Share Email Print
cover

Proceedings Paper

Road user tracker based on robust regression with GNC and preconditioning
Author(s): Andreas Leich; Marek Junghans; Karsten Kozempel; Hagen Saul
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

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.

Paper Details

Date Published: 4 March 2015
PDF: 16 pages
Proc. SPIE 9407, Video Surveillance and Transportation Imaging Applications 2015, 940702 (4 March 2015); doi: 10.1117/12.2082520
Show Author Affiliations
Andreas Leich, Deutsches Zentrum für Luft- und Raumfahrt e.V. (Germany)
Marek Junghans, Deutsches Zentrum für Luft- und Raumfahrt e.V. (Germany)
Karsten Kozempel, Deutsches Zentrum für Luft- und Raumfahrt e.V. (Germany)
Hagen Saul, Deutsches Zentrum für Luft- und Raumfahrt e.V. (Germany)


Published in SPIE Proceedings Vol. 9407:
Video Surveillance and Transportation Imaging Applications 2015
Robert P. Loce; Eli Saber, Editor(s)

© SPIE. Terms of Use
Back to Top