Visual Tracking Using Wang–Landau Reinforcement Sampler
Open Access
- 3 November 2020
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 10 (21), 7780
- https://doi.org/10.3390/app10217780
Abstract
In this study, we present a novel tracking system, in which the tracking accuracy can be considerably enhanced by state prediction. Accordingly, we present a new Q-learning-based reinforcement method, augmented by Wang–Landau sampling. In the proposed method, reinforcement learning is used to predict a target configuration for the subsequent frame, while Wang–Landau sampler balances the exploitation and exploration degrees of the prediction. Our method can adapt to control the randomness of policy, using statistics on the number of visits in a particular state. Thus, our method considerably enhances conventional Q-learning algorithm performance, which also enhances visual tracking performance. Numerical results demonstrate that our method substantially outperforms other state-of-the-art visual trackers and runs in realtime because our method contains no complicated deep neural network architectures.This publication has 36 references indexed in Scilit:
- Convolutional Features for Correlation Filter Based Visual TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Patch-based Scale Calculation for Real-time Visual TrackingIEEE Signal Processing Letters, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Visual Tracking via Locally Structured Gaussian Process RegressionIEEE Signal Processing Letters, 2015
- Visual Tracking via Structure Constrained GroupingIEEE Signal Processing Letters, 2014
- The devil is in the details: an evaluation of recent feature encoding methodsPublished by British Machine Vision Association and Society for Pattern Recognition ,2011
- Efficient, Multiple-Range Random Walk Algorithm to Calculate the Density of StatesPhysical Review Letters, 2001
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Q-learningMachine Learning, 1992
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992