L'algorithme des mouches : une strategie d'evolution individuelle appliquee en stereovision
Created by W.Langdon from
gp-bibliography.bib Revision:1.8098
- @InProceedings{Louchet:2000:RFIA,
-
author = "J. Louchet",
-
title = "L'algorithme des mouches : une strategie d'evolution
individuelle appliquee en stereovision",
-
title_en = "The Fly Algorithm: an Individual Evolutionary Strategy
applied to Stereovision",
-
booktitle = "RFIA 2000, Reconnaissance des Formes et Intelligence
Artificielle",
-
year = "2000",
-
month = feb,
-
keywords = "genetic algorithms, genetic programming, Parisian GP,
3D vision, Algorithmes genetiques, strategies
d'evolution, approche individuelle, vision robotique,
detectiond'obstacles",
-
URL = "http://jean.louchet.free.fr/publis/rfia14t.pdf",
-
size = "11 pages",
-
abstract = "This paper presents an Individual Evolutionary
Strategy devised for fast image analysis applications.
The example problem chosen is obstacle detection using
a pair of cameras. The algorithm evolves a population
of three-dimensional points (flies) in the cameras
fields of view, using a low complexity fitness function
giving highest values to flies likely to be on the
surfaces of 3-D obstacles. The algorithm uses classical
sharing, mutation and crossover operators. The final
result is a fraction of the population rather than a
single individual. Some test results are presented and
potential extensions to real-time image sequence
processing,mobile objects tracking and mobile robotics
are discussed.",
-
resume = "Cet article presente l'application d'une
strategied'evolution individuelle (variante
d'algorithme genetique) a la resolution rapide
approchee de certains problemes d'analyse de scenes.
L'exemple choisi est la detection d'obstacles par
stereovision. La population est un ensemble de points
(mouches) dans le champdes cameras. La fonction de
performance favorise les mouches situees sur les
surfaces apparentes des objets. L'algorithme uses des
operateurs classiques de partage, mutation et
croisement. Le resultat est un ensemble de points de la
population, representant les surfaces des objets. Des
resultats experiment aux sont presentes ainsi que les
extensions en cours a la vision d'un robot mobile et au
suivi d'objets en deplacement.",
-
notes = "In French",
- }
Genetic Programming entries for
Jean Louchet
Citations