A Novel Anchor-Free Model With Salient Feature Fusion Mechanism for Ship Detection in SAR Images
Open Access
- 27 September 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 9089-9105
Abstract
Ship detection in synthetic aperture radar (SAR) images has gained great attention in civil and military fields. Anchor-based detection algorithms usually rely on preset candidate boxes, and a large amount of anchor boxes with different sizes will result in a large amount of computing resources being consumed. Recently, anchor-free algorithms have found wide applications in ship detection from SAR images. However, there are still some problems which limit the ship detection performance to a certain extent, such as how to effectively fuse salient features and unbalanced distribution of positive samples. In order to tackle the above problems, we propose a novel anchor-free model named SFF-YOLOX with salient feature fusion (SFF) mechanism. Firstly, we redesign the network of YOLOX to obtain the best balance between detection accuracy and running speed. Secondly, a saliency region extraction (SRE) module is introduced to generate the corresponding salient guide map of the input image. Besides, the SFF mechanism is proposed by fusing deep features and salient features to better enhance the discrimination of the multiscale targets. Finally, we improve the SimOTA mechanism by combining the predicted IoUs (intersection over union) and the anchor IoUs to the ground truth bounding boxes to instruct label assignment. We evaluate the detection accuracy and running speed of SFF-YOLOX on the public dataset SSD and test the generalization ability on HRSID and two complex large-scale SAR images, the experimental results prove the model's effectiveness for ship detection task in SAR images.Keywords
Funding Information
- National Natural Science Foundation of China (61401425)
- Key R&D project of Jilin Provincial Science and Technology Development Plan (2022021146GX)
This publication has 57 references indexed in Scilit:
- An Intensity-Space Domain CFAR Method for Ship Detection in HR SAR ImagesIEEE Geoscience and Remote Sensing Letters, 2017
- Scheme of Parameter Estimation for Generalized Gamma Distribution and Its Application to Ship Detection in SAR ImagesIEEE Transactions on Geoscience and Remote Sensing, 2016
- Ship Detection for Complex Background SAR Images Based on a Multiscale Variance Weighted Image Entropy MethodIEEE Geoscience and Remote Sensing Letters, 2016
- New Hierarchical Saliency Filtering for Fast Ship Detection in High-Resolution SAR ImagesIEEE Transactions on Geoscience and Remote Sensing, 2016
- SSD: Single Shot MultiBox Detector2016
- Statistical Modeling of PMA Detector for Ship Detection in High-Resolution Dual-Polarization SAR ImagesIEEE Transactions on Geoscience and Remote Sensing, 2016
- SalientShape: group saliency in image collectionsThe Visual Computer, 2013
- Context-Aware Saliency DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- An automatic ship and ship wake detection system for spaceborne SAR images in coastal regionsIEEE Transactions on Geoscience and Remote Sensing, 1996