Robust visual tracking using latent subspace projection pursuit

Jin, Wei; Liu, Risheng; Su, Zhixun; Zhang, Changcheng; Bai, Shanshan

doi:10.1109/icme.2014.6890263

Cited by 6 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, the observation model aims to reflect the similarity between the initially specified object of interest and the tracked object through the video sequence. The similarity could be modeled either by a color similarity based distance metric [9] or in terms of a reconstruction error minimized by using a sparse representation of the target object [17,18,19,20]. As a discriminative detector the statistical classifiers including support vector machines (SVM), online or offline learning schemes and CNN based detectors are widely used [11,16,21,22,23,24,25,26].…”

Section: Introductionmentioning

confidence: 99%

Integration of Regularized l1 Tracking and Instance Segmentation for Video Object Tracking

Gurkan,

Gunsel

2019

Preprint

View full text Add to dashboard Cite

We introduce a tracking-by-detection method that integrates a deep object detector with a particle filter tracker under the regularization framework where the tracked object is represented by a sparse dictionary. A novel observation model which establishes consensus between the detector and tracker is formulated that enables us to update the dictionary with the guidance of the deep detector. This yields an efficient representation of the object appearance through the video sequence hence improves robustness to occlusion and pose changes. Moreover we propose a new state vector consisting of translation, rotation, scaling and shearing parameters that allows tracking the deformed object bounding boxes hence significantly increases robustness to scale changes. Numerical results reported on challenging VOT2016 and VOT2018 benchmarking data sets demonstrate that the introduced tracker, L1DPF-M, achieves comparable robustness on both data sets while it outperforms state-of-the-art trackers on both data sets where the improvement achieved in success rate at IoU-th=0.5 is 11% and 9%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Integration of Regularized l1 Tracking and Instance Segmentation for Video Object Tracking

Gurkan,

Gunsel

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…We focus on the generative one and will briefly review the relevant work below. Recently, sparse representation has been successfully applied to visual tracking (e.g., [15,10,25,6]). The trackers based on sparse representation are under the assumption that the appearance of a tracked object can be sparsely represented by a over-complete dictionary which can be dynamically updated to maintain holistic appearance information.…”

Section: Introductionmentioning

confidence: 99%

Sparse Coding and Counting for Robust Visual Tracking

Liu¹,

Wang²,

Shang³

et al. 2016

PLoS ONE

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a novel sparse coding and counting method under Bayesian framework for visual tracking. In contrast to existing methods, the proposed method employs the combination of L0 and L1 norm to regularize the linear coefficients of incrementally updated linear basis. The sparsity constraint enables the tracker to effectively handle difficult challenges, such as occlusion or image corruption. To achieve real-time processing, we propose a fast and efficient numerical algorithm for solving the proposed model. Although it is an NP-hard problem, the proposed accelerated proximal gradient (APG) approach is guaranteed to converge to a solution quickly. Besides, we provide a closed solution of combining L0 and L1 regularized representation to obtain better sparsity. Experimental results on challenging video sequences demonstrate that the proposed method achieves state-of-the-art results both in accuracy and speed.

show abstract