CVSL Logo
FrancaisHome
AboutPeopleResearchPublicationsEventsProfile
About

 

 

 

CERVIM

REPARTI

MIVIM

Construction and simulation of realistic virtual environments using information contained in geographic databases
Masters
Simon Tremblay
Denis Laurendeau (Supervisor)
Problem: Currently, when civil or military operations are planned and simulated, often the information available on the environment where the operation is taking place are provided on separate maps, aerial photos and databases. It is therefore very difficult to imagine what the terrain looks like and to integrate the different sources of information so as to make an enlightened decision. Pre-operational training, simulation and place recognition are also difficult to carry out.
Motivation: This project strives to find a method which will enable the rapid creation of a virtual environment based on the information that is known and then enable the performance of simulations on this environment while at the same time have access to the known information. The model of the environment could be manually modified using 3D modeling tools to increase realism. The project will also include additions and modification to the APIA simulation framework so as to support the interrogation of the geographical database during the simulations.
Challenges: One of the challenges of the project is to quickly and realistically recreate a virtual environment which corresponds to a known place. The size of the place and the large quantity of information makes manual reconstruction impossible. Another significant challenge involves the interrogation of the geographic database during the simulation, especially since the coordinate system of the virtual environment does not correspond to that of the geographic database from which the virtual environment is being constructed.
Applications: The applications are numerous. For example, this type of system could be used to plan an operation involving fire-fighting in a forest so as to provide the fire-fighters with a preliminary image of the terrain and to enable them to better visualize the probable behaviour of the fire.
Calendar: September 2004 - December 2007
Last modification: 2007/10/01 by strembla

     
   
   

©2002-. Computer Vision and Systems Laboratory. All rights reserved