Skip to main content

Research Repository

Advanced Search

Experimentally Defined Convolutional Neural Network Architecture Variants for Non-temporal Real-time Fire Detection

Dunnings, A.; Breckon, T.P.

Experimentally Defined Convolutional Neural Network Architecture Variants for Non-temporal Real-time Fire Detection Thumbnail


Authors

A. Dunnings



Abstract

In this work we investigate the automatic detection of fire pixel regions in video (or still) imagery within real-time bounds without reliance on temporal scene information. As an extension to prior work in the field, we consider the performance of experimentally defined, reduced complexity deep convolutional neural network architectures for this task. Contrary to contemporary trends in the field, our work illustrates maximal accuracy of 0.93 for whole image binary fire detection, with 0.89 accuracy within our superpixel localization framework can be achieved, via a network architecture of signficantly reduced complexity. These reduced architectures additionally offer a 3–4 fold increase in computational performance offering up to 17 fps processing on contemporary hardware independent of temporal information. We show the relative performance achieved against prior work using benchmark datasets to illustrate maximally robust real-time fire region detection.

Citation

Dunnings, A., & Breckon, T. (2018). Experimentally Defined Convolutional Neural Network Architecture Variants for Non-temporal Real-time Fire Detection. In Proc. Int. Conf. on Image Processing (1558-1562). https://doi.org/10.1109/ICIP.2018.8451657

Conference Name 25th IEEE International Conference on Image Processing (ICIP).
Conference Location Athens, Greece
Start Date Oct 7, 2018
End Date Oct 10, 2018
Acceptance Date May 30, 2018
Online Publication Date Sep 6, 2018
Publication Date 2018
Deposit Date May 30, 2018
Publicly Available Date Mar 28, 2024
Pages 1558-1562
Series ISSN 2381-8549
Book Title Proc. Int. Conf. on Image Processing
ISBN 9781479970629
DOI https://doi.org/10.1109/ICIP.2018.8451657
Keywords fire detection, CNN, deep-learning real-time, non-temporal
Public URL https://durham-repository.worktribe.com/output/1146797
Publisher URL https://breckon.org/toby/publications/papers/dunnings18fire.pdf

Files


Accepted Conference Proceeding (Revised version) (715 Kb)
PDF

Copyright Statement
Revised version © 2018 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.





You might also like



Downloadable Citations