RT Journal Article
T1 Multiview Summarization and Activity Recognition Meet Edge Computing in IoT Environments
A1 Hussain, Tanveer
A1 Muhammad, Khan
A1 Ullah, Amin
A1 Ser, Javier Del
A1 Gandomi, Amir H.
A1 Sajjad, Muhammad
A1 Baik, Sung Wook
A1 De Albuquerque, Victor Hugo C.
AB Multiview video summarization (MVS) has not received much attention from the research community due to inter-view correlations and views' overlapping, etc. The majority of previous MVS works are offline, relying on only summary, and require additional communication bandwidth and transmission time, with no focus on foggy environments. We propose an edge intelligence-based MVS and activity recognition framework that combines artificial intelligence with Internet of Things (IoT) devices. In our framework, resource-constrained devices with cameras use a lightweight CNN-based object detection model to segment multiview videos into shots, followed by mutual information computation that helps in a summary generation. Our system does not rely solely on a summary, but encodes and transmits it to a master device using a neural computing stick for inter-view correlations computation and efficient activity recognition, an approach which saves computation resources, communication bandwidth, and transmission time. Experiments show an increase of 0.4 unit in F -measure on an MVS Office dateset and 0.2% and 2% improved accuracy for UCF-50 and YouTube 11 datesets, respectively, with lower storage and transmission times. The processing time is reduced from 1.23 to 0.45 s for a single frame and optimally 0.75 seconds faster MVS. A new dateset is constructed by synthetically adding fog to an MVS dateset to show the adaptability of our system for both certain and uncertain IoT surveillance environments.
SN 2327-4662
YR 2021
FD 2021-06-15
LK https://hdl.handle.net/11556/5189
UL https://hdl.handle.net/11556/5189
LA eng
NO Hussain , T , Muhammad , K , Ullah , A , Ser , J D , Gandomi , A H , Sajjad , M , Baik , S W & De Albuquerque , V H C 2021 , ' Multiview Summarization and Activity Recognition Meet Edge Computing in IoT Environments ' , IEEE Internet of Things Journal , vol. 8 , no. 12 , 9208765 , pp. 9634-9644 . https://doi.org/10.1109/JIOT.2020.3027483
NO Publisher Copyright: © 2014 IEEE.
NO Manuscript received March 30, 2020; revised June 21, 2020 and August 29, 2020; accepted September 10, 2020. Date of publication September 29, 2020; date of current version June 7, 2021. This work was supported by the Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government (MSIT, Development of AI-Convergence Technologies for Smart City Industry Productivity Innovation) under Grant 2019-0-00136. (Corresponding author: Sung Wook Baik.) Tanveer Hussain, Amin Ullah, and Sung Wook Baik are with Sejong University, Seoul 143-747, South Korea (e-mail: tanveer445@ieee.org; aminullah@ieee.org; sbaik@sejong.ac.kr).
DS TECNALIA Publications
RD 28 sept 2024