Aerial Imagery Pile Burn Detection using Deep Learning

Abstract

Wildfires are one of the costliest and deadliest natural disasters around the globe, affecting millions of acres of forest resources and threatening the lives of human and animals. Thousands of forest fires across the globe results in serious damage to the environment. Further, industrial explosions, domestic fires, farm fires, and wildfires are huge problem that causes negative effects on the environment contributing significantly towards the issue of climate change. Damage caused by such incidents are time-sensitive and can be fatal resulting in a huge loss to life and property if not timely dealt with. Recent advances in aerial images show that they can be beneficial in wildfire studies. Among different technologies and methods for collecting aerial images, drones have been used recently for manual/automatic monitoring of potential risk areas. Images received from the drones can be processed using vision and machine learning techniques for automated and timely detection of fires thus shortening the response time and reducing the damage caused by the fire whilst minimizing the cost of firefighting. Automated vision-based fire detection has therefore become an important research topic in recent years. Desired properties of good vision-based fire detection are low false alarm rate, fast response time, and high accuracy. This thesis presents a comprehensive literature review of recent vision-based approaches for the automated detection of fire from images and videos. It also includes computing the area under the fire and planning to mitigate the fire. The literature has broadly been categorized into classic vision/machine learning-based approaches and deep learning-based approaches. Based on the comparison of these approaches using a variety of datasets and performance metrics, it has been observed that deep learning-based approaches generally yield better performance as compared to classic vision/machine learning-based techniques. In this research, we further explored various deep learning alternatives for accurate fire detection. A Yolov5-based deep learning model has been proposed in this research for efficient region-based detection and segmentation of fire. Pixel level segmentation is also performed using Mask RCNN to estimate the area under the fire so that planning can be done to mitigate with the fire. The problem of availability of limited labeled training data as compared to the training samples required for deep learning-based model training is mitigated through variety of preprocessing and augmentation techniques. Comparison with existing vision-based fire segmentation approaches on publicly available datasets show the improved performance of proposed approach as compared to the competitors.