Abstract
Unmanned Aerial Systems, hereafter referred to as UAS, are of great use in hazard events such as wildfire due to their ability to provide high-resolution video imagery over areas deemed too dangerous for manned aircraft and ground crews. This aerial perspective allows for identification of ground-based hazards such as spot fires and fire lines, and to communicate this information with fire fighting crews. Current technology relies on visual interpretation of UAS imagery, with little to no computer-assisted automatic detection. With the help of big labeled data and the significant increase of computing power, deep learning has seen great successes on object detection with fixed patterns, such as people and vehicles. However, little has been done for objects, such as spot fires, with amorphous and irregular shapes. Additional challenges arise when data are collected via UAS as high-resolution aerial images or videos; an ample solution must provide reasonable accuracy with low delays. In this paper, we examined 4K ( 3840 × 2160 ) videos collected by UAS from a controlled burn and created a set of labeled video sets to be shared for public use. We introduce a coarse-to-fine framework to auto-detect wildfires that are sparse, small, and irregularly-shaped. The coarse detector adaptively selects the sub-regions that are likely to contain the objects of interest while the fine detector passes only the details of the sub-regions, rather than the entire 4K region, for further scrutiny. The proposed two-phase learning therefore greatly reduced time overhead and is capable of maintaining high accuracy. Compared against the real-time one-stage object backbone of YoloV3, the proposed methods improved the mean average precision(mAP) from 0 . 29 to 0 . 67 , with an average inference speed of 7.44 frames per second. Limitations and future work are discussed with regard to the design and the experiment results.
Highlights
Wildfire is one of the most common hazardous threats to human society
We propose an Adaptive sub-Region Select Block (ARSB) to extract a rough area that contains the objects from high resolution images
We summarize related object detection methods using deep learning methods, and review machine learning and deep learning methods used in wildfire detection
Summary
Wildfire is one of the most common hazardous threats to human society. According to the 2017 report from National Fire Protection Association [1], 3400 people died in United States wildfires with associated property damage estimated at around 23 billion USD. To face the growing threat of wildfire, fire fighting crews and first-responders rely on different ways to combat, control, and eliminate the threat of wildfire. Among the methods and tools available, Unmanned Aerial Systems (UAS), commonly referred to as drones, are seeing increasing use in supporting ground crews in fire events [2,3]. UAS are a powerful tool in wildfire because of their ability to deploy rapidly and into areas where manned aircraft cannot.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call