UnivIS
Information system of Friedrich-Alexander-University Erlangen-Nuremberg © Config eG 
FAU Logo
  Collection/class schedule    module collection Home  |  Legal Matters  |  Contact  |  Help    
search:      semester:   
 
 Layout
 
printable version

 
 
Robust Sensing of the Automotive Environment

In order to increase safety and comfort in future vehicles, reliable sensing of the vehicle surroundings is of fundamental necessity. This is a challenging task given the dynamic nature and adverse conditions found in a typical sensing environment. Among all the signal processing and pattern analysis methods applied in deriving such an environment description, our research concentrates on techniques for tracking multiple targets, with specific focus on Sequential Monte Carlo methods, also called Particle Filters. The advantage of such a framework is that we are able to describe in a probabilistic fashion the acquired sensor data, and robustly fuse them, while always considering the scene dynamics over time. As a result we are able to increase the reliability of the derived driving-environment information. We apply with success such methodologies in typical surrounding sensing tasks, such as lane, road signs and vehicles detection, as well as in support functions such as camera calibration. This project is funded by Elektrobit Automotive GmbH.
Project manager:
Elli Angelopoulou, Ph.D., Akad. Rat

Project participants:
Andre Guilherme Linarth, M. Sc.

Keywords:
Sequential Monte Carlo; particle filters; lane detection; road sign recognition; auto-calibration

Duration: 1.11.2007 - 30.6.2012

Sponsored by:
EB Elektrobit Automotive GmbH

Contact:
Linarth, Andre Guilherme
E-Mail: andre.linarth@cs.fau.de
Publications
Doebert, Alexander ; Linarth, Andre Guilherme ; Kollorz, Eva: Map Guided Lane Detection. In: Weka Fachmedien GmbH (Ed.) : Proceedings of Embedded World Conference 2009 (Embedded World Conference 2009 Nuremberg 3-5.3.2009). 2009, pp -.
Linarth, Andre Guilherme ; Brucker, Manuel ; Angelopoulou, Elli: Robust Ground Plane Estimation Based on Particle Filters. In: - (Ed.) : Proceedings of the 12th International IEEE Conference on Intelligent Transportation Systems (12th International IEEE Conference on Intelligent Transportation Systems St. Louis, MO, U.S.A. 4-7.10.2009). 2009, pp 134-140. - ISBN 978-1-4244-5520-1
Linarth, Andre Guilherme ; Angelopoulou, Elli: On Feature Templates for Particle Filter Based Lane Detection. In: IEEE (Ed.) : 14th International IEEE Conference on Intelligent Transportation Systems (14th International IEEE Conference on Intelligent Transportation Systems Washington, DC, USA 05.10.2011). 2011, pp 1721-1726. - ISBN 978-1-4577-2196-0

Institution: Chair of Computer Science 5 (Pattern Recognition)
UnivIS is a product of Config eG, Buckenhof