Aerial imagery pile burn detection using deep learning: The FLAME dataset
Aerial imagery pile burn detection using deep learning: The FLAME dataset
复制标题
DOI：
10.1016/j.comnet.2021.108001
复制
发表时间：
2021-07-05
影响因子：
5.6
通讯作者：
Blasch, Erik
中科院分区：
文献类型：
--
作者：
Shamsoshoara, Alireza;Afghah, Fatemeh;Blasch, Erik
野火是美国最昂贵和最致命的自然灾害之一，对数百万公顷的森林资源造成破坏，并威胁到人和动物的生命。特别重要的是消防员和行动部队面临的风险，这突出表明需要利用技术来最大限度地减少对人员和财产的危险。FLAME（Fire Luminosity Airborne Machine learning Evaluation）提供了一个火灾的航空图像数据集沿着火灾检测和分割方法，可以帮助消防员和研究人员制定最佳的火灾管理策略。本文提供了一个无人机在亚利桑那州松林中指定燃烧堆积碎屑期间收集的火灾图像数据集。该数据集包括由红外摄像机捕获的视频记录和热图。捕获的视频和图像被注释，并按帧标记，以帮助研究人员轻松应用他们的火灾检测和建模算法。本文还强调了两个机器学习问题的解决方案：（1）基于火焰的存在[和不存在]对视频帧进行二进制分类。人工神经网络（ANN）的方法，实现了76%的分类精度。(2)使用分割方法精确确定火灾边界的火灾检测。设计了一种基于U-Net上采样和下采样方法的深度学习方法，从视频帧中提取火灾掩模。我们的FLAME方法接近92%的准确率和84%的召回率。未来的研究将扩大技术自由燃烧的广播火灾使用热图像。
Wildfires are one of the costliest and deadliest natural disasters in the US, causing damage to millions of hectares of forest resources and threatening the lives of people and animals. Of particular importance are risks to firefighters and operational forces, which highlights the need for leveraging technology to minimize danger to people and property. FLAME (Fire Luminosity Airborne-based Machine learning Evaluation) offers a dataset of aerial images of fires along with methods for fire detection and segmentation which can help firefighters and researchers to develop optimal fire management strategies.This paper provides a fire image dataset collected by drones during a prescribed burning piled detritus in an Arizona pine forest. The dataset includes video recordings and thermal heatmaps captured by infrared cameras. The captured videos and images are annotated, and labeled frame-wise to help researchers easily apply their fire detection and modeling algorithms. The paper also highlights solutions to two machine learning problems: (1) Binary classification of video frames based on the presence [and absence] of fire flames. An Artificial Neural Network (ANN) method is developed that achieved a 76% classification accuracy. (2) Fire detection using segmentation methods to precisely determine fire borders. A deep learning method is designed based on the U-Net up-sampling and down-sampling approach to extract a fire mask from the video frames. Our FLAME method approached a precision of 92%, and recall of 84%. Future research will expand the technique for free burning broadcast fire using thermal images.