No Cover Image

Journal article 43163 views 100 downloads

DS-KCF: a real-time tracker for RGB-D data

Sion Hannuna, Massimo Camplani, Jake Hall, Majid Mirmehdi, Dima Damen, Tilo Burghardt, Adeline Paiement, Lili Tao

Journal of Real-Time Image Processing, Volume: 16, Issue: 5, Pages: 1439 - 1458

Swansea University Author: Adeline Paiement

  • DSKCFVOR.pdf

    PDF | Version of Record

    Released under the terms of a Creative Commons Attribution License (CC-BY).

    Download (2.38MB)

Check full text

DOI (Published version): 10.1007/s11554-016-0654-3

Abstract

We propose an RGB-D single-object tracker, built upon the extremely fast RGB-only KCF tracker that is able to exploit depth information to handle scale changes, occlusions, and shape changes. Despite the computational demands of the extra functionalities, we still achieve real-time performance rates...

Full description

Published in: Journal of Real-Time Image Processing
ISSN: 1861-8200 1861-8219
Published: Springer Science and Business Media LLC 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa31410
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2016-12-09T14:59:18Z
last_indexed 2020-07-31T18:48:10Z
id cronfa31410
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2020-07-31T15:47:28.1835981</datestamp><bib-version>v2</bib-version><id>31410</id><entry>2016-12-09</entry><title>DS-KCF: a real-time tracker for RGB-D data</title><swanseaauthors><author><sid>f50adf4186d930e3a2a0f9a6d643cf53</sid><firstname>Adeline</firstname><surname>Paiement</surname><name>Adeline Paiement</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2016-12-09</date><deptcode>FGHSS</deptcode><abstract>We propose an RGB-D single-object tracker, built upon the extremely fast RGB-only KCF tracker that is able to exploit depth information to handle scale changes, occlusions, and shape changes. Despite the computational demands of the extra functionalities, we still achieve real-time performance rates of 35&#x2013;43 fps in MATLAB and 187 fps in our C++ implementation. Our proposed method includes fast depth-based target object segmentation that enables, (1) efficient scale change handling within the KCF core functionality in the Fourier domain, (2) the detection of occlusions by temporal analysis of the target&#x2019;s depth distribution, and (3) the estimation of a target&#x2019;s change of shape through the temporal evolution of its segmented silhouette allows. Finally, we provide an in-depth analysis of the factors affecting the throughput and precision of our proposed tracker and perform extensive comparative analysis. Both the MATLAB and C++ versions of our software are available in the public domain.</abstract><type>Journal Article</type><journal>Journal of Real-Time Image Processing</journal><volume>16</volume><journalNumber>5</journalNumber><paginationStart>1439</paginationStart><paginationEnd>1458</paginationEnd><publisher>Springer Science and Business Media LLC</publisher><issnPrint>1861-8200</issnPrint><issnElectronic>1861-8219</issnElectronic><keywords>RGB-D tracking; Correlation filters; Scale and shape changes handling; Occlusion detection; Depth-based segmentation</keywords><publishedDay>1</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-10-01</publishedDate><doi>10.1007/s11554-016-0654-3</doi><url/><notes/><college>COLLEGE NANME</college><department>Humanities and Social Sciences - Faculty</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>FGHSS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2020-07-31T15:47:28.1835981</lastEdited><Created>2016-12-09T12:06:01.7551790</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Sion</firstname><surname>Hannuna</surname><order>1</order></author><author><firstname>Massimo</firstname><surname>Camplani</surname><order>2</order></author><author><firstname>Jake</firstname><surname>Hall</surname><order>3</order></author><author><firstname>Majid</firstname><surname>Mirmehdi</surname><order>4</order></author><author><firstname>Dima</firstname><surname>Damen</surname><order>5</order></author><author><firstname>Tilo</firstname><surname>Burghardt</surname><order>6</order></author><author><firstname>Adeline</firstname><surname>Paiement</surname><order>7</order></author><author><firstname>Lili</firstname><surname>Tao</surname><order>8</order></author></authors><documents><document><filename>31410__17820__f8553b8311834c8d8485bb1d1cfa5c97.pdf</filename><originalFilename>DSKCFVOR.pdf</originalFilename><uploaded>2020-07-31T15:45:20.6368792</uploaded><type>Output</type><contentLength>2498226</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Released under the terms of a Creative Commons Attribution License (CC-BY).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2020-07-31T15:47:28.1835981 v2 31410 2016-12-09 DS-KCF: a real-time tracker for RGB-D data f50adf4186d930e3a2a0f9a6d643cf53 Adeline Paiement Adeline Paiement true false 2016-12-09 FGHSS We propose an RGB-D single-object tracker, built upon the extremely fast RGB-only KCF tracker that is able to exploit depth information to handle scale changes, occlusions, and shape changes. Despite the computational demands of the extra functionalities, we still achieve real-time performance rates of 35–43 fps in MATLAB and 187 fps in our C++ implementation. Our proposed method includes fast depth-based target object segmentation that enables, (1) efficient scale change handling within the KCF core functionality in the Fourier domain, (2) the detection of occlusions by temporal analysis of the target’s depth distribution, and (3) the estimation of a target’s change of shape through the temporal evolution of its segmented silhouette allows. Finally, we provide an in-depth analysis of the factors affecting the throughput and precision of our proposed tracker and perform extensive comparative analysis. Both the MATLAB and C++ versions of our software are available in the public domain. Journal Article Journal of Real-Time Image Processing 16 5 1439 1458 Springer Science and Business Media LLC 1861-8200 1861-8219 RGB-D tracking; Correlation filters; Scale and shape changes handling; Occlusion detection; Depth-based segmentation 1 10 2019 2019-10-01 10.1007/s11554-016-0654-3 COLLEGE NANME Humanities and Social Sciences - Faculty COLLEGE CODE FGHSS Swansea University 2020-07-31T15:47:28.1835981 2016-12-09T12:06:01.7551790 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Sion Hannuna 1 Massimo Camplani 2 Jake Hall 3 Majid Mirmehdi 4 Dima Damen 5 Tilo Burghardt 6 Adeline Paiement 7 Lili Tao 8 31410__17820__f8553b8311834c8d8485bb1d1cfa5c97.pdf DSKCFVOR.pdf 2020-07-31T15:45:20.6368792 Output 2498226 application/pdf Version of Record true Released under the terms of a Creative Commons Attribution License (CC-BY). true eng http://creativecommons.org/licenses/by/4.0/
title DS-KCF: a real-time tracker for RGB-D data
spellingShingle DS-KCF: a real-time tracker for RGB-D data
Adeline Paiement
title_short DS-KCF: a real-time tracker for RGB-D data
title_full DS-KCF: a real-time tracker for RGB-D data
title_fullStr DS-KCF: a real-time tracker for RGB-D data
title_full_unstemmed DS-KCF: a real-time tracker for RGB-D data
title_sort DS-KCF: a real-time tracker for RGB-D data
author_id_str_mv f50adf4186d930e3a2a0f9a6d643cf53
author_id_fullname_str_mv f50adf4186d930e3a2a0f9a6d643cf53_***_Adeline Paiement
author Adeline Paiement
author2 Sion Hannuna
Massimo Camplani
Jake Hall
Majid Mirmehdi
Dima Damen
Tilo Burghardt
Adeline Paiement
Lili Tao
format Journal article
container_title Journal of Real-Time Image Processing
container_volume 16
container_issue 5
container_start_page 1439
publishDate 2019
institution Swansea University
issn 1861-8200
1861-8219
doi_str_mv 10.1007/s11554-016-0654-3
publisher Springer Science and Business Media LLC
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description We propose an RGB-D single-object tracker, built upon the extremely fast RGB-only KCF tracker that is able to exploit depth information to handle scale changes, occlusions, and shape changes. Despite the computational demands of the extra functionalities, we still achieve real-time performance rates of 35–43 fps in MATLAB and 187 fps in our C++ implementation. Our proposed method includes fast depth-based target object segmentation that enables, (1) efficient scale change handling within the KCF core functionality in the Fourier domain, (2) the detection of occlusions by temporal analysis of the target’s depth distribution, and (3) the estimation of a target’s change of shape through the temporal evolution of its segmented silhouette allows. Finally, we provide an in-depth analysis of the factors affecting the throughput and precision of our proposed tracker and perform extensive comparative analysis. Both the MATLAB and C++ versions of our software are available in the public domain.
published_date 2019-10-01T03:38:22Z
_version_ 1763751705912016896
score 11.013148

Similar Items