.png){kind=icon}
返回
Correlation filter tracking algorithm based on spatial-temporal regularization and context awareness
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-022-03458-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The tracker based on correlation filters can achieve effective positioning at a relatively fast speed, resulting from its operation in the frequency domain. As a result, it is commonly employed in the field of object tracking. However, this characteristic introduces boundary effect and affects the tracking performance in some scenes. In this work, a correlation filter tracking algorithm with spatial-temporal regularization and context awareness (STCACF) is proposed: (1) the spatial-temporal information and context awareness is added to the training process to mitigate the boundary effect and enhance the overall tracking performance; (2) the tracker model adopts the iterative method of alternating direction method of multipliers (ADMM), so that each subproblem can be solved in a closed-loop solution, which can realize real-time tracking; (3) the spatial regularization is employed to reduce the influence of filter degradation. Experiments on the OTB-2013, the OTB-2015 and the TC-128 benchmark datasets demonstrate that the suggested STCACF is capable of significantly improving the tracking performance compared with state-of-the-art trackers. The STCACF tracker runs at a frame rate of approximately 22 frames per second (FPS) on a single central processing unit (CPU).
Keyword:
Correlation filter
Boundary effect
Spatial-temporal regularization
Context awareness
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Occluded object tracking using object-background prototypes and particle filter.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏SiamOAN: Siamese object-aware network for real-time target trackingSiamOAN: 用于实时目标跟踪的暹罗对象感知网络NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容