>Multimedia Information Systems</subject><subject>Multiprocessing</subject><subject>Optical tracking</subject><subject>Optimization</subject><subject>Original Research Paper</subject><subject>Pattern Recognition</subject><subject>Sensors</subject><subject>Signal,Image and Speech Processing</subject><subject>Source code</subject><issn>1861-8200</issn><issn>1861-8219</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNp1UL1OwzAQthBIlMIDsEVigcFwTuKfjKiUFqkSHdoRWa5zqVLauNjp0I134A15ElwFlYnpvtP3c7qPkGsG9wxAPgTGOM8pME6BZ4ruT0iPKcGoSllxesQA5-QihBWAkCLjPfI2xha9W2KDbheSwXT-_fk1ms6T1hv7XjfLuK7R-KaDZVTbtnZNcjums8nTXVI5n3g0a9rWG0zcYhX5o_mSnFVmHfDqd_bJ_Hk4G4zp5HX0MnicUJsx0dJUKslVxXNecluBTRUYUagC0hJylnOBYHjJpMplJlTOMHKiKvOFRY4LY7M-uelyt9597DC0euV2vokndVrE1yWXhYwq1qmsdyF4rPTW1xvj95qBPrSouxZ1bFEfWtT76Ek7T4jaZon-L_l_0w8J5Hcu</recordid><startdate>20190401</startdate><enddate>20190401</enddate><creator>Gurcan, Ilker</creator><creator>Temizel, Alptekin</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</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></search><sort><creationdate>20190401</creationdate><title>Heterogeneous CPU–GPU tracking–learning–detection (H-TLD) for real-time object tracking</title><author>Gurcan, Ilker ; Temizel, Alptekin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c316t-278758f545d5cf0c280a698902d041456e0a5d1784736841e9896fd4bce5ebac3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>Central processing units</topic><topic>Computer Graphics</topic><topic>Computer Science</topic><topic>CPUs</topic><topic>Data transfer (computers)</topic><topic>Graphics processing units</topic><topic>Image Processing and Computer Vision</topic><topic>Multimedia Information Systems</topic><topic>Multiprocessing</topic><topic>Optical tracking</topic><topic>Optimization</topic><topic>Original Research Paper</topic><topic>Pattern Recognition</topic><topic>Sensors</topic><topic>Signal,Image and Speech Processing</topic><topic>Source code</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Gurcan, Ilker</creatorcontrib><creatorcontrib>Temizel, Alptekin</creatorcontrib><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central</collection><collection>Advanced Technologies & Aerospace Database (1962 - current)</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer science database</collection><collection>ProQuest advanced technologies & aerospace journals</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><jtitle>Journal of real-time image processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Gurcan, Ilker</au><au>Temizel, Alptekin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Heterogeneous CPU–GPU tracking–learning–detection (H-TLD) for real-time object tracking</atitle><jtitle>Journal of real-time image processing</jtitle><stitle>J Real-Time Image Proc</stitle><date>2019-04-01</date><risdate>2019</risdate><volume>16</volume><issue>2</issue><spage>339</spage><epage>353</epage><pages>339-353</pages><issn>1861-8200</issn><eissn>1861-8219</eissn><abstract>The recently proposed tracking–learning–detection (TLD) method has become a popular visual tracking algorithm as it was shown to provide promising long-term tracking results. On the other hand, the high computational cost of the algorithm prevents it being used at higher resolutions and frame rates. In this paper, we describe the design and implementation of a heterogeneous CPU–GPU TLD (H-TLD) solution using OpenMP and CUDA. Leveraging the advantages of the heterogeneous architecture, serial parts are run asynchronously on the CPU while the most computationally costly parts are parallelized and run on the GPU. Design of the solution ensures keeping data transfers between CPU and GPU at a minimum and applying stream compaction and overlapping data transfer with computation whenever such transfers are necessary. The workload is balanced for a uniform work distribution across the GPU multiprocessors. Results show that 10.25 times speed-up is achieved at 1920
×
1080 resolution compared to the baseline TLD. The source code has been made publicly available to download from the following address:
http://gpuresearch.ii.metu.edu.tr/codes/
.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s11554-015-0538-y</doi><tpages>15</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1861-8200 |
ispartof | Journal of real-time image processing, 2019-04, Vol.16 (2), p.339-353 |
issn | 1861-8200 1861-8219 |
language | eng |
recordid | cdi_proquest_journals_2918675797 |
source | Springer Link |
subjects | Algorithms Central processing units Computer Graphics Computer Science CPUs Data transfer (computers) Graphics processing units Image Processing and Computer Vision Multimedia Information Systems Multiprocessing Optical tracking Optimization Original Research Paper Pattern Recognition Sensors Signal,Image and Speech Processing Source code |
title | Heterogeneous CPU–GPU tracking–learning–detection (H-TLD) for real-time object tracking |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T15%3A21%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Heterogeneous%20CPU%E2%80%93GPU%20tracking%E2%80%93learning%E2%80%93detection%20(H-TLD)%20for%20real-time%20object%20tracking&rft.jtitle=Journal%20of%20real-time%20image%20processing&rft.au=Gurcan,%20Ilker&rft.date=2019-04-01&rft.volume=16&rft.issue=2&rft.spage=339&rft.epage=353&rft.pages=339-353&rft.issn=1861-8200&rft.eissn=1861-8219&rft_id=info:doi/10.1007/s11554-015-0538-y&rft_dat=%3Cproquest_cross%3E2918675797%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c316t-278758f545d5cf0c280a698902d041456e0a5d1784736841e9896fd4bce5ebac3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2918675797&rft_id=info:pmid/&rfr_iscdi=true |