TU Darmstadt / ULB / TUprints

Multi-Session Visual Roadway Mapping

Boschenriedter, Stefan and Hossbach, Phillip and Linnhoff, Clemens and Luthardt, Stefan and Wu, Siqian (2018):
Multi-Session Visual Roadway Mapping.
In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, Hawaii, USA, November 4-7, 2018, pp. 394-400, DOI: 10.1109/ITSC.2018.8570004,
[Conference or Workshop Item]

Luthardt_ITSC_2018_Roadway.pdf - Accepted Version
Available under only the rights of use according to UrhG.

Download (3MB) | Preview
Item Type: Conference or Workshop Item
Title: Multi-Session Visual Roadway Mapping
Language: English

This paper proposes an algorithm for camera based roadway mapping in urban areas. With a convolutional neural network the roadway is detected in images taken by a camera mounted in the vehicle. The detected roadway masks from all images of one driving session are combined according to their corresponding GPS position to create a probabilistic grid map of the roadway. Finally, maps from several driving sessions are merged by a feature matching algorithm to compensate for errors in the roadway detection and localization inaccuracies. Hence, this approach utilizes solely low-cost sensors common in usual production vehicles and can generate highly detailed roadway maps from crowd-sourced data.

Classification DDC: 600 Technik, Medizin, angewandte Wissenschaften > 600 Technik
600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften
Divisions: 18 Department of Electrical Engineering and Information Technology > Institut für Automatisierungstechnik und Mechatronik > Control Methods and Robotics
Event Title: 2018 21st International Conference on Intelligent Transportation Systems (ITSC)
Event Location: Maui, Hawaii, USA
Event Dates: November 4-7, 2018
Date Deposited: 16 Jan 2019 12:17
Last Modified: 09 Jul 2020 02:28
DOI: 10.1109/ITSC.2018.8570004
URN: urn:nbn:de:tuda-tuprints-83567
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/8356
Actions (login required)
View Item View Item