Learning spatio-temporal context via hierarchical features for visual tracking

2018 ◽  
Vol 66 ◽  
pp. 50-65 ◽  
Author(s):  
Yi Cao ◽  
Hongbing Ji ◽  
Wenbo Zhang ◽  
Fei Xue
Keyword(s):  
Visual Tracking ◽  
Temporal Context ◽  
Spatio Temporal ◽  
Hierarchical Features

scholarly journals Multi-Channel Features Spatio-Temporal Context Learning for Visual Tracking

IEEE Access ◽  
2017 ◽  
Vol 5 ◽  
pp. 12856-12864 ◽  
Author(s):  
Xiaoqin Zhou ◽  
Xiaofeng Liu ◽  
Chenguang Yang ◽  
Aimin Jiang ◽  
Bin Yan
Keyword(s):  
Visual Tracking ◽  
Temporal Context ◽  
Context Learning ◽  
Spatio Temporal

scholarly journals Orderless and Blurred Visual Tracking via Spatio-temporal Context

2015 ◽  
pp. 25-36 ◽  
Author(s):  
Manna Dai ◽  
Peijie Lin ◽  
Lijun Wu ◽  
Zhicong Chen ◽  
Songlin Lai ◽  
...  
Keyword(s):  
Visual Tracking ◽  
Temporal Context ◽  
Spatio Temporal

scholarly journals Robust Online Learned Spatio-Temporal Context Model for Visual Tracking

2014 ◽  
Vol 23 (2) ◽  
pp. 785-796 ◽  
Author(s):  
Longyin Wen ◽  
Zhaowei Cai ◽  
Zhen Lei ◽  
Dong Yi ◽  
Stan Z. Li
Keyword(s):  
Visual Tracking ◽  
Temporal Context ◽  
Context Model ◽  
Spatio Temporal

Oversaturated part-based visual tracking via spatio-temporal context learning

2016 ◽  
Vol 55 (25) ◽  
pp. 6960 ◽  
Author(s):  
Wei Liu ◽  
Jicheng Li ◽  
Zhiguang Shi ◽  
Xiaotian Chen ◽  
Xiao Chen
Keyword(s):  
Visual Tracking ◽  
Temporal Context ◽  
Context Learning ◽  
Spatio Temporal

scholarly journals Fast Visual Tracking via Dense Spatio-temporal Context Learning

2014 ◽  
pp. 127-141 ◽  
Author(s):  
Kaihua Zhang ◽  
Lei Zhang ◽  
Qingshan Liu ◽  
David Zhang ◽  
Ming-Hsuan Yang
Keyword(s):  
Visual Tracking ◽  
Temporal Context ◽  
Context Learning ◽  
Spatio Temporal

scholarly journals A Robust Visual Tracking Algorithm Based on Spatial-Temporal Context Hierarchical Response Fusion

Algorithms ◽  
2018 ◽  
Vol 12 (1) ◽  
pp. 8 ◽  
Author(s):  
Wancheng Zhang ◽  
Yanmin Luo ◽  
Zhi Chen ◽  
Yongzhao Du ◽  
Daxin Zhu ◽  
...  
Keyword(s):  
Visual Tracking ◽  
Correlation Filter ◽  
Temporal Context ◽  
Visual Object ◽  
Correlation Filters ◽  
Visual Object Tracking ◽  
Illumination Changes ◽  
Model Update ◽  
Benchmark Datasets ◽  
Hierarchical Features

Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual object tracking. However, visual tracking is still challenging when the target objects undergo complex scenarios such as occlusion, deformation, scale changes and illumination changes. In this paper, we utilize the hierarchical features of convolutional neural networks (CNNs) and learn a spatial-temporal context correlation filter on convolutional layers. Then, the translation is estimated by fusing the response score of the filters on the three convolutional layers. In terms of scale estimation, we learn a discriminative correlation filter to estimate scale from the best confidence results. Furthermore, we proposed a re-detection activation discrimination method to improve the robustness of visual tracking in the case of tracking failure and an adaptive model update method to reduce tracking drift caused by noisy updates. We evaluate the proposed tracker with DCFs and deep features on OTB benchmark datasets. The tracking results demonstrated that the proposed algorithm is superior to several state-of-the-art DCF methods in terms of accuracy and robustness.

Sign in / Sign up

Export Citation Format

Share Document