Abstract
Thanks to the availability of large-scale data, deep Convolutional Neural Networks (CNNs) have witnessed success in various applications of computer vision. However, the performance of CNNs on Synthetic Aperture Radar (SAR) image classification is unsatisfactory due to the lack of well-labeled SAR data, as well as the differences in imaging mechanisms between SAR images and optical images. Therefore, this paper addresses the problem of SAR image classification by employing the Generative Adversarial Network (GAN) to produce more labeled SAR data. We propose special GANs for generating SAR images to be used in the training process. First, we incorporate the quadratic operation into the GAN, extending the convolution to make the discriminator better represent the SAR data; second, the statistical characteristics of SAR images are integrated into the GAN to make its value function more reasonable; finally, two types of parallel connected GANs are designed, one of which we call PWGAN, combining the Deep Convolutional GAN (DCGAN) and Wasserstein GAN with Gradient Penalty (WGAN-GP) together in the structure, and the other, which we call CNN-PGAN, applying a pre-trained CNN as a discriminator to the parallel GAN. Both PWGAN and CNN-PGAN consist of a number of discriminators and generators according to the number of target categories. Experimental results on the TerraSAR-X single polarization dataset demonstrate the effectiveness of the proposed method.
Highlights
Both PWGAN and Convolutional Neural Networks (CNNs)-PGAN consist of a number of discriminators and generators according to the number of target categories
We extended the convolution of the Generative Adversarial Network (GAN) with a quadratic term and incorporated Synthetic Aperture Radar (SAR) image features into the value function
We designed two types of GANs to generate SAR images that were more suitable for classification tasks
Summary
Synthetic Aperture Radar (SAR) has gained immense popularity for its unique imaging capabilities. SAR provides high-resolution images independent of daylight, cloud coverage, and almost all weather conditions [1]. SAR images are useful for a multitude of applications, including remote sensing of the Earth’s surface, crop identification in agriculture, and flood mapping for disaster monitoring. SAR image classification has received extensive attention since. 2000, when a reasonable number of SAR orbital systems became available. In the field of image classification, feature extraction and feature selection are important steps
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have