Prediction-Based Scale Adaptive Correlation Filter Tracker

Zuopeng ZHAO  Hongda ZHANG  Yi LIU  Nana ZHOU  Han ZHENG  Shanyi SUN  Xiaoman LI  Sili XIA  

IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.11   pp.2267-2271
Publication Date: 2019/11/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2019EDL8101
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
visual tracking,  correlation filter,  scale prediction,  model update,  fast motion,  

Full Text: PDF>>
Buy this Article

Although correlation filter-based trackers have demonstrated excellent performance for visual object tracking, there remain several challenges to be addressed. In this work, we propose a novel tracker based on the correlation filter framework. Traditional trackers face difficulty in accurately adapting to changes in the scale of the target when the target moves quickly. To address this, we suggest a scale adaptive scheme based on prediction scales. We also incorporate a speed-based adaptive model update method to further improve overall tracking performance. Experiments with samples from the OTB100 and KITTI datasets demonstrate that our method outperforms existing state-of-the-art tracking algorithms in fast motion scenes.