Post-Processing of Multi-Target Trajectories for Traffic Safety Analysis

2018 | conference paper. A publication with affiliation to the University of Göttingen.

Original publication

Jump to: Cite & Linked | Documents & Media | Details | Version history

Cite this publication

​Post-Processing of Multi-Target Trajectories for Traffic Safety Analysis​
Janz, T.; Leich, A.; Junghans, M.; Gimm, K.; Yang, S.   & Baum, M. ​ (2018)
pp. 1​-8. ​21st International Conference on Information Fusion (FUSION)​, Cambridge, UK.
IEEE. DOI: https://doi.org/10.23919/ICIF.2018.8455280 

Documents & Media

License

GRO License GRO License

Details

Authors
Janz, Thorben; Leich, Andreas; Junghans, Marek; Gimm, Kay; Yang, Shishan ; Baum, Marcus 
Abstract
This work presents a method for qualitatively improving the output of an existing video and radar-based multitarget tracking system by means of post-processing. The proposed method is a novel two-pass track stitching method, which involves a breaking phase for tracklet creation and a linking phase to create putative assignments. Minimum-cost network flow techniques are utilized to find optimal tracks. The method has been tested with data from a research intersection in Braunschweig, Germany, which is operated by the German Aerospace Center for the purpose of traffic safety analysis. Furthermore, an evaluation with the publicly available MOTChallenge benchmark is provided. Improvements achieved are: 14% to 33% less ID switches and 40% less track fragmentations. Both criteria are especially relevant for traffic safety analysis.
Issue Date
2018
Publisher
IEEE
Conference
21st International Conference on Information Fusion (FUSION)
ISBN
978-0-9964527-6-2
Conference Place
Cambridge, UK
Event start
2018-07-10
Event end
2018-07-13
Language
English

Reference

Citations


Social Media