Dimensionality-varied convolutional neural network for spectral-spatial classification of hyperspectral data

Wanjun Liu; Xuejian Liang; Haicheng Qu

doi:10.1117/12.2295865

15 November 2017 Dimensionality-varied convolutional neural network for spectral-spatial classification of hyperspectral data

Wanjun Liu, Xuejian Liang, Haicheng Qu

Author Affiliations +

Proceedings Volume 10605, LIDAR Imaging Detection and Target Recognition 2017; 106053S (2017) https://doi.org/10.1117/12.2295865
Event: LIDAR Imaging Detection and Target Recognition 2017, 2017, Changchun, China

Abstract

Hyperspectral image (HSI) classification is one of the most popular topics in remote sensing community. Traditional and deep learning-based classification methods were proposed constantly in recent years. In order to improve the classification accuracy and robustness, a dimensionality-varied convolutional neural network (DVCNN) was proposed in this paper. DVCNN was a novel deep architecture based on convolutional neural network (CNN). The input of DVCNN was a set of 3D patches selected from HSI which contained spectral-spatial joint information. In the following feature extraction process, each patch was transformed into some different 1D vectors by 3D convolution kernels, which were able to extract features from spectral-spatial data. The rest of DVCNN was about the same as general CNN and processed 2D matrix which was constituted by by all 1D data. So that the DVCNN could not only extract more accurate and rich features than CNN, but also fused spectral-spatial information to improve classification accuracy. Moreover, the robustness of network on water-absorption bands was enhanced in the process of spectral-spatial fusion by 3D convolution, and the calculation was simplified by dimensionality varied convolution. Experiments were performed on both Indian Pines and Pavia University scene datasets, and the results showed that the classification accuracy of DVCNN improved by 32.87% on Indian Pines and 19.63% on Pavia University scene than spectral-only CNN. The maximum accuracy improvement of DVCNN achievement was 13.72% compared with other state-of-the-art HSI classification methods, and the robustness of DVCNN on water-absorption bands noise was demonstrated.

Citation Download Citation

Wanjun Liu, Xuejian Liang, and Haicheng Qu "Dimensionality-varied convolutional neural network for spectral-spatial classification of hyperspectral data", Proc. SPIE 10605, LIDAR Imaging Detection and Target Recognition 2017, 106053S (15 November 2017); https://doi.org/10.1117/12.2295865

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available