Advertisement

A Transfer Learning Method for Ship Target Recognition in Remote Sensing Image

  • Hongbo LiEmail author
  • Bin Guo
  • Hao Chen
  • Shuai Han
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 516)

Abstract

In this paper, an effective approach of ship target recognition is proposed. This method based on the theory of transfer learning aims at using labeled ships with different imaging angles and different resolutions to help identifying unlabeled ships in a fixed angle. Since training ship samples and test ship samples are imaging in different angles, they obey different distributions. However, in traditional machine learning method, training data and test data obey the same distribution. In order to solve this problem, we proposed a method called mapped subspace alignment (MSA) which is different from other domain adaptation methods. While maximizing the difference between different categories, it first uses Isometric Feature Mapping (Isomap) to generate subspace and uses objective functions to spatial alignment and probabilistic adaptation. This paper focuses on the identification of three types of ships which are destroyers, cruisers, and aircraft carriers basing on MSA. The experimental results show that this method is better than several state-of-the-art methods.

Keywords

Ship target recognition Transfer learning Domain adaptation 

Notes

Acknowledgments

This work was supported in part by a grant from the Defense Industrial Technology Development Program (No. JCKY2016603C004).

References

  1. 1.
    Bi F, Liu F, Gao L. A hierarchical salient-region based algorithm for ship detection in remote sensing images. In: Lecture notes in electrical engineering; 2010, vol. 67. Berlin/Heidelberg, Germany: Springer.Google Scholar
  2. 2.
    Du Q, Zhang Y, Liu W et al. Ship target classification based on Hu invariant moments and ART for maritime video surveillance. In: International conference on transportation information and safety; 2017. p. 414–9,  https://doi.org/10.1109/ictis.2017.8047799.
  3. 3.
    Fernando B, Habrard A, Sebban M et al. Unsupervised visual domain adaptation using subspace alignment. In: IEEE international conference on computer vision; 2014, vol. 58, no. 8. p. 2960–7,  https://doi.org/10.1109/iccv.2013.368.
  4. 4.
    Gong B, Shi Y, Sha F et al. Geodesic flow kernel for unsupervised domain adaptation. In: IEEE conference on computer vision and pattern recognition; 2012. p. 1–8.Google Scholar
  5. 5.
    Grauman K. Geodesic flow kernel for unsupervised domain adaptation. In: IEEE conference on computer vision & pattern recognition; 2012, vol. 157, no. 10. p. 2066–2073.Google Scholar
  6. 6.
    Long M, Wang J, Ding G et al. Transfer feature learning with joint distribution adaptation. In: IEEE international conference on computer vision; 2014. p. 2200–7.Google Scholar
  7. 7.
    Pan SJ, Tsang IW, Kwok JT, Yang Q, et al. Domain adaptation via transfer component analysis. IEEE Trans Neural Netw. 2011;22(2):199–210.CrossRefGoogle Scholar
  8. 8.
    Tenenbaum JB, de Silva V, Langford J. A global geometric framework for nonlinear dimensionality reduction. Science. 2000;290(5500):2319–38.CrossRefGoogle Scholar
  9. 9.
    Zhang J, Li W, Ogunbona P. Joint geometrical and statistical alignment for visual domain adaptation. In: IEEE conference on computer vision and pattern recognition; 2017.Google Scholar
  10. 10.
    Zhu C, Zhou H, Wang R, et al. A novel hierarchical method of ship detection from spaceborne optical image based on shape and texture features. IEEE Trans Geosci Remote Sens. 2010;48(9):3446–56.  https://doi.org/10.1109/tgrs.2010.2046330.CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.School of Electronic and Information EngineeringHarbin Institute of TechnologyHarbinChina

Personalised recommendations