FireFly A Synthetic Dataset for Ember Detection in Wildfire
This work addresses a domain-specific problem for wildfire management by providing a synthetic dataset to improve ember detection, though it is incremental as it builds on existing object detection methods.
The paper tackled the lack of ember-specific training data for wildfire detection by creating the FireFly synthetic dataset using Unreal Engine 4, resulting in up to 8.57% improvement in mean Average Precision for real-world scenarios compared to models trained on small real datasets.
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.