Visual Tracking via Hierarchical Deep Reinforcement Learning

Authors

  • Dawei Zhang Zhejiang Normal University
  • Zhonglong Zheng Zhejiang Normal University
  • Riheng Jia Zhejiang Normal University
  • Minglu Li Zhejiang Normal University Shanghai Jiao Tong University

Keywords:

Motion & Tracking, Video Understanding & Activity Analysis

Abstract

Visual tracking has achieved great progress due to numerous different algorithms. However, deep trackers based on classification or Siamese network still have their specific limitations. In this work, we show how to teach machines to track a generic object in videos like humans, who can use a few search steps to perform tracking. By constructing a Markov decision process in Deep Reinforcement Learning (DRL), our agents can learn to determine hierarchical decisions on tracking mode and motion estimation. To be specific, our Hierarchical DRL framework is composed of a Siamese-based observation network which models the motion information of an arbitrary target, a policy network for mode switch and an actor-critic network for box regression. This tracking strategy is more in line with human behavior paradigm, and is effective and efficient to cope with fast motion, background clutter and large deformations. Extensive experiments on the GOT-10k, OTB-100, UAV-123, VOT and LaSOT tracking benchmarks, demonstrate that the proposed tracker achieves state-of-the-art performance while running in real-time.

Downloads

Published

2021-05-18

How to Cite

Zhang, D., Zheng, Z., Jia, R., & Li, M. (2021). Visual Tracking via Hierarchical Deep Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 3315-3323. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16443

Issue

Section

AAAI Technical Track on Computer Vision III