Multiobject Tracking in Videos Based on LSTM and Deep Reinforcement Learning

Multiple-object tracking is a challenging issue in the computer vision community. In this paper, we propose a multiobject tracking algorithm in videos based on long short-term memory (LSTM) and deep reinforcement learning. Firstly, the multiple objects are detected by the object detector YOLO V2. Se...

Full description

Saved in:
Bibliographic Details
Main Authors: Ming-xin Jiang, Chao Deng, Zhi-geng Pan, Lan-fang Wang, Xing Sun
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2018/4695890
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849696316138979328
author Ming-xin Jiang
Chao Deng
Zhi-geng Pan
Lan-fang Wang
Xing Sun
author_facet Ming-xin Jiang
Chao Deng
Zhi-geng Pan
Lan-fang Wang
Xing Sun
author_sort Ming-xin Jiang
collection DOAJ
description Multiple-object tracking is a challenging issue in the computer vision community. In this paper, we propose a multiobject tracking algorithm in videos based on long short-term memory (LSTM) and deep reinforcement learning. Firstly, the multiple objects are detected by the object detector YOLO V2. Secondly, the problem of single-object tracking is considered as a Markov decision process (MDP) since this setting provides a formal strategy to model an agent that makes sequence decisions. The single-object tracker is composed of a network that includes a CNN followed by an LSTM unit. Each tracker, regarded as an agent, is trained by utilizing deep reinforcement learning. Finally, we conduct a data association using LSTM for each frame between the results of the object detector and the results of single-object trackers. From the experimental results, we can see that our tracker achieves better performance than the other state-of-the-art methods. Multiple targets can be steadily tracked even when frequent occlusions, similar appearances, and scale changes happened.
format Article
id doaj-art-cc01435e4e9046a9838d405fa60e7e61
institution DOAJ
issn 1076-2787
1099-0526
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-cc01435e4e9046a9838d405fa60e7e612025-08-20T03:19:29ZengWileyComplexity1076-27871099-05262018-01-01201810.1155/2018/46958904695890Multiobject Tracking in Videos Based on LSTM and Deep Reinforcement LearningMing-xin Jiang0Chao Deng1Zhi-geng Pan2Lan-fang Wang3Xing Sun4Faculty of Electronic Information Engineering, Huaiyin Institute of Technology, Huaian 223003, ChinaSchool of Physics & Electronic Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaInstitute of Industrial VR, Foshan University, Foshan 528000, ChinaFaculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223003, ChinaFaculty of Electronic Information Engineering, Huaiyin Institute of Technology, Huaian 223003, ChinaMultiple-object tracking is a challenging issue in the computer vision community. In this paper, we propose a multiobject tracking algorithm in videos based on long short-term memory (LSTM) and deep reinforcement learning. Firstly, the multiple objects are detected by the object detector YOLO V2. Secondly, the problem of single-object tracking is considered as a Markov decision process (MDP) since this setting provides a formal strategy to model an agent that makes sequence decisions. The single-object tracker is composed of a network that includes a CNN followed by an LSTM unit. Each tracker, regarded as an agent, is trained by utilizing deep reinforcement learning. Finally, we conduct a data association using LSTM for each frame between the results of the object detector and the results of single-object trackers. From the experimental results, we can see that our tracker achieves better performance than the other state-of-the-art methods. Multiple targets can be steadily tracked even when frequent occlusions, similar appearances, and scale changes happened.http://dx.doi.org/10.1155/2018/4695890
spellingShingle Ming-xin Jiang
Chao Deng
Zhi-geng Pan
Lan-fang Wang
Xing Sun
Multiobject Tracking in Videos Based on LSTM and Deep Reinforcement Learning
Complexity
title Multiobject Tracking in Videos Based on LSTM and Deep Reinforcement Learning
title_full Multiobject Tracking in Videos Based on LSTM and Deep Reinforcement Learning
title_fullStr Multiobject Tracking in Videos Based on LSTM and Deep Reinforcement Learning
title_full_unstemmed Multiobject Tracking in Videos Based on LSTM and Deep Reinforcement Learning
title_short Multiobject Tracking in Videos Based on LSTM and Deep Reinforcement Learning
title_sort multiobject tracking in videos based on lstm and deep reinforcement learning
url http://dx.doi.org/10.1155/2018/4695890
work_keys_str_mv AT mingxinjiang multiobjecttrackinginvideosbasedonlstmanddeepreinforcementlearning
AT chaodeng multiobjecttrackinginvideosbasedonlstmanddeepreinforcementlearning
AT zhigengpan multiobjecttrackinginvideosbasedonlstmanddeepreinforcementlearning
AT lanfangwang multiobjecttrackinginvideosbasedonlstmanddeepreinforcementlearning
AT xingsun multiobjecttrackinginvideosbasedonlstmanddeepreinforcementlearning