Action-Driven Visual Object Tracking With Deep Reinforcement Learning
- Authors
- Yun, Sangdoo; Choi, Jongwon; Yoo, Youngjoon; Yun, Kimin; Choi, Jin Young
- Issue Date
- Jun-2018
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Deep neural network; reinforcement learning (RL); visual tracking
- Citation
- IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, v.29, no.6, pp 2239 - 2252
- Pages
- 14
- Journal Title
- IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
- Volume
- 29
- Number
- 6
- Start Page
- 2239
- End Page
- 2252
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/45249
- DOI
- 10.1109/TNNLS.2018.2801826
- ISSN
- 2162-237X
2162-2388
- Abstract
- In this paper, we propose an efficient visual tracker, which directly captures a bounding box containing the target object in a video by means of sequential actions learned using deep neural networks. The proposed deep neural network to control tracking actions is pretrained using various training video sequences and fine-tuned during actual tracking for online adaptation to a change of target and background. The pretraining is done by utilizing deep reinforcement learning (RL) as well as supervised learning. The use of RL enables even partially labeled data to be successfully utilized for semisupervised learning. Through the evaluation of the object tracking benchmark data set, the proposed tracker is validated to achieve a competitive performance at three times the speed of existing deep network-based trackers. The fast version of the proposed method, which operates in real time on graphics processing unit, outperforms the state-of-the-art real-time trackers with an accuracy improvement of more than 8%.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.