Wildfire aerial thermal image segmentation using unsupervised methods: a multilayer level set approach.

Background and aims: Infrared thermal images of a propagating wildfire taken by manned or unmanned aerial vehicles can help firefighting authorities with combat planning. Segmenting these images into regions of different fire temperatures is a necessary step to measure the fire perimeter and determine the location of the fire front. Methods: This work proposes a multilayer segmentation method based on level sets, which have the property of handling topology, making them suitable to segment images that contain scattered fire areas. The experimental results were compared using hand-drawn labels over a set of images provided by the Portuguese Air Force as ground truth. These labels were carefully drawn by the authors to ensure that they complied with the requirements indicated by the Portuguese National Authority for Emergency and Civil Protection. The proposed method was optimised to ensure contour smoothness and reliability, as well as reduce computation time. Key results: The proposed method can surpass other common unsupervised methods in terms of intersection over union, although it has not yet been able to perform real-time segmentation. Conclusions: Although falling out of use in relation to supervised and deep learning methods, unsupervised segmentation can still be very useful when annotated datasets are unavailable. The infrared thermal images of a propagating wildfire taken by aerial vehicles can help firefighting authorities in combat planning. We propose a method that is able to separate the wildfire into different temperature regions, which facilitates identification of the fire perimeter and location of the active front. (This paper is part of a Special Issue that includes papers on research presented at the IX International Conference on Forest Fire Research, Coimbra, Portugal, November 2022.) [ABSTRACT FROM AUTHOR]