Crop extraction combined with airborne hyperspectral images and deep convolutional neural network

Qiang Li; Zhitao Shao; Yaping Liu; Tian Li; Xiyao Wang; Junchuan Yu

doi:10.1117/12.2607131

24 November 2021 Crop extraction combined with airborne hyperspectral images and deep convolutional neural network

Qiang Li, Zhitao Shao, Yaping Liu, Tian Li, Xiyao Wang, Junchuan Yu

Author Affiliations +

Proceedings Volume 12065, AOPC 2021: Optical Sensing and Imaging Technology; 120653T (2021) https://doi.org/10.1117/12.2607131
Event: Applied Optics and Photonics China 2021, 2021, Beijing, China

Abstract

Hyperspectral Images (HSI) contains hundreds of spectral information, which provides detailed spectral information, has an inherent advantage in land cover classification. Due to the shortage of spatial resolution of spaceborne hyperspectral data, previous study mainly focused on studying the natural spectral signature of the target and distinguished different object categories through hand-crafted spectral rules or supervised learning-based models. With the increase of spatial resolution of hyperspectral data, the study of joint characteristics extraction of the spectrum and spatial information is of great significance. Benefit from the remarkable learning ability of convolutional neural networks (CNN), deep learning methods can better realize the extraction and fusion of spatial and spectral features. In this paper, a new airborne HSI from Liaozhong area of Shenyang with the sub-meter resolution is introduced. Different data combinations and CNN-based methods are employed in the experiment to illustrate which factors are effective in improving the accuracy of hyperspectral classification. The experimental results show that the double-branch structure is more coducive to improving the classification accuracy, and the principal component analysis (PCA) methods is more effective than hand-crafted band selection in dimension reducing while maintaining accuracy.

Citation Download Citation

Qiang Li, Zhitao Shao, Yaping Liu, Tian Li, Xiyao Wang, and Junchuan Yu "Crop extraction combined with airborne hyperspectral images and deep convolutional neural network", Proc. SPIE 12065, AOPC 2021: Optical Sensing and Imaging Technology, 120653T (24 November 2021); https://doi.org/10.1117/12.2607131

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

RGB color model

Hyperspectral imaging

Data modeling

Spatial resolution

Principal component analysis

Convolutional neural networks

Image classification

Show All Keywords

Keywords/Phrases

Search In:

Publication Years