An Enhanced Shuffle Attention with Context Decoupling Head with Wise IoU Loss for SAR Ship Detection
Open Access
- 5 November 2024
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 16 (22) , 4128
Abstract
Synthetic Aperture Radar (SAR) imagery is widely utilized in military and civilian applications. Recent deep learning advancements have led to improved ship detection algorithms, enhancing accuracy and speed over traditional Constant False-Alarm Rate (CFAR) methods. However, challenges remain with complex backgrounds and multi-scale ship targets amidst significant interference. This paper introduces a novel method that features a context-based decoupled head, leveraging positioning and semantic information, and incorporates shuffle attention to enhance feature map interpretation. Additionally, we propose a new loss function with a dynamic non-monotonic focus mechanism to tackle these issues. Experimental results on the HRSID and SAR-Ship-Dataset demonstrate that our approach significantly improves detection performance over the original YOLOv5 algorithm and other existing methods.Keywords
Funding Information
- Three Dimensional Cross Band Multi Frequency Composite Antenna Microsystem Technology (E3Z221030F)
This publication has 59 references indexed in Scilit:
- FS-YOLO: a multi-scale SAR ship detection network in complex scenesSignal, Image and Video Processing, 2024
- Dualistic cascade convolutional neural network dedicated to fully PolSAR image ship detectionISPRS Journal of Photogrammetry and Remote Sensing, 2023
- CRAS-YOLO: A Novel Multi-Category Vessel Detection and Classification Model Based on YOLOv5s AlgorithmIEEE Access, 2023
- A Decoupled Head and Coordinate Attention Detection Method for Ship Targets in SAR ImagesIEEE Access, 2022
- HRSID: A High-Resolution SAR Images Dataset for Ship Detection and Instance SegmentationIEEE Access, 2020
- CornerNet: Detecting Objects as Paired KeypointsInternational Journal of Computer Vision, 2019
- You Only Look Once: Unified, Real-Time Object Detection2016
- A model for extremely heterogeneous clutterIEEE Transactions on Geoscience and Remote Sensing, 1997
- An automatic ship and ship wake detection system for spaceborne SAR images in coastal regionsIEEE Transactions on Geoscience and Remote Sensing, 1996
- A CFAR adaptive matched filter detectorIEEE Transactions on Aerospace and Electronic Systems, 1992