Skip to main content

Research Repository

Advanced Search

Ellipse Encoding for Arbitrary-Oriented SAR Ship Detection Based on Dynamic Key Points

Gao, Fei; Huo, Yiyang; Sun, Jinping; Yu, Tao; Hussain, Amir; Zhou, Huiyu

Authors

Fei Gao

Yiyang Huo

Jinping Sun

Tao Yu

Huiyu Zhou



Abstract

In recent years, there has been growing interest in developing oriented bounding box (OBB)-based deep learning approaches to detect arbitrary-oriented ship targets in synthetic aperture radar (SAR) images. However, most existing OBB-based detection methods suffer from boundary discontinuity problems for bounding box angle prediction and key point regression challenges. In this article, we present a novel OBB-based detection algorithm that utilizes ellipse encoding to effectively exploit the geometric and scattering properties of ship targets. Specifically, the ship contour is fit by an OBB inscribed ellipse that is encoded as a set of distances between dynamic key points on the bow and target center. By combining the bow angle interval and the decoding process, the negative impact of the boundary discontinuity problem is avoided. In addition, we propose an elliptical Gaussian distribution heatmap and a pooling strategy termed double-peak max-pooling (DPM) to deal with the challenge of separating densely distributed ships in inshore scenes. The former can enhance the heatmap’s ship-side score gap between neighboring ship targets, while the latter can solve the problem of target center responses being suppressed after max-pooling. Simulation experiments conducted on the benchmark Rotating SAR Ship Detection Dataset (RSSDD) and Rotated Ship Detection Dataset in SAR Images (RSDD-SAR) demonstrate the superior performance of our method for ship target detection compared to several state-of-the-art OBB-based algorithms. Ablation experiments show that elliptical Gaussian distribution heatmap and DPM can further improve the inshore detection performance.

Journal Article Type Article
Acceptance Date Dec 1, 2022
Online Publication Date Dec 7, 2022
Publication Date 2022
Deposit Date Feb 2, 2023
Publicly Available Date Feb 2, 2023
Journal IEEE Transactions on Geoscience and Remote Sensing
Print ISSN 0196-2892
Electronic ISSN 1558-0644
Publisher Institute of Electrical and Electronics Engineers
Peer Reviewed Peer Reviewed
Volume 60
Article Number 5240528
DOI https://doi.org/10.1109/tgrs.2022.3227260
Keywords Arbitrary-oriented, boundary discontinuity, ellipse encoding, ship detection, synthetic aperture radar (SAR)

Files




You might also like



Downloadable Citations