Proceedings ArticleDOI
Online Robust Non-negative Dictionary Learning for Visual Tracking
Naiyan Wang,Jingdong Wang,Dit-Yan Yeung +2 more
- pp 657-664
TLDR
This paper proposes 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.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.read more
Citations
More filters
Journal ArticleDOI
Struck: Structured Output Tracking with Kernels
Sam Hare,Stuart Golodetz,Amir Saffari,Vibhav Vineet,Ming-Ming Cheng,Stephen Hicks,Philip H. S. Torr +6 more
TL;DR: A framework for adaptive visual object tracking based on structured output prediction that is able to outperform state-of-the-art trackers on various benchmark videos and can easily incorporate additional features and kernels into the framework, which results in increased tracking performance.
Journal ArticleDOI
A Survey of Sparse Representation: Algorithms and Applications
TL;DR: A comprehensive overview of sparse representation is provided and an experimentally comparative study of these sparse representation algorithms was presented, which could sufficiently reveal the potential nature of the sparse representation theory.
Proceedings ArticleDOI
Understanding and Diagnosing Visual Tracking Systems
TL;DR: Zhang et al. as mentioned in this paper proposed a framework by breaking a tracker down into five constituent parts, namely, motion model, feature extractor, observation model, model updater, and ensemble post-processor, and conduct ablative experiments on each component to study how it affects the overall result.
Posted Content
Transferring Rich Feature Hierarchies for Robust Visual Tracking
TL;DR: This work pre-training a CNN offline and then transferring the rich feature hierarchies learned to online tracking, and proposes to generate a probability map instead of producing a simple class label to fit the characteristics of object tracking.
References
More filters
Journal ArticleDOI
Regression Shrinkage and Selection via the Lasso
TL;DR: A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
Journal ArticleDOI
A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking
TL;DR: Both optimal and suboptimal Bayesian algorithms for nonlinear/non-Gaussian tracking problems, with a focus on particle filters are reviewed.
Journal ArticleDOI
$rm K$ -SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
TL;DR: A novel algorithm for adapting dictionaries in order to achieve sparse signal representations, the K-SVD algorithm, an iterative method that alternates between sparse coding of the examples based on the current dictionary and a process of updating the dictionary atoms to better fit the data.
Proceedings Article
Algorithms for Non-negative Matrix Factorization
Daniel D. Lee,H. Sebastian Seung +1 more
TL;DR: Two different multiplicative algorithms for non-negative matrix factorization are analyzed and one algorithm can be shown to minimize the conventional least squares error while the other minimizes the generalized Kullback-Leibler divergence.
BookDOI
Sequential Monte Carlo methods in practice
TL;DR: This book presents the first comprehensive treatment of Monte Carlo techniques, including convergence results and applications to tracking, guidance, automated target recognition, aircraft navigation, robot navigation, econometrics, financial modeling, neural networks, optimal control, optimal filtering, communications, reinforcement learning, signal enhancement, model averaging and selection.