Spectral-Spatial Hyperspectral Image Classification Using Robust Dual-Stage Spatial Embedding

Peng Shan,Wentao Fu,Zhenqiang Li,Yi Li

doi:10.1109/access.2021.3099631

Abstract

Recently, many spectral-special classification models have emerged one after another in the remote sensing community. These models aim to introduce the spatial information of the pixel to improve the accuracy of the class attribute of the pixel. However, for the spectral-spatial classification algorithms, not all pixels need to introduce the corresponding spatial information since the use of a large amount of spatial information has a costly time. To solve this problem, this paper proposes a robust dual-stage spatial embedding (RDSSE) model for spectral-spatial classification of hyperspectral image, which is composed of the following several main steps: First, an over-segmentation algorithm is employed to cluster original hyperspectral image into many superpixel blocks with shape adaptive characteristics. Then, we design a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> -peak criterion to fuse the spectral feature of pixels within and between superpixels. Next, a low time-consumption spectral classifier is introduced to conduct primary classification for a testing pixel to achieve the corresponding probability distribution. Specifically, the difference between the probability of the largest class and that of the second-largest class is served as class confidence. Finally, the predicted label of the low-confidence testing pixels is reclassified based on a high-accuracy spectral-spatial classification method. Experimental results on several real images illustrated that the proposed RDSSE method can obtain superior performance with respect to several competitive methods.

Highlights

H IGH spectral resolution images are available increasingly with hyperspectral satellite sensors, such as Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) [1]
Experiments on public data sets illustrated that the SuperPCA method significantly outperforms the conventional principal component analysis (PCA)-based dimensionality reduction baselines for hyperspectral image (HSI) classification
Indian Pines: The Indian Pines image is from the Indian Pines test site in northwest Indiana, which was captured by the airborne visible/infrared imaging spectrometer (AVIRIS) sensor

Summary

Introduction

H IGH spectral resolution images are available increasingly with hyperspectral satellite sensors, such as Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) [1]. The HSI classification technology has been studied by a large number of researchers and applied to practical applications such as mineral exploration [14] and precision agriculture [15]. In these applications, supervised pixel-wise classifiers, e.g., support vector machines (SVM) [16], extreme learning machine (ELM) [17], sparse representation (SR) learning [18]–[23], active learning methods [24]– [26], and kernel-based techniques [27]–[29], have demonstrated very good performances in terms of interpretation of hyperspectral data [30].

Methods

Results

Conclusion