# Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification

## TL;DR

This paper introduces a bidirectional convolutional LSTM network that effectively learns spectral and spatial features from hyperspectral images, significantly improving classification accuracy over existing methods.

## Contribution

The paper presents a novel Bi-CLSTM framework combining spectral sequence learning with spatial convolution for hyperspectral image classification.

## Key findings

- Bi-CLSTM outperforms state-of-the-art methods in classification accuracy.
- The bidirectional recurrent structure enhances spectral feature extraction.
- The framework demonstrates robustness across multiple hyperspectral datasets.

## Abstract

This paper proposes a novel deep learning framework named bidirectional-convolutional long short term memory (Bi-CLSTM) network to automatically learn the spectral-spatial feature from hyperspectral images (HSIs). In the network, the issue of spectral feature extraction is considered as a sequence learning problem, and a recurrent connection operator across the spectral domain is used to address it. Meanwhile, inspired from the widely used convolutional neural network (CNN), a convolution operator across the spatial domain is incorporated into the network to extract the spatial feature. Besides, to sufficiently capture the spectral information, a bidirectional recurrent connection is proposed. In the classification phase, the learned features are concatenated into a vector and fed to a softmax classifier via a fully-connected operator. To validate the effectiveness of the proposed Bi-CLSTM framework, we compare it with several state-of-the-art methods, including the CNN framework, on three widely used HSIs. The obtained results show that Bi-CLSTM can improve the classification performance as compared to other methods.