A new application for salliency maps: Synthetic vision of autonomous actors.

Nicolas Courty 1, 2 E. Marchand 3 Bruno Arnaldi 2
2 SIAMES - Computer generated images, animation, modeling and simulation
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, INRIA Rennes
3 VISTA - Vision spatio-temporelle et active
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : We present in this paper a new and original application for saliency maps, intending to simulate the visual perception of a synthetic actor. Within computer graphics field, simulating virtual humans has become a challenging task. Animating such an autonomous actor within a virtual environment requires most of time the modeling of a perception-decision-action cycle. To model a part of the perception process, we have designed a new model of saliency map, based on geometric and depth information, allowing our synthetic humanoid to perceive its environment in a biologically plausible way.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/inria-00352078
Contributor : Eric Marchand <>
Submitted on : Monday, January 12, 2009 - 2:19:47 PM
Last modification on : Friday, November 16, 2018 - 1:24:28 AM
Long-term archiving on : Tuesday, June 8, 2010 - 7:35:21 PM

File

2003_icip_courty.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00352078, version 1

Citation

Nicolas Courty, E. Marchand, Bruno Arnaldi. A new application for salliency maps: Synthetic vision of autonomous actors.. IEEE Int. Conf. on Image Processing, ICIP'03, 2003, Barcelona, Spain, France. pp.1065-1068. ⟨inria-00352078⟩

Share

Metrics

Record views

439

Files downloads

156