A Support Vector Machine-Based Particle Filter For Improved Land Cover Classification Applied To Modis Data

There are two important factors to improve the accuracy of the support vector machine(SVM) classifier. First, selected training samples should uniquely represent each class. Second, SVM training parameters which are pre-defined by the user should be suitable for training samples to obtain satisfied results of the SVM classifier. The proposed method of this paper presents a technique to adjust the SVM training parameters by particle filter algorithm. The parameters were tuned based on the weight of particles in each iteration time of particle filter processes. An experiment implemented annual mean of Normalized Difference Vegetation Index and Enhanced Vegetation Index extracted from the Moderate Resolution Imaging Spectroradiometer data with 250-m resolution in a study area of Poyang Lake, China, during the year of 2009. The proposed method for adjusting the SVM training parameters provided the an improved performance SVM classification model.