Low-Rank Representation with Graph Constraints for Robust Visual Tracking

Jieyan LIU; Ao MA; Jingjing LI; Ke LU

doi:10.1587/transinf.2016EDP7422

Low-Rank Representation with Graph Constraints for Robust Visual Tracking

Jieyan LIU, Ao MA, Jingjing LI, Ke LU

Full Text Views

0

Share
Cite this

Summary :

Subspace representation model is an important subset of visual tracking algorithms. Compared with models performed on the original data space, subspace representation model can effectively reduce the computational complexity, and filter out high dimensional noises. However, for some complicated situations, e.g., dramatic illumination changing, large area of occlusion and abrupt object drifting, traditional subspace representation models may fail to handle the visual tracking task. In this paper, we propose a novel subspace representation algorithm for robust visual tracking by using low-rank representation with graph constraints (LRGC). Low-rank representation has been well-known for its superiority of handling corrupted samples, and graph constraint is flexible to characterize sample relationship. In this paper, we aim to exploit benefits from both low-rank representation and graph constraint, and deploy it to handle challenging visual tracking problems. Specifically, we first propose a novel graph structure to characterize the relationship of target object in different observation states. Then we learn a subspace by jointly optimizing low-rank representation and graph embedding in a unified framework. Finally, the learned subspace is embedded into a Bayesian inference framework by using the dynamical model and the observation model. Experiments on several video benchmarks demonstrate that our algorithm performs better than traditional ones, especially in dynamically changing and drifting situations.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.6 pp.1325-1338

Publication Date: 2017/06/01

Publicized: 2017/03/08

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDP7422

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Authors

Jieyan LIU
  University of Electronic Science & Technology of China
Ao MA
  University of Electronic Science & Technology of China
Jingjing LI
  University of Electronic Science & Technology of China
Ke LU
  University of Electronic Science & Technology of China

Keyword

visual tracking, low-rank representation, graph embedding

Cite this

Copy

Jieyan LIU, Ao MA, Jingjing LI, Ke LU, "Low-Rank Representation with Graph Constraints for Robust Visual Tracking" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 6, pp. 1325-1338, June 2017, doi: 10.1587/transinf.2016EDP7422.
Abstract: Subspace representation model is an important subset of visual tracking algorithms. Compared with models performed on the original data space, subspace representation model can effectively reduce the computational complexity, and filter out high dimensional noises. However, for some complicated situations, e.g., dramatic illumination changing, large area of occlusion and abrupt object drifting, traditional subspace representation models may fail to handle the visual tracking task. In this paper, we propose a novel subspace representation algorithm for robust visual tracking by using low-rank representation with graph constraints (LRGC). Low-rank representation has been well-known for its superiority of handling corrupted samples, and graph constraint is flexible to characterize sample relationship. In this paper, we aim to exploit benefits from both low-rank representation and graph constraint, and deploy it to handle challenging visual tracking problems. Specifically, we first propose a novel graph structure to characterize the relationship of target object in different observation states. Then we learn a subspace by jointly optimizing low-rank representation and graph embedding in a unified framework. Finally, the learned subspace is embedded into a Bayesian inference framework by using the dynamical model and the observation model. Experiments on several video benchmarks demonstrate that our algorithm performs better than traditional ones, especially in dynamically changing and drifting situations.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7422/_p

Copy

@ARTICLE{e100-d_6_1325,
author={Jieyan LIU, Ao MA, Jingjing LI, Ke LU, },
journal={IEICE TRANSACTIONS on Information},
title={Low-Rank Representation with Graph Constraints for Robust Visual Tracking},
year={2017},
volume={E100-D},
number={6},
pages={1325-1338},
abstract={Subspace representation model is an important subset of visual tracking algorithms. Compared with models performed on the original data space, subspace representation model can effectively reduce the computational complexity, and filter out high dimensional noises. However, for some complicated situations, e.g., dramatic illumination changing, large area of occlusion and abrupt object drifting, traditional subspace representation models may fail to handle the visual tracking task. In this paper, we propose a novel subspace representation algorithm for robust visual tracking by using low-rank representation with graph constraints (LRGC). Low-rank representation has been well-known for its superiority of handling corrupted samples, and graph constraint is flexible to characterize sample relationship. In this paper, we aim to exploit benefits from both low-rank representation and graph constraint, and deploy it to handle challenging visual tracking problems. Specifically, we first propose a novel graph structure to characterize the relationship of target object in different observation states. Then we learn a subspace by jointly optimizing low-rank representation and graph embedding in a unified framework. Finally, the learned subspace is embedded into a Bayesian inference framework by using the dynamical model and the observation model. Experiments on several video benchmarks demonstrate that our algorithm performs better than traditional ones, especially in dynamically changing and drifting situations.},
keywords={},
doi={10.1587/transinf.2016EDP7422},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - Low-Rank Representation with Graph Constraints for Robust Visual Tracking
T2 - IEICE TRANSACTIONS on Information
SP - 1325
EP - 1338
AU - Jieyan LIU
AU - Ao MA
AU - Jingjing LI
AU - Ke LU
PY - 2017
DO - 10.1587/transinf.2016EDP7422
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2017
AB - Subspace representation model is an important subset of visual tracking algorithms. Compared with models performed on the original data space, subspace representation model can effectively reduce the computational complexity, and filter out high dimensional noises. However, for some complicated situations, e.g., dramatic illumination changing, large area of occlusion and abrupt object drifting, traditional subspace representation models may fail to handle the visual tracking task. In this paper, we propose a novel subspace representation algorithm for robust visual tracking by using low-rank representation with graph constraints (LRGC). Low-rank representation has been well-known for its superiority of handling corrupted samples, and graph constraint is flexible to characterize sample relationship. In this paper, we aim to exploit benefits from both low-rank representation and graph constraint, and deploy it to handle challenging visual tracking problems. Specifically, we first propose a novel graph structure to characterize the relationship of target object in different observation states. Then we learn a subspace by jointly optimizing low-rank representation and graph embedding in a unified framework. Finally, the learned subspace is embedded into a Bayesian inference framework by using the dynamical model and the observation model. Experiments on several video benchmarks demonstrate that our algorithm performs better than traditional ones, especially in dynamically changing and drifting situations.
ER -