Combining a single shot multibox detector with transfer learning for ship detection using sentinel-1 SAR images

ABSTRACT With the capabilities of constant use in any weather condition and a wide coverage area, synthetic aperture radar (SAR) technology is widely used in marine transportation safety and fishing law enforcement. Currently, due to automatic learning of discriminative features, deep learning has achieved enormous success in object detection. Compared to other detection models, the single shot multiBox detector (SSD) has the advantages of high detection accuracy with relatively high speed, which is suitable for inferences in a large volume of SAR images. This paper focuses on the application of the SSD to address ship detection in complex backgrounds. Due to a limited number of datasets, transfer learning is adapted to train the model. Ten scenes of Sentinel-1 SAR images are used to evaluate our approach. Experimental results reveal that 1) transfer learning improves the detection accuracy and overall performance and reduces the false positives, and 2) compared with the faster RCNN and other SSD models, the SSD-512 model with transfer learning achieves the best overall performance, which demonstrates the effectiveness of our approach.

[1]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[2]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  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.

[5]  Trevor Darrell,et al.  Fully convolutional networks for semantic segmentation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  Colin P. Schwegmann,et al.  Very deep learning for ship discrimination in Synthetic Aperture Radar imagery , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

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

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

[11]  Weike Pan,et al.  A survey of transfer learning for collaborative recommendation with auxiliary data , 2016, Neurocomputing.

[12]  Björn Tings,et al.  Ship-Iceberg Discrimination with Convolutional Neural Networks in High Resolution SAR Images , 2016 .

[13]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Zhao Lin,et al.  A modified faster R-CNN based on CFAR algorithm for SAR ship detection , 2017, 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP).

[16]  Yang Liu,et al.  SAR ship detection using sea-land segmentation-based convolutional neural network , 2017, 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP).

[17]  Zhao Lin,et al.  Contextual Region-Based Convolutional Neural Network with Multilayer Fusion for SAR Ship Detection , 2017, Remote. Sens..

[18]  Hong Zhang,et al.  Integrating H-A-α with fully convolutional networks for fully PolSAR classification , 2017, 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP).

[19]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).