A deep learning framework for hyperspectral image classification using spatial pyramid pooling

TLDR

DCNNs are robust to distortion but extract features at a single scale, limiting their ability to handle large‑scale object variance. The authors present a deep learning framework for spectral–spatial classification of hyperspectral images. The framework merges spectral and spatial features using stacked autoencoders for dimensionality reduction, deep convolutional neural networks for rich feature learning, spatial pyramid pooling to produce fixed‑length spatial representations, and a logistic regression classifier. Experiments on widely used hyperspectral datasets show that classifiers built with this framework achieve competitive performance.

Abstract

In this letter, a new deep learning framework for spectral–spatial classification of hyperspectral images is presented. The proposed framework serves as an engine for merging the spatial and spectral features via suitable deep learning architecture: stacked autoencoders (SAEs) and deep convolutional neural networks (DCNNs) followed by a logistic regression (LR) classifier. In this framework, SAEs is aimed to get useful high-level features for the one-dimensional features which is suitable for the dimension reduction of spectral features, while DCNNs can learn rich features from the training data automatically and has achieved state-of-the-art performance in many image classification databases. Though the DCNNs has shown robustness to distortion, it only extracts features of the same scale, and hence is insufficient to tolerate large-scale variance of object. As a result, spatial pyramid pooling (SPP) is introduced into hyperspectral image classification for the first time by pooling the spatial feature maps of the top convolutional layers into a fixed-length feature. Experimental results with widely used hyperspectral data indicate that classifiers built in this deep learning-based framework provide competitive performance.