Object Classification via Feature Fusion Based Marginalized Kernels
Lists
Only you see this
Abstract
Various types of features can be extracted from very high resolution remote sensing images for object classification. It has been widely acknowledged that the classification performance can benefit from proper feature fusion. In this letter, we propose a softmax regression-based feature fusion method by learning distinct weights for different features. Our fusion method enables the estimation of object-to-class similarity measures and the conditional probabilities that each object belongs to different classes. Moreover, we introduce an approximate method for calculating the class-to-class similarities between different classes. Finally, the obtained fusion and similarity information are integrated into a marginalized kernel to build a support vector machine classifier. The advantages of our method are validated on QuickBird imagery.
BibTeX
@article{bai2015object,
author = {Xiao Bai and Chuntian Liu and Peng Ren and Jun Zhou and Huijun Zhao and Yun Su},
title = {{Object Classification via Feature Fusion Based Marginalized Kernels}},
journal = {IEEE Geosci. Remote. Sens. Lett.},
year = {2015},
doi = {10.1109/lgrs.2014.2322953},
}Loading related content...