Visual tracking with representative templates based on low-rank matrix

Authors:
Deqian Fu;Shunbo Hu;Seong Tae Jhang
Affiliations:
Linyi University, Linyi, China and The University of Suwon Hwaseong-si Gyeonggi-do, Korea;Linyi University, Linyi, Linyi city, Shangdong Province, P.R.China;The University of Suwon, Hwaseong-si Gyeonggi-do, Korea
Venue:
Proceedings of the 2013 Research in Adaptive and Convergent Systems
Year:
2013

Citing 8
Cited 0

EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation

International Journal of Computer Vision
W4: A Real Time System for Detecting and Tracking People

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
On-Road Vehicle Detection: A Review

IEEE Transactions on Pattern Analysis and Machine Intelligence
Ensemble Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Support vector tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking by Sampling Trackers

ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Visual tracking via multiple representative basic appearance models based on l 1 minimization

Proceedings of the 2012 ACM Research in Applied Computation Symposium
Low-rank sparse learning for robust visual tracking

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI

Quantified Score

Hi-index	0.00

Visualization

Abstract

Robust visual tracking, as a critical problem in community of computer vision, is still knotty, especially in challenging scenarios. In this paper, using the nature of low-rank matrix recovery, we propose a tracker with structured appearance model consisting of multiple representative models. By exploring the signal recovery power of Low-Rank matrix, we get effective representation of target and background for tracking; at the same time maintain a robust appearance model with multiple representative templates. Benefitting from low-rank recovery power, the representation matrix of candidates w.r.t the low-rank dictionary shows low-rank and sparse. Meanwhile, by our update strategy, a novel dictionary is maintained with low-rank models derived from multiple representative templates, which further encourages the sparse representation of particles. The proposed algorithm is demonstrated by extensive experiments on several challenging databases.