Preliminary Wildfire Detection Using State-of-the-art PTZ (Pan, Tilt, Zoom) Camera Technology and Convolutional Neural Networks

TL;DR

This paper explores early wildfire detection using advanced PTZ cameras combined with convolutional neural networks, aiming for faster, more accurate identification to prevent damage and save lives.

Contribution

It introduces a more representative and balanced dataset for wildfire detection and demonstrates the effectiveness of CNNs in real-world scenarios.

Findings

CNN models generalize well on the dataset

Balanced data improves detection accuracy

Potential for real-time wildfire monitoring

Abstract

Wildfires are uncontrolled fires in the environment that can be caused by humans or nature. In 2020 alone, wildfires in California have burned 4.2 million acres, damaged 10,500 buildings or structures, and killed more than 31 people, exacerbated by climate change and a rise in average global temperatures. This also means there has been an increase in the costs of extinguishing these treacherous wildfires. The objective of the research is to detect forest fires in their earlier stages to prevent them from spreading, prevent them from causing damage to a variety of things, and most importantly, reduce or eliminate the chances of someone dying from a wildfire. A fire detection system should be efficient and accurate with respect to extinguishing wildfires in their earlier stages to prevent the spread of them along with their consequences. Computer Vision is potentially a more reliable, fast, and widespread method we need. The current research in the field of preliminary fire detection has several problems related to unrepresentative data being used to train models and their existing varied amounts of label imbalance in the classes of their dataset. We propose a more representative and evenly distributed data through better settings, lighting, atmospheres, etc., and class distribution in the entire dataset. After thoroughly examining the results of this research, it can be inferred that they supported the datasets strengths by being a viable resource when tested in the real world on unfamiliar data. This is evident since as the model trains on the dataset, it is able to generalize on it, hence confirming this is a viable Machine Learning setting that has practical impact.