A modified shadow segmentation technique for satellite images

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Satellite images provide plenty of information about the the earth and it’s environment. However, presence of shadows hinders the image analysis process. This paper introduces a new technique for shadow identification which involves color models and an optimization algorithm. The RGB color image is transformed to C1C2C3 and HSI color images since they contain more shadow information than the RGB image. Subsequently these images are fed individually to the ant colony optimization algorithm which identifies shadows based on its properties. The resulting ouputs of the color models are combined using the Boolean operator which retrieves the binary image containing shadows.

  • References

      [1] P. L. Rosin and T. Ellis, “Image Difference Threshold Strategies and Shadow Detection,” in sixth British Machine Vision Conference, Birmingham, page 347-356, 1996.

      [2] W. Zhang, X.Z. Fang, and X. Yang, “Moving Cast Shadows Detection Based on Ratio Edge,” IEEE International Conference on Pattern Recognition, page 763-766, November 2006.

      [3] Y. L. Tian, M. Lu, and A. Hampapur, “Robust and Efficient Foreground Analysis for Real-time Video Surveillance,” IEEE Computer Vision and Pattern Recognition, 005, pp. I: 1182-1187.

      [4] A.A.Polidorio, F.C.Flores, N.N.Imai, A.M.Tomaselli and C.Franco, “Automatic Shadow Segmentation in Aerial Images”, Proc. Brazilian Symposium on Computer Graphics and Image Processing, 2003, pp. 270-277.

      [5] V V.J.D.Tsai, “A Comparative Study on Shadow Compensation of Color Aerial Images in Invariant Color Models”, IEEE Transactions on Geoscience and Remote Sensing, vol. 44, no. 6, pp. 1661-1671, June 2006. https://doi.org/10.1109/TGRS.2006.869980.

      [6] K.L.Chung, Y.R.Lin, Y.H.Huang, “Efficient Shadow Detection of Color Aerial Images Based Successive Thresholding Scheme”, IEEE Transactions on Geoscience and Remote Sensing, pp. 671-682, 2009. https://doi.org/10.1109/TGRS.2008.2004629.

      [7] Salvador E, Cavallaro A and Ebrahimi T, 2004, “Cast Shadow Segmentation using Invariant Color Features”, Computer Vision and Image Understanding, 95, pp. 238-259. https://doi.org/10.1016/j.cviu.2004.03.008.

      [8] V.Arevalo, J.Gonzalez and G.Ambrosio, “Shadow Detection in Color High-resolution Satellite Images”, International Journal of Remote Sensing, Vol.29, No.7, April 2008, 1945-1963. https://doi.org/10.1080/01431160701395302.

      [9] M.Dorigo, V.Maniezzo, A.Colorni “Ant System: Optimization by a Colony of Cooperating Agents”, Man and Cybernetics, vol.26, pp. 29-41, 1996. https://doi.org/10.1109/3477.484436.

      [10] N.Otsu, “A Threshold Selection Method from Gray Level Histograms”, IEEE Transactions on System, Man and Cybernetics, 1979.

      [11] D.Usha Nandini, Dr.Ezil Sam Leni, “A Survey of the Existing Shadow Detection Techniques”, International Conference on Control, Instrumentation, Communication and Computational Technologies, pp.175-177, 2014.

      [12] D.Usha Nandini, Dr.Ezil Sam Leni, “Shadow Identification using Ant Colony Optimization”, Journal of Theoretical and Applied Information Technology, vol. 78,no.2, pp.195-200, 2015.

      [13] M.Dorigo, L.M.Gambardella, “Ant Colony System: A Cooperative Learning Approach to the Travelling Salesman Problem”, IEEE Transactions on Evolutionary Computation, vol. 1, pp. 53-66, 1997. https://doi.org/10.1109/4235.585892.




Article ID: 21565
DOI: 10.14419/ijet.v7i4.21565

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.