顾及上下文信息的混合广义高斯密度模型遥感影像分类方法研究

基金项目: 国家“十一五”国防基础科研资助项目(A1420060213)

详细信息

A Remote Sensing Image Classification Method Based on Generalized Gaussian Mixture Model

¹School of Remote Sensing and Information Engineering,Wuhan University,129 Luoyu Road,Wuhan 430079,China;²Wuhan Geotechnical Engineering and Surveying Institute,209 Wansongyuan Road,Wuhan 430022,China

Funds: 国家“十一五”国防基础科研资助项目(A1420060213)

摘要: 提出了一种基于混合广义高斯密度模型(generalize Gaussian mixture model,GGMM),并顾及影像上下文信息的遥感影像分类方法。试验结果表明,该方法具有较强的鲁棒性,分类精度较传统的分类方法要好,在细节保持方面,较某些尺度上的面向对象的分类方法要好。
- 遥感影像分类 /
- 混合广义高斯密度模型 /
- 马尔可夫随机场模型
Abstract: Generalized Gaussian mixture model(GGMM) is used to classify remote sensing images.The experimental results show that the method can obtain higher accuracy than maximum likelihood classification,and obtain more structure details than eCognition on some scales.
- remote sensing image classification /
- generalized Gaussian mixture model /
- Markov random field(MRF)