Enhancement of Ship Type Classification from a Combination of CNN and KNN
Abstract
:1. Introduction
2. Data
2.1. Modified Ship Images
2.2. Korean Coast Static AIS
3. Methodology
3.1. CNN Model
3.2. KNN
3.3. Confusion of CNN and KNN Probability
4. Results
5. Discussion
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Agnew, D.J.; Pearce, J.; Pramod, G.; Peatman, T.; Watson, R.; Beddington, J.R.; Pitcher, T.J. Estimating the worldwide extent of illegal fishing. PLoS ONE 2009, 4, e4570. [Google Scholar] [CrossRef] [Green Version]
- Pelich, R.; Chini, M.; Hostache, R.; Matgen, P.; Lopez-Martinez, C.; Nuevo, M.; Ries, P.; Eiden, G. Large-scale automatic vessel monitoring based on dual-polarization sentinel-1 and AIS data. Remote Sens. 2019, 11, 1078. [Google Scholar] [CrossRef] [Green Version]
- Rao, N.S.; Ali, M.M.; Rao, M.V.; Ramana, I.V. Estimation of Ship Velocities from MODIS and OCM. IEEE Geosci. Remote Sens. Lett. 2005, 2, 437–439. [Google Scholar]
- Lemoine, G.; Chesworth, J.; Schwartz-Juste, G.; Kourti, N.; Shepherd, I. Near real time vessel detection using spaceborne SAR imagery in support of fisheries monitoring and control operations. In Proceedings of the 2004 IGARSS, Anchorage, AK, USA, 20–24 September 2004; pp. 4825–4828. [Google Scholar]
- Cumming, I.G.; Wong, F.W. Digital Processing of Synthetic Aperture Radar Data: Algorithms and Implementation; Artech House: Norwood, MA, USA, 2005. [Google Scholar]
- Chen, S.; Wang, H. SAR target recognition based on deep learning. In Proceedings of the 2014 Int. Conference on Data Science and Advanced Analytics, Montreal, QC, Canada, 17–19 October 2016; pp. 541–547. [Google Scholar]
- Chen, S.; Wang, H.; Xu, F.; Jin, Y.Q. Target Classification Using the Deep Convolutional Networks for SAR Images. IEEE Trans. Geosci. Remote Sens. 2016, 54, 4806–4817. [Google Scholar] [CrossRef]
- Ding, J.; Chen, B.; Liu, H.; Huang, M. Convolutional Neural Network with Data Augmentation for SAR Target Recognition. IEEE Geosci. Remote Sens. Lett. 2016, 13, 364–368. [Google Scholar] [CrossRef]
- Pei, J.; Huang, Y.; Huo, W.; Zhang, Y.; Yang, J.; Yeo, T.S. SAR Automatic Target Recognition Based on Multiview Deep Learning Framework. IEEE Trans. Geosci. Remote Sens. 2018, 56, 2196–2210. [Google Scholar] [CrossRef]
- Gao, G.; Shi, G.; Li, G.; Cheng, J. Performance comparison between reflection symmetry metric and product of multilook amplitudes for ship detection in dual-polarization SAR images, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017, 10, 5026–5038. [Google Scholar] [CrossRef]
- Kim, S.; Bae, J.; Yang, C.-S. Satellite Image-Based Ship Classification Method with Sentinel-1 IW Mode Data. In Proceedings of the 2019 IGARSS, Yokohama, Japan, 28 July–2 August 2019. [Google Scholar]
- LeCun, Y.; Bottou, L.; Bengio, Y.; Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 1998, 86, 2278–2324. [Google Scholar] [CrossRef] [Green Version]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet classification with deep convolutional neural networks. In Proceedings of the 2012 the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA, 3–8 December 2012; pp. 1097–1105. [Google Scholar]
- Kaiming, H.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, NSA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; et al. ImageNet Large Scale Visual Recognition Challenge. Int. J. Comput. Vis. IJCV 2015, 115, 211–252. [Google Scholar] [CrossRef] [Green Version]
- Jeon, H.-K.; Kim, S.; Edwin, J.; Yang, C.-S. Sea Fog Identification from GOCI Images Using CNN Transfer Learning Models. Electronics 2020, 9, 311. [Google Scholar] [CrossRef]
- Aghdam, H.H.; Heravi, E.J. Guide to Convolutional Neural Networks: A Practical Application to Traffic-Sign Detection and Classification; Springer: Cham, Switzerland, 2017. [Google Scholar]
- Lawrence, S.; Giles, C.L.; Tsoi, A.C.; Back, A.D. Face recognition: A convolutional neural-network approach. IEEE Trans. Neural Netw. 1997, 8, 98–113. [Google Scholar] [CrossRef] [Green Version]
- Gao, F.; Huang, T.; Wang, J.; Sun, J.; Yang, E.; Hussain, A. Combining Deep Convolutional Neural Network and SVM to SAR Image Target Recognition. In Proceedings of the 2017 IEEE Int. Conf. on Internet of Things, Exeter, UK, 21–23 June 2017; pp. 1082–1085. [Google Scholar]
- Lin, Z.; Ji, K.; Kang, M.; Leng, X. Deep Convolutional Highway Unit Network for SAR Target Classification With Limited Labeled Training Data. IEEE Geosci. Remote Sens. Lett. 2017, 14, 1091–1095. [Google Scholar] [CrossRef]
- Lang, H.; Wu, S.; Xu, Y. Ship Classification in SAR Images Improved by AIS Knowledge Transfer. IEEE Geosci. Remote Sens. Lett. 2018, 15, 439–443. [Google Scholar] [CrossRef]
- Song, J.; Kim, D.-J.; Kang, K.-M. Automated Procurement of Training Data for Machine Learning Algorithm on Ship Detection Using AIS Information. Remote Sens. 2020, 12, 1443. [Google Scholar] [CrossRef]
- Ma, M.; Chen, J.; Yang, W. Ship Classification and Detection Based on CNN Using GF-3 SAR Images. Remote Sens. 2018, 10, 2043. [Google Scholar] [CrossRef] [Green Version]
- Xie, Y.; Dai, W.; Hu, Z.; Liu, Y.; Li, C.; Pu, X. A Novel Convolutional Neural Network Architecture for SAR Target Recognition. J. Sens. 2019, 2019, 1246548. [Google Scholar] [CrossRef] [Green Version]
- Huang, L.; Liu, B.; Li, B.; Guo, W.; Yu, W.; Zhang, Z.; Yu, W. OpenSARShip: A Dataset Dedictated to Sentienl-1 Ship Detection. Appl. Earth Obs. Remote Sens. 2018, 11, 195–208. [Google Scholar] [CrossRef]
- Li, H.; Perrie, W.; He, Y.; Lehner, H.; Brusch, S. Target Detection on the Ocean with the Relative Phase of Compact Polarimetry SAR. IEEE Trans. Geosci. Remote Sens. 2013, 51, 3299–3305. [Google Scholar] [CrossRef]
- Bae, J.; Yang, C.-S. A Method of Suppress False Alarms of Sentinel-1 to Improve Ship Detection. Korean J. Remote Sens. 2020, 4, 535–544. [Google Scholar]
- Eriksen, T.; Høye, G.; Narheim, B.; Meland, B.J. Maritime traffic monitoring using a space-based AIS receiver. Acta Astronaut. 2016, 58, 537–549. [Google Scholar] [CrossRef]
- Hong, D.-B.; Yang, C.-S.; Kim, T.-H. Investigation of Passing Ships in Inaccessible Areas Using Satellite-based Automatic Identification System (S-AIS) Data. Korean J. Remote Sens. 2018, 34, 579–590. [Google Scholar]
- Parsa, A.; Hansen, N.H. Comparison of Vertically and Horizontally Polarized Radar Antennas for Target Detection in Sea Clutter. In Proceedings of the 2012 IEEE Radar Conference, Atlanta, GA, USA, 7–11 May 2012; pp. 653–658. [Google Scholar]
- Fix, E.; Hodges, J.L. Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties. Int. Stat. Rev. 1989, 57, 238–247. [Google Scholar]
- OpenSAR. Available online: https://opensar.sjtu.edu.cn (accessed on 11 May 2021).
- Glorot, X.; Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. J. Mach. Learn. Res. 2010, 9, 249–256. [Google Scholar]
- Kingma, P.; Ba, J.L. Adam: A Method for Stochastic Optimization. arXiv 2017, arXiv:1412.6980. [Google Scholar]
- Dominic Master, M.; Luschi, C. Revisiting Small Batch Training for Deep Neural Networks. arXiv 2018, arXiv:1804.07612. [Google Scholar]
- Simonyan, K.; Andrew, Z. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar]
- Bozinovski, S.; Fulgosi, A. The influence of pattern similarity and transfer learning upon the training of a base perceptron B2. (original in Croatian). In Proceedings of the Symposium Informatica 3-121-5, Bled, Slovenia, 1976; Available online: http://www.informatica.si/ojs-2.4.3/index.php/informatica/article/viewFile/2828/1433 (accessed on 13 May 2021).
Parameter | Setting |
---|---|
Training epoch | 300 |
Batch | 20 |
Optimizer | Adam |
Learning rate | 0.0001 |
Cost function | CEE |
Method | Image Type | Precision (%) | Recall (%) | Accuracy (%) | F1-Score (%) |
---|---|---|---|---|---|
Image alone | VH | 85.6 | 86.3 | 85.6 | 85.0 |
VV | 83.3 | 83.3 | 83.3 | 83.2 | |
MaxVHVV | 82.2 | 83.5 | 82.2 | 81.2 | |
MinVHVV | 84.4 | 85.2 | 84.4 | 84.1 | |
Max (I, T) | VH | 90.0 | 90.3 | 90.0 | 90.0 |
VV | 92.2 | 92.5 | 92.2 | 92.2 | |
MaxVHVV | 91.1 | 91.3 | 91.1 | 91.0 | |
MinVHVV | 92.2 | 92.3 | 92.2 | 92.1 | |
Ave (I, T) | VH | 93.3 | 93.9 | 93.3 | 93.1 |
VV | 94.4 | 94.9 | 94.4 | 94.3 | |
MaxVHVV | 93.3 | 93.5 | 93.3 | 93.2 | |
MinVHVV | 94.4 | 94.9 | 92.2 | 94.3 | |
Cond_Std (I, T) | VH | 91.1 | 91.3 | 91.1 | 91.0 |
VV | 93.3 | 93.5 | 93.3 | 93.3 | |
MaxVHVV | 90.0 | 90.2 | 90.0 | 89.9 | |
MinVHVV | 92.2 | 92.3 | 92.2 | 92.1 | |
Cond_Max (I, T) | VH | 91.1 | 91.3 | 91.1 | 91.0 |
VV | 92.2 | 92.5 | 92.2 | 92.2 | |
MaxVHVV | 91.1 | 91.3 | 91.1 | 91.0 | |
MinVHVV | 92.2 | 92.3 | 92.2 | 92.1 |
Model | Image Type | Precision (%) | Recall (%) | Accuracy (%) | F1-Score (%) |
---|---|---|---|---|---|
VGG19 | VH | 33.3 | 11.1 | 33.3 | 16.7 |
VV | 33.3 | 11.1 | 33.3 | 16.7 | |
MaxVHVV | 33.3 | 11.1 | 33.3 | 16.7 | |
MinVHVV | 33.3 | 11.1 | 33.3 | 16.7 | |
VGG19-TL | VH | 78.9 | 78.8 | 78.9 | 77.9 |
VV | 78.9 | 78.5 | 78.9 | 78.4 | |
MaxVHVV | 76.7 | 76.4 | 76.7 | 75.6 | |
MinVHVV | 74.4 | 73.4 | 74.4 | 73.1 | |
ResNet50 | VH | 77.8 | 77.5 | 77.8 | 76.4 |
VV | 70.0 | 73.5 | 70.0 | 68.3 | |
MaxVHVV | 33.3 | 11.1 | 33.3 | 16.7 | |
MinVHVV | 33.3 | 11.1 | 33.3 | 16.7 | |
ResNet50-TL | VH | 81.1 | 81.2 | 81.1 | 80.4 |
VV | 81.1 | 80.9 | 81.1 | 80.3 | |
MaxVHVV | 80.0 | 79.7 | 80.0 | 79.0 | |
MinVHVV | 77.8 | 77.2 | 77.8 | 77.0 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jeon, H.-K.; Yang, C.-S. Enhancement of Ship Type Classification from a Combination of CNN and KNN. Electronics 2021, 10, 1169. https://doi.org/10.3390/electronics10101169
Jeon H-K, Yang C-S. Enhancement of Ship Type Classification from a Combination of CNN and KNN. Electronics. 2021; 10(10):1169. https://doi.org/10.3390/electronics10101169
Chicago/Turabian StyleJeon, Ho-Kun, and Chan-Su Yang. 2021. "Enhancement of Ship Type Classification from a Combination of CNN and KNN" Electronics 10, no. 10: 1169. https://doi.org/10.3390/electronics10101169