Dense-Weak Ship Detection Based on Foreground-Guided Background Generation Network in SAR Images
- 21 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-16
Abstract
Currently, ship detection based on synthetic aperture radar (SAR) images still faces significant challenges, particularly in detecting weak and densely distributed ships within complex backgrounds. In areas such as ports and land, the complex background features often resemble those of densely distributed ships, leading to reduced detection accuracy. In addition, the overlapping and mutual interference of features among dense ships can cause the network to miss detections or produce false positives. Therefore, this article proposes a foreground-guided background generation network (FGBG-Net), which includes a Gaussian foreground localization (GFL) model and a background feature removal (BFR) module. The GFL module identifies the approximate high-probability regions of ship foregrounds on the feature map, guiding the network to focus on these regions. The BFR module then progressively removes background interference features based on the positions provided by the GFL module, generating feature maps that are more suitable for detecting weak and dense ships. Our network has been validated on multiple SAR ship datasets, and the experimental results demonstrate noticeable performance improvements, with a mean average precision (mAP) increase of 3.4% on the SSDD and HRSID datasets. The relevant code is available at the following link: https://github.com/Xidian-AIGroup190726/FBGBNet/tree/masterKeywords
Funding Information
- National Natural Science Foundation of China (U22B2054)
- National Natural Science Foundation of China (62076192, 62276199, 62431020, 62276201)
- Higher Education Discipline Innovation Project
- Program for Cheung Kong Scholars and Innovative Research Team in University (IRT15R53)
- Science and Technology Innovation Project from the Chinese Ministry of Education
This publication has 43 references indexed in Scilit:
- Speckle noise detection and correction for frequency-scanning interferometry in vibration measurementMeasurement, 2024
- NRENet: Neighborhood removal-and-emphasis network for ship detection in SAR ImagesInternational Journal of Applied Earth Observation and Geoinformation, 2024
- CBAM + ASFF-YOLOXs: An improved YOLOXs for guiding agronomic operation based on the identification of key growth stages of lettuceComputers and Electronics in Agriculture, 2022
- Ship detection based on deep learning using SAR imagery: a systematic literature reviewSoft Computing, 2022
- Joint-attention feature fusion network and dual-adaptive NMS for object detectionKnowledge-Based Systems, 2022
- Automated LoD-2 model reconstruction from very-high-resolution satellite-derived digital surface model and orthophotoISPRS Journal of Photogrammetry and Remote Sensing, 2021
- End-to-End Object Detection with Transformers2020
- HRSID: A High-Resolution SAR Images Dataset for Ship Detection and Instance SegmentationIEEE Access, 2020
- CornerNet: Detecting Objects as Paired Keypoints2018
- Gaussian Mixture Models2009