An Evolutionary Optimization Method for Parameter Search in 3D Points Cloud Reconstruction

Reconstruction of 3D laser scanned point clouds may generate a mesh characterized by a high number of triangles. Unfortunately, in Computer Aided Design environments neither a simple triangle reduction, nor decimation filters are feasible for mesh optimization, because of their intrinsic errors. In this paper we show how Genocop III can be effectively used to reconstruct a point cloud bounding the error under a certain threshold. Moreover, we define an optimized algorithm for evaluating the reconstruction error, that exploits AABB-trees and pre-computation and provides a useful metric to the genetic algorithm.

[1]  Vitoantonio Bevilacqua,et al.  Evolutionary approach to inverse planning in coplanar radiotherapy , 2007, Image Vis. Comput..

[2]  Gino van den Bergen Efficient Collision Detection of Complex Deformable Models using AABB Trees , 1997, J. Graphics, GPU, & Game Tools.

[3]  Zoltan-Csaba Marton,et al.  On Fast Surface Reconstruction Methods for Large and Noisy Datasets , 2009, IEEE International Conference on Robotics and Automation.

[4]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.

[5]  Tony DeRose,et al.  Surface reconstruction from unorganized points , 1992, SIGGRAPH.

[6]  Manuel Menezes de Oliveira Neto,et al.  A hole-filling strategy for reconstruction of smooth surfaces in range images , 2003, 16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003).

[7]  Z. Michalewicz,et al.  Genocop III: a co-evolutionary algorithm for numerical optimization problems with nonlinear constraints , 1995, Proceedings of 1995 IEEE International Conference on Evolutionary Computation.

[8]  Vitoantonio Bevilacqua,et al.  Improving a genetic algorithm segmentation by means of a fast edge detection technique , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[9]  David E. Goldberg,et al.  Genetic algorithms and Machine Learning , 1988, Machine Learning.

[10]  Zoltan-Csaba Marton,et al.  On fast surface reconstruction methods for large and noisy point clouds , 2009, 2009 IEEE International Conference on Robotics and Automation.

[11]  Vitoantonio Bevilacqua,et al.  Extending Hough Transform to a Points' Cloud for 3D-Face Nose-Tip Detection , 2008, ICIC.

[12]  William E. Lorensen,et al.  Decimation of triangle meshes , 1992, SIGGRAPH.

[13]  Michael M. Kazhdan,et al.  Poisson surface reconstruction , 2006, SGP '06.

[14]  P. Lancaster,et al.  Surfaces generated by moving least squares methods , 1981 .