Efficient Encoder-Decoder Network With Estimated Direction for SAR Ship Detection

doi:10.1109/LGRS.2022.3145790

Efficient Encoder-Decoder Network With Estimated Direction for SAR Ship Detection

2022-01-01

7

PRE

AI

DOI：10.1109/LGRS.2022.3145790

Original

Original request for help

Save

Abstract

En 中文

Synthetic aperture radar (SAR) image ship detection has important applications in marine surveillance. There are two limitations when applying advanced detection methods naively for SAR ship detection. First, most detectors construct the model as an encoder and rely on the feature pyramid network (FPN) head for accurate prediction, which may lead to high computational costs. Second, the background noises in the ground truth (annotated as rectangular bounding boxes) of angular ships bring difficulties for model training. To meet these challenges, we propose an efficient encoder-decoder network with estimated direction for ship detection in SAR images. First, we present an anchor-free encoder-decoder model that can efficiently extract multiple-level features. Second, we formulate ship detection as a multitask learning problem, including a bounding box prediction and a ship direction regression. The estimated ship direction can weakly supervise and benefit ship detection. Furthermore, we develop a center-weighted labeling method for overlapped annotations. Comprehensive experiments on SAR-Ship-Detection and SSDD datasets show that our method achieves state-of-the-art performance with a high running speed.

Keywords:

Marine vehicles

Radar polarimetry

Synthetic aperture radar

Decoding

Feature extraction

Task analysis

Background noise

Encoder-decoder

multitask learning

ship detection in SAR image

synthetic aperture radar (SAR) image

Efficient Encoder-Decoder Network With Estimated Direction for SAR Ship Detection

Abstract

Journal

Organization