Efficient Deep CNN-Based Fire Detection and Localisation in Video Surveillance Applications
- Submitting institution
-
Liverpool John Moores University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1579
- Type
- D - Journal article
- DOI
-
10.1109/TSMC.2018.2830099
- Title of journal
- IEEE Transactions on Systems Man and Cybernetics: Systems
- Article number
- -
- First page
- 1419
- Volume
- 49
- Issue
- 7
- ISSN
- 2168-2216
- Open access status
- Other exception
- Month of publication
- June
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 49
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is an output of an international collaboration with researchers in South Korea, China and Italy, supported by a grant (2016R1A2B4011712) from the National Research Foundation of Korea. It proposes an energy-friendly and computationally efficient solution to simplify the use of video surveillance applications for fire detection and localisation. The experiments conducted demonstrate that the simplified solution can achieve comparable accuracies to more complex models while offering its easier implementation. The paper has inspired further research in related areas, including the follow-up work in https://doi.org/10.1109/TII.2019.2897594.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
