Spatial-spectral classification with local regional filter and Markov random field

This paper presents an improved spatial-spectral classification method combining local average filter (LAF) and Markov Random Field (MRF) model. LAF is used for spatial-spectral feature generation for classification, and MRF is for after-classification context analysis. The proposed method utilizes spatial and information before- and after-classification, for a more exquisite incorporation of the spatial information in different levels. Classification is done with the classical support vector machine (SVM) classifier. Experimental results demonstrate the improvement from the proposed LAF-SVM-MRF over the LAF-SVM considering before-classification spatial features and SVM-MRF with after-classification spatial features.

[1]  Paolo Gamba,et al.  A collection of data for urban area characterization , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[2]  Qian Du,et al.  Hyperspectral image classification with improved local-region filters , 2014 .

[3]  Johannes R. Sveinsson,et al.  Classification of hyperspectral data from urban areas based on extended morphological profiles , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Qian Du,et al.  An efficient spatial-spectral classification method for hyperspectral imagery , 2014, Sensing Technologies + Applications.

[5]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[7]  Johannes R. Sveinsson,et al.  Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles , 2008, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[8]  James E. Fowler,et al.  Hyperspectral Image Classification Using Gaussian Mixture Models and Markov Random Fields , 2014, IEEE Geoscience and Remote Sensing Letters.