论文信息 - A Two Stage Neural Architecture for Segmentation and Superquadrics Recovery from Range Data

A Two Stage Neural Architecture for Segmentation and Superquadrics Recovery from Range Data

A novel, two stage, neural architecture for the segmentation of range data and their modeling with undeformed superquadrics is presented. The system is composed by two distinct neural networks: a SOM is used to perform data segmentation, and, for each segment, a multilayer feed-forward network performs model estimation.

Roberto Pirrone | Antonio Chella | R. Pirrone | A. Chella

[1] Teuvo Kohonen,et al. The self-organizing map , 1990 .

[2] Martin Fodslette Møller,et al. A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[3] D. Marquardt. An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[4] Ruzena Bajcsy,et al. Recovery of Parametric Models from Range Images: The Case for Superquadrics with Global Deformations , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[5] Barr,et al. Superquadrics and Angle-Preserving Transformations , 1981, IEEE Computer Graphics and Applications.

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

[7] Mubarak Shah,et al. Analysis of shape from shading techniques , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

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

[9] Bernd Fritzke,et al. Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.