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

• Main Authors: Jianhui Zhao, Erqian Dong, Mingui Sun, Wenyan Jia, Dengyi Zhang, Zhiyong Yuan
• Format: Article
• Language: English
• Published: Hindawi Limited 2013-01-01
• Series: The Scientific World Journal
• Online Access: http://dx.doi.org/10.1155/2013/572393

A novel wildfire segmentation algorithm is proposed with the help of sample training based 2D histogram θ-division and minimum error. Based on minimum error principle and 2D color histogram, the θ-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 evaluate θ-division segmentations, and the optimal angle θ is 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 both θ-division and other segmentation methods such as GMM. Our approach is tested on real images, and the experiments prove its efficiency for wildfire segmentation.