A Neural Architecture for 3D Segmentation

An original neural scheme for segmentation of range data is presented, which is part of a more general 3D vision system for robotic applications. The entire process relies on a neural architecture aimed to perform first order image irradiance analysis, that is local estimation of magnitude and orientation of the image irradiance gradient.

[1]  Roberto Pirrone,et al.  Part-Based Segmentation and Modeling of Range Data by Moving Target , 2001 .

[2]  Ruzena Bajcsy,et al.  Volumetric segmentation of range images of 3D objects using superquadric models , 1993 .

[3]  Umberto Maniscalco,et al.  A new robust approach to image shading analysis and 3-D shape reconstruction , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[4]  A. Chella,et al.  Conceptual representations of actions for autonomous robots , 2001, Robotics Auton. Syst..

[5]  J. Koenderink,et al.  Representation of local geometry in the visual system , 1987, Biological Cybernetics.

[6]  Frank P. Ferrie,et al.  Darboux Frames, Snakes, and Super-Quadrics: Geometry from the Bottom Up , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Ennio Mingolla,et al.  Neural dynamics of perceptual grouping: Textures, boundaries, and emergent segmentations , 1985 .

[8]  R A Kirsch,et al.  Computer determination of the constituent structure of biological images. , 1971, Computers and biomedical research, an international journal.

[9]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[10]  Franc Solina,et al.  Superquadrics for Segmenting and Modeling Range Data , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  F. Callari,et al.  Hybrid Methods for Robust Irradiance Analysis and 3-D Shape Reconstruction from Images , 1994 .