Wildfire and smoke early detection for drone applications: a light-weight deep learning approach

Simple item page
dc.contributor.authorKumar, Abhinav
dc.contributor.authorPerrusquía, Adolfo
dc.contributor.authorAl-Rubaye, Saba
dc.contributor.authorGuo, Weisi
dc.date.accessioned2024-08-12T08:32:19Z
dc.date.available2024-08-12T08:32:19Z
dc.date.freetoread2024-08-12
dc.date.issued2024-10-01
dc.date.pubOnline2024-07-23
dc.description.abstractDrones have become a crucial element in current wildfire and smoke detection applications. Several deep learning architectures have been developed to detect fire and smoke using either colour-based methodologies or semantic segmentation techniques with impressive results. However, the computational demands of these models reduce their usability on memory-restricted devices such as drones. To overcome this memory constraint whilst maintaining the high detection capabilities of deep learning models, this paper proposes two lightweight architectures for fire and smoke detection in forest environments. The approaches use the Deeplabv3+ architecture for image segmentation as baseline. The novelty lies in the incorporation of vision transformers and a lightweight convolutional neural network architecture that heavily reduces the model complexity, whilst maintaining state-of-the-art performance. Two datasets for fire and smoke segmentation, based on the Corsican, FLAME, SMOKE5K, and AI-For-Mankind datasets, are created to cover different real-world scenarios of wildfire to produce models with better detection capabilities. Experiments are conducted to show the benefits of the proposed approach and its relevance in current drone-based wildfire detection applications.
dc.description.journalNameEngineering Applications of Artificial Intelligence
dc.format.extentArticle number 108977
dc.identifier.citationKumar A, Perrusquía A, Al-Rubaye S, Guo W. (2024) Wildfire and smoke early detection for drone applications: a light-weight deep learning approach. Engineering Applications of Artificial Intelligence, Volume 136, Part B, October 2024, Article number 108977
dc.identifier.issn0952-1976
dc.identifier.urihttps://doi.org/10.1016/j.engappai.2024.108977
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/22770
dc.language.isoen
dc.publisherElsevier
dc.publisher.urihttps://www.sciencedirect.com/science/article/pii/S0952197624011357
dc.rightsAttribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectDeeplabv3+
dc.subjectMobile vision transformers
dc.subjectMobilenet
dc.subjectWildfire and smoke detection
dc.subjectSegmentation
dc.titleWildfire and smoke early detection for drone applications: a light-weight deep learning approach
dc.typeArticle
dcterms.dateAccepted2024-07-11

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Wildfire_and_smoke_early_detection_for_drone_applications-2024.pdf
Size:
2.86 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)