Shorten Spatial-spectral RNN with Parallel-GRU for Hyperspectral Image Classification

10/30/2018
by   Haowen Luo, et al.
6

Convolutional neural networks (CNNs) attained a good performance in hyperspectral sensing image (HSI) classification, but CNNs consider spectra as orderless vectors. Therefore, considering the spectra as sequences, recurrent neural networks (RNNs) have been applied in HSI classification, for RNNs is skilled at dealing with sequential data. However, for a long-sequence task, RNNs is difficult for training and not as effective as we expected. Besides, spatial contextual features are not considered in RNNs. In this study, we propose a Shorten Spatial-spectral RNN with Parallel-GRU (St-SS-pGRU) for HSI classification. A shorten RNN is more efficient and easier for training than band-by-band RNN. By combining converlusion layer, the St-SSpGRU model considers not only spectral but also spatial feature, which results in a better performance. An architecture named parallel-GRU is also proposed and applied in St-SS-pGRU. With this architecture, the model gets a better performance and is more robust.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

research
02/28/2019

Cascaded Recurrent Neural Networks for Hyperspectral Image Classification

By considering the spectral signature as a sequence, recurrent neural ne...
research
09/13/2015

Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks

Existing deep convolutional neural networks (CNNs) have shown their grea...
research
06/11/2019

Band Attention Convolutional Networks For Hyperspectral Image Classification

Redundancy and noise exist in the bands of hyperspectral images (HSIs). ...
research
06/09/2019

Pixel DAG-Recurrent Neural Network for Spectral-Spatial Hyperspectral Image Classification

Exploiting rich spatial and spectral features contributes to improve the...
research
04/01/2021

SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification

Hyperspectral Image (HSI) classification using Convolutional Neural Netw...
research
05/09/2019

Feature Extraction and Classification Based on Spatial-Spectral ConvLSTM Neural Network for Hyperspectral Images

In recent years, deep learning has presented a great advance in hyperspe...
research
08/11/2016

Recurrent Neural Networks to Correct Satellite Image Classification Maps

While initially devised for image categorization, convolutional neural n...

Please sign up or login with your details

Forgot password? Click here to reset