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.
KeywordsSOM Range data segmentation
Unable to display preview. Download preview PDF.
- Kohonen, T.: The Self-Organizing Map. Proceedings of the IEEE, 78(9):1464–1480, September 1990.Google Scholar
- Paul, R.: Robot Manipulators. MIT Press, Cambridge, MA, 1981.Google Scholar
- Pirrone, R.: Part based Segmentation and Modeling of Range Data by Moving Target. Journal of Intelligent Systems, 11(4):217–247, 2001.Google Scholar
- Zhang, R., Tsai, P.-S., Cryer, J.E. and Shah, M.: Analysis of shape from shading techniques. In Proc. of international Conference on Computer Vision Pattern Recognition CVPR’94, 377–384, Seattle, Whashington, 1994.Google Scholar