A Novel Hyperspectral Remote Sensing Images Classification using Gaussian Processes with Conditional Random Fields

摘要：

Classification is an important task in Hyperspectral data analysis. Hyperspectral images show strong correlations across spatial and spectral neighbors. Theoretically, classifier designed with a joint spectral and spatial correlations can improve classification performance than classifier which only utilize one of the correlations. Gaussian Processes(GPs) have been used for Hyperspectral imagery classification successfully by exploiting spectral correlation. Meanwhile,conditional random fields(CRFs) classify image regions by incorporating neighborhood Spatial interactions in the labels as well as the observed data. In this paper, we make a combination of GPs and CRFs and propose a novel GPCRF classifier to exploit spectral and spatial interactions in Hyperspectral remote sensing images. Experiments on the realworld Hyperspectral image attest to the accuracy and robust of the proposed method.

作者: Futian Yao Yuntao Qian Zhenfang Hu Jiming Li

作者单位: College of Computer Science,Zhejiang University, HangZhou 310027,China

会议类型: 国际会议

会议名称: The 2010 International Conference on Intelligent Systems and Knowledge Engineering(第五届智能系统与知识工程国际会议)

会议地点: 杭州

会议语种:英文

页码: 197-202

在线出版日期: 2010-11-15（万方平台首次上网日期，不代表论文的发表时间）