Check out RSS, or use RSS reader to subscribe this item
Confirmation
Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
Sponsored by the Center for Science and Technology Development of the Ministry of Education
Supervised by Ministry of Education of the People's Republic of China
Kernel Correlation Filter Tracking based on Spatial Constraint
LI Zhi-Yong *,Chen Li
College of Computer Science and Electronic Engineering of Hunan University, and Key Laboratory for Embedded and Network Computing of Hunan Province, Changsha 410082
*Correspondence author
#Submitted by
Subject:
Funding:
The National Natural Science Foundation of China (No.61672215), The National Natural Science Foundation of China (No.U1613209)
Correlation filter (CF) based trackers have become quite popular in video tracking because of their impressive performance and high frame rates. A large amount of recent research focuses on the improvement of training model of correlation filter to get a tracker with better discriminative power. However, this only helps the tracker to discriminate the target object from background within a small neighborhood, which is not suitable for fast motion scenes. In this paper, we propose a new detection model to dig out the potential of the correlation filter to deal with the challenge of fast motion. The model performs detection operations on multiple small search areas within a large one. Thus, our tracker can accurately localize the target object in a larger search area. In addition, we also added space constraints to boost the tracking performance of the model. The extensive experimental results demonstrate that the proposed tracker outperforms several state-of-the-art trackers on the challenging benchmark dataset with 51 sequences.
Keywords:Visual tracking; correlation filter; fast motion; detection model; space constraints.