Superquadric modeling of multiple objects from shading images using genetic algorithms

This paper describes an application of genetic algorithms (GAs) to the modeling of multiple objects from CCD images. Shape modeling is a very important issue for shape recognition for robot vision, representing 3-D shapes in the virtual world, and so on. Superquadrics are often used for shape modeling because they can represent various shapes by using a single equation. The proposed method estimates the superquadric parameters of every object from shading images which are taken with a CCD camera. The parameter estimation is performed by GAs because the GAs can efficiently find the optimized solution. The superquadric parameters are represented by strings. The string is evaluated by the similarity between the given 2-D shading image and the calculated shading image from the 3-D shape represented by the parameters. In the proposed method, the sharing scheme is used for finding multiple solutions efficiently. Some results of the computer experiments demonstrate that the proposed method can provide good model descriptions from shading images