Visual Monocular Obstacle Avoidance for Small Unmanned Vehicles
Abstract
This paper presents and extensively evaluates a visual obstacle avoidance method using frames of a single camera, intended for application on small devices (ground or aerial robots or even smartphones). It is based on image region classification using so called relative focus maps, it does not require a priori training, and it is applicable in both indoor and outdoor environments, which we demonstrate through evaluations using both simulated and real data.
Cite
Text
Kovács. "Visual Monocular Obstacle Avoidance for Small Unmanned Vehicles." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016. doi:10.1109/CVPRW.2016.114Markdown
[Kovács. "Visual Monocular Obstacle Avoidance for Small Unmanned Vehicles." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016.](https://mlanthology.org/cvprw/2016/kovacs2016cvprw-visual/) doi:10.1109/CVPRW.2016.114BibTeX
@inproceedings{kovacs2016cvprw-visual,
title = {{Visual Monocular Obstacle Avoidance for Small Unmanned Vehicles}},
author = {Kovács, Levente},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2016},
pages = {877-884},
doi = {10.1109/CVPRW.2016.114},
url = {https://mlanthology.org/cvprw/2016/kovacs2016cvprw-visual/}
}