Optimal Range Segmentation Parameters through Genetic Algorithms

A wide number of algorithmsfor surjtiacesegmentationin range images have been recentlyproposed characterizedby different approaches (edgefilling, regiongrowing, ...), different su$ace types (eitherfor planar or curved suifaces) and different parameters involved. Optimization of the parameter set is a particularly critical task since the range of parameter variability is often quite large:parameter selection depends on surface type, sensors and the required speed which strongly affectpeqormance. A framework for parameters optimization is proposed based on genetic algorithms. Such algorithms allow a general approach that has been succesfully applied on different state-of-the-art segmenters and different range image databases.

• Type: Conference
• Year: 2000
• Where: ICPR
• Authors: Luigi Cinque, Stefano Levialdi, Gianluca Pignalberi, Rita Cucchiara, Stefano Martinz
• Keywords: Computer Vision, ICPR 2000, Parameter Variability, Parameters Optimization, Such Algorithms