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

• Published in: Remote sensing (Basel, Switzerland) Vol. 12; no. 2; p. 280
• Main Authors: Liu, Liqin, Shi, Zhenwei, Pan, Bin, Zhang, Ning, Luo, Huanlin, Lan, Xianchao
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2020
• Subjects: Annotations; Classification; Deep learning; Feature extraction; fully convolutional networks (fcn); hyperspectral image classification; hyperspectral imagery; Hyperspectral imaging; Image classification; Machine learning; multiscale spatial feature; Networks; Neural networks; Pixels; Principal components analysis; processing technology; Remote sensing; Semantics; Support vector machines; virtual rgb image
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs12020280

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.