SAR-ShipNet: SAR-Ship Detection Neural Network via Bidirectional Coordinate Attention and Multi-resolution Feature Fusion

TL;DR

This paper introduces SAR-ShipNet, a neural network for SAR ship detection that uses bidirectional coordinate attention and multi-resolution feature fusion to improve accuracy and robustness against complex backgrounds and varying ship shapes.

Contribution

The paper proposes SAR-ShipNet with novel bidirectional coordinate attention and multi-resolution feature fusion, enhancing SAR ship detection performance over existing methods.

Findings

Achieves competitive speed and accuracy on SAR-Ship dataset.

Effectively suppresses background noise and enhances small ship features.

Handles varying ship aspect ratios using elliptical Gaussian distribution.

Abstract

This paper studies a practically meaningful ship detection problem from synthetic aperture radar (SAR) images by the neural network. We broadly extract different types of SAR image features and raise the intriguing question that whether these extracted features are beneficial to (1) suppress data variations (e.g., complex land-sea backgrounds, scattered noise) of real-world SAR images, and (2) enhance the features of ships that are small objects and have different aspect (length-width) ratios, therefore resulting in the improvement of ship detection. To answer this question, we propose a SAR-ship detection neural network (call SAR-ShipNet for short), by newly developing Bidirectional Coordinate Attention (BCA) and Multi-resolution Feature Fusion (MRF) based on CenterNet. Moreover, considering the varying length-width ratio of arbitrary ships, we adopt elliptical Gaussian probability distribution in CenterNet to improve the performance of base detector models. Experimental results on the public SAR-Ship dataset show that our SAR-ShipNet achieves competitive advantages in both speed and accuracy.