An Improved Lightweight RetinaNet for Ship Detection in SAR Images

The rapid development of remote sensing technology has led to a sharp increase in the amount of synthetic aperture radar (SAR) measurements, which put forward higher requirements for remote sensing image processing. As an important application of SAR, fast and accurate ship detection has always been...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing 2022, Vol.15, p.4667-4679
Main Authors: Miao, Tian, Zeng, HongCheng, Yang, Wei, Chu, Boce, Zou, Fei, Ren, Weijia, Chen, Jie
Format: Article
Language:English
Subjects:
Algorithms
Aspect ratio
Clustering
Datasets
Detection
Feature extraction
Floating point arithmetic
Image processing
Lightweight
Lightweight design
Marine vehicles
Modules
Object detection
Optical losses
Radar polarimetry
Remote sensing
Retinanet
Robustness (mathematics)
SAR (radar)
Satellite imagery
ship detection
Synthetic aperture radar
synthetic aperture radar (SAR)
Target detection
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The rapid development of remote sensing technology has led to a sharp increase in the amount of synthetic aperture radar (SAR) measurements, which put forward higher requirements for remote sensing image processing. As an important application of SAR, fast and accurate ship detection has always been a research hotspot. In this article, an improved lightweight RetinaNet for ship detection in SAR images is proposed. Compared with the standard RetinaNet, the shallow convolutional layers of the backbone are replaced by ghost modules and the number of the deep convolutional layers is reduced. The spatial and channel attention modules are embedded into the model to enhance detectability. K -means clustering algorithm is applied to adjust the initial aspect ratios of the model. The effectiveness and robustness of the proposed method is demonstrated by numerical experiments with SSDD dataset, Gaofen-3 mini dataset, and a large-scale SAR image of Hisea-1 satellite, it is shown that the proposed method can significantly reduce the floating-point operations and the number of parameters without decreasing the detection accuracy and recall ratio. Moreover, the experimental results also show the proposed model's robustness and the ability to detect ship targets in small datasets.
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2022.3180159