GANN Snake for Object Extractions from High Resolution Satellite Imagery

Active contour model, well known as snakes are used to extract objects like land parcels and buildings from high resolution satellite imageries like IKONOS and Quickbird. Object extraction from satellite imagery has more a long history. However, increasing image variation, required level of details and higher resolution imagery acquired, object extractions have to be improved continuously. Evolutionary computing approaches can enhance satellite imagerypsilas object extraction. This paper discusses the prototyping of a genetic algorithm (GA) and neural network (NN) snake. The coefficients for snake energy obtained through GANN are compared with ordinary snake for performance.

[1]  G. Sohn,et al.  Extraction of buildings from high-resolution satellite data and airborne Lidar , 2000 .

[2]  Tim J. Dennis,et al.  An adaptive implementation of the SUSAN method for image edge and feature detection , 1997, Proceedings of International Conference on Image Processing.

[3]  Raymond Chiong,et al.  An improved snake for automatic building extraction , 2007 .

[4]  Luc Van Gool,et al.  A probabilistic approach to roof extraction and reconstruction , 2002 .

[5]  Joachim Weickert,et al.  Coherence-Enhancing Diffusion Filtering , 1999, International Journal of Computer Vision.

[6]  Neil Davey,et al.  Analysis of Human Motion Using Snakes and Neural Networks , 2000, AMDO.

[7]  Yi-Hsing Tseng,et al.  SEMIAUTOMATED BUILDING EXTRACTION BASED ON CSG MODEL-IMAGE FITTING , 2003 .

[8]  Armin Grün.  Potential and limitations of highresolution satellite imagery , 2000 .

[9]  T. H. Kolbe,et al.  Integration of 2D and 3D reasoning for building reconstruction using a generic hierarchical model , 1997 .

[10]  Wolfgang Förstner,et al.  Towards automatic building extraction from high-resolution digital elevation models , 1995 .

[11]  S. D. Mayungaa,et al.  SEMI-AUTOMATIC BUILDING EXTRACTION UTILIZING QUICKBIRD IMAGERY , 2005 .

[12]  Clive S. Fraser,et al.  Processing of Ikonos imagery for submetre 3D positioning and building extraction , 2002 .

[13]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[14]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[15]  Martin Kerschner.  HOMOLOGOUS TWIN SNAKES INTEGRATED IN A BUNDLE BLOCK ADJUSTMENT , 1998 .

[16]  Heinz Rüther,et al.  Application of snakes and dynamic programming optimisation technique in modeling of buildings in informal settlement areas , 2002 .

[17]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[18]  Andrew Zisserman,et al.  A PLANE-SWEEP STRATEGY FOR THE 3D RECONSTRUCTION OF BUILDINGS FROM MULTIPLE IMAGES , 2000 .

[19]  Laurent D. Cohen,et al.  A finite element method applied to new active contour models and 3D reconstruction from cross sections , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[20]  Josiane Zerubia,et al.  Building extraction from digital elevation models , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[21]  T. Toutin,et al.  3D MODELS FOR HIGH RESOLUTION IMAGES: EXAMPLES WITH QUICKBIRD, IKONOS AND EROS , 2002 .

[22]  I. Dowman,et al.  Data fusion of high-resolution satellite imagery and LiDAR data for automatic building extraction * , 2007 .

[23]  Yun Zhang,et al.  Semi-Automatic Building Extraction Utilizing QuickBird Imagery , 2005 .