eCite Digital Repository

Cloud-assisted multi-view video summarization using CNN and bi-directional LSTM

Citation

Hussain, T and Muhammad, K and Ullah, A and Cao, Z and Baik, SW and de Albuquerque, VHC, Cloud-assisted multi-view video summarization using CNN and bi-directional LSTM, IEEE Transactions on Industrial Informatics, 16, (1) pp. 77-86. ISSN 1551-3203 (2020) [Refereed Article]


Preview
PDF
1Mb
  

Copyright Statement

2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

DOI: doi:10.1109/TII.2019.2929228

Abstract

The massive amount of video data produced by surveillance networks in industries instigate various challenges in exploring these videos for many applications such as video summarization, analysis, indexing, and retrieval. The task of multi-view video summarization (MVS) is very challenging due to the gigantic size of data, redundancy, overlapping in views, light variations, and inter-view correlations. To address these challenges, various low-level features and clustering based soft computing techniques are proposed that cannot fully exploit MVS. In this article, we achieve MVS by integrating deep neural network based soft computing techniques in a two tier framework. The first online tier performs target appearance based shots segmentation and stores them in a lookup table that is transmitted to cloud for further processing. The second tier extracts deep features from each frame of a sequence in the lookup table and pass them to deep bi-directional long short-term memory (DB-LSTM) to acquire probabilities of informativeness to generate summary. Experimental evaluation on MVS benchmark dataset and industrial surveillance data from YouTube confirms the higher accuracy of our system compared to state-of-the-art MVS methods.

Item Details

Item Type:Refereed Article
Keywords:artificial intelligence, cloud computing, convolutional neural networks, industrial surveillance, multi-view videos, soft computing, video summarization, LSTM
Research Division:Information and Computing Sciences
Research Group:Computer vision and multimedia computation
Research Field:Pattern recognition
Objective Division:Defence
Objective Group:Defence
Objective Field:Intelligence, surveillance and space
UTAS Author:Cao, Z (Dr Zehong Cao)
ID Code:133983
Year Published:2020 (online first 2019)
Web of Science® Times Cited:39
Deposited By:Information and Communication Technology
Deposited On:2019-07-18
Last Modified:2020-10-08
Downloads:12 View Download Statistics

Repository Staff Only: item control page