IEICE TRANSACTIONS on Information
Low-Rank Representation with Graph Constraints for Robust Visual Tracking
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
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
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://global.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 -
English
