SAR Ship Detection Using Image Histograms and Machine Learning Approach

Abstract

Detection of objects through remote sensing is a current research area. Ship detection in SAR images is a very intense research area today. Convenience is provided to those concerned in applications such as military surveillance and tracking of commercial ships. In this study, ship images were classified using the Hessian matrix and HOG algorithm. Using the eigenvalues of the Hessian matrix, the angle and orientation information of the HOG method was calculated. Thus, distinctive pixel characteristics were coded. The proposed method has achieved successful results in experimental studies.

Keywords

• Remote sensing
• Synthetic aperture radar
• Machine learning
• Eigenvalues

References

1. Huang S qi, Liu D zhi, Gao G qing, Guo X jian. A novel method for speckle noise reduction and ship target detection in SAR images. Pattern Recognit 2009;42:1533–42. https://doi.org/10.1016/J.PATCOG.2009.01.013.
2. Huo W, Huang Y, Pei J, Zhang Q, Gu Q, Yang J. Ship Detection from Ocean SAR Image Based on Local Contrast Variance Weighted Information Entropy. Sensors 2018, Vol 18, Page 1196 2018;18:1196. https://doi.org/10.3390/S18041196.
3. Fu J, Sun X, Wang Z, Fu K. An Anchor-Free Method Based on Feature Balancing and Refinement Network for Multiscale Ship Detection in SAR Images. IEEE Trans Geosci Remote Sens 2021;59:1331–44. https://doi.org/10.1109/TGRS.2020.3005151.
4. Pan X, Wu Z, Yang L, Huang Z. Ship Detection Method Based on Scattering Contribution for PolSAR Image. IEEE Geosci Remote Sens Lett 2022;19. https://doi.org/10.1109/LGRS.2021.3138796.
5. Liu T, Jiang Y, Marino A, Gao G, Yang J. The Polarimetric Detection Optimization Filter and its Statistical Test for Ship Detection. IEEE Trans Geosci Remote Sens 2022;60. https://doi.org/10.1109/TGRS.2021.3055801.
6. Gao G, Bai Q, Zhang C, Zhang L, Yao L. Dualistic cascade convolutional neural network dedicated to fully PolSAR image ship detection. ISPRS J Photogramm Remote Sens 2023;202:663–81. https://doi.org/10.1016/J.ISPRSJPRS.2023.07.006.
7. Zhu H, Xie Y, Huang H, Jing C, Rong Y, Wang C. DB-YOLO: A Duplicate Bilateral YOLO Network for Multi-Scale Ship Detection in SAR Images. Sensors 2021, Vol 21, Page 8146 2021;21:8146. https://doi.org/10.3390/S21238146.
8. Guo H, Yang X, Wang N, Gao X. A CenterNet++ model for ship detection in SAR images. Pattern Recognit 2021;112:107787.

9. Heiselberg P, Sørensen K, Heiselberg H. Ship velocity estimation in SAR images using multitask deep learning. Remote Sens Environ 2023;288:113492. https://doi.org/10.1016/J.RSE.2023.113492.
10. Liu L, Fu L, Zhang Y, Ni W, Wu B, Li Y, et al. CLFR-Det: Cross-level feature refinement detector for tiny-ship detection in SAR images. Knowledge-Based Syst 2024;284:111284. https://doi.org/10.1016/J.KNOSYS.2023.111284.
11. Hanbay K, Özdemir TB. SAR Ship Detection Based on Differential Image Analysis and Machine Learning Approach. Int. Conf. Eng. Soc. Sci. Humanit., Mecca: 2024, p. 46.
12. Copernicus Data Space Ecosystem | Europe’s eyes on Earth 2024. https://dataspace.copernicus.eu/.
13. Dalal N, Triggs B. Histograms of oriented gradients for human detection. Proc - 2005 IEEE Comput Soc Conf Comput Vis Pattern Recognition, CVPR 2005 2005;I:886–93. https://doi.org/10.1109/CVPR.2005.177.
14. Hanbay K, Alpaslan N, Talu MF, Hanbay D, Karci A, Kocamaz AF. Continuous rotation invariant features for gradient-based texture classification. Comput Vis Image Underst 2015;132:87–101. https://doi.org/10.1016/J.CVIU.2014.10.004.
15. Ojala T, Pietikäinen M, Mäenpää T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 2002;24:971–87. https://doi.org/10.1109/TPAMI.2002.1017623.