Online Multi-Expert Learning for Visual Tracking
- 16 August 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 934-946
Abstract
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.Keywords
Funding Information
- Natural Science Foundation of Hunan Province (2018JJ1025)
This publication has 49 references indexed in Scilit:
- Robust Visual Tracking via Exclusive Context ModelingIEEE Transactions on Cybernetics, 2015
- Object Tracking BenchmarkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Pyramid-Based Visual Tracking Using Sparsity Represented Mean Transform2014
- Visual Tracking: An Experimental SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- A survey of appearance models in visual object trackingACM Transactions on Intelligent Systems and Technology, 2013
- Object Tracking by Occlusion Detection via Structured Sparse Learning2013
- Robust Visual Tracking via Structured Multi-Task Sparse LearningInternational Journal of Computer Vision, 2012
- Kernel-based object trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Tracking of Objects in Video Scenes with Time Varying ContentEURASIP Journal on Advances in Signal Processing, 2002