Going Deeper with Contextual CNN for Hyperspectral Image Classification

TL;DR

This paper introduces a deeper, wider convolutional neural network that effectively captures local spatio-spectral relationships for hyperspectral image classification, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a novel contextual deep CNN with multi-scale filters to jointly exploit local spatio-spectral information for improved hyperspectral image classification.

Findings

Enhanced classification accuracy on Indian Pines, Salinas, and Pavia datasets.

Outperforms current state-of-the-art methods.

Effective joint spatio-spectral feature extraction.

Abstract

In this paper, we describe a novel deep convolutional neural network (CNN) that is deeper and wider than other existing deep networks for hyperspectral image classification. Unlike current state-of-the-art approaches in CNN-based hyperspectral image classification, the proposed network, called contextual deep CNN, can optimally explore local contextual interactions by jointly exploiting local spatio-spectral relationships of neighboring individual pixel vectors. The joint exploitation of the spatio-spectral information is achieved by a multi-scale convolutional filter bank used as an initial component of the proposed CNN pipeline. The initial spatial and spectral feature maps obtained from the multi-scale filter bank are then combined together to form a joint spatio-spectral feature map. The joint feature map representing rich spectral and spatial properties of the hyperspectral image is then fed through a fully convolutional network that eventually predicts the corresponding label of each pixel vector. The proposed approach is tested on three benchmark datasets: the Indian Pines dataset, the Salinas dataset and the University of Pavia dataset. Performance comparison shows enhanced classification performance of the proposed approach over the current state-of-the-art on the three datasets.