High-Speed Ship Detection in SAR Images Based on a Grid Convolutional Neural Network
Abstract
:1. Introduction
- The detection speed of our proposed method is faster than the existing other methods.
- We established a brand new network structure G-CNN.
2. Methodology
2.1. Dataset
2.2. G-CNN
Algorithm 1 [25]. Batch Normalizing Transform, applied to activation x over a batch. |
Input: Values of x over a batch: Parameters to be learned: |
Output: |
2.3. Model
2.4. Anchor Box
2.5. Evaluation Indicator
3. Experiments and Results
3.1. Establishment of Training Model
3.2. Feature Maps
3.3. Results of G-CNN
3.4. Results of Different Methods
3.5. Actual Ship Detection for RadarSat-1 and Gaofen-3
4. Discussion
4.1. Complexity Analysis
4.2. Detection Time
5. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Schwartz, G.; Alvarez, M.; Varfis, A.; Kourti, N. Elimination of false positives in vessels detection and identification by remote sensing. In Proceedings of the 2002 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Toronto, ON, Canada, 24–28 June 2002; pp. 116–118. [Google Scholar]
- Sempreviva, A.M.; Barthelmie, R.J.; Pryor, S.C. Review of Methodologies for Offshore Wind Resource Assessment in European Seas. Surv. Geophys. 2008, 29, 471–497. [Google Scholar] [CrossRef]
- Raj, N.; Sethunadh, R.; Aparna, P.R. Object detection in SAR image based on bandlet transform. J. Vis. Commun. Image Represent. 2016, 40, 376–383. [Google Scholar] [CrossRef]
- Kuttikkad, S.; Chellappa, R. Non-gaussian CFAR techniques for target detection in high resolution SAR images. In Proceedings of the IEEE International Conference on Image Processing (ICIP-94.), Austin, TX, USA, 13–16 November 1994. [Google Scholar]
- Anastassopoulos, V.; Lampropoulos, G.A. Optimal CFAR detection in Weibull clutter. IEEE Trans. Aerosp. Electron. Syst. 1995, 31, 52–64. [Google Scholar] [CrossRef]
- Zhu, J.; Qiu, X.; Pan, Z.; Zhang, Y.; Lei, B. Projection Shape Template-Based Ship Target Recognition in TerraSAR-X Images. IEEE Geosci. Remote Sens. Lett. 2017, 14, 222–226. [Google Scholar] [CrossRef]
- Wang, C.; Bi, F.; Chen, L.; Chen, J. A novel threshold template algorithm for ship detection in high-resolution SAR images. In Proceedings of the IEEE Geoscience and Remote Sensing Symposium, Beijing, China, 10–15 July 2016. [Google Scholar]
- Lecun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436. [Google Scholar] [CrossRef] [PubMed]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet classification with deep convolutional neural networks. In Proceedings of the International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA, 3–6 December 2012. [Google Scholar]
- Girshick, R.; Donahue, J.; Darrell, T.; Malik, J. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014; pp. 580–587. [Google Scholar]
- Girshick, R. Fast R-CNN. In Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7–13 December 2015; pp. 1440–1448. [Google Scholar]
- Ren, S.; He, K.; Girshick, R.; Sun, J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 1137–1149. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Redmon, J.; Divvala, S.; Girshick, R.; Farhadi, A. You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
- Redmon, J.; Farhadi, A. YOLO9000: Better, Faster, Stronger. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 6517–6525. [Google Scholar]
- Joseph, R.; Ali, F. YOLOv3: An Incremental Improvement. Available online: https://pjreddie.com/media/files/papers/YOLOv3.pdf (accessed on 1 April 2019).
- Li, J.; Qu, C.; Peng, S.; Jiang, Y. Ship Detection in SAR images Based on Generative Adversarial Network and Online Hard Examples Mining. J. Electron. Inf. Technol. 2019, 41, 143–149. [Google Scholar]
- Li, J.; Qu, C.; Peng, S.; Deng, B. Ship detection in SAR images based on convolutional neural network. Syst. Eng. Electron. 2018, 40, 1953–1959. [Google Scholar]
- Li, J.; Qu, C.; Shao, J. Ship detection in SAR images based on an improved faster R-CNN. In Proceedings of the SAR Big Data Era: Models, Methods, Applications (BIGSARDATA), Beijing, China, 13–14 November 2017. [Google Scholar]
- Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.Y.; Berg, A.C. SSD: Single Shot MultiBox Detector. In Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands, 11–14 October 2016; pp. 21–37. [Google Scholar]
- Github. Available online: https://github.com/tzutalin/labelImg (accessed on 7 May 2019).
- Lopes, A.; Touzi, R.; Nezry, E. Adaptive speckle filters and scene heterogeneity. IEEE Trans. Geosci. Remote Sens. 1990, 28, 992–1000. [Google Scholar] [CrossRef]
- Simonyan, K.; Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recongnition. Available online: http://vc.cs.nthu.edu.tw/home/paper/codfiles/melu/201604250548/VGG.pdf (accessed on 1 April 2019).
- Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going Deeper with Convolutions. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015. [Google Scholar]
- Howard, A.G.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. 2017. Available online: https://arxiv.org/pdf/1704.04861.pdf (accessed on 1 April 2019).
- Ioffe, S.; Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the International Conference on Machine Learning, Lille, France, 6–11 July 2015. [Google Scholar]
- Jarrett, K.; Kavukcuoglu, K.; LeCun, Y. What is the best multi-stage architecture for object recognition? In Proceedings of the 2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan, 29 September–2 October 2009; pp. 2146–2153. [Google Scholar]
- Everingham, M.; Eslami, S.A.; Van Gool, L.; Williams, C.K.; Winn, J.; Zisserman, A. The Pascal Visual Object Classes Challenge: A Retrospective. Int. J. Comput. Vis. 2015, 111, 98–136. [Google Scholar] [CrossRef]
- Hosang, J.; Benenson, R.; Schiele, B. Learning Non-maximum Suppression. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 6469–6477. [Google Scholar]
- Buckland, M.; Gey, F. The Relationship between Recall and Precision. J. Am. Soc. Inf. Sci. 1994, 45, 12–19. [Google Scholar] [CrossRef]
- Liu, L.; Tamer Özsu, M. Mean Average Precision; Springer: New York, NY, USA, 2009. [Google Scholar]
- Manaswi, N.K. Understanding and Working with Keras. In Deep Learning with Applications Using Python; Apress: Berkeley, CA, USA, 2018. [Google Scholar]
- Kingma, D.; Ba, J. Adam: A Method for Stochastic Optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
- Ketkar, N. Deep Learning with Python, Chapter 8, Stochastic Gradient Descent. Available online: https://link.springer.com/content/pdf/10.1007/978-1-4842-2766-4_8.pdf (accessed on 3 May 2019).
- You, Y.; Gitman, I.; Ginsburg, B. Scaling SGD Batch Size to 32K for ImageNet Training. 2017. Available online: https://arxiv.org/abs/1708.03888v1 (accessed on 1 April 2019).
- Yao, Y.; Rosasco, L.; Caponnetto, A. On Early Stopping in Gradient Descent Learning. Constr. Approx. 2007, 26, 289–315. [Google Scholar] [CrossRef]
- Zeiler, M.D.; Fergus, R. Visualizing and Understanding Convolutional Networks. 2013. Available online: https://arxiv.org/abs/1311.2901 (accessed on 3 May 2019).
- Gui, Y.; Li, X.; Xue, L. A Multilayer Fusion Light-Head Detector for SAR Ship Detection. Sensors 2019, 19, 1124. [Google Scholar] [CrossRef]
- Wang, Y.; Chao, W.; Hong, Z. Combining a single shot multibox detector with transfer learning for ship detection using sentinel-1 SAR images. Remote Sens. Lett. 2018, 9, 780–788. [Google Scholar] [CrossRef]
- Wang, J.; Lu, C.; Jiang, W. Simultaneous Ship Detection and Orientation Estimation in SAR Images Based on Attention Module and Angle Regression. Sensors 2018, 18, 2851. [Google Scholar] [CrossRef] [PubMed]
- Lin, H.; Chen, H.; Wang, H.; Yin, J.; Yang, J. Ship Detection for PolSAR Images via Task-Driven Discriminative Dictionary Learning. Remote Sens. 2019, 11, 769. [Google Scholar] [CrossRef]
- Zhang, S.; Wu, R.; Xu, K.; Wang, J.; Sun, W. R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery. Remote Sens. 2019, 11, 631. [Google Scholar] [CrossRef]
- Wang, Y.; Wang, C.; Zhang, H.; Dong, Y.; Wei, S. Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery. Remote Sens. 2019, 11, 531. [Google Scholar] [CrossRef]
- Chang, Y.-L.; Anagaw, A.; Chang, L.; Wang, Y.C.; Hsiao, C.-Y.; Lee, W.-H. Ship Detection Based on YOLOv2 for SAR Imagery. Remote Sens. 2019, 11, 786. [Google Scholar] [CrossRef]
Sensors | Place | Polarization | Resolution | #(Images) | #(Ships) |
---|---|---|---|---|---|
RadarSat-2 TerraSAR-X Sentinel-1 | Yantai, China Visakhapatnam, India | HH, VV, VH, HV | 1 m–15 m | 1160 | 2358 |
Name | Receptive Field | Anchor Boxes (Width, Height) |
---|---|---|
D-CNN-13 | Big | (9,11), (11,22), (14,26) |
D-CNN-26 | Medium | (16,40), (17,12), (27,57) |
D-CNN-52 | Small | (28,17), (57,28), (69,72) |
Dataset | Recall | Precision | AP | Test Time per Image |
---|---|---|---|---|
SSDD | 89.46% | 82.20% | 87.48% | 21.12 ms |
ESSDD | 92.13% | 90.34% | 90.16% | 21.36 ms |
No. | D-CNN-13 | D-CNN-26 | D-CNN-52 | AP | Test Time |
---|---|---|---|---|---|
1 | √ | 33.78% | 7 ms | ||
2 | √ | 59.51% | 11 ms | ||
3 | √ | 62.95% | 14 ms | ||
4 | √ | √ | 75.93% | 15 ms | |
5 | √ | √ | 72.40% | 16 ms | |
6 | √ | √ | 71.60% | 19 ms | |
7 | √ | √ | √ | 90.16% | 21 ms |
No. | Sensor | Polarization | Resolution | Time | Position |
---|---|---|---|---|---|
Image 1 | RadarSat-1 | HH | 30 m | 16 June 2002 | Vancouver, Canada. |
Image 2 | Gaofen-3 | HH | 1 m | 17 August 2016 | Wuhan, China. |
No. | #(Ground Truth) | #(TP) | #(FN) | #(FP) | Recall | Precision |
---|---|---|---|---|---|---|
Image 1 | 21 | 20 | 1 | 2 | 90.90% | 95.24% |
Image 2 | 73 | 69 | 4 | 7 | 90.79% | 94.52% |
© 2019 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 (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, T.; Zhang, X. High-Speed Ship Detection in SAR Images Based on a Grid Convolutional Neural Network. Remote Sens. 2019, 11, 1206. https://doi.org/10.3390/rs11101206
Zhang T, Zhang X. High-Speed Ship Detection in SAR Images Based on a Grid Convolutional Neural Network. Remote Sensing. 2019; 11(10):1206. https://doi.org/10.3390/rs11101206
Chicago/Turabian StyleZhang, Tianwen, and Xiaoling Zhang. 2019. "High-Speed Ship Detection in SAR Images Based on a Grid Convolutional Neural Network" Remote Sensing 11, no. 10: 1206. https://doi.org/10.3390/rs11101206
APA StyleZhang, T., & Zhang, X. (2019). High-Speed Ship Detection in SAR Images Based on a Grid Convolutional Neural Network. Remote Sensing, 11(10), 1206. https://doi.org/10.3390/rs11101206