Abstract
Spectral features cannot effectively reflect the differences among the ground objects and distinguish their boundaries in hyperspectral image (HSI) classification. Multi-scale feature extraction can solve this problem and improve the accuracy of HSI classification. The Gaussian pyramid can effectively decompose HSI into multi-scale structures, and efficiently extract features of different scales by stepwise filtering and downsampling. Therefore, this paper proposed a Gaussian pyramid based multi-scale feature extraction (MSFE) classification method for HSI. First, the HSI is decomposed into several Gaussian pyramids to extract multi-scale features. Second, we construct probability maps in each layer of the Gaussian pyramid and employ edge-preserving filtering (EPF) algorithms to further optimize the details. Finally, the final classification map is acquired by a majority voting method. Compared with other spectral-spatial classification methods, the proposed method can not only extract the characteristics of different scales, but also can better preserve detailed structures and the edge regions of the image. Experiments performed on three real hyperspectral datasets show that the proposed method can achieve competitive classification accuracy.
Highlights
Hyperspectral remote sensing technology can acquire spectral images of continuous bands to achieve accurate identification of surface objects
It can be seen that the classification performance of the support vector machine (SVM) is not very good compared with other comparison methods (e.g., extended morphological profiles (EMP), edge-preserving filtering (EPF), image fusion and recursive filtering (IFRF), joint sparse representation (JSR), superpixel-based classification via multiple kernels (SCMK), multiscale adaptive sparse representation (MASR), and multi-scale feature extraction (MSFE))
It can be observed that when the number of training samples changes, the proposed method significantly improved the classification accuracies in comparison with other approaches
Summary
Hyperspectral remote sensing technology can acquire spectral images of continuous bands to achieve accurate identification of surface objects. Effective feature extraction algorithms [40,41] and multifeature fusion [42,43] techniques have been developed in which the spectral-spatial characteristics of different materials in the image scene are more effectively represented. The region kernel is designed to be a linear combination of multiscale box kernels, which can handle the HSI regions with arbitrary shape and size These methods consider the spatial context information of the pixel and surrounding pixels while using the spectral information of the ground object for classification. Different kinds of multi-scale feature extraction methods were proposed to improve the accuracy of HSIs classification. This paper proposed a multi-scale feature extraction (MSFE) method for HSI classification.
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
