Visual Tracking Using Wang–Landau Reinforcement Sampler
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 predic...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/21/7780 |
| _version_ | 1797548951832887296 |
|---|---|
| author | Dokyeong Kwon Junseok Kwon |
| author_facet | Dokyeong Kwon Junseok Kwon |
| author_sort | Dokyeong Kwon |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T15:08:06Z |
| format | Article |
| id | doaj.art-76b4e0b0ec6e49188b493a73af1ac0e2 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:08:06Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-76b4e0b0ec6e49188b493a73af1ac0e22023-11-20T19:37:34ZengMDPI AGApplied Sciences2076-34172020-11-011021778010.3390/app10217780Visual Tracking Using Wang–Landau Reinforcement SamplerDokyeong Kwon0Junseok Kwon1School of Computer Science and Engineering, Chung-Ang University, Seoul 156-756, KoreaSchool of Computer Science and Engineering, Chung-Ang University, Seoul 156-756, KoreaIn 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.https://www.mdpi.com/2076-3417/10/21/7780Wang–Landau Monte Carloreinforcement learningvisual tracking |
| spellingShingle | Dokyeong Kwon Junseok Kwon Visual Tracking Using Wang–Landau Reinforcement Sampler Applied Sciences Wang–Landau Monte Carlo reinforcement learning visual tracking |
| title | Visual Tracking Using Wang–Landau Reinforcement Sampler |
| title_full | Visual Tracking Using Wang–Landau Reinforcement Sampler |
| title_fullStr | Visual Tracking Using Wang–Landau Reinforcement Sampler |
| title_full_unstemmed | Visual Tracking Using Wang–Landau Reinforcement Sampler |
| title_short | Visual Tracking Using Wang–Landau Reinforcement Sampler |
| title_sort | visual tracking using wang landau reinforcement sampler |
| topic | Wang–Landau Monte Carlo reinforcement learning visual tracking |
| url | https://www.mdpi.com/2076-3417/10/21/7780 |
| work_keys_str_mv | AT dokyeongkwon visualtrackingusingwanglandaureinforcementsampler AT junseokkwon visualtrackingusingwanglandaureinforcementsampler |