inria-00000845, version 1
Pareto Optimal Sensing Strategies for an Active Vision System
Marc Schoenauer
1Enrique Dunn
2Gustavo Olague
2Evelyne Lutton
3
CEC 2004 (2004)
Résumé : We present a multi-objective methodology, based on evolutionary computation, for solving the sensor planning problem for an active vision system. The application of different representation schemes, that allow to consider either xed or variable size camera networks in a single evolutionary process, is studied. Furthermore, a novel representation of the recombination and mutation operators is brought forth. The developed methodology is incorporated into a 3D simulation environment and experimental results shown. Results validate the exibility and effectiveness of our approach and offer new research alternatives in the eld of sensor planning.
- 1 : TAO (INRIA Futurs)
- INRIA – CNRS : UMR8623 – Université Paris XI - Paris Sud
- 2 : Centro de Investigación Científica y de Educación Superior de Ensenada (CICESE)
- Consejo Nacional de Ciencia y Tecnología
- 3 : COMPLEX (INRIA Rocquencourt)
- INRIA
- inria-00000845, version 1
- http://hal.inria.fr/inria-00000845
- oai:hal.inria.fr:inria-00000845
- Contributeur : Marc Schoenauer
- Soumis le : Jeudi 24 Novembre 2005, 14:57:40
- Dernière modification le : Jeudi 24 Novembre 2005, 14:57:40






Exporter