Please use this identifier to cite or link to this item: http://hdl.handle.net/10662/20324
Title: Capsule networks for hyperspectral image classification
Authors: Paoletti Ávila, Mercedes Eugenia
Haut Hurtado, Juan Mario
Fernández Beltrán, Rubén
Plaza Miguel, Javier
Plaza, Antonio
Pla, Filiberto
Keywords: Imagen hiperespectral;Red neuronal convolucional;Redes de cápsulas;Hyperspectral imaging;Convolutional neural networks;Capsule networks
Issue Date: 2018
Publisher: IEEE
Abstract: Convolutional neural networks (CNNs) have recently exhibited an excellent performance in hyperspectral image classification tasks. However, the straightforward CNN-based network architecture still finds obstacles when effectively exploiting the relationships between hyperspectral imaging (HSI) features in the spectral-spatial domain, which is a key factor to deal with the high level of complexity present in remotely sensed HSI data. Despite the fact that deeper architectures try to mitigate these limitations, they also find challenges with the convergence of the network parameters, which eventually limit the classification performance under highly demanding scenarios. In this paper, we propose a new CNN architecture based on spectral-spatial capsule networks in order to achieve a highly accurate classification of HSIs while significantly reducing the network design complexity. Specifically, based on Hinton's capsule networks, we develop a CNN model extension that redefines the concept of capsule units to become spectral-spatial units specialized in classifying remotely sensed HSI data. The proposed model is composed by several building blocks, called spectral-spatial capsules, which are able to learn HSI spectral-spatial features considering their corresponding spatial positions in the scene, their associated spectral signatures, and also their possible transformations. Our experiments, conducted using five well-known HSI data sets and several state-of-the-art classification methods, reveal that our HSI classification approach based on spectral-spatial capsules is able to provide competitive advantages in terms of both classification accuracy and computational time.
URI: http://hdl.handle.net/10662/20324
ISSN: 0196-2892
Appears in Collections:DTCYC - Artículos

Files in This Item:
File Description SizeFormat 
TGRS_2018_2871782.pdf2,01 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons