Analysis of Deep Learning Architectures and Efficacy of Detecting Forest Fires

TL;DR

This paper reviews computer vision techniques for forest fire detection, emphasizing the need for specialized datasets and methods to support machine learning practitioners lacking domain expertise.

Contribution

It introduces domain-specific datasets and methods to improve accessibility and effectiveness of deep learning in forest fire detection.

Findings

Assessment of current deep learning architectures for fire detection

Identification of gaps in existing datasets for forest fire analysis

Proposals for new datasets to enhance model training

Abstract

The aim of this research is to review the state of computer vision as applied to combatting forest fires. My motivation to research this topic comes from the urgency with which new participants and stakeholders require guidance in this field. One of these new stakeholder groups are practitioners of machine learning that lack domain expertise. Introducing these new entrants to domain specific datasets and methods is critical to supporting this aim as general computer vision datasets are insufficient to support specialized research initiatives. The overarching aim of the research is to introduce datasets and methods to make them more accessible to the community.