DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Road user tracker based on robust regression with GNC and preconditioning

Leich, Andreas and Marek, Junghans and Krsten, Kozempel and Hagen, Saul (2015) Road user tracker based on robust regression with GNC and preconditioning. In: Proceedings of SPIE, 9407. SPIE. IS&T/SPIE Electronic Imaging 2015, 8.2.2015 - 12.2.2015, San Francisco. doi: 10.1117/12.2082520. ISBN 9781628414974.

[img] PDF

Official URL: http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=2195297


In this paper an early vision tracking algorithm particularly adapted to the tracking of road users in video image sequences is presented. The algorithm is an enhanced version of the regression based motion estimator in Lucas-Kanade style. Robust regression algorithms work in the presence of outliers, while one distinct property of the proposed algorithm is that it can handle with datasets including 90% outliers. Robust regression involves finding the global minimum of a cost function, where the cost function measures if the motion model is conform with the measured data. The minimization task can be addressed with the graduated non convexity (GNC) heuristics. GNC is a scale space analysis of the cost function in parameter space. Although the approach is elegant and reasonable, several attempts to use GNC for solving robust regression tasks known from literature failed in the past. The main improvement of the proposed method compared with prior approaches is the use of a preconditioning technique to avoid GNC from getting stuck in a local minimum.

Item URL in elib:https://elib.dlr.de/96103/
Document Type:Conference or Workshop Item (Speech)
Title:Road user tracker based on robust regression with GNC and preconditioning
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Leich, Andreasandreas.leich (at) dlr.deUNSPECIFIED
Marek, Junghansmarek.junghans (at) dlr.deUNSPECIFIED
Krsten, Kozempelkarsten.kozempel (at) dlr.deUNSPECIFIED
Hagen, Saulhagen.saul (at) dlr.deUNSPECIFIED
Date:4 March 2015
Journal or Publication Title:Proceedings of SPIE
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
EditorsEmailEditor's ORCID iD
Loce, Robert P.PARC, A Xerox CompanyUNSPECIFIED
Saber, EliRochester Institute of TechnologyUNSPECIFIED
Series Name:Proceedings of SPIE-IS&T
Keywords:Motion Estimation, Optical Flow, Robust Regression, Object Tracking, Gaussian Continuation, GNC
Event Title:IS&T/SPIE Electronic Imaging 2015
Event Location:San Francisco
Event Type:international Conference
Event Dates:8.2.2015 - 12.2.2015
Organizer:SPIE IS&T
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Traffic Management (old)
DLR - Research area:Transport
DLR - Program:V VM - Verkehrsmanagement
DLR - Research theme (Project):V - I.MoVe (old)
Location: Berlin-Adlershof
Institutes and Institutions:Institute of Transportation Systems
Deposited By: Leich, Dr.-Ing. Andreas
Deposited On:10 Jun 2015 10:02
Last Modified:31 Jul 2019 19:52

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.