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

Pi, Jiatian; Zeng, Shaohua; Zuo, Qing; Wei, Yan

doi:10.1587/transinf.2018edl8116

Cited by 3 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, DCF-based approaches have shown outstanding results in object tracking benchmarks [2], [3]. The improvement in DCF-based tracking performance is mainly due to improvements in feature selection [4], [5], scale estimation [4], [6], [7], and tracking models [5], [8]- [11]. Among them, DRT [10] takes both discrimination and reliability information to reduce the tracking-model degradation caused by the unexpected salient regions on the feature map.…”

Section: Introductionmentioning

confidence: 99%

Prediction-Based Scale Adaptive Correlation Filter Tracker

Zhao¹,

Zhang²,

Liu³

et al. 2019

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

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.

show abstract