Balanced Feature Pyramid Network for Ship Detection in Synthetic Aperture Radar Images

Ship detection in Synthetic Aperture Radar (SAR) images is a fundamental but challenging task. Nowadays, given that the huge imbalance between sparse-distribution ships and complex backgrounds in training process, most existing deep-learning-based SAR ship detectors often face great difficulty in further improving accuracy. Therefore, to solve this problem, in this paper, a novel Balanced Feature Pyramid Network (B-FPN) is applied to enhance detection accuracy. Different from the raw Feature Pyramid Network (FPN), B-FPN utilizes the same-deep integration balanced semantic features to strengthen the multi-level features in the feature pyramid, by means of four steps, namely rescaling, integrating, refining and strengthening, which do not increase too much network parameter quantity. Experimental results on the open SAR Ship Detection Dataset (SSDD) shows that B-FPN can make a 7.15% mean Average Precision (mAP) improvement than FPN.

[1]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[2]  Xiaoling Zhang,et al.  Depthwise Separable Convolution Neural Network for High-Speed SAR Ship Detection , 2019, Remote. Sens..

[3]  Bernt Schiele,et al.  Learning Non-maximum Suppression , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Kai Chen,et al.  MMDetection: Open MMLab Detection Toolbox and Benchmark , 2019, ArXiv.

[5]  Tao Lai,et al.  Detection of Moving Ships Based on a Combination of Magnitude and Phase in Along-Track Interferometric SAR—Part II: Statistical Modeling and CFAR Detection , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[7]  Jiao Jiao,et al.  A Densely Connected End-to-End Neural Network for Multiscale and Multiscene SAR Ship Detection , 2018, IEEE Access.

[8]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[9]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Jie Yang,et al.  A New Automatic Ship Detection Method Using $L$-Band Polarimetric SAR Imagery , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[11]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[12]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Chao Wang,et al.  Combining a single shot multibox detector with transfer learning for ship detection using sentinel-1 SAR images , 2018, Remote Sensing Letters.

[14]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Jianwei Li,et al.  Ship detection in SAR images based on an improved faster R-CNN , 2017, 2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA).

[17]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[18]  Gangyao Kuang,et al.  Squeeze and Excitation Rank Faster R-CNN for Ship Detection in SAR Images , 2019, IEEE Geoscience and Remote Sensing Letters.

[19]  Takuya Akiba,et al.  Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes , 2017, ArXiv.

[20]  Lena Chang,et al.  Ship Detection Based on YOLOv2 for SAR Imagery , 2019, Remote. Sens..

[21]  Zongxu Pan,et al.  Projection Shape Template-Based Ship Target Recognition in TerraSAR-X Images , 2017, IEEE Geoscience and Remote Sensing Letters.

[22]  Qi Li,et al.  Dense Attention Pyramid Networks for Multi-Scale Ship Detection in SAR Images , 2019, IEEE Transactions on Geoscience and Remote Sensing.