The Statistics of Driving Sequences - And What We Can Learn from Them
Abstract
The motion of a driving car is highly constrained and we claim that powerful predictors can be built that 'learn' the typical egomotion statistics, and support the typical tasks of feature matching, tracking, and egomotion estimation. We analyze the statistics of the 'ground truth' data given in the KITTI odometry benchmark sequences and confirm that a coordinated turn motion model, overlaid by moderate vibrations, is a very realistic model. We develop a predictor that is able to significantly reduce the uncertainty about the relative motion when a new image frame comes in. Such predictors can be used to steer the matching process from frame n to frame n + 1. We show that they can also be employed to detect outliers in the temporal sequence of egomotion parameters.
Cite
Text
Bradler et al. "The Statistics of Driving Sequences - And What We Can Learn from Them." IEEE/CVF International Conference on Computer Vision Workshops, 2015. doi:10.1109/ICCVW.2015.24Markdown
[Bradler et al. "The Statistics of Driving Sequences - And What We Can Learn from Them." IEEE/CVF International Conference on Computer Vision Workshops, 2015.](https://mlanthology.org/iccvw/2015/bradler2015iccvw-statistics/) doi:10.1109/ICCVW.2015.24BibTeX
@inproceedings{bradler2015iccvw-statistics,
title = {{The Statistics of Driving Sequences - And What We Can Learn from Them}},
author = {Bradler, Henry and Wiegand, Birthe Anne and Mester, Rudolf},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2015},
pages = {106-114},
doi = {10.1109/ICCVW.2015.24},
url = {https://mlanthology.org/iccvw/2015/bradler2015iccvw-statistics/}
}