1.China University of Geosciences(Beijing),School of the Earth Sciences and Resources,Beijing 100083,China;2.China Aero Geophysical Survey and Remote Sensing Center for Land and Resources,Beijing 100083,China
The parallelepiped classifier (PC),minimum distance classifier (MDC),Maximum Likelihood Classifier (MLC),Neural network (NN) and,especially,the newly developed Support Vector Machines (SVM) were assessed in the object-based image analysis of VHSR data. The impacts of kernel configuration on the performance of the SVM and of the selection of training data of the four classifiers were also evaluated. The result reveals that SVM can improve the accuracy significantly,and is by far more stable than other algorithms in the classification of VHSR data based on OBIA.
于海洋, 甘甫平, 武法东, 党福星. VHSR图像基于分割对象分类器性能评价[J]. 国土资源遥感, 2008, 20(2): 30-34.
YU Hai-Yang, GAN Fu-Ping, WU Fa-Dong, DANG Fu-Xing. THE PERFORMANCE OF OBJECT-BASED CLASSIFIERS IN THE CLASSIFICATION OF VHSR IMAGE. REMOTE SENSING FOR LAND & RESOURCES, 2008, 20(2): 30-34.