Robust visual tracking based on online learning of joint sparse dictionary

Author(s):  
Qiaozhe Li ◽  
Yu Qiao ◽  
Jie Yang ◽  
Li Bai
IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 14790-14798 ◽  
Author(s):  
Weiming Yang ◽  
Meirong Zhao ◽  
Yinguo Huang ◽  
Yelong Zheng

Sensors ◽  
2017 ◽  
Vol 17 (10) ◽  
pp. 2382 ◽  
Author(s):  
Guokai Shi ◽  
Tingfa Xu ◽  
Jiqiang Luo ◽  
Jie Guo ◽  
Zishu Zhao

2014 ◽  
Vol 945-949 ◽  
pp. 1794-1800
Author(s):  
Wen Hua He ◽  
Zhi Jing Liu ◽  
Jian Ming Qu

In order to adapt to the target appearance changes during visual tracking, feature model needs to be updated by online learning. However, online adaptive methods suffer from the drifting problem: error data are used for updating and will finally lead to tracking failure. In this paper, we propose a novel hierarchical online ensemble tracking method. Optical flow tracker is employed to predict the rough location. Online learning classifier is employed to detect the target. Template match is used to filter the data for updating. All these parts are combined together hierarchically by their confidence to ensure the stability of online learning and tracking. In contrast to the individual online learning and semi-supervised online learning, our method show more adaptability and stability. We demonstrate the performance on several public video sequences, which shows the improvement of our method over other online tracking approaches.


Author(s):  
Siyuan Li ◽  
Zhi Zhang ◽  
Ziyu Liu ◽  
Anna Wang ◽  
Linglong Qiu ◽  
...  

Target localization and proposal generation are two essential subtasks in generic visual tracking, and it is a challenge to address both the two efficiently. In this paper, we propose an efficient two-stage architecture which makes full use of the complementarity of two subtasks to achieve robust localization and high-quality proposals generation of the target jointly. Specifically, our model performs a novel deformable central correlation operation by an online learning model in both two stages to locate new target centers while generating target proposals in the vicinity of these centers. The proposals are refined in the refinement stage to further improve accuracy and robustness. Moreover, the model benefits from multi-level features aggregation in a neck module and a feature enhancement module. We conduct extensive ablation studies to demonstrate the effectiveness of our proposed methods. Our tracker runs at over 30 FPS and sets a new state-of-the-art on five tracking benchmarks, including LaSOT, VOT2018, TrackingNet, GOT10k, OTB2015.


2017 ◽  
Vol 226 ◽  
pp. 221-237 ◽  
Author(s):  
Tao Zhou ◽  
Harish Bhaskar ◽  
Fanghui Liu ◽  
Jie Yang ◽  
Ping Cai

Author(s):  
Mohammed Y. Abbass ◽  
Ki-Chul Kwon ◽  
Nam Kim ◽  
Safey A. Abdelwahab ◽  
Fathi E. Abd El-Samie ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document