This paper presents "FireFly", a synthetic dataset for ember detection created using Unreal Engine 4 (UE4), designed to overcome the current lack of ember-specific training resources. To create the dataset, we present a tool that allows the automated generation of the synthetic labeled dataset with adjustable parameters, enabling data diversity from various environmental conditions, making the dataset both diverse and customizable based on user requirements. We generated a total of 19,273 frames that have been used to evaluate FireFly on four popular object detection models. Further to minimize human intervention, we leveraged a trained model to create a semi-automatic labeling process for real-life ember frames. Moreover, we demonstrated an up to 8.57% improvement in mean Average Precision (mAP) in real-world wildfire scenarios compared to models trained exclusively on a small real dataset.
Cite
@article{arxiv.2308.03164,
title = {FireFly A Synthetic Dataset for Ember Detection in Wildfire},
author = {Yue Hu and Xinan Ye and Yifei Liu and Souvik Kundu and Gourav Datta and Srikar Mutnuri and Namo Asavisanu and Nora Ayanian and Konstantinos Psounis and Peter Beerel},
journal= {arXiv preprint arXiv:2308.03164},
year = {2023}
}
Comments
Artificial Intelligence (AI) and Humanitarian Assistance and Disaster Recovery (HADR) workshop, ICCV 2023 in Paris, France