Corinne Plazanet

Experiments with Learning Techniques for Spatial Model Enrichment and Line Generalization

The nature of map generalization may be non-uniform along the length of an individual line, requiring the application of methods that adapt to the local geometry and the geographical context. Geographical databases need to be enriched in terms of shape description structures (geometrical knowledge), knowledge of appropriate order of operations and of appropriate algorithms (procedural knowledge). Stored knowledge should take account of semantic and morphological characteristics, and of cartographic constraints.This paper proposes and discusses three experiments on knowledge acquisition using unsupervised and supervised learning techniques. In order to exploit geometrical shape knowledge, classifications were computed according to a set of morphological measures using unsupervised learning. Choice of appropriate operations was determined by the results of a test with IGN cartographers considering line characteristics. These results were given to a supervised learning algorithm, along with corresponding computed measures in order to discover rules. The approach and the resulting rules are presented and discussed. Tests have also been conducted on the tuning of parameter values, applying a Gaussian smoothing tolerance value to a set of lines using the supervised learning algorithm. The values obtained by means of the learning algorithm have been compared with interactive choices of an expert. Results are promising with a prediction rate higher than 80% having been obtained.

GIS and LIDAR Data Analysis for the Integration of Multidimensional Indicators on Urban Morphogenesis Multi-agent Vector Based Geosimulation

In this paper we present an application of GIS and Airborne Light Detection and Ranging (LIDAR) data analysis for computation of buildings visibility, solar exposition and extraction of morphological indicators in the context of urban group analysis and morphogenesis geosimulation. The interdisciplinary project between geomaticians and architects aims to provide a simulation model based upon dynamic computation of building agents’ satisfaction degree, incorporating analysis results using a hybrid approach derived from GIS and raw LIDAR data.

COSIS: A Content-Oriented Shoeprint Identification System

COSIS is a content-based image retrieval system designed for the shoeprint identification. It consists of a matching-based query tool, an attribute-based query tool and an icon-based browser. The matching-based tool considers the complete and partial shoeprints as query images. The completeshoeprint query tool is fully-automatic whereas the partial-shoeprint one is user-driven. The development of the matching-based query tool is inspired from the template-matching approach largely used in pattern recognition. This paper presents COSIS by focusing, in particular, on its main component: the Matching-based Query Tool.