Ship Detection and Segmentation using Unet

Maritime surveillance is very crucial for every nation even if it is surrounded by land. The surveillance can not only inform about the threats and illegal activities but also manage the traffic and regulate a lot of movement on water. With more and more satellites with Synthetic-Aperture Radar (SAR) and other capabilities to capture high-resolution images being launched, automation of ship detection from these images is now a necessity. The experiments are performed on satellite image datasets where various encoders and loss functions for the Unet model are evaluated based on segmentation results over the test dataset. Our research and analysis of these encoders and loss functions for the Unet model lead us to certain conclusions as to which situation would benefit from which of the loss function and encoder and their combination. The research shows that the modes are robust and can perform well even with difficult backgrounds like clouds, waves etc. Our best model archived 0.823 on F2 score at different IOU thresholds on Airbus ship detection challenge test dataset.

[1]  Danijel Skočaj,et al.  Automated System for Ship Detection from Medium Resolution Satellite Optical Imagery , 2019, OCEANS 2019 MTS/IEEE SEATTLE.

[2]  Lining Gao,et al.  A Visual Search Inspired Computational Model for Ship Detection in Optical Satellite Images , 2012, IEEE Geoscience and Remote Sensing Letters.

[3]  Mesut Kartal,et al.  Ship Detection from Optical Satellite Images with Deep Learning , 2019, 2019 9th International Conference on Recent Advances in Space Technologies (RAST).

[4]  Wei Ao,et al.  Robust Ship Detection in SAR Images from Complex Background , 2018, 2018 IEEE International Conference on Computational Electromagnetics (ICCEM).

[5]  Xu Sun,et al.  Ship Detection Without Sea-Land Segmentation for Large-Scale High-Resolution Optical Satellite Images , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[6]  Haigang Sui,et al.  Automatic ship detection for optical satellite images based on visual attention model and LBP , 2014, 2014 IEEE Workshop on Electronics, Computer and Applications.

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

[8]  Xu Shou-shi.  Ship Target Detection Scheme for Optical Remote Sensing Images , 2008 .

[9]  Deniz Erdogmus,et al.  Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks , 2017, MLMI@MICCAI.

[10]  Jeremy Howard,et al.  fastai: A Layered API for Deep Learning , 2020, Inf..

[11]  Hui Zhou,et al.  A Novel Hierarchical Method of Ship Detection from Spaceborne Optical Image Based on Shape and Texture Features , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Jonathan Li,et al.  Ship Detection Using a Fully Convolutional Network with Compact Polarimetric SAR Images , 2019, Remote. Sens..

[13]  Feng Gao,et al.  Ship detection from optical satellite images based on visual search mechanism , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[14]  Yuan Tian,et al.  Ship Detection Using Texture Statistics from Optical Satellite Images , 2011, 2011 International Conference on Digital Image Computing: Techniques and Applications.

[15]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Leslie N. Smith,et al.  A disciplined approach to neural network hyper-parameters: Part 1 - learning rate, batch size, momentum, and weight decay , 2018, ArXiv.

[17]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[18]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[19]  Bo Wang,et al.  Inshore Ship Detection Based on Convolutional Neural Network in Optical Satellite Images , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[20]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[21]  Hong Zhang,et al.  Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery , 2019, Remote. Sens..

[22]  Leslie N. Smith,et al.  Cyclical Learning Rates for Training Neural Networks , 2015, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).