A CenterNet++ model for ship detection in SAR images

作者：

Highlights：

• We propose an effective and stable single-stage detector in a refined manner, achieving high accuracy for small ship detection.

• We design a feature pyramids fusion module and a head enhancement module to improve ship detection performance under complex background.

• We achieve favorable results on different SAR image datasets, demonstrating the effectiveness and robustness of our method.

摘要

•We propose an effective and stable single-stage detector in a refined manner, achieving high accuracy for small ship detection.•We design a feature pyramids fusion module and a head enhancement module to improve ship detection performance under complex background.•We achieve favorable results on different SAR image datasets, demonstrating the effectiveness and robustness of our method.

论文关键词：Ship detection,Synthetic aperture radar (SAR),Deep learning

论文评审过程：Received 21 July 2020, Revised 26 November 2020, Accepted 2 December 2020, Available online 28 December 2020, Version of Record 28 December 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107787