Details

Autor(en) / Beteiligte

• Liao, Huaizhang
• Xia, Jingyuan
• Yang, Zhixiong
• Liu, Zhen
• Liu, Yongxiang

Titel

Hierarchical Domain Prior CycleGAN: Translated Satellites ISAR Image from the Optical Domain

Ist Teil von

• 2023 China Automation Congress (CAC), 2023, p.1658-1662

Ort / Verlag

IEEE

Erscheinungsjahr

2023

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• Despite the deep learning has shown revolutionary success in classification tasks, the performance is determined by the training data. Therefore, image augmentation and generation are necessary for the tasks that are lack of sufficient training samples. This paper focuses on generating Inverse Synthetic Aperture Radar (ISAR) images from the optical counterparts, in particular, for the classification of the satellite tasks. We propose a hierarchical domain prior CycleGAN (HDP-CycleGAN) to achieve an image translation between the ISAR and optical satellite images, as such providing synthetic training samples for deep classification models. The proposed HDP-CycleGAN constitutes a physical feature projection consistency for ISAR scattering distribution feature extraction and a classification-consistency to integrate the identifying feature with the generative model. Extensive simulations validate that the obtained ISAR images have better visible-authenticity and training-effectiveness than the existing image translation alternatives.