Thematic information detection for remote sensing image using SVM kernel functions

Thematic information detection is an important application of remote sensing image. Support vector machine (SVM) has been widely used in MODIS remote sensing detection. However, the difficulty of SVM application is how to select the suitable kernel function for remote sensing image. In this paper, the Sangeang Api volcanic ash cloud on May 30, 2014 is taken as an example, and the linear, polynomial, radial basis function (RBF) and sigmoid kernel functions are used to detect volcanic ash cloud from MODIS remote sensing image. And then the detected volcanic ash cloud information is evaluated in terms of simulation experiment and contrastive precision accuracy. The results show that the RBF kernel function is more effective and more robust for MODIS remote sensing image.