Real-time moving obstacle detection using optical flow models

In this paper, we propose a real-time method to detect obstacles using theoretical models of optical flow fields. The idea of our approach is to segment the image in two layers: the pixels which match our optical flow model and those that do not (i.e. the obstacles). In this paper, we focus our appr...

Full description

Saved in:
Bibliographic Details
Main Authors: Braillon, C., Pradalier, C., Crowley, J.L., Laugier, C.
Format: Conference Proceeding
Language:English
Subjects:
Biomedical optical imaging
Cameras
Image motion analysis
Image sequences
Mobile robots
Navigation
Optical computing
Optical detectors
Optical sensors
Robot vision systems
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a real-time method to detect obstacles using theoretical models of optical flow fields. The idea of our approach is to segment the image in two layers: the pixels which match our optical flow model and those that do not (i.e. the obstacles). In this paper, we focus our approach on a model of the motion of the ground plane. Regions of the visual field that violate this model indicate potential obstacles. In the first part of this paper, we describe the method we used to determine our model of the ground plane's motion. Then we focus on the method to match both the model and the real optical flow field. Experiments have been carried on the Cycab mobile robot in real-time on a standard PC laptop
ISSN:1931-0587
2642-7214
DOI:10.1109/IVS.2006.1689672