In recent years, increased wildfires have caused irreversible damage to forest resources worldwide, threatening wildlives and human living conditions. The lack of accurate frontline information in real-time can pose great risks to firefighters. Though a plethora of machine learning algorithms have been developed to detect wildfires using aerial images and videos captured by drones, there is a lack of methods corresponding to drone deployment. We propose a wildfire rapid response system that optimizes the number and relative positions of drones to achieve full coverage of the whole wildfire area. Trained on the data from historical wildfire events, our model evaluates the possibility of wildfires at different scales and accordingly allocates the resources. It adopts plane geometry to deploy drones while balancing the capability and safety with inequality constrained nonlinear programming. The method can flexibly adapt to different terrains and the dynamic extension of the wildfire area. Lastly, the operation cost under extreme wildfire circumstances can be assessed upon the completion of the deployment. We applied our model to the wildfire data collected from eastern Victoria, Australia, and demonstrated its great potential in the real world.
翻译:近年来,越来越多的野火对全世界的森林资源造成了不可逆转的损害,威胁到了野生生命和人类生活条件。缺乏准确的前线实时信息可能对消防员构成巨大风险。虽然已经开发了大量机器学习算法,利用无人机拍摄的航空图像和视频探测野火,但缺乏与无人机部署相应的方法。我们建议建立一个野火快速反应系统,优化无人机的数量和相对位置,以全面覆盖整个野火区。根据历史野火事件的数据培训,我们的模型评估了不同规模野火的可能性,并相应分配了资源。我们采用了飞机几何方法部署无人机,同时平衡能力和安全,同时限制非线性规划的不平等。这种方法可以灵活地适应不同的地形和野火区的动态延伸。最后,在部署完成后,可以评估极端野火环境下的操作成本。我们用模型来评估从澳大利亚东维多利亚州收集的野火数据,并展示了其在现实世界的巨大潜力。