Decision Controller for Object Tracking With Deep Reinforcement Learning

Decision Controller for Object Tracking With Deep Reinforcement Learning

There are many decisions which are usually made heuristically both in single object tracking (SOT) and multiple object tracking (MOT). Existing methods focus on tackling decision-making problems on special tasks in tracking without a unified framework. In this paper, we propose a decision controller...

Full description

Bibliographic Details
Main Authors: Zhao Zhong, Zichen Yang, Weitao Feng, Wei Wu, Yangyang Hu, Cheng-Lin Liu
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Computer vision
deep learning
object tracking
reinforcement learning
Online Access:https://ieeexplore.ieee.org/document/8648377/

Internet

https://ieeexplore.ieee.org/document/8648377/

Similar Items