Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 23, pp 34173–34191 | Cite as

Superpixel-based principal component analysis for high resolution remote sensing image classification

  • Tengfei SuEmail author
Article
  • 83 Downloads

Abstract

In object-based image analysis (OBIA), it is often difficult to select the most useful features from a large number of segment-based information. The problem of choosing superpixel-based features is also very challenging. In order to solve this issue, this paper proposes a principal component analysis (PCA)-based method for superpixel-based classification of high resolution remote sensing imagery. This technique transforms the spectral features of superpixels, and the resulted feature variables are used to train a support vector machine classifier. Experiments based on 4 high resolution multispectral images indicated that although the performance is sensitive to the two parameters, the proposed method can increase classification accuracy effectively.

Keywords

Image classification Superpixel Principal component analysis Feature transform 

Notes

Acknowledgments

This work is supported by national natural science foundation of China, under grant of 61701265. The anonymous reviewers are sincerely thanked because of their constructive comments which helped improve the quality of this paper.

References

  1. 1.
    Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2012) SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282.  https://doi.org/10.1109/TPAMI.2012.120 CrossRefGoogle Scholar
  2. 2.
    Belgiu M, Dragut L (2016) Random forest in remote sensing: a review of applications and future directions. ISPRS J Photogramm Remote Sens 114:24–31.  https://doi.org/10.1016/j.isprsjprs.2016.01.011 CrossRefGoogle Scholar
  3. 3.
    Benz UC, Hofmann P, Willhauck G, Lingenfelder I, Heynen M (2004) Multiresolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS J Photogramm Remote Sens 58:239–258.  https://doi.org/10.1016/j.isprsjprs.2003.10.002 CrossRefGoogle Scholar
  4. 4.
    Blaschke T, Hay GJ, Kelly M, Lang S, Hofmann P, Addink E, Queiroz Feitosa R et al (2014) Geographic object-based image analysis-towards a new paradigm. ISPRS J Photogramm Remote Sens 87:180–191.  https://doi.org/10.1016/j.isprsjprs.2013.09.014 CrossRefGoogle Scholar
  5. 5.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32.  https://doi.org/10.1023/A:101093340 CrossRefzbMATHGoogle Scholar
  6. 6.
    Cai J, Huang B, Song Y (2017) Using multi-source geospatial big data to identify the structure of polycentric cities. Remote Sens Environ 202:210–221.  https://doi.org/10.1016/j.rse.2017.06.039 CrossRefGoogle Scholar
  7. 7.
    Chang C, Lin C (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1–27.  https://doi.org/10.1145/1961189.1961199 CrossRefGoogle Scholar
  8. 8.
    Chen K, Fu K, Yan M, Gao X, Sun X, Wei X (2017) Semantic segmentation of aerial images with shuffling convolutional neural networks. IEEE Geosci Remote Sens Lett 15(2):173–177.  https://doi.org/10.1109/LGRS.2017.2778181 CrossRefGoogle Scholar
  9. 9.
    Chen Y, Jiang H, Jia X, Ghamisi P (2016) Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans Geosci Remote Sens 54(10):6232–6251.  https://doi.org/10.1109/TGRS.2016.2584107 CrossRefGoogle Scholar
  10. 10.
    Congalton RG, Green K (2008) Assessing the accuracy of remotely sensed data: principals and practices. 2nd ED. CRC Press, USACrossRefGoogle Scholar
  11. 11.
    Gao Y, Mas JF, Kerle N, Navarrete Pacheco JA (2011) Optimal region growing segmentation and its effect on classification accuracy. Int J Remote Sens 32:3747–3763.  https://doi.org/10.1080/01431161003777189 CrossRefGoogle Scholar
  12. 12.
    Längkvist M, Kiselev A, Alirezaie M, Loutfi A (2016) Classification and segmentation of satellite orthoimagery using convolutional neural networks. Remote Sens 8(4):329.  https://doi.org/10.3390/rs8040329 CrossRefGoogle Scholar
  13. 13.
    Levinshtein A, Stere A, Kutulakos KN, Fleet DJ, Dickinson SJ, Siddiqi K (2009) TurboPixels: fast superpixels using geometric flows. IEEE Trans Pattern Anal Mach Intell 31(12):2290–2297.  https://doi.org/10.1109/TPAMI.2009.96 CrossRefGoogle Scholar
  14. 14.
    Liu D, Xia F (2010) Assessing object-based classification: advantages and limitations. Remote Sens Lett 1(4):187–194.  https://doi.org/10.1080/01431161003743173 CrossRefGoogle Scholar
  15. 15.
    Niesterowicz J, Stepinski TF (2017) Pattern-based, multi-scale segmentation and regionalization of EOSD land cover. Int J Appl Earth Obs Geoinf 62:192–200.  https://doi.org/10.1016/j.jag.2017.06.012 CrossRefGoogle Scholar
  16. 16.
    Panboonyuen T, Jitkajornwanich K, Lawawirojwong S, Srestasathiern P, Vateekul P (2017) Road segmentation of remotely-sensed images using deep convolutional neural networks with landscape metrics and conditional random fields. Remote Sens 9(7):680.  https://doi.org/10.3390/rs9070680 CrossRefGoogle Scholar
  17. 17.
    Peña JM, Gutiérrez PA, Hervás-Martínez C, Six J, Plant RE, López-Granados F (2014) Object-based image classification of summer crops with machine learning methods. Remote Sens 6:5019–5041.  https://doi.org/10.3390/rs6065019 CrossRefGoogle Scholar
  18. 18.
    Stehman S, Wickham J (2011) Pixels, blocks of pixels, and polygons: choosing a spatial unit for thematic accuracy assessment. Remote Sens Environ 115:3044–3055.  https://doi.org/10.1016/j.rse.2011.06.007 CrossRefGoogle Scholar
  19. 19.
    Su T, Zhang S, Tian Y (2019) Extracting croplands in western Inner Mongolia by using random forest and temporal feature selection. J Spat Sci.  https://doi.org/10.1080/14498596.2018.1552542
  20. 20.
    Su T (2017) Efficient Paddy field mapping using Landsat-8 imagery and object-based image analysis based on advanced fractal net evolution approach. GISci Remote Sens 54(3):354–380.  https://doi.org/10.1080/15481603.2016.1273438 CrossRefGoogle Scholar
  21. 21.
    Yang J, He Y, Caspersen J (2017) Region merging using local spectral angle thresholds: a more accurate method for hybrid segmentation of remote sensing images. Remote Sens Environ 190:137–148.  https://doi.org/10.1016/j.rse.2016.12.011 CrossRefGoogle Scholar
  22. 22.
    Yu B, Yang L, Chen F (2018) Semantic segmentation for high spatial resolution remote sensing images based on convolution neural network and pyramid pooling module. IEEE J-STARS 11(9):3252–3261.  https://doi.org/10.1109/JSTARS.2018.2860989 CrossRefGoogle Scholar
  23. 23.
    Zhang L, Zhang L, Du B (2016b) Deep learning for remote sensing data: a technical tutorial on the state of the art. IEEE GEOSci Remote Sens M 4(2):22–40.  https://doi.org/10.1109/MGRS.2016.2540798 CrossRefGoogle Scholar
  24. 24.
    Zhang X, Sun Y, Shang K, Zhang L, Wang S (2016a) Crop classification based on feature band set construction and object-oriented approach using Hyperspectral images. IEEE J-STARS 9(9):4117–4128.  https://doi.org/10.1109/JSTARS.2016.2577339 CrossRefGoogle Scholar
  25. 25.
    Zhu X, Tuia D, Mou L, Xia G, Zhang L, Xu F, Fraundorfer F (2017) Deep learning in remote sensing: a comprehensive review and list of resources. IEEE GEOSci Remote Sens M 5(4):8–36.  https://doi.org/10.1109/MGRS.2017.2762307 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of Water Conservancy and Civil EngineeringInner Mongolia Agricultural UniversityHohhotChina

Personalised recommendations