Next Article in Journal
Harmonization of Landsat and Sentinel 2 for Crop Monitoring in Drought Prone Areas: Case Studies of Ninh Thuan (Vietnam) and Bekaa (Lebanon)
Previous Article in Journal
Sentinel-2 Sharpening via Parallel Residual Network
Previous Article in Special Issue
Do Game Data Generalize Well for Remote Sensing Image Segmentation?
Open AccessArticle

Multiscale Deep Spatial Feature Extraction Using Virtual RGB Image for Hyperspectral Imagery Classification

by Liqin Liu 1,2,3, Zhenwei Shi 1,2,3,*, Bin Pan 4, Ning Zhang 5, Huanlin Luo 5 and Xianchao Lan 5
1
Image Processing Center, School of Astronautics, Beihang University, Beijing 100191, China
2
Beijing Key Laboratory of Digital Media, Beihang University, Beijing 100191, China
3
State Key Laboratory of Virtual Reality Technology and Systems, School of Astronautics, Beihang University, Beijing 100191, China
4
School of Statistics and Data Science, Nankai University, Tianjin 300071, China
5
Shanghai Aerospace Electronic Technology Institute, Shanghai 201109, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(2), 280; https://doi.org/10.3390/rs12020280
Received: 16 December 2019 / Revised: 7 January 2020 / Accepted: 13 January 2020 / Published: 15 January 2020
In recent years, deep learning technology has been widely used in the field of hyperspectral image classification and achieved good performance. However, deep learning networks need a large amount of training samples, which conflicts with the limited labeled samples of hyperspectral images. Traditional deep networks usually construct each pixel as a subject, ignoring the integrity of the hyperspectral data and the methods based on feature extraction are likely to lose the edge information which plays a crucial role in the pixel-level classification. To overcome the limit of annotation samples, we propose a new three-channel image build method (virtual RGB image) by which the trained networks on natural images are used to extract the spatial features. Through the trained network, the hyperspectral data are disposed as a whole. Meanwhile, we propose a multiscale feature fusion method to combine both the detailed and semantic characteristics, thus promoting the accuracy of classification. Experiments show that the proposed method can achieve ideal results better than the state-of-art methods. In addition, the virtual RGB image can be extended to other hyperspectral processing methods that need to use three-channel images. View Full-Text
Keywords: hyperspectral image classification; feature extraction; fully convolutional networks (FCN); virtual RGB image; multiscale spatial feature hyperspectral image classification; feature extraction; fully convolutional networks (FCN); virtual RGB image; multiscale spatial feature
Show Figures

Graphical abstract

MDPI and ACS Style

Liu, L.; Shi, Z.; Pan, B.; Zhang, N.; Luo, H.; Lan, X. Multiscale Deep Spatial Feature Extraction Using Virtual RGB Image for Hyperspectral Imagery Classification. Remote Sens. 2020, 12, 280.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop