Egomotion and the Stabilized World
Abstract
This paper formulates the tasks of moving-object detection and motion-based depth recovery as a problem of sensor fusion in the presence of uncertainty. We utilize two sensor systems, one providing information about the local image velocity (spsecifying a point in image-velocity space), and the othter providing information about the camera motion (specifying a line segment in image-velocity space). 1Ne utilize Mahalanobis distance as a threshold rule for determining consistency between the measurements from the two sensor systems. We also suggest a framework for using the resulting segmented flow field to update estimates of the egomotion parameters.
Cite
Text
Heeger and Hager. "Egomotion and the Stabilized World." IEEE/CVF International Conference on Computer Vision, 1988. doi:10.1109/CCV.1988.590020Markdown
[Heeger and Hager. "Egomotion and the Stabilized World." IEEE/CVF International Conference on Computer Vision, 1988.](https://mlanthology.org/iccv/1988/heeger1988iccv-egomotion/) doi:10.1109/CCV.1988.590020BibTeX
@inproceedings{heeger1988iccv-egomotion,
title = {{Egomotion and the Stabilized World}},
author = {Heeger, David J. and Hager, Greg},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {1988},
pages = {435-440},
doi = {10.1109/CCV.1988.590020},
url = {https://mlanthology.org/iccv/1988/heeger1988iccv-egomotion/}
}