Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization

• Published in: 2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 3057 - 3064
• Main Authors: Brubaker, Marcus A., Geiger, Andreas, Urtasun, Raquel
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2013
• Subjects: Accuracy; Approximation methods; Global Positioning System; localization; mixture model; Probabilistic logic; Roads; Vehicles; visual odometry; Visualization

In this paper we propose an affordable solution to self-localization, which utilizes visual odometry and road maps as the only inputs. To this end, we present a probabilistic model as well as an efficient approximate inference algorithm, which is able to utilize distributed computation to meet the r...