Hierarchical Tracking by Reinforcement Learning-Based Searching and Coarse-to-Fine Verifying
- 5 December 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 28 (5), 2331-2341
- https://doi.org/10.1109/tip.2018.2885238
Abstract
A class-agnostic tracker typically consists of three key components, i.e., its motion model, its target appearance model, and its updating strategy. However, most recent top-performing trackers mainly focus on constructing complicated appearance models and updating strategies, while using comparatively simple and heuristic motion models that may result in an inefficient search and degrade the tracking performance. To address this issue, we propose a hierarchical tracker that learns to move and track based on the combination of data-driven search at the coarse level and coarse-to-fine verification at the fine level. At the coarse level, a data-driven motion model learned from deep recurrent reinforcement learning provides our tracker with coarse localization of an object. By formulating motion search as an action-decision problem in reinforcement learning, our tracker utilizes a recurrent convolutional neural network-based deep Q-network to effectively learn data-driven searching policies. The learned motion model can not only significantly reduce the search space but also provide more reliable interested regions for further verifying. At the fine level, a kernelized correlation filter (KCF)-based appearance model is adopted to densely yet efficiently verify a local region centered on the predicted location from the motion model. Through use of circulant matrices and fast Fourier transformation, a large number of candidate samples in the local region can be efficiently and effectively evaluated by the KCF-based appearance model. Finally, a simple yet robust estimator is designed to analyze possible tracking failure. The experiments on OTB50 and OTB100 illustrate that our tracker achieves better performance than the state-of-the-art trackers.Keywords
Funding Information
- National Natural Science Foundation of China (61572205, 61802135, 61728103)
- Natural Science Foundation of Fujian Province (2017J01113)
- Division of Information and Intelligent Systems (1651902)
This publication has 49 references indexed in Scilit:
- Human-level control through deep reinforcement learningNature, 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
- Accurate Scale Estimation for Robust Visual TrackingPublished by British Machine Vision Association and Society for Pattern Recognition ,2014
- 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 trackingACM Computing Surveys, 2006
- Kernel-based object trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Mechanisms of Visual Attention in the Human CortexAnnual Review of Neuroscience, 2000
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992