The authors present a knowledge-based architecture that integrates data provided by different sensors to achieve a more reliable description of a scene and to meet safety requirements. The high complexity of this operation is reduced by acquiring, filtering, segmenting, and extracting features (described by means of frames) from each separate sensor channel. Procedural knowledge (production rules) drives the fusion process, linking to a symbolic frame all the segmented regions characterized by similar properties. The system has been applied to road detection in outdoor natural scenes. Results are promising, and a test performed to assess the system capabilities has been fully satisfactory.

Knowledge-based multisensor data integration applied to road detection

REGAZZONI, CARLO;VERNAZZA, GIANNI
1989-01-01

Abstract

The authors present a knowledge-based architecture that integrates data provided by different sensors to achieve a more reliable description of a scene and to meet safety requirements. The high complexity of this operation is reduced by acquiring, filtering, segmenting, and extracting features (described by means of frames) from each separate sensor channel. Procedural knowledge (production rules) drives the fusion process, linking to a symbolic frame all the segmented regions characterized by similar properties. The system has been applied to road detection in outdoor natural scenes. Results are promising, and a test performed to assess the system capabilities has been fully satisfactory.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/869777
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact