Learning spatial-temporally regularized complementary kernelized correlation filters for visual tracking

2020 ◽  
Vol 79 (33-34) ◽  
pp. 25171-25188
Author(s):  
Zhenyang Su ◽  
Jing Li ◽  
Jun Chang ◽  
Chengfang Song ◽  
Yafu Xiao ◽  
...  
Keyword(s):  
Visual Tracking ◽  
Correlation Filters ◽  
Kernelized Correlation Filters

Visual tracking tracker via object proposals and co-trained kernelized correlation filters

2019 ◽  
Vol 36 (6) ◽  
pp. 1173-1187 ◽  
Author(s):  
Jimmy T. Mbelwa ◽  
Qingjie Zhao ◽  
Fasheng Wang
Keyword(s):  
Visual Tracking ◽  
Correlation Filters ◽  
Object Proposals ◽  
Kernelized Correlation Filters

Robust Visual Tracking Model Designs Through Kernelized Correlation Filters

2019 ◽  
pp. -1--1
Author(s):  
Detian Huang Huang ◽  
Peiting Gu ◽  
Hsuan-Ming Feng ◽  
Yanming Lin ◽  
Lixin Zheng
Keyword(s):  
Visual Tracking ◽  
Correlation Filters ◽  
Tracking Model ◽  
Kernelized Correlation Filters

Robust visual tracking via co-trained Kernelized correlation filters

2017 ◽  
Vol 69 ◽  
pp. 82-93 ◽  
Author(s):  
Le Zhang ◽  
Ponnuthurai Nagaratnam Suganthan
Keyword(s):  
Visual Tracking ◽  
Correlation Filters ◽  
Kernelized Correlation Filters

Visual tracking with kernelized correlation filters based on multiple features

2018 ◽  
Author(s):  
Zhi Cai ◽  
Haoyuan Du ◽  
Liquan Dong ◽  
Ming Liu ◽  
Yuejin Zhao ◽  
...  
Keyword(s):  
Visual Tracking ◽  
Correlation Filters ◽  
Multiple Features ◽  
Kernelized Correlation Filters

scholarly journals Effective Visual Tracking Using Multi-Block and Scale Space Based on Kernelized Correlation Filters

Sensors ◽  
2017 ◽  
Vol 17 (3) ◽  
pp. 433 ◽  
Author(s):  
Soowoong Jeong ◽  
Guisik Kim ◽  
Sangkeun Lee
Keyword(s):  
Visual Tracking ◽  
Scale Space ◽  
Correlation Filters ◽  
Kernelized Correlation Filters

scholarly journals Multi-experts Joint Decision with Adaptive Model Updater for Robust Visual Tracking

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Da Li ◽  
Qixiang Zou ◽  
Ke Zhang
Keyword(s):  
Visual Tracking ◽  
Ensemble Methods ◽  
Adaptive Model ◽  
Decision Strategy ◽  
Correlation Filters ◽  
Joint Decision ◽  
Benchmark Datasets ◽  
Kernelized Correlation Filters ◽  
And Performance ◽  
High Level

AbstractOver these years, correlation filters based trackers have shown edges both in accuracy and speed. However, variations of target appearance caused by heavy occlusion, rotation, background clutters and target deformations are the major challenges for tracking. To solve these problems, many works put on exploiting the power of target representation, such as high-level convolutional features. Nonetheless, these methods make a great compromise between the speed and performance. At the same time, there are few researches on improving the performance of model updater and the ensemble methods. In this paper, a multi-experts joint decision strategy base on kernelized correlation filters is proposed to obtain robust and accurate visual tracking, two trackers with handcrafted features and deep convolutional neural network features are integrated in this framework. We also investigate the mechanism of tracking failure caused by occlusion and background clutters, and propose a novel criterion to evaluate the reliability of samples. Our work includes extending the kernelized correlation filter-based tracker with the capability of handling scale changes as well. The proposed tracker is extensively evaluated on the OTB-2013, OTB-2015 and VOT2015 benchmark datasets. Compared with the state-of-the-art trackers, the distinguished experimental results demonstrate the effectiveness of the proposed framework.

Sign in / Sign up

Export Citation Format

Share Document