TY - GEN
T1 - Online learning of multi-feature weights for robust object tracking
AU - Zhou, Tao
AU - Bhaskar, Harish
AU - Xie, Kai
AU - Yang, Jie
AU - He, Xiangjian
AU - Shi, Pengfei
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/12/9
Y1 - 2015/12/9
N2 - Sparse Representation based Classification (SRC) and its potential in object tracking have been explored in recent years. However, the trade-off between the discriminative ability of the overly emphasized sparse representation and the lack of insight on correlation of visual information has raised questions over the general applicability of such methods in object tracking. In addition, the need for the optimization of a series of l1-regularized least square norm, increases the computational complexity thereby limiting their usage in real-time applications. In this paper, a novel approach to robust object tracking is proposed. First, the variations in the appearance of the tracked target is modelled using PCA basis vectors, and further, a l2-regularized least square method is used to solve the proposed representation model. In order to improve the robustness of feature representation in object tracking applications, weights are associated with multiple trackers; each formulated using a different feature, and adapted via an online learning scheme. Finally, a decision fusion criterion is imposed to generate an optimized output through the weighted combination of different tracking results. Experiments on challenging video sequences have demonstrated the superior accuracy and robustness of the proposed method in comparison to thirteen other state-of-the-art baselines.
AB - Sparse Representation based Classification (SRC) and its potential in object tracking have been explored in recent years. However, the trade-off between the discriminative ability of the overly emphasized sparse representation and the lack of insight on correlation of visual information has raised questions over the general applicability of such methods in object tracking. In addition, the need for the optimization of a series of l1-regularized least square norm, increases the computational complexity thereby limiting their usage in real-time applications. In this paper, a novel approach to robust object tracking is proposed. First, the variations in the appearance of the tracked target is modelled using PCA basis vectors, and further, a l2-regularized least square method is used to solve the proposed representation model. In order to improve the robustness of feature representation in object tracking applications, weights are associated with multiple trackers; each formulated using a different feature, and adapted via an online learning scheme. Finally, a decision fusion criterion is imposed to generate an optimized output through the weighted combination of different tracking results. Experiments on challenging video sequences have demonstrated the superior accuracy and robustness of the proposed method in comparison to thirteen other state-of-the-art baselines.
KW - l-regularized least square
KW - l-regularized least square
KW - object tracking
KW - PCA
KW - sparse representation
UR - http://www.scopus.com/inward/record.url?scp=84956610957&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2015.7350894
DO - 10.1109/ICIP.2015.7350894
M3 - Conference contribution
AN - SCOPUS:84956610957
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 725
EP - 729
BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
PB - IEEE Computer Society
T2 - IEEE International Conference on Image Processing, ICIP 2015
Y2 - 27 September 2015 through 30 September 2015
ER -