Advertisement

A Novel Method of River Detection for High Resolution Remote Sensing Image Based on Corner Feature and SVM

  • Ziheng Tian
  • Chengdong Wu
  • Dongyue Chen
  • Xiaosheng Yu
  • Li Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7368)

Abstract

In this paper, a new method to detect rivers in high resolution remote sensing images based on corner feature and Support Vector Machine (SVM) is presented. It introduces corner feature into river detection for the first time. First, we detect corners in sample images and test images, and extract image corner feature with all the corners detected above. Then the corner feature and other feature of sample images, for example texture feature and entropy feature, are input into SVM for training. At last we obtain the water decision function, with which we classify each pixel into river region or background region. This method comprehensively utilizes the corner, entropy and texture feature of remote sensing images. Experimental results show that this method performances well in river automatic detection of remote sensing images.

Keywords

River Detection Feature Extraction Corner Feature SVM 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cheng, M.Y., Ye, Q., Zhang, S.M., Chen, Y.Y., Li, W.: Water Automatic Detection from SAR Image Based on Fuzzy Weighted SVM. Computer Engineering 35, 219–221 (2009)Google Scholar
  2. 2.
    Han, Y., Zheng, H., Cao, Q., Wang, Y.: An Effective Method for Bridge Detection from Satellite Imagery. In: Second IEEE Conference on Industrial Electronics and Applications, pp. 2753–2757 (2007)Google Scholar
  3. 3.
    Chen, A.J., Dong, G.H.: A Method to Rapidly Detect Great Rivers in High-Resolution Satellite Images. In: International Conference on Remote Sensing, pp. 322–325 (2010)Google Scholar
  4. 4.
    Zhang, L.L., Zhang, Y.N., Li, Y., Wang, M.: A Fast Detection of Bridges in SAR Images. Chinese Journal of Electronics 16, 481–484 (2007)MathSciNetGoogle Scholar
  5. 5.
    Xiao, C.H., Yung, N.H.C.: Curvature Scale Space Corner Detector with Adaptive Threshold and Dynamic Region of Support. In: Proceedings of the 17th International Conference on Pattern Recognition, pp. 791–794 (2004)Google Scholar
  6. 6.
    Xiao, C.H., Yung, N.H.C.: Corner detector based on global and local curvature properties. Optical Engineering 47, 057008-1–057008-12 (2008)Google Scholar
  7. 7.
    Wang, G.J.: Multi-Object Pattern Segmentation Based on Maximum Local Entropy Method. J. Huazhong Univ. of Sci. & Tech. 28, 4–5 (2000)Google Scholar
  8. 8.
    Pal, N.R., Pal, S.K.: Object-background segmentation using new definitions of entropy. In: IEE Proceedings E (Computers and Digital Techniques), vol. 136, pp. 284–295 (1989)Google Scholar
  9. 9.
    Cristianini, N., Campbell, C., Burges, C.: Kernel methods: Current research and future directions. Mach. Learn. 46, 5–9 (2002)CrossRefGoogle Scholar
  10. 10.
    Zhang, S.Y., Zhao, Y.M., Li, J.L.: Algorithm and implementation of image classification based on SVM. Computer Engineering and Applications 46, 40–42 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Ziheng Tian
    • 1
  • Chengdong Wu
    • 1
  • Dongyue Chen
    • 1
  • Xiaosheng Yu
    • 1
  • Li Wang
    • 1
  1. 1.College of Information Science & EngineeringNortheastern UniversityShenyangChina

Personalised recommendations