Abstract
Recently, the sparse representation based classification methods have received particular attention in the classification of hyperspectral imagery. However, current sparse representation based classification models have not considered all the test pixels simultaneously. In this paper, we propose a hyperspectral classification method with spatial filtering and norm (SFL) that can deal with all the test pixels simultaneously. The norm regularization is used to extract relevant training samples among the whole training data set with joint sparsity. In addition, the norm loss function is adopted to make it robust for samples that deviate significantly from the rest of the samples. Moreover, to take the spatial information into consideration, a spatial filtering step is implemented where all the training and testing samples are spatially averaged with its nearest neighbors. Furthermore, the non-negative constraint is added to the sparse representation matrix motivated by hyperspectral unmixing. Finally, the alternating direction method of multipliers is used to solve SFL. Experiments on real hyperspectral images demonstrate that the proposed SFL method can obtain better classification performance than some other popular classifiers.
Highlights
Over the past few decades, hyperspectral imagery has been widely used in different remote sensing applications owing to its high-resolution spectral information of the materials in the scene [1,2,3].Various hyperspectral image classification techniques have been presented for a lot of real applications including material recognition, urban mapping and so on [4,5,6,7,8].To date, a lot of hyperspectral image classification methods have been presented
Since the spectral signatures of neighboring pixels are highly correlated, which make them belong to the same material with high probability, we adopt the simple strategy in [47] to exploit the local continuity, and all the training and testing samples are spatially averaged with their nearest neighbors to take the spatial information into consideration, which can be seen as spatial filtering
“`2,1 +`2,1 +SF+NC” and “`2,1 +`2,1 ” generally have better overall accuracy than “F+`2,1 +SF+NC” and “F+`2,1 ”, respectively, which demonstrate that the2,1 norm loss function is more robust for outliers than F norm loss function
Summary
Over the past few decades, hyperspectral imagery has been widely used in different remote sensing applications owing to its high-resolution spectral information of the materials in the scene [1,2,3]. To take the spatial information into consideration, a novel convolutional neural networks framework for hyperspectral image classification using both spectral and spatial features was presented [39]. To overcome the imbalance between dimensionality and the number of available training samples, Ghamisi et al proposed a self-improving band selection based convolutional neural networks method for hyperspectral image classification [41]. Shi et al proposed a 3D convolutional neural networks (3D-CNN) method for hyperspectral image classification that can take both the spectral and spatial information into consideration [45]. Inspired by the theoretical work in [46], in this paper, we propose a hyperspectral classification method with spatial filtering and norm (SFL) to deal with all the test samples simultaneously, which can take much less time and obtain comparable good or better classification performance. Experiments on real hyperspectral images demonstrate that the proposed SFL method can obtain better classification performance than some other popular classifiers
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
