期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 29, 期 -, 页码 934-946出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2019.2931082
关键词
Object tracking; multi-expert; second-order quantile Methods; minimum entropy criterion
资金
- Hunan Provincial Natural Science Foundation of China for Distinguished Young Scholars [2018JJ1025]
The correlation filters based trackers have achieved an excellent performance for object tracking in recent years. However, most existing methods use only one filter but ignore the information of the previous filters. In this paper, we propose a novel online multi-expert learning algorithm for visual tracking. In our proposed scheme, there are former trackers which retain the previous filters, and those trackers will give their predictions in each frame. The current tracker represents the filter of current frame, and both the current tracker and the former trackers constitute our expert ensemble. We use an adaptive Second-order Quantile strategy to learn the weights of each expert, which can take full advantage of all the experts. To simplify our model and remove some bad experts, we prune our models via a minimum entropy criterion. Finally, we propose a new update strategy to avoid the model corruption problem. Extensive experimental results on both OTB2013 and OTB2015 benchmarks demonstrate that our proposed tracker performs favorably against state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据