Smoke Objection Detection in Deep Learning for Real-Time Wildfire Environments Using Faster R-CNN

DOI

10.2991/978-94-6239-693-7_63How to use a DOI?

Keywords

Object Detection; Real time dataset; Faster R-CNN; Deep Learning

Abstract

The increasing frequency and severity of wildfires have highlighted the urgent need for intelligent, real-time monitoring systems. These systems are capable of detecting early signs of forest fire activity. This paper experiments with the real time datasets from various websites with deep learning techniques. The dataset is a real dataset that comprises UAV and CCTV imagery. Here the data geometric augmentated dataset is passed into the model. In this paper, experimental analysis and evaluation are performed to predict and distinguish the regions containing smoke and non-smoke. The proposed approach here uses the deep learning model called Faster Region-Based Convolutional Neural Network (Faster R-CNN) architecture to accurately recognise and localise smoke related to environmental conditions. The model is trained and validated on the dataset, and it ensures a strong performance on the both aerial and ground-level perspectives. Evaluation metrics scale for these deep learning models includes precision, recall, f1-score and accuracy. They are used to find the model’s performance for near real-time deployment in wildfire surveillance systems. The results of this model show the efficiency of the smoke object detection on early detection capabilities.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - N. Nithya
AU  - R. Priya
PY  - 2026
DA  - 2026/06/16
TI  - Smoke Objection Detection in Deep Learning for Real-Time Wildfire Environments Using Faster R-CNN
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 635
EP  - 646
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_63
DO  - 10.2991/978-94-6239-693-7_63
ID  - Nithya2026
ER  -