Skip to Main content Skip to Navigation
New interface
Conference papers

Grid based fusion of offboard cameras

Manuel Yguel 1 Olivier Aycard 1 David Raulo 1 Christian Laugier 1 
1 E-MOTION - Geometry and Probability for Motion and Action
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes
Abstract : The goal of a perception system is to built an environment model. This model could be a list of features and objects present in the environment but could also be a grid (ie, a discretization of the environment in cells), where each cell gives the probability that the corresponding part of the environment is occupied or not. In this paper, we describe the perception system, based on a grid environment model, developped in the frame of the French project PUVAME. This system consists of several offboard cameras observing an intersection to detect objects (ie, pedestrian, cyclists and vehicules...). We present a generic and new method to design a sensor model for offboard camera where each of the video camera feed is processed independantly by a dedicated detector. Moreover, to add tolerance to miss detections and false alarms, we model the failure of the sensor. We also detail how to build an occupancy grid, fusionning the information from the different cameras. Experimental results showing that our approach is well suited to build an environment model are provided.
Document type :
Conference papers
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download
Contributor : Christian Laugier Connect in order to contact the contributor
Submitted on : Wednesday, October 24, 2007 - 6:25:52 PM
Last modification on : Wednesday, February 2, 2022 - 3:58:37 PM
Long-term archiving on: : Monday, September 24, 2012 - 2:35:28 PM


  • HAL Id : inria-00182016, version 1



Manuel Yguel, Olivier Aycard, David Raulo, Christian Laugier. Grid based fusion of offboard cameras. Proc. of the IEEE Intelligent Vehicle Symp., 2006, Tokyo, Japan. ⟨inria-00182016⟩



Record views


Files downloads