Visual Localization at Intersections with Digital Maps

Published in 2019 International Conference on Robotics and Automation (ICRA), 2019

Recommended citation: ballardini2019

Abstract. This paper deals with the task of ego-vehicle localization at intersections, a significant task in autonomous road driving. We propose an online vision-based method that can hence be applied if the intersection is visible. It relies on stereo images and on a coarse street-level pose estimate, used to retrieve intersection data from a digital map service. Pixel-level semantic segmentation, and 3D reconstruction from state-of-the art Deep Neural Networks are coupled with an intersection model; this allows good positioning accuracy compared to the state-of-the-art in this task. To demonstrate the effectiveness of the method and make it possible to compare it with other methods, an extensive activity has been conducted in order to set up a dataset of approaches to an intersection, which has then been used to benchmark the proposed method. The dataset is made available to the community, and it currently includes more than forty intersection approaches, from KITTI. Another important contribution of the paper is the definition of criteria for the comparison of different methods, on recorded datasets. The proposed method achieves nearly sub-meter accuracy in difficult real conditions.

Download paper here

Recommended citation: @INPROCEEDINGS{8794413, author={A. L. {Ballardini} and D. {Cattaneo} and D. G. {Sorrenti}}, booktitle={2019 International Conference on Robotics and Automation (ICRA)}, title={Visual Localization at Intersections with Digital Maps}, year={2019}, volume={}, number={}, pages={6651-6657}, keywords={computer vision;feature extraction;image reconstruction;image segmentation;neural nets;object detection;pose estimation;road vehicles;stereo image processing;traffic engineering computing;ego-vehicle localization;autonomous road driving;online vision-based method;digital map service;pixel-level semantic segmentation;intersection approaches;visual localization;deep neural networks;coarse street-level pose estimation;Roads;Three-dimensional displays;Semantics;Image segmentation;Pipelines;Geometry;Task analysis}, doi={10.1109/ICRA.2019.8794413}, ISSN={1050-4729}, month={May},}