SKLFS-WildFire Test
Overview
SKLFS-WildFire Test is a real-world test set for open-scene early wildfire smoke detection. It was introduced in Wildfire Smoke Detection System: Model Architecture, Training Mechanism, and Dataset to support systematic evaluation of wildfire smoke detection models under practical conditions.
The test split contains 50,735 images from 3,309 videos, including 3,588 smoke-positive images from 340 real wildfire videos. The dataset also includes a large number of negative samples with smoke-like interference objects, making it suitable for evaluating model robustness in unpredictable open environments.
Key Features
- Real-world early wildfire scenes collected from practical application data.
- 50,735 test images from 3,309 videos.
- 3,588 smoke-positive images from 340 real wildfire videos.
- Difficult negative samples with smoke-like visual interference.
- Bounding-box-level annotation for smoke detection evaluation.
- The training split is not released; the public dataset is the SKLFS-WildFire Test split.
Citation
If you use this dataset, please cite:
@article{https://doi.org/10.1155/int/1610145,
author = {Wang, Chong and Xu, Chen and Akram, Adeel and Wang, Zhong and Shan, Zhilin and Zhang, Qixing},
title = {Wildfire Smoke Detection System: Model Architecture, Training Mechanism, and Dataset},
journal = {International Journal of Intelligent Systems},
volume = {2025},
number = {1},
pages = {1610145},
year = {2025}
}