scholarly journals Visual Tracking using Weighted Discriminative Correlation Filter

2016 ◽  
Vol 21 (11) ◽  
pp. 49-57 ◽  
Author(s):  
Tae-Eun Song ◽  
Kyung-Hyun Jang
Keyword(s):  
Visual Tracking ◽  
Correlation Filter ◽  
Discriminative Correlation Filter

scholarly journals Transfer learning-based discriminative correlation filter for visual tracking

2020 ◽  
Vol 100 ◽  
pp. 107157 ◽  
Author(s):  
Bo Huang ◽  
Tingfa Xu ◽  
Jianan Li ◽  
Ziyi Shen ◽  
Yiwen Chen
Keyword(s):  
Transfer Learning ◽  
Visual Tracking ◽  
Correlation Filter ◽  
Discriminative Correlation Filter

scholarly journals Coupled-Region Visual Tracking Formulation Based on a Discriminative Correlation Filter Bank

Electronics ◽  
2018 ◽  
Vol 7 (10) ◽  
pp. 244 ◽  
Author(s):  
Jian Wei ◽  
Feng Liu
Keyword(s):  
Visual Tracking ◽  
Filter Bank ◽  
Correlation Filter ◽  
Appearance Model ◽  
Intrinsic Structure ◽  
Target Region ◽  
Global Target ◽  
Estimation Scheme ◽  
Discriminative Correlation Filter ◽  
Partially Occluded

The visual tracking algorithm based on discriminative correlation filter (DCF) has shown excellent performance in recent years, especially as the higher tracking speed meets the real-time requirement of object tracking. However, when the target is partially occluded, the traditional single discriminative correlation filter will not be able to effectively learn information reliability, resulting in tracker drift and even failure. To address this issue, this paper proposes a novel tracking-by-detection framework, which uses multiple discriminative correlation filters called discriminative correlation filter bank (DCFB), corresponding to different target sub-regions and global region patches to combine and optimize the final correlation output in the frequency domain. In tracking, the sub-region patches are zero-padded to the same size as the global target region, which can effectively avoid noise aliasing during correlation operation, thereby improving the robustness of the discriminative correlation filter. Considering that the sub-region target motion model is constrained by the global target region, adding the global region appearance model to our framework will completely preserve the intrinsic structure of the target, thus effectively utilizing the discriminative information of the visible sub-region to mitigate tracker drift when partial occlusion occurs. In addition, an adaptive scale estimation scheme is incorporated into our algorithm to make the tracker more robust against potential challenging attributes. The experimental results from the OTB-2015 and VOT-2015 datasets demonstrate that our method performs favorably compared with several state-of-the-art trackers.

Dilated-aware discriminative correlation filter for visual tracking

2018 ◽  
Vol 22 (2) ◽  
pp. 791-805 ◽  
Author(s):  
Guoxia Xu ◽  
Hu Zhu ◽  
Lizhen Deng ◽  
Lixin Han ◽  
Yujie Li ◽  
...  
Keyword(s):  
Visual Tracking ◽  
Correlation Filter ◽  
Discriminative Correlation Filter

Visual tracking via dynamic saliency discriminative correlation filter

2021 ◽  
Author(s):  
Lina Gao ◽  
Bing Liu ◽  
Ping Fu ◽  
Mingzhu Xu ◽  
Junbao Li
Keyword(s):  
Visual Tracking ◽  
Correlation Filter ◽  
Discriminative Correlation Filter

scholarly journals Spatio-temporal joint aberrance suppressed correlation filter for visual tracking

2021 ◽  
Author(s):  
Libin Xu ◽  
Pyoungwon Kim ◽  
Mengjie Wang ◽  
Jinfeng Pan ◽  
Xiaomin Yang ◽  
...  
Keyword(s):  
Visual Tracking ◽  
State Of The Art ◽  
Boundary Effect ◽  
Correlation Filter ◽  
Star Model ◽  
Unified Framework ◽  
Alternating Direction ◽  
Background Clutter ◽  
Discriminative Correlation Filter ◽  
Spatio Temporal

AbstractThe discriminative correlation filter (DCF)-based tracking methods have achieved remarkable performance in visual tracking. However, the existing DCF paradigm still suffers from dilemmas such as boundary effect, filter degradation, and aberrance. To address these problems, we propose a spatio-temporal joint aberrance suppressed regularization (STAR) correlation filter tracker under a unified framework of response map. Specifically, a dynamic spatio-temporal regularizer is introduced into the DCF to alleviate the boundary effect and filter degradation, simultaneously. Meanwhile, an aberrance suppressed regularizer is exploited to reduce the interference of background clutter. The proposed STAR model is effectively optimized using the alternating direction method of multipliers (ADMM). Finally, comprehensive experiments on TC128, OTB2013, OTB2015 and UAV123 benchmarks demonstrate that the STAR tracker achieves compelling performance compared with the state-of-the-art (SOTA) trackers.

Learning spatio-temporal correlation filter for visual tracking

2021 ◽  
Vol 436 ◽  
pp. 273-282
Author(s):  
Youmin Yan ◽  
Xixian Guo ◽  
Jin Tang ◽  
Chenglong Li ◽  
Xin Wang
Keyword(s):  
Visual Tracking ◽  
Temporal Correlation ◽  
Correlation Filter ◽  
Spatio Temporal
Sign in / Sign up

Export Citation Format

Share Document