Volume XLII-4/W18
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W18, 63–69, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W18-63-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W18, 63–69, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W18-63-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

  18 Oct 2019

18 Oct 2019

VIRTUAL TRAINING SAMPLE GENERATION BY GENERATIVE ADVERSARIAL NETWORKS FOR HYPERSPECTRAL IMAGES CLASSIFICATION

T. Alipourfard and H. Arefi T. Alipourfard and H. Arefi
  • School of Surveying and Geospatial Engineering, University of Tehran, Tehran, Iran

Keywords: Deep Learning, Hyperspectral Image, Convolutional Neural Network, Generative Adversarial Networks

Abstract. Convolutional Neural Networks (CNNs) as a well-known deep learning technique has shown a remarkable performance in visual recognition applications. However, using such networks in the area of hyperspectral image classification is a challenging and time-consuming process due to the high dimensionality and the insufficient training samples. In addition, Generative Adversarial Networks (GANs) has attracted a lot of attentions in order to generate virtual training samples. In this paper, we present a new classification framework based on integration of multi-channel CNNs and new architecture for generator and discriminator of GANs to overcome Small Sample Size (SSS) problem in hyperspectral image classification. Further, in order to reduce the computational cost, the methods related to the reduction of subspace dimension were proposed to obtain the dominant feature around the training sample to generate meaningful training samples from the original one. The proposed framework overcomes SSS and overfitting problem in classifying hyperspectral images. Based on the experimental results on real and well-known hyperspectral benchmark images, our proposed strategy improves the performance compared to standard CNNs and conventional data augmentation strategy. The overall classification accuracy in Pavia University and Indian Pines datasets was 99.8% and 94.9%, respectively.