Real time robust L1 tracker using accelerated proximal gradient approach

Recently sparse representation has been applied to visual tracker by modeling the target appearance using a sparse approximation over a template set, which leads to the so-called L1 trackers as it needs to solve an ℓ 1 norm related minimization problem for many times. While these L1 trackers showed...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2012 IEEE Conference on Computer Vision and Pattern Recognition S. 1830 - 1837
Hauptverfasser: Chenglong Bao, Yi Wu, Haibin Ling, Hui Ji
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2012
Schlagworte:
Accuracy
Minimization
Noise
Real time systems
Robustness
Target tracking
Visualization
ISBN:9781467312264, 1467312266
ISSN:1063-6919, 1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recently sparse representation has been applied to visual tracker by modeling the target appearance using a sparse approximation over a template set, which leads to the so-called L1 trackers as it needs to solve an ℓ 1 norm related minimization problem for many times. While these L1 trackers showed impressive tracking accuracies, they are very computationally demanding and the speed bottleneck is the solver to ℓ 1 norm minimizations. This paper aims at developing an L1 tracker that not only runs in real time but also enjoys better robustness than other L1 trackers. In our proposed L1 tracker, a new ℓ 1 norm related minimization model is proposed to improve the tracking accuracy by adding an ℓ 1 norm regularization on the coefficients associated with the trivial templates. Moreover, based on the accelerated proximal gradient approach, a very fast numerical solver is developed to solve the resulting ℓ 1 norm related minimization problem with guaranteed quadratic convergence. The great running time efficiency and tracking accuracy of the proposed tracker is validated with a comprehensive evaluation involving eight challenging sequences and five alternative state-of-the-art trackers.
ISBN:9781467312264
1467312266
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2012.6247881