Most traditional approaches classify hyperspectral image (HSI) pixels relying only on the spectral values of the input channels. However, the spatial context around a pixel is also very important and can enhance the classification performance. In order to effectively exploit and fuse both the spatial context and spectral structure, we propose a novel two-stream deep architecture for HSI classification. The proposed method consists of a two-stream architecture and a novel fusion scheme. In the two-stream architecture, one stream employs the stacked denoising autoencoder to encode the spectral values of each input pixel, and the other stream takes as input the corresponding image patch and deep convolutional neural networks are employed to process the image patch. In the fusion scheme, the prediction probabilities from two streams are fused by adaptive class-specific weights, which can be obtained by a fully connected layer. Finally, a weight regularizer is added to the loss function to alleviate the overfitting of the class-specific fusion weights. Experimental results on real HSIs demonstrate that the proposed two-stream deep architecture can achieve competitive performance compared with the state-of-the-art methods.

Two-Stream Deep Architecture for Hyperspectral Image Classification / Hao, Siyuan; Wang, Wei; Ye, Yuanxin; Nie, Tingyuan; Bruzzone, Lorenzo. - In: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. - ISSN 0196-2892. - STAMPA. - 56:4(2018), pp. 2349-2361. [10.1109/TGRS.2017.2778343]

Two-Stream Deep Architecture for Hyperspectral Image Classification

Hao, Siyuan;Wang, Wei;Ye, Yuanxin;Bruzzone, Lorenzo
2018-01-01

Abstract

Most traditional approaches classify hyperspectral image (HSI) pixels relying only on the spectral values of the input channels. However, the spatial context around a pixel is also very important and can enhance the classification performance. In order to effectively exploit and fuse both the spatial context and spectral structure, we propose a novel two-stream deep architecture for HSI classification. The proposed method consists of a two-stream architecture and a novel fusion scheme. In the two-stream architecture, one stream employs the stacked denoising autoencoder to encode the spectral values of each input pixel, and the other stream takes as input the corresponding image patch and deep convolutional neural networks are employed to process the image patch. In the fusion scheme, the prediction probabilities from two streams are fused by adaptive class-specific weights, which can be obtained by a fully connected layer. Finally, a weight regularizer is added to the loss function to alleviate the overfitting of the class-specific fusion weights. Experimental results on real HSIs demonstrate that the proposed two-stream deep architecture can achieve competitive performance compared with the state-of-the-art methods.
2018
4
Hao, Siyuan; Wang, Wei; Ye, Yuanxin; Nie, Tingyuan; Bruzzone, Lorenzo
Two-Stream Deep Architecture for Hyperspectral Image Classification / Hao, Siyuan; Wang, Wei; Ye, Yuanxin; Nie, Tingyuan; Bruzzone, Lorenzo. - In: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. - ISSN 0196-2892. - STAMPA. - 56:4(2018), pp. 2349-2361. [10.1109/TGRS.2017.2778343]
File in questo prodotto:
File Dimensione Formato  
08240968.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 5.01 MB
Formato Adobe PDF
5.01 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/193698
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 114
  • ???jsp.display-item.citation.isi??? 109
  • OpenAlex ND
social impact