Browse > Article
http://dx.doi.org/10.7472/jksii.2018.19.4.35

Iceberg-Ship Classification in SAR Images Using Convolutional Neural Network with Transfer Learning  

Choi, Jeongwhan (Dept. of Software Engineering, Chonbuk National University)
Publication Information
Journal of Internet Computing and Services / v.19, no.4, 2018 , pp. 35-44 More about this Journal
Abstract
Monitoring through Synthesis Aperture Radar (SAR) is responsible for marine safety from floating icebergs. However, there are limits to distinguishing between icebergs and ships in SAR images. Convolutional Neural Network (CNN) is used to distinguish the iceberg from the ship. The goal of this paper is to increase the accuracy of identifying icebergs from SAR images. The metrics for performance evaluation uses the log loss. The two-layer CNN model proposed in research of C.Bentes et al.[1] is used as a benchmark model and compared with the four-layer CNN model using data augmentation. Finally, the performance of the final CNN model using the VGG-16 pre-trained model is compared with the previous model. This paper shows how to improve the benchmark model and propose the final CNN model.
Keywords
Convolutional Neural Network; Deep Learning; Transfer Learning; VGG-16; Pooling Layer; Adam Optimizer; Data Augmentation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 K. Fukushima, "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position," Biol. Cybern., vol. 36, no. 4, pp. 193-202, 2016. https://doi.org/10.1007/bf00344251   DOI
2 Kaggle.com, "Statoil/C-CORE Iceberg Classifier Challenge l Kaggle." [Online]. Available: https://www.kaggle.com/c/statoil-iceberg-classifier-challenge/data. [Accessed: 24-Feb-2018].
3 J. Ding, B. Chen, H. Liu, and M. Huang, "Convolutional Neural Network with Data Augmentation for SAR Target Recognition," IEEE Geosci. Remote Sens. Lett., vol. 13, no. 3, pp. 364-368, 2016. https://doi.org/10.1109/lgrs.2015.2513754   DOI
4 A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Adv. Neural Inf. Process. Syst., pp. 1-9, 2012.
5 D. C. Cireşan, U. Meier, J. Masci, L. M. Gambardella, and J. Schmidhuber, "High-Performance Neural Networks for Visual Object Classification," 2011. https://doi.org/10.1145/3065386
6 D. Cireşan, U. Meier, and J. Schmidhuber, "Multi-column Deep Neural Networks for Image Classification," Int. Conf. Pattern Recognit., no. February, pp. 3642-3649, 2012. https://doi.org/10.1109/cvpr.2012.6248110   DOI
7 R. Wagner, M. Thom, R. Schweiger, G. Palm, and A. Rothermel, "Learning convolutional neural networks from few samples," Proc. Int. Jt. Conf. Neural Networks, pp. 1884-1890, 2013. https://doi.org/10.1109/ijcnn.2013.6706969   DOI
8 W. Zhao, "Research on the deep learning of the small sample data based on transfer learning," vol. 020018, p. 020018, 2017. https://doi.org/10.1063/1.4992835   DOI
9 N. . C. B. . P.-S. A. . C. A. . Chakraborty D.a b Kovvali, "Structural damage detection with insufficient data using transfer learning techniques," Proc. SPIE - Int. Soc. Opt. Eng., vol. 7981, no. May, pp. 1-9, 2011. https://doi.org/10.1117/12.882025   DOI
10 E. Attema et al., "Sentinel-1 ESA's new European SAR mission," Proc. SPIE, vol. 6744, pp. 674403-674403-8, 2007. https://doi.org/10.1117/12.747146   DOI
11 Y. Z. Jeff Hwang, "Image Colorization with Deep Convolutional Neural Networks," Cs231N. Stanford.Edu, 2016. https://doi.org/10.1109/icmla.2016.0019
12 W. McKinney, "Data Structures for Statistical Computing in Python," Proc. 9th Python Sci. Conf., vol. 1697900, no. Scipy, pp. 51-56, 2010.
13 D. P. Kingma and J. L. Ba, "Adam: A Method for Stochastic Optimization," arXiv preprint arXiv:1412.6980, 2014. [Online]. Available: http://arxiv.org/abs/1412.6980.
14 V. Nair and G. E. Hinton, "Rectified Linear Units Improve Restricted Boltzmann Machines," Proc. 27th Int. Conf. Mach. Learn., no. 3, pp. 807-814, 2010. https://doi.org/10.1109/icassp.2010.5495651   DOI
15 L. Prechelt, "Early stopping - But when?," Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 7700 LECTU, pp. 53-67, 2012.
16 S. Ruder, "An overview of gradient descent optimization algorithms,", pp. 1-14, 2016
17 C. Bentes, A. Frost, D. Velotto, and B. Tings, "Ship-iceberg discrimination with convolutional neural networks in high resolution SAR images," in EUSAR 2016: 11th European Conference on Synthetic Aperture Radar, Proceedings of, pp. 1-4, 2016. https://doi.org/10.1109/joe.2017.2767106   DOI
18 K. Simonyan and A. Zisserman, "Very Deep Networks for Large-Scale Image Recognition,", pp. 1-14, 2014. https://doi.org/10.1109/cvpr.2014.219