Data Augmentation and Classification of Sea–Land Clutter for Over-the-Horizon Radar Using AC-VAEGAN

In the sea–land clutter classification of sky-wave over-the-horizon-radar (OTHR), the imbalanced and scarce data lead to a poor performance of the deep learning-based classification model. To solve this problem, this article proposes an improved auxiliary classifier generative adversarial network (AC-GAN) architecture, namely, auxiliary classifier variational autoencoder GAN (AC-VAEGAN). AC-VAEGAN can synthesize higher quality sea–land clutter samples than AC-GAN and serve as an effective tool for data augmentation. Specifically, a 1-D convolutional AC-VAEGAN architecture is designed to synthesize sea–land clutter samples. Additionally, an evaluation method combining both traditional evaluation of the GAN domain and statistical evaluation of the signal domain is proposed to evaluate the quality of synthetic samples. Using a dataset of OTHR sea–land clutter, both the quality of the synthetic samples and the performance of data augmentation of AC-VAEGAN are verified. Furthermore, the effect of AC-VAEGAN as a data augmentation method on the classification performance of imbalanced and scarce sea–land clutter samples is validated. The experiment results show that the quality of samples synthesized by AC-VAEGAN is better than those synthesized by the state-of-the-art GAN-based methods, and the data augmentation method with AC-VAEGAN is able to improve the classification performance in the case of the imbalanced and scarce sea–land clutter samples.