Real-time visual tracking using complementary kernel support correlation filters

2019 ◽  
Vol 14 (2) ◽  
pp. 417-429 ◽  
Author(s):  
Zhenyang Su ◽  
Jing Li ◽  
Jun Chang ◽  
Bo Du ◽  
Yafu Xiao
Keyword(s):  
Real Time ◽  
Visual Tracking ◽  
Correlation Filters

scholarly journals Real-Time Visual Tracking with Variational Structure Attention Network

Sensors ◽  
2019 ◽  
Vol 19 (22) ◽  
pp. 4904 ◽  
Author(s):  
Yeongbin Kim ◽  
Joongchol Shin ◽  
Hasil Park ◽  
Joonki Paik
Keyword(s):  
Real Time ◽  
Visual Tracking ◽  
Boundary Effect ◽  
Online Training ◽  
Correlation Filter ◽  
Shape Distortion ◽  
Correlation Filters ◽  
Attention Network ◽  
Real Time Processing ◽  
Variational Structure

Online training framework based on discriminative correlation filters for visual tracking has recently shown significant improvement in both accuracy and speed. However, correlation filter-base discriminative approaches have a common problem of tracking performance degradation when the local structure of a target is distorted by the boundary effect problem. The shape distortion of the target is mainly caused by the circulant structure in the Fourier domain processing, and it makes the correlation filter learn distorted training samples. In this paper, we present a structure–attention network to preserve the target structure from the structure distortion caused by the boundary effect. More specifically, we adopt a variational auto-encoder as a structure–attention network to make various and representative target structures. We also proposed two denoising criteria using a novel reconstruction loss for variational auto-encoding framework to capture more robust structures even under the boundary condition. Through the proposed structure–attention framework, discriminative correlation filters can learn robust structure information of targets during online training with an enhanced discriminating performance and adaptability. Experimental results on major visual tracking benchmark datasets show that the proposed method produces a better or comparable performance compared with the state-of-the-art tracking methods with a real-time processing speed of more than 80 frames per second.

scholarly journals Robust Scale Adaptive and Real-Time Visual Tracking with Correlation Filters

2016 ◽  
Vol E99.D (7) ◽  
pp. 1895-1902
Author(s):  
Jiatian PI ◽  
Keli HU ◽  
Yuzhang GU ◽  
Lei QU ◽  
Fengrong LI ◽  
...  
Keyword(s):  
Real Time ◽  
Visual Tracking ◽  
Correlation Filters

scholarly journals Accurate Scale Adaptive and Real-Time Visual Tracking with Correlation Filters

2018 ◽  
Vol E101.D (11) ◽  
pp. 2855-2858 ◽  
Author(s):  
Jiatian PI ◽  
Shaohua ZENG ◽  
Qing ZUO ◽  
Yan WEI
Keyword(s):  
Real Time ◽  
Visual Tracking ◽  
Correlation Filters

scholarly journals Real-Time Scalable Visual Tracking via Quadrangle Kernelized Correlation Filters

2018 ◽  
Vol 19 (1) ◽  
pp. 140-150 ◽  
Author(s):  
Guiguang Ding ◽  
Wenshuo Chen ◽  
Sicheng Zhao ◽  
Jungong Han ◽  
Qiaoyan Liu
Keyword(s):  
Real Time ◽  
Visual Tracking ◽  
Correlation Filters ◽  
Kernelized Correlation Filters

Real-time Visual Tracking of Multiple Targets Using Bootstrap Importance Sampling

2012 ◽  
Vol 38 (10) ◽  
pp. 1663
Author(s):  
Le-Jun SHEN ◽  
Zhi-Sheng YOU ◽  
Xiao-Feng LI
Keyword(s):  
Real Time ◽  
Importance Sampling ◽  
Visual Tracking ◽  
Multiple Targets
Sign in / Sign up

Export Citation Format

Share Document