Advertisement

Object-Based Classification from Tiangong-2 Using Support Vector Machine Optimized with Evolutionary Algorithm

  • Huijiao Qiao
  • Xue Wan
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 541)

Abstract

Land cover information extraction using object-based image classification has become a widely accepted trend in remote sensing. Segmented objects have abundant features including spectrum, shape and texture, and feature selection affects the precision and efficiency of classification. However, how to select less features while achieving high classification accuracy remains unsolved. In this paper, an object-based image classification method based on Support Vector Machine (SVM) combined with Particle Swarm Optimization (PSO)-based feature selection evolutionary algorithm is proposed to evaluate its potential on land cover classification. The experiments results using Tiangong-2 Wide-band images demonstrate that the proposed SVM classification combined with PSO for low-middle resolution images can yield a preferable classification outcome especially for grassland, water and forest with the user’s accuracy higher than 90%.

Keywords

Tiangong-2 Object PSO SVM Feature selection Classification 

Notes

Acknowledgements

Thanks to China Manned Space Engineering for providing space science and application data products of Tiangong-2.

References

  1. 1.
    MSADC Homepage. http://www.msadc.cn/en/sjfw/xzsm/mbxz/. Accessed 10 July 2018
  2. 2.
    Soliman, O.S., Mahmoud, A.S.: Remote sensing satellite images classification using support vector machine and particle swarm optimization. In: Innovations in Bio-Inspired Computing and Applications (IBICA), Third International Conference on IEEE, pp. 280–285 (2012)Google Scholar
  3. 3.
    Vapnik, V.N.: The nature of statistical learning theory. IEEE Trans. Neural Netw. 8(6), 1564 (1997)CrossRefGoogle Scholar
  4. 4.
    Vapnik, V.N.: Statistical Learning Theory. Wiley, New York (1998)zbMATHGoogle Scholar
  5. 5.
    Cristianini, N., Shawe-Taylor, J, T.: An Introduction to Support Vector Machines. Cambridge University Press, CambridgeGoogle Scholar
  6. 6.
    Hsu, C.-W., Chang, C.-C.: A practical guide to support vector classification, 1–16 (2003)Google Scholar
  7. 7.
    Frohlich, H, Chapelle, O.: Feature selection for support vector machines by means of genetic algorithm. In: 15th IEEE International Conference, pp. 142–148. IEEE (2003)Google Scholar
  8. 8.
    Huang, C.L., Wang, C.J.: A GA-based feature selection and parameters optimization for support vector machines. Expert Syst. Appl. 31(2), 231–240 (2006)CrossRefGoogle Scholar
  9. 9.
    Yang, J., Honavar, V.: Feature Subset Selection Using a Genetic Algorithm. Feature Extraction, Construction and Selection, pp. 117–136. Springer, Boston, MA (1998)Google Scholar
  10. 10.
    Chen, Q., Chen, Y.: Genetic particle swarm optimization–based feature selection for very-high-resolution remotely sensed imagery object change detection. Sensors 16(8), 1204 (2016)CrossRefGoogle Scholar
  11. 11.
    Hall, M.A., Smith, L.A.: Feature selection for machine learning: comparing a correlation-based filter approach to the wrapper. In: FLAIRS Conference, pp. 235–239 (1999)Google Scholar
  12. 12.
    Huang, Y., Zhao, C.: Feature selection solution with high dimensionality and low-sample size for land cover classification in object-based image analysis. Remote Sens. 9(9), 939 (2017)CrossRefGoogle Scholar
  13. 13.
    Moradi, P., Gholampour, M.: A hybrid particle swarm optimization for feature subset selection by integrating a novel local search strategy. Appl. Soft Comput. 43, 117–130 (2016)CrossRefGoogle Scholar
  14. 14.
    Eberhart, R.C.: Particle swarm optimization: developments, applications and researches. In: Proceedings of the 2001 Congress on Evolutionary Computation, pp. 81–86 (2001)Google Scholar
  15. 15.
    Agrawal, R.K., Bawane, N.G.: Multiobjective PSO based adaption of neural network topology for pixel classification in satellite imagery. Appl. Soft Comput. 28, 217–225 (2015)CrossRefGoogle Scholar
  16. 16.
    Xue, B., Zhang, M.: Particle swarm optimization for feature selection in classification: Novel initialization and updating mechanisms. Appl. Soft Comput. 18, 261–276 (2014)CrossRefGoogle Scholar
  17. 17.
    Wang, X., Yang, J.: Feature selection based on rough sets and particle swarm optimization. Pattern Recogn. Lett. 28(4), 459–471 (2007)CrossRefGoogle Scholar
  18. 18.
    Bratton, D., Kennedy, J.: Defining a standard for particle swarm optimization. In: Swarm Intelligence Symposium, pp. 120–127. IEEE (2007)Google Scholar
  19. 19.
    Shi, Y., Eberhart, R.: A modified particle swarm optimizer. In: Evolutionary Computation Proceedings IEEE World Congress on Computational Intelligence, pp. 69–73. IEEE (1998)Google Scholar
  20. 20.
    Kennedy, J.: The particle swarm: social adaptation of knowledge. In: Evolutionary Computation IEEE International Conference, pp. 303–308. IEEE (1997)Google Scholar
  21. 21.
    Wikipedia Homepage. https://en.wikipedia.org/wiki/Particle_swarm_optimization. Accessed 25 Aug 2018
  22. 22.
    Nieto, P.J.G., Garcia-Gonzalo, E.: Hybrid PSO–SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability. Reliab. Eng. Syst. Saf. 138, 219–231 (2015)CrossRefGoogle Scholar
  23. 23.
    Huang, C.L., Dun, J.F.: A distributed PSO–SVM hybrid system with feature selection and parameter optimization. Appl. Soft Comput. 8(4), 1381–1391 (2008)CrossRefGoogle Scholar
  24. 24.
    Li, P., Hong, Z.: Genetic feature selection for texture classification. Geo-spatial Inf. Sci. 7(3), 162–166 (2004)CrossRefGoogle Scholar
  25. 25.
    Imaging, D.: eCognition Developer Software:9.01. Reference Book. Trimble Germany GmbH, Raunheim (2012)Google Scholar
  26. 26.
    Chaofan, W., Jinsong, D.: Object-based classification approach for greenhouse mapping using Landsat-8 imagery. Int. J. Agric. Biol. Eng. 9(1), 79–88 (2016)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Remote Sensing and Information EngineeringWuhan UniversityWuhanChina
  2. 2.Technology and Engineering Center for Space Utilization, Chinese Academy of ScienceBeijingChina
  3. 3.Key Laboratory of Space UtilizationChinese Academy of SciencesBeijingChina

Personalised recommendations