Recognising building patterns using matched filters and genetic search

This paper is concerned with recognising buildings in aerial images. We abstract the images in terms of relational graphs. Specifically, we use Delaunay triangulations to represent the arrangement of located buildings. Localisation is realised using matched filters. The filters are trained by drawing upon the duality between convolution in the image domain and multiplication in the Fourier domain. The matched filters prove to be remarkably stable. We match Delaunay graphs representing image pairs using genetic search with a Bayesian relational consistency criterion as fitness function. The use of genetic search allows us to perform the optimisation without the traditional problems of sensitivity to initial conditions and convergence to local optima.

[1]  Michel Roux,et al.  Feature matching for building extraction from multiple views , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[2]  King-Sun Fu,et al.  A distance measure between attributed relational graphs for pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  V. Rao Vemuri,et al.  Multiniche Crowding in Genetic Algorithms and Its Application to the Assembly of DNA Restriction-Fragments , 1994, Evolutionary Computation.

[4]  Larry J. Eshelman,et al.  The CHC Adaptive Search Algorithm: How to Have Safe Search When Engaging in Nontraditional Genetic Recombination , 1990, FOGA.

[5]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Edwin R. Hancock,et al.  Matching delaunay graphs , 1997, Pattern Recognit..

[7]  Ramakant Nevatia,et al.  Detection of buildings using perceptual grouping and shadows , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Edwin R. Hancock,et al.  Structural Matching by Discrete Relaxation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Josef Kittler,et al.  Minimum error thresholding , 1986, Pattern Recognit..

[10]  Robert M. Haralick,et al.  A Metric for Comparing Relational Descriptions , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Shaun Quegan,et al.  Matching map features to synthetic aperture radar (SAR) images using template matching , 1992, IEEE Trans. Geosci. Remote. Sens..

[12]  Dov Dori,et al.  Shape, Structure and Pattern Recognition , 1995 .

[13]  David B. Fogel,et al.  An introduction to simulated evolutionary optimization , 1994, IEEE Trans. Neural Networks.

[14]  Edwin R. Hancock,et al.  A Bayesian compatibility model for graph matching , 1996, Pattern Recognit. Lett..

[15]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[16]  Edwin R. Hancock,et al.  Relational matching with dynamic graph structures , 1995, Proceedings of IEEE International Conference on Computer Vision.

[17]  Sushil J. Louis,et al.  Syntactic Analysis of Convergence in Genetic Algorithms , 1992, FOGA.

[18]  Edwin R. Hancock,et al.  Relational matching by discrete relaxation , 1995, Image Vis. Comput..

[19]  Olivier D. Faugeras,et al.  Representing Stereo Data with the Delaunay Triangulation , 1990, Artif. Intell..

[20]  Edwin R. Hancock,et al.  Softening Discrete Relaxation , 1996, NIPS.

[21]  Edwin R. Hancock,et al.  Relational matching with mean field annealing , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[22]  Yong Gao,et al.  Comments on "Theoretical analysis of evolutionary algorithms with an infinite population size in continuous space. I. Basic properties of selection and mutation" [and reply] , 1998, IEEE Trans. Neural Networks.

[23]  Lawrence Davis,et al.  Bit-Climbing, Representational Bias, and Test Suite Design , 1991, ICGA.

[24]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[25]  Yuan Yan Tang,et al.  Multiple-level information source and entropy-reduced transformation models , 1991, Pattern Recognit..