Edge Intelligence-Assisted Smoke Detection in Foggy Surveillance Environments

Khan Muhammad, Salman Khan, Vasile Palade, Irfan Mehmood, Victor Hugo C. De Albuquerque

Research output: Contribution to journalArticle

9 Downloads (Pure)

Abstract

Smoke detection in foggy surveillance environments is a challenging task and plays a key role in disaster management for industrial systems. The current smoke detection methods are applicable to only normal surveillance videos, providing unsatisfactory results for video streams captured from foggy environments, due to challenges related to clutter and unclear contents. In this paper, an energy-friendly edge intelligence-assisted smoke detection method is proposed using deep convolutional neural networks (CNN) for foggy surveillance environments. Our method uses a light-weight architecture, considering all necessary requirements regarding accuracy, running time, and deployment feasibility for smoke detection in industrial setting, compared to other complex and computationally expensive architectures including AlexNet, GoogleNet, and VGG. Experiments are conducted on available benchmark smoke detection datasets, and the obtained results show better performance of the proposed method over state-of-the-art for early smoke detection in foggy surveillance.
Original languageEnglish
Pages (from-to)(In-press)
JournalIEEE Transactions on Industrial Informatics
Volume(In-press)
Early online date8 May 2019
DOIs
Publication statusE-pub ahead of print - 8 May 2019

Fingerprint

Smoke
Disasters
Neural networks
Experiments

Bibliographical note

© 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.


Paper is not published yet, but in print, and available online as early access, on the journal web site while waiting to be printed.

Keywords

  • Smoke Detection
  • Convolutional Neural Nets (CNNs)
  • Foggy Surveillance Environments

Cite this

Edge Intelligence-Assisted Smoke Detection in Foggy Surveillance Environments. / Muhammad, Khan; Khan, Salman; Palade, Vasile; Mehmood, Irfan; De Albuquerque, Victor Hugo C.

In: IEEE Transactions on Industrial Informatics, Vol. (In-press), 08.05.2019, p. (In-press).

Research output: Contribution to journalArticle

Muhammad, Khan ; Khan, Salman ; Palade, Vasile ; Mehmood, Irfan ; De Albuquerque, Victor Hugo C. / Edge Intelligence-Assisted Smoke Detection in Foggy Surveillance Environments. In: IEEE Transactions on Industrial Informatics. 2019 ; Vol. (In-press). pp. (In-press).
@article{262a9f0f16754113bebd287ef6ae061d,
title = "Edge Intelligence-Assisted Smoke Detection in Foggy Surveillance Environments",
abstract = "Smoke detection in foggy surveillance environments is a challenging task and plays a key role in disaster management for industrial systems. The current smoke detection methods are applicable to only normal surveillance videos, providing unsatisfactory results for video streams captured from foggy environments, due to challenges related to clutter and unclear contents. In this paper, an energy-friendly edge intelligence-assisted smoke detection method is proposed using deep convolutional neural networks (CNN) for foggy surveillance environments. Our method uses a light-weight architecture, considering all necessary requirements regarding accuracy, running time, and deployment feasibility for smoke detection in industrial setting, compared to other complex and computationally expensive architectures including AlexNet, GoogleNet, and VGG. Experiments are conducted on available benchmark smoke detection datasets, and the obtained results show better performance of the proposed method over state-of-the-art for early smoke detection in foggy surveillance.",
keywords = "Smoke Detection, Convolutional Neural Nets (CNNs), Foggy Surveillance Environments",
author = "Khan Muhammad and Salman Khan and Vasile Palade and Irfan Mehmood and {De Albuquerque}, {Victor Hugo C.}",
note = "{\circledC} 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. Paper is not published yet, but in print, and available online as early access, on the journal web site while waiting to be printed.",
year = "2019",
month = "5",
day = "8",
doi = "10.1109/TII.2019.2915592",
language = "English",
volume = "(In-press)",
pages = "(In--press)",
journal = "IEEE Transactions on Industrial Informatics",
issn = "1551-3203",
publisher = "Institute of Electrical and Electronics Engineers",

}

TY - JOUR

T1 - Edge Intelligence-Assisted Smoke Detection in Foggy Surveillance Environments

AU - Muhammad, Khan

AU - Khan, Salman

AU - Palade, Vasile

AU - Mehmood, Irfan

AU - De Albuquerque, Victor Hugo C.

N1 - © 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. Paper is not published yet, but in print, and available online as early access, on the journal web site while waiting to be printed.

PY - 2019/5/8

Y1 - 2019/5/8

N2 - Smoke detection in foggy surveillance environments is a challenging task and plays a key role in disaster management for industrial systems. The current smoke detection methods are applicable to only normal surveillance videos, providing unsatisfactory results for video streams captured from foggy environments, due to challenges related to clutter and unclear contents. In this paper, an energy-friendly edge intelligence-assisted smoke detection method is proposed using deep convolutional neural networks (CNN) for foggy surveillance environments. Our method uses a light-weight architecture, considering all necessary requirements regarding accuracy, running time, and deployment feasibility for smoke detection in industrial setting, compared to other complex and computationally expensive architectures including AlexNet, GoogleNet, and VGG. Experiments are conducted on available benchmark smoke detection datasets, and the obtained results show better performance of the proposed method over state-of-the-art for early smoke detection in foggy surveillance.

AB - Smoke detection in foggy surveillance environments is a challenging task and plays a key role in disaster management for industrial systems. The current smoke detection methods are applicable to only normal surveillance videos, providing unsatisfactory results for video streams captured from foggy environments, due to challenges related to clutter and unclear contents. In this paper, an energy-friendly edge intelligence-assisted smoke detection method is proposed using deep convolutional neural networks (CNN) for foggy surveillance environments. Our method uses a light-weight architecture, considering all necessary requirements regarding accuracy, running time, and deployment feasibility for smoke detection in industrial setting, compared to other complex and computationally expensive architectures including AlexNet, GoogleNet, and VGG. Experiments are conducted on available benchmark smoke detection datasets, and the obtained results show better performance of the proposed method over state-of-the-art for early smoke detection in foggy surveillance.

KW - Smoke Detection

KW - Convolutional Neural Nets (CNNs)

KW - Foggy Surveillance Environments

U2 - 10.1109/TII.2019.2915592

DO - 10.1109/TII.2019.2915592

M3 - Article

VL - (In-press)

SP - (In-press)

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

ER -