The FLAME dataset: Aerial Imagery Pile burn detection using drones (UAVs)|无人机监测数据集|火灾检测数据集

Wildfires are one of the deadliest and dangerous natural disasters in the world. Wildfires burn millions of forests and they put many lives of humans and animals in danger. Predicting fire behavior can help firefighters to have better fire management and scheduling for future incidents and also it reduces the life risks for the firefighters. Recent advance in aerial images shows that they can be beneficial in wildfire studies. Among different methods and technologies for aerial images, Unmanned Aerial Vehicles (UAVs) and drones are beneficial to collect information regarding the fire. This study provides an aerial imagery FLAME (Fire Luminosity Airborne-based Machine learning Evaluation) dataset using drones during a prescribed pile burn in Northern Arizona, USA. This dataset consists of different repositories including raw aerial videos recorded by drones' cameras and also raw heatmap footage recorded by an infrared thermal camera. To help researchers, two well-known studies; fire classification and fire segmentation are defined based on the dataset. For approaches such as Neural Networks (NNs) and fire classification, 39,375 frames are labeled ("Fire" vs "Non-Fire") for the training phase. Also, another 8,617 frames are labeled for the test data. 2,003 frames are considered for the fire segmentation and regarding that, 2,003 masks are generated for the purpose of Ground Truth data with pixel-wise annotation.The published article is available here:https://www.sciencedirect.com/science/article/pii/S1389128621001201The preprint article of this dataset is available here:https://arxiv.org/pdf/2012.14036.pdfMore information about this study and the two machine learning challenges that we used is available here:https://github.com/AlirezaShamsoshoara/Fire-Detection-UAV-Aerial-Image-Classification-Segmentation-UnmannedAerialVehicleA sample video is available on YouTube:https://www.youtube.com/watch?v=bHK6g37_KyATo find other projects and articles in our group:https://www.cefns.nau.edu/~fa334/

野火是全球最为致命且危险的自然灾害之一。野火燃烧了数百万公顷的森林，对人类及动物的众多生命构成了严重威胁。预测火势行为有助于消防员进行更有效的火情管理和未来事件的调度，同时也能降低消防员的生命风险。近期在航空影像领域的进展表明，航空影像在野火研究中具有潜在益处。在众多航空影像处理方法和技术中，无人机（UAV）和无人机技术在收集有关火灾的信息方面具有显著优势。本研究提供了一组使用无人机在亚利桑那州北部进行预定堆积燃烧期间收集的航空影像FLAME（基于空中火光机器学习评估）数据集。该数据集包括由无人机摄像机记录的原始航空视频以及由红外热像仪记录的原始热图影像。为了协助研究人员，基于该数据集定义了两项知名研究；火灾分类和火灾分割。对于如神经网络（NNs）和火灾分类等途径，共有39,375帧图像被标注为“火灾”与“非火灾”，用于训练阶段。此外，另有8,617帧图像被标注用于测试数据。针对火灾分割，考虑了2,003帧图像，并为此生成了2,003个掩码，以提供像素级的地面真实数据。相关发表文章可在此处查阅：https://www.sciencedirect.com/science/article/pii/S1389128621001201。该数据集的预印本文章可在此处查阅：https://arxiv.org/pdf/2012.14036.pdf。更多关于本研究以及所使用的两个机器学习挑战的信息可在此处获取：https://github.com/AlirezaShamsoshoara/Fire-Detection-UAV-Aerial-Image-Classification-Segmentation-UnmannedAerialVehicle。YouTube上可观看样视频：https://www.youtube.com/watch?v=bHK6g37_KyA。有关我们团队的其他项目和文章，可在此处查阅：https://www.cefns.nau.edu/~fa334/。