中国邮电高校学报(英文版) ›› 2020, Vol. 27 ›› Issue (4): 8-16.doi: 10.19682/j.cnki.1005-8885.2020.0032

• Artificial Intelligence • 上一篇    下一篇

Generative adversarial networks for hyperspectral image spatial super-resolution

蒋伊琳 邵然 唐三强   

  1. 哈尔滨工程大学
  • 收稿日期:2020-02-28 修回日期:2020-08-13 出版日期:2020-08-31 发布日期:2020-08-31
  • 通讯作者: 邵然 E-mail:shaoran@hrbeu.edu.cn

Generative adversarial networks for hyperspectral image spatial super-resolution

Jiang Yilin, Shao Ran, Tang Sanqiang   

  • Received:2020-02-28 Revised:2020-08-13 Online:2020-08-31 Published:2020-08-31
  • Contact: Shao Ran E-mail:shaoran@hrbeu.edu.cn

摘要:

It is becoming increasingly easier to obtain more abundant supplies for hyperspectral images ( HSIs). Despite this, achieving high resolution is still critical. In this paper, a method named hyperspectral images super-resolution generative adversarial network ( HSI-RGAN ) is proposed to enhance the spatial resolution of HSI without decreasing its spectral resolution. Different from existing methods with the same purpose, which are based on convolutional neural networks ( CNNs) and driven by a pixel-level loss function, the new generative adversarial network (GAN) has a redesigned framework and a targeted loss function. Specifically, the discriminator uses the structure of the relativistic discriminator, which provides feedback on how much the generated HSI looks like the ground truth. The generator achieves more authentic details and textures by removing the place of the pooling layer and the batch normalization layer and presenting smaller filter size and two-step upsampling layers. Furthermore, the loss function is improved to specially take spectral distinctions into account to avoid artifacts and minimize potential spectral distortion, which may be introduced by neural networks. Furthermore, pre-training with the visual geometry group (VGG) network helps the entire model to initialize more easily. Benefiting from these changes, the proposed method obtains significant advantages compared to the original GAN. Experimental results also reveal that the proposed method performs better than several state-of-the-art methods.

关键词:

HSI-SRGAN, hyperspectral image, super-resolution

Abstract: It is becoming increasingly easier to obtain more abundant supplies for hyperspectral images ( HSIs). Despite this, achieving high resolution is still critical. In this paper, a method named hyperspectral images super-resolution generative adversarial network ( HSI-RGAN ) is proposed to enhance the spatial resolution of HSI without decreasing its spectral resolution. Different from existing methods with the same purpose, which are based on convolutional neural networks ( CNNs) and driven by a pixel-level loss function, the new generative adversarial network (GAN) has a redesigned framework and a targeted loss function. Specifically, the discriminator uses the structure of the relativistic discriminator, which provides feedback on how much the generated HSI looks like the ground truth. The generator achieves more authentic details and textures by removing the place of the pooling layer and the batch normalization layer and presenting smaller filter size and two-step upsampling layers. Furthermore, the loss function is improved to specially take spectral distinctions into account to avoid artifacts and minimize potential spectral distortion, which may be introduced by neural networks. Furthermore, pre-training with the visual geometry group (VGG) network helps the entire model to initialize more easily. Benefiting from these changes, the proposed method obtains significant advantages compared to the original GAN. Experimental results also reveal that the proposed method performs better than several state-of-the-art methods.

Key words: HSI-SRGAN, hyperspectral image, super-resolution

中图分类号: