ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Action-Driven Visual Object Tracking With Deep Reinforcement Learning
Cited 56 time in scopus Download 17 time Share share facebook twitter linkedin kakaostory
Authors
Sangdoo Yun, Jongwon Choi, Youngjoon Yoo, Kimin Yun, Jin Young Choi
Issue Date
2018-06
Citation
IEEE Transactions on Neural Networks and Learning Systems, v.29, no.6, pp.2239-3352
ISSN
2162-237X
Publisher
IEEE
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.1109/TNNLS.2018.2801826
Project Code
18HS4600, Development of High Performance Visual Discovery Platform for Realtime and Large-Scale Data Analysis and Prediction, Park Jongyoul
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%.
KSP Keywords
Benchmark datasets, Bounding Box, Competitive performance, Deep neural network(DNN), Deep reinforcement learning, Graphic Processing Unit(GPU), Online adaptation, Partially labeled data, Real-Time, Reinforcement Learning(RL), Semi-Supervised Learning(SSL)