Map-Driven Image Interpretation by Associative Model Indexing

d at a high abstraction level, and consists in an expectation-driven search starting from symbolic object descriptions and using a version of a distributed blackboard system for recognition [4], where a module devoted to scene analysis has been inserted. The paper is organized into in four sections. Section I1 deals with a general formulation of the problem, pointing out the characteristic of the sensors employed . Section Ill containsa brief reviewof associativememory techniques, and Section IV containsa descriptionof the model here employed and it reports preliminary results obtained on a set of real imagesand on the relatedterritorialmap. terrain map are transformed so that they can be fused with data acquired with a TV-camera, . Then, the recognition processperformedat the symbolic level is described. 21cartographivirtualsensor A topologic map (TM) representing a scenario through which an autonomous vehicle can ride provides useful informationto be used by a multisensorrecognitions...

• Type: Conference
• Year: 1990
• Where: MVA
• Authors: Gian Luca Foresti, Vittorio Murino, Carlo S. Regazzoni, Rodolfo Zunino
• Keywords: Contour Lines, MVA 1990, MVA 2007, Section I1 Deals, Symbolic Object Descriptions