Visual features for vehicle localization and ego-motion estimation

This paper introduces a novel method for vehicle pose estimation and motion tracking using visual features. The method combines ideas from research on visual odometry with a feature map that is automatically generated from aerial images into a visual navigation system. Given an initial pose estimate, e.g. from a GPS receiver, the system is capable of robustly tracking the vehicle pose in geographical coordinates over time, using image data as the only input. Experiments on real image data have shown that the precision of the position estimate with respect to the feature map typically lies within only several centimeters. This makes the algorithm interesting for a wide range of applications like navigation, path planning or lane keeping.

I. Introduction

A precise digital representation of the road network is crucial for autonomous navigation. At present, coverage of such high-precision digital maps is very low and mainly focused on some major cities, as the generation of these maps is costly and time-consuming.