Acta Geodaetica et Cartographica Sinica ›› 2024, Vol. 53 ›› Issue (4): 610-619.doi: 10.11947/j.AGCS.2024.20230281

• Real-time Remote Sensing Mapping • Previous Articles     Next Articles

Fast SAR autofocus based on convolutional neural networks

Zhi LIU1(), Shuyuan YANG1(), Zifan YU1, Zhixi FENG1, Quanwei GAO1, Min WANG2   

  1. 1.Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi'an 710071, China
    2.National Key Laboratory of Radar Signal Processing, School of Electronic Engineering, Xidian University, Xi'an 710071, China
  • Received:2023-07-24 Revised:2024-03-13 Published:2024-05-13
  • Contact: Shuyuan YANG E-mail:zhiliu@stu.xidian.edu.cn;syyang@xidian.edu.cn
  • About author:LIU Zhi (1989—), male, PhD, senior algorithm engineer, majors in deep learning and radar signal processing. E-mail: zhiliu@stu.xidian.edu.cn
  • Supported by:
    The National Natural Science Foundation of China(62171357);The Natural Science Basic Research Plan in Shaanxi Province of China(2023-JC-YB-524);The Education Scientific Program of the 13th Five-year Plan in Shaanxi Province of China(SGH18H350)

Abstract:

Autofocus is a key technology for high-resolution synthetic aperture radar imaging. However, traditional SAR autofocus methods require too many iterations, have low computational efficiency, and are unsuitable for on-orbit processing. This paper proposes a fast SAR autofocus method based on convolutional neural networks. This method utilizes CNNs to learn the mapping from defocused images to focused images, mainly designed to correct the azimuth phase errors. It has a real-time performance and is more suitable for on-orbit processing since it does not need to iterate or adjust parameters in the testing phase. Experimental results on real SAR data show that our proposed method has the highest focusing quality and speed.

Key words: convolutional neural networks, SAR, phase error, autofocus

CLC Number: