Long-term correlation tracking
Citations Over TimeTop 1% of 2015 papers
Abstract
In this paper, we address the problem of long-term visual tracking where the target objects undergo significant appearance variation due to deformation, abrupt motion, heavy occlusion and out-of-view. In this setting, we decompose the task of tracking into translation and scale estimation of objects. We show that the correlation between temporal context considerably improves the accuracy and reliability for translation estimation, and it is effective to learn discriminative correlation filters from the most confident frames to estimate the scale change. In addition, we train an online random fern classifier to re-detect objects in case of tracking failure. Extensive experimental results on large-scale benchmark datasets show that the proposed algorithm performs favorably against state-of-the-art methods in terms of efficiency, accuracy, and robustness.
Related Papers
- → Multi-target tracking by on-line learned discriminative appearance models(2010)287 cited
- Survey of Generative and Discriminative Appearance Models in Visual Object Tracking(2018)
- → Discriminative Bag-of-Words-Based Adaptive Appearance Model for Robust Visual Tracking(2017)3 cited
- → Cascaded Generative and Discriminative Learning for Visual Tracking(2013)2 cited
- Multi-person tracking using a discriminative color appearance model(2013)