Sample Training Based Wildfire Segmentation by 2D Histogramθ-Division with Minimum Error

Abstract

A novel wildfire segmentation algorithm is proposed with the help of sample training based 2D histogramθ-division and minimum error. Based on minimum error principle and 2D color histogram, theθ-division methods were presented recently, but application of prior knowledge on them has not been explored. For the specific problem of wildfire segmentation, we collect sample images with manually labeled fire pixels. Then we define the probability function of error division to evaluateθ-division segmentations, and the optimal angleθis determined by sample training. Performances in different color channels are compared, and the suitable channel is selected. To further improve the accuracy, the combination approach is presented with bothθ-division and other segmentation methods such as GMM. Our approach is tested on real images, and the experiments prove its efficiency for wildfire segmentation.