TY - JOUR
T1 - Video surveillance on mobile edge networks - A reinforcement-learning-based approach
AU - Hu, Haoji
AU - Shan, Hangguan
AU - Wang, Chuankun
AU - Sun, Tengxu
AU - Zhen, Xiaojian
AU - Yang, Kunpeng
AU - Yu, Lu
AU - Zhang, Zhaoyang
AU - Quek, Tony Q.S.
N1 - Funding Information:
Manuscript received July 26, 2019; revised September 26, 2019, November 13, 2019, and December 27, 2019; accepted January 9, 2020. Date of publication January 23, 2020; date of current version June 12, 2020. This work was supported in part by the National Key Research and Development Program of China under Grant 2018YFB1801104; in part by the National Natural Science Foundation Program of China under Grant 61771427, Grant 61725104, and Grant U1709214; in part by the SUTD-ZJU Research Collaboration under Grant SUTD-ZJU/RES/05/2016; in part by the SUTD Growth Plan Grant for AI; in part by the Ng Teng Fong Charitable Foundation in the form of ZJU-SUTD IDEA Grant; in part by the SUTD-ZJU IDEA Grant for Visiting Professor under Grant 201804; and in part by the Huawei Technologies Company Ltd. under Grant YBN2018115223. (Corresponding author: Hangguan Shan.) Haoji Hu and Hangguan Shan are with the College of Information Science and Electronic Engineering, Zhejiang Provincial Key Laboratory of Information Processing and Communication Networks, and SUTD-ZJU IDEA, Zhejiang University, Hangzhou 310027, China, and also with the Zhejiang Laboratory, Hangzhou 310000, China (e-mail: [email protected]; [email protected]).
Publisher Copyright:
© 2014 IEEE.
PY - 2020/6
Y1 - 2020/6
N2 - Video surveillance systems or Internet of Multimedia Things are playing a more and more important role in our daily life. To obtain useful surveillance information timely and accurately, not only image recognition algorithms but also computing and communication resources can be bottlenecks of the whole system. In this article, taking face recognition application as an example, we study how to build video surveillance systems by utilizing mobile edge computing (MEC), one of the 5G's key technologies. Specifically, to achieve high recognition accuracy and low recognition time, we design image recognition algorithms for both the camera sensor and MEC server, and utilize the action-value methods to train actions of the system by jointly optimizing offloading decision and image compression parameters. The experimental results show the advantages of the proposed system for enabling communication environment-adaptive, efficient, and intelligent video surveillance.
AB - Video surveillance systems or Internet of Multimedia Things are playing a more and more important role in our daily life. To obtain useful surveillance information timely and accurately, not only image recognition algorithms but also computing and communication resources can be bottlenecks of the whole system. In this article, taking face recognition application as an example, we study how to build video surveillance systems by utilizing mobile edge computing (MEC), one of the 5G's key technologies. Specifically, to achieve high recognition accuracy and low recognition time, we design image recognition algorithms for both the camera sensor and MEC server, and utilize the action-value methods to train actions of the system by jointly optimizing offloading decision and image compression parameters. The experimental results show the advantages of the proposed system for enabling communication environment-adaptive, efficient, and intelligent video surveillance.
UR - http://www.scopus.com/inward/record.url?scp=85086572492&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086572492&partnerID=8YFLogxK
U2 - 10.1109/JIOT.2020.2968941
DO - 10.1109/JIOT.2020.2968941
M3 - Article
AN - SCOPUS:85086572492
SN - 2327-4662
VL - 7
SP - 4746
EP - 4760
JO - IEEE Internet of Things Journal
JF - IEEE Internet of Things Journal
IS - 6
M1 - 8966998
ER -