User: Guest  Login
Title:

Building representative velocity profiles using FastDTW and spectral clustering

Document type:
Konferenzbeitrag
Author(s):
Lohrer, Jürgen; Lienkamp, Markus
Abstract:
The use of map based representative velocity profiles allows to predict the future state of a vehicle. The suggested approach is based on Fast Dynamic Time Warping. Spectral clustering is used to distinguish velocity profiles. Applying abstraction can significantly reduce computation time with a minor effect on cluster allocation. Outlier removal increases the quality of cluster identification. The approach was applied to the road network of Munich, to prove the universal applicability.
Keywords:
FTM Smarte Mobilität
Book / Congress title:
14th International Conference on ITS Telecommunications
Date of congress:
02.-04.12.2015
Date of publication:
08.01.2016
Year:
2016
Covered by:
Scopus
Fulltext / DOI:
doi:10.1109/ITST.2015.7377398
TUM Institution:
Lehrstuhl für Fahrzeugtechnik
 BibTeX