Multiscale Spatial-Spectral Convolutional Network with Image-Based Framework for Hyperspectral Imagery Classification

Ximin Cui,Bing Zhang,Dong Yang,Lianru Gao,Ke Zheng,Jinchang Ren

doi:10.3390/rs11192220

Abstract

Jointly using spatial and spectral information has been widely applied to hyperspectral image (HSI) classification. Especially, convolutional neural networks (CNN) have gained attention in recent years due to their detailed representation of features. However, most of CNN-based HSI classification methods mainly use patches as input classifier. This limits the range of use for spatial neighbor information and reduces processing efficiency in training and testing. To overcome this problem, we propose an image-based classification framework that is efficient and straightforward. Based on this framework, we propose a multiscale spatial-spectral CNN for HSIs (HyMSCN) to integrate both multiple receptive fields fused features and multiscale spatial features at different levels. The fused features are exploited using a lightweight block called the multiple receptive field feature block (MRFF), which contains various types of dilation convolution. By fusing multiple receptive field features and multiscale spatial features, the HyMSCN has comprehensive feature representation for classification. Experimental results from three real hyperspectral images prove the efficiency of the proposed framework. The proposed method also achieves superior performance for HSI classification.

Highlights

Hyperspectral image (HSI) has attracted a lot of attention in recent years since it has hundreds of continuous observation bands throughout the electromagnetic spectrum, ranging from visible to near-infrared wavelengths
Hyperspectral image is characterized by an abundance of spectral features and spatial structure information
It has been demonstrated that convolutional neural networks have a strong ability to extract spatial-spectral features for classification and feature representation

Summary

Introduction

Hyperspectral image (HSI) has attracted a lot of attention in recent years since it has hundreds of continuous observation bands throughout the electromagnetic spectrum, ranging from visible to near-infrared wavelengths. HSI has been used in many applications due to its high-dimensionality and distinct spectral features [1,2,3]. Supervised classification is one of the most critical applications and is widely used in remote sensing. Spectral-based classification methods typically only measure the spectral characteristics of objects and ignore spatial neighborhood information [4]. Hyperspectral image classification (HSIC) can be improved by considering both spatial and spectral information [5]. The multiscale spatial-spectral classification method is well adapted for HSI since different scale regions contain complementary but interconnected information for classification

Methods

Results

Discussion

Conclusion