No Cover Image

Journal article 686 views 109 downloads

A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems

Hans Ren, Freya Hu, San Hlaing Myint, Kun Hou, Xiuyu Zhang, Min Zuo, Chi Zhang, Qingchuan Zhang, Haipeng Li

Wireless Communications and Mobile Computing, Volume: 2021, Pages: 1 - 15

Swansea University Authors: Hans Ren, Freya Hu, Chi Zhang

  • 58621.pdf

    PDF | Version of Record

    © 2021 Hanchi Ren et al. This is an open access article distributed under the Creative Commons Attribution License

    Download (6.51MB)

Check full text

DOI (Published version): 10.1155/2021/6711561

Abstract

The development of the Internet of Things (IoT) stimulates many research works related to Multimedia Communication Systems (MCS), such as human face detection and tracking. This trend drives numerous progressive methods. Among these methods, the deep learning-based methods can spot face patch in an...

Full description

Published in: Wireless Communications and Mobile Computing
ISSN: 1530-8669 1530-8677
Published: Hindawi Limited 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa58621
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-11-11T14:25:41Z
last_indexed 2021-11-12T04:26:10Z
id cronfa58621
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-11-11T15:02:53.6399601</datestamp><bib-version>v2</bib-version><id>58621</id><entry>2021-11-11</entry><title>A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems</title><swanseaauthors><author><sid>9e043b899a2b786672a28ed4f864ffcc</sid><firstname>Hans</firstname><surname>Ren</surname><name>Hans Ren</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>aa73524c5e3969c88fb7a3a5bde919b1</sid><firstname>Freya</firstname><surname>Hu</surname><name>Freya Hu</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>46f911dbfa7c27cbbe839e897559b142</sid><firstname>Chi</firstname><surname>Zhang</surname><name>Chi Zhang</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-11-11</date><deptcode>SCS</deptcode><abstract>The development of the Internet of Things (IoT) stimulates many research works related to Multimedia Communication Systems (MCS), such as human face detection and tracking. This trend drives numerous progressive methods. Among these methods, the deep learning-based methods can spot face patch in an image effectively and accurately. Many people consider face tracking as face detection, but they are two different techniques. Face detection focuses on a single image, whose shortcoming is obvious, such as unstable and unsmooth face position when adopted on a sequence of continuous images; computing is expensive due to its heavy reliance on Convolutional Neural Networks (CNNs) and limited detection performance on the edge device. To overcome these defects, this paper proposes a novel face tracking strategy by combining CNN and optical flow, namely, C-OF, which achieves an extremely fast, stable, and long-term face tracking system. Two key things for commercial applications are the stability and smoothness of face positions in a sequence of image frames, which can provide more probability for face biological signal extraction, silent face antispoofing, and facial expression analysis in the fields of IoT-based MCS. Our method captures face patterns in every two consequent frames via optical flow to get rid of the unstable and unsmooth problems. Moreover, an innovative metric for measuring the stability and smoothness of face motion is designed and adopted in our experiments. The experimental results illustrate that our proposed C-OF outperforms both face detection and object tracking methods.</abstract><type>Journal Article</type><journal>Wireless Communications and Mobile Computing</journal><volume>2021</volume><journalNumber/><paginationStart>1</paginationStart><paginationEnd>15</paginationEnd><publisher>Hindawi Limited</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1530-8669</issnPrint><issnElectronic>1530-8677</issnElectronic><keywords>Electrical and Electronic Engineering, Computer Networks and Communications, Information Systems</keywords><publishedDay>31</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-10-31</publishedDate><doi>10.1155/2021/6711561</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This study is supported by the National Key Technology R&amp;D Program of China (No. 2019YFC1606401), Beijing Natural Science Foundation (No. 4202014), and Humanity and Social Science Youth Foundation of Ministry of Education of China (No. 20YJCZH229)</funders><lastEdited>2021-11-11T15:02:53.6399601</lastEdited><Created>2021-11-11T14:18:39.4431456</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>Hans</firstname><surname>Ren</surname><order>1</order></author><author><firstname>Freya</firstname><surname>Hu</surname><order>2</order></author><author><firstname>San Hlaing</firstname><surname>Myint</surname><order>3</order></author><author><firstname>Kun</firstname><surname>Hou</surname><order>4</order></author><author><firstname>Xiuyu</firstname><surname>Zhang</surname><order>5</order></author><author><firstname>Min</firstname><surname>Zuo</surname><order>6</order></author><author><firstname>Chi</firstname><surname>Zhang</surname><order>7</order></author><author><firstname>Qingchuan</firstname><surname>Zhang</surname><order>8</order></author><author><firstname>Haipeng</firstname><surname>Li</surname><order>9</order></author></authors><documents><document><filename>58621__21495__1e05acd249594b4596d6890f3b6bae61.pdf</filename><originalFilename>58621.pdf</originalFilename><uploaded>2021-11-11T14:23:49.6020908</uploaded><type>Output</type><contentLength>6828986</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2021 Hanchi Ren et al. This is an open access article distributed under the Creative Commons Attribution License</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2021-11-11T15:02:53.6399601 v2 58621 2021-11-11 A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems 9e043b899a2b786672a28ed4f864ffcc Hans Ren Hans Ren true false aa73524c5e3969c88fb7a3a5bde919b1 Freya Hu Freya Hu true false 46f911dbfa7c27cbbe839e897559b142 Chi Zhang Chi Zhang true false 2021-11-11 SCS The development of the Internet of Things (IoT) stimulates many research works related to Multimedia Communication Systems (MCS), such as human face detection and tracking. This trend drives numerous progressive methods. Among these methods, the deep learning-based methods can spot face patch in an image effectively and accurately. Many people consider face tracking as face detection, but they are two different techniques. Face detection focuses on a single image, whose shortcoming is obvious, such as unstable and unsmooth face position when adopted on a sequence of continuous images; computing is expensive due to its heavy reliance on Convolutional Neural Networks (CNNs) and limited detection performance on the edge device. To overcome these defects, this paper proposes a novel face tracking strategy by combining CNN and optical flow, namely, C-OF, which achieves an extremely fast, stable, and long-term face tracking system. Two key things for commercial applications are the stability and smoothness of face positions in a sequence of image frames, which can provide more probability for face biological signal extraction, silent face antispoofing, and facial expression analysis in the fields of IoT-based MCS. Our method captures face patterns in every two consequent frames via optical flow to get rid of the unstable and unsmooth problems. Moreover, an innovative metric for measuring the stability and smoothness of face motion is designed and adopted in our experiments. The experimental results illustrate that our proposed C-OF outperforms both face detection and object tracking methods. Journal Article Wireless Communications and Mobile Computing 2021 1 15 Hindawi Limited 1530-8669 1530-8677 Electrical and Electronic Engineering, Computer Networks and Communications, Information Systems 31 10 2021 2021-10-31 10.1155/2021/6711561 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University This study is supported by the National Key Technology R&D Program of China (No. 2019YFC1606401), Beijing Natural Science Foundation (No. 4202014), and Humanity and Social Science Youth Foundation of Ministry of Education of China (No. 20YJCZH229) 2021-11-11T15:02:53.6399601 2021-11-11T14:18:39.4431456 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Hans Ren 1 Freya Hu 2 San Hlaing Myint 3 Kun Hou 4 Xiuyu Zhang 5 Min Zuo 6 Chi Zhang 7 Qingchuan Zhang 8 Haipeng Li 9 58621__21495__1e05acd249594b4596d6890f3b6bae61.pdf 58621.pdf 2021-11-11T14:23:49.6020908 Output 6828986 application/pdf Version of Record true © 2021 Hanchi Ren et al. This is an open access article distributed under the Creative Commons Attribution License true eng https://creativecommons.org/licenses/by/4.0/
title A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems
spellingShingle A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems
Hans Ren
Freya Hu
Chi Zhang
title_short A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems
title_full A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems
title_fullStr A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems
title_full_unstemmed A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems
title_sort A Real-Time and Long-Term Face Tracking Method Using Convolutional Neural Network and Optical Flow in IoT-Based Multimedia Communication Systems
author_id_str_mv 9e043b899a2b786672a28ed4f864ffcc
aa73524c5e3969c88fb7a3a5bde919b1
46f911dbfa7c27cbbe839e897559b142
author_id_fullname_str_mv 9e043b899a2b786672a28ed4f864ffcc_***_Hans Ren
aa73524c5e3969c88fb7a3a5bde919b1_***_Freya Hu
46f911dbfa7c27cbbe839e897559b142_***_Chi Zhang
author Hans Ren
Freya Hu
Chi Zhang
author2 Hans Ren
Freya Hu
San Hlaing Myint
Kun Hou
Xiuyu Zhang
Min Zuo
Chi Zhang
Qingchuan Zhang
Haipeng Li
format Journal article
container_title Wireless Communications and Mobile Computing
container_volume 2021
container_start_page 1
publishDate 2021
institution Swansea University
issn 1530-8669
1530-8677
doi_str_mv 10.1155/2021/6711561
publisher Hindawi Limited
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 The development of the Internet of Things (IoT) stimulates many research works related to Multimedia Communication Systems (MCS), such as human face detection and tracking. This trend drives numerous progressive methods. Among these methods, the deep learning-based methods can spot face patch in an image effectively and accurately. Many people consider face tracking as face detection, but they are two different techniques. Face detection focuses on a single image, whose shortcoming is obvious, such as unstable and unsmooth face position when adopted on a sequence of continuous images; computing is expensive due to its heavy reliance on Convolutional Neural Networks (CNNs) and limited detection performance on the edge device. To overcome these defects, this paper proposes a novel face tracking strategy by combining CNN and optical flow, namely, C-OF, which achieves an extremely fast, stable, and long-term face tracking system. Two key things for commercial applications are the stability and smoothness of face positions in a sequence of image frames, which can provide more probability for face biological signal extraction, silent face antispoofing, and facial expression analysis in the fields of IoT-based MCS. Our method captures face patterns in every two consequent frames via optical flow to get rid of the unstable and unsmooth problems. Moreover, an innovative metric for measuring the stability and smoothness of face motion is designed and adopted in our experiments. The experimental results illustrate that our proposed C-OF outperforms both face detection and object tracking methods.
published_date 2021-10-31T04:15:17Z
_version_ 1763754028495273984
score 11.035634

Similar Items