Using Planar Parallax to Estimate the Time-to-Contact
Abstract
To avoid collisions, mobile robots need a measure for assessing the proximity of obstacles. A measure that is well suited to this purpose is provided by the time-to-contact. In this paper, a novel method for estimating the time-to-contact is presented. The method is based on the assumption that the robot is moving on a locally planar ground, parts of which are visible in the acquired images. Using the optical flow field induced by the robot's motion, the time-to-contact with points on the ground is first estimated and then the concept of planar parallax is exploited to recover the time-to-contact with obstacle points. The computation of high order derivatives of the image flow, which are known to be very difficult to estimate accurately, is completely avoided. Moreover, no knowledge of the egomotion is necessary. Experimental results from the application of the method on real and simulated flow fields are also reported.
Cite
Text
Lourakis and Orphanoudakis. "Using Planar Parallax to Estimate the Time-to-Contact." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.784993Markdown
[Lourakis and Orphanoudakis. "Using Planar Parallax to Estimate the Time-to-Contact." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/lourakis1999cvpr-using/) doi:10.1109/CVPR.1999.784993BibTeX
@inproceedings{lourakis1999cvpr-using,
title = {{Using Planar Parallax to Estimate the Time-to-Contact}},
author = {Lourakis, Manolis I. A. and Orphanoudakis, Stelios C.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1999},
pages = {2640-2645},
doi = {10.1109/CVPR.1999.784993},
url = {https://mlanthology.org/cvpr/1999/lourakis1999cvpr-using/}
}