6533b7d7fe1ef96bd1267909

RESEARCH PRODUCT

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

Roberto PirroneAntonio Chella

subject

Range (mathematics)Artificial neural networkComputer sciencebusiness.industrySuperquadricsComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONFeed forwardScale-space segmentationSegmentationComputer visionArtificial intelligencebusiness

description

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.

https://doi.org/10.1007/3-540-45808-5_14