Next Article in Journal
Decoding Complex Erosion Responses for the Mitigation of Coastal Rockfall Hazards Using Repeat Terrestrial LiDAR
Next Article in Special Issue
Crop Classification Method Based on Optimal Feature Selection and Hybrid CNN-RF Networks for Multi-Temporal Remote Sensing Imagery
Previous Article in Journal
Evaluation of Rapeseed Winter Crop Damage Using UAV-Based Multispectral Imagery
Previous Article in Special Issue
Segmentation of Vegetation and Flood from Aerial Images Based on Decision Fusion of Neural Networks
Open AccessArticle

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

1
School of Electronic Information Engineering, Beihang University, Beijing 100191, China
2
Cognitive Big Data and Cyber-Informatics (CogBID) Laboratory, School of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, UK
3
Department of Informatics, University of Leicester, Leicester LE1 7RH, UK
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(16), 2619; https://doi.org/10.3390/rs12162619
Received: 24 July 2020 / Revised: 12 August 2020 / Accepted: 12 August 2020 / Published: 13 August 2020
(This article belongs to the Special Issue Deep Neural Networks for Remote Sensing Applications)
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 upsampling 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 nonmaximum 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. View Full-Text
Keywords: ship detection; convolutional neural networks (CNN); synthetic aperture radar (SAR); anchor-free; feature aggregation; attention mechanism ship detection; convolutional neural networks (CNN); synthetic aperture radar (SAR); anchor-free; feature aggregation; attention mechanism
Show Figures

Graphical abstract

MDPI and ACS Style

Gao, F.; He, Y.; Wang, J.; Hussain, A.; Zhou, H. Anchor-free Convolutional Network with Dense Attention Feature Aggregation for Ship Detection in SAR Images. Remote Sens. 2020, 12, 2619.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop