University of Leicester
Browse
remotesensing-12-02619-v2.pdf (6.92 MB)

Anchor-free Convolutional Network with Dense Attention Feature Aggregation for Ship Detection in SAR Images

Download (6.92 MB)
journal contribution
posted on 2021-03-19, 11:13 authored by F Gao, Y He, J Wang, A Hussain, Huiyu Zhou
In recent years, with the improvement of synthetic aperture radar (SAR) imaging resolution, it is urgent to develop methods with higher accuracy and faster speed for ship detection in high-resolution SAR images. Among all kinds of methods, deep-learning-based algorithms bring promising performance due to end-to-end detection and automated feature extraction. However, several challenges still exist: (1) standard deep learning detectors based on anchors have certain unsolved problems, such as tuning of anchor-related parameters, scale-variation and high computational costs. (2) SAR data is huge but the labeled data is relatively small, which may lead to overfitting in training. (3) To improve detection speed, deep learning detectors generally detect targets based on low-resolution features, which may cause missed detections for small targets. In order to address the above problems, an anchor-free convolutional network with dense attention feature aggregation is proposed in this paper. Firstly, we use a lightweight feature extractor to extract multiscale ship features. The inverted residual blocks with depth-wise separable convolution reduce the network parameters and improve the detection speed. Secondly, a novel feature aggregation scheme called dense attention feature aggregation (DAFA) is proposed to obtain a high-resolution feature map with multiscale information. By combining the multiscale features through dense connections and iterative fusions, DAFA improves the generalization performance of the network. In addition, an attention block, namely spatial and channel squeeze and excitation (SCSE) block is embedded in the up sampling process of DAFA to enhance the salient features of the target and suppress the background clutters. Third, an anchor-free detector, which is a center-point-based ship predictor (CSP), is adopted in this paper. CSP regresses the ship centers and ship sizes simultaneously on the high-resolution feature map to implement anchor-free and non maximum suppression (NMS)-free ship detection. The experiments on the AirSARShip-1.0 dataset demonstrate the effectiveness of our method. The results show that the proposed method outperforms several mainstream detection algorithms in both accuracy and speed.

History

Citation

Remote Sens. 2020, 12(16), 2619; https://doi.org/10.3390/rs12162619

Author affiliation

School of Informatics

Version

  • VoR (Version of Record)

Published in

Remote Sensing

Volume

12

Issue

16

Publisher

MDPI AG

eissn

2072-4292

Acceptance date

2020-08-12

Copyright date

2020

Available date

2021-03-19

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC