International E-publication: Publish Projects, Dissertation, Theses, Books, Souvenir, Conference Proceeding with ISBN.  International E-Bulletin: Information/News regarding: Academics and Research

Study of Road Extraction Based on a Snake Model

    ,

Author Affiliations

  • 1Department of Mathematics, Science and Research Branch, Islamic Azad University, Tehran, IRAN
  • 2Department of Geometric Engineering, Collage of Engineering, University Of Tehran, Tehran, IRAN

Res. J. Recent Sci., Volume 5, Issue (1), Pages 1-8, January,2 (2016)

Abstract

The extraction of linear features like roadsides from satellite images is an important task in engineering sciences. In this paper, we aims to find the best curves which represent the roadsides visible in satellite images. An improved hybrid mathematical model based on a snake model is proposed to represents the linear features. Snake is a parametric curve which is permitted to deform from some arbitrary initial location toward the desired final location by reducing an energy function based on the internal and external energy. The model first uses the ant colony algorithm based on a proposed heuristic information parameter to find the photometric constraints in the snake model and then a cubic spline is used to interpolate “smooth curves” to the points derived from the snake model. In comparison of our model with other snake algorithms based on edge extraction, the model showed good results with improvement of about 10 percent. This success is due to the use of linear features knowledge (here roadsides) in the model.

References

  1. Amini J., Sarajian M.R., Blais J.A.R., Lucas C. and AziziA. (2002), Automatic road-side extraction from largescale image maps, International journal of applied earthobservation and geo information, 4(2), 95-107.
  2. Mohammadzadeh A. and Valadan Zoej M.J.A (2010)., Self-organizing fuzzy segmentation (SOFS) method forroad detection from high resolution satellite images, Photogrammetric Engineering and Remote Sensing (PEand RS), 76(1).
  3. Kass M., Witkin A. and Terzopoulos D. (1988). Snakes, Active contour models, Int. J. Comput. Vis, 1(4), 321331.
  4. Bentabet L., Jodouin S. and Ziou D. (2003), Road vectorsupdate using SAR imagery, a snake-based method, IEEETransactions on Geosciences and Remote Sensing, 41,17851803.
  5. Neuenschwander W. (1996), Elastic Deformable Contourand Surface Models for 2-D and 3-D ImageSegmentation, Hartung-Gorre Verlag, Konstanz.
  6. Courant R. and Hilbert D. (1989), Methods ofMathematical Physics, Volume 1. Wiley, New York.
  7. Fua P. and Leclerc Y. (1990), Model Driven EdgeDetection, Mach. Vis. Applicat.
  8. Luis Osbipo S. (1977), Applied Numerical Analysis,Addision-Wesley Publishing November.
  9. Dorigo M., Birattari M. and Stutzle T. (2006), Antcolony optimization, IEEE Computational IntelligenceMagazine, (1), 2839.
  10. Neuenschwander W. (1996), From Ziplok Snakes toVelcro Surfaces, Mach. Vis. Applicat.
  11. Harvey W. (1999), Performance evaluation for roadextraction, In Proceedings of the ISPRS Workshop on 3DGeospatial Data Production, Meeting ApplicationRequirements.
  12. Doucette P., Agouris P. and stefanidis A. (2004), Automated road extraction from high resolutionmultispectral imagery, Photogrammetric EngineeringRemote Sensing, 70(12), 1405-1416.