Online Robust Non-negative Dictionary Learning for Visual Tracking
- 1 December 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2013 IEEE International Conference on Computer Vision
- p. 657-664
- https://doi.org/10.1109/iccv.2013.87
Abstract
This paper studies the visual tracking problem in video sequences and presents a novel robust sparse tracker under the particle filter framework. In particular, we propose an online robust non-negative dictionary learning algorithm for updating the object templates so that each learned template can capture a distinctive aspect of the tracked object. Another appealing property of this approach is that it can automatically detect and reject the occlusion and cluttered background in a principled way. In addition, we propose a new particle representation formulation using the Huber loss function. The advantage is that it can yield robust estimation without using trivial templates adopted by previous sparse trackers, leading to faster computation. We also reveal the equivalence between this new formulation and the previous one which uses trivial templates. The proposed tracker is empirically compared with state-of-the-art trackers on some challenging video sequences. Both quantitative and qualitative comparisons show that our proposed tracker is superior and more stable.Keywords
This publication has 19 references indexed in Scilit:
- Online Robust Dictionary LearningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Robust Visual Tracking via Structured Multi-Task Sparse LearningInternational Journal of Computer Vision, 2012
- Sparse coding based visual tracking: Review and experimental comparisonPattern Recognition, 2012
- Robust nonnegative matrix factorization using L21-normPublished by Association for Computing Machinery (ACM) ,2011
- Incremental Learning for Robust Visual TrackingInternational Journal of Computer Vision, 2007
- Object trackingACM Computing Surveys, 2006
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006
- Real-Time Tracking via On-line BoostingPublished by British Machine Vision Association and Society for Pattern Recognition ,2006
- A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian trackingIEEE Transactions on Signal Processing, 2002
- Robust Estimation of a Location ParameterThe Annals of Mathematical Statistics, 1964