Monocular Rear-View Obstacle Detection Using Residual Flow
Abstract
We present a system for automatically detecting obstacles from a moving vehicle using a monocular wide angle camera. Our system was developed in the context of finding obstacles and particularly children when backing up. Camera viewpoint is transformed to a virtual bird-eye view. We developed a novel image registration algorithm to obtain ego-motion that in combination with variational dense optical flow outputs a residual motion map with respect to the ground. The residual motion map is used to identify and segment 3D and moving objects. Our main contribution is the feature-based image registration algorithm that is able to separate and obtain ground layer ego-motion accurately even in cases of ground covering only 20% of the image, outperforming RANSAC.
Cite
Text
Molineros et al. "Monocular Rear-View Obstacle Detection Using Residual Flow." European Conference on Computer Vision Workshops, 2012. doi:10.1007/978-3-642-33868-7_50Markdown
[Molineros et al. "Monocular Rear-View Obstacle Detection Using Residual Flow." European Conference on Computer Vision Workshops, 2012.](https://mlanthology.org/eccvw/2012/molineros2012eccvw-monocular/) doi:10.1007/978-3-642-33868-7_50BibTeX
@inproceedings{molineros2012eccvw-monocular,
title = {{Monocular Rear-View Obstacle Detection Using Residual Flow}},
author = {Molineros, Jose and Cheng, Shinko Y. and Owechko, Yuri and Levi, Dan and Zhang, Wende},
booktitle = {European Conference on Computer Vision Workshops},
year = {2012},
pages = {504-514},
doi = {10.1007/978-3-642-33868-7_50},
url = {https://mlanthology.org/eccvw/2012/molineros2012eccvw-monocular/}
}