Actor–Critic Reinforcement Learning and Application in Developing Computer-Vision-Based Interface Tracking

This paper synchronizes control theory with computer vision by formalizing object tracking as a sequential decision-making process. A reinforcement learning (RL) agent successfully tracks an interface between two liquids, which is often a critical variable to track in many chemical, petrochemical, m...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Oguzhan Dogru, Kirubakaran Velswamy, Biao Huang
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Interface tracking Object tracking Occlusion Reinforcement learning Uniform manifold approximation and projection Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/a624e2d1afb747039710f977d50ab005
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a624e2d1afb747039710f977d50ab005
record_format	dspace
spelling	oai:doaj.org-article:a624e2d1afb747039710f977d50ab0052021-11-14T04:32:22ZActor–Critic Reinforcement Learning and Application in Developing Computer-Vision-Based Interface Tracking2095-809910.1016/j.eng.2021.04.027https://doaj.org/article/a624e2d1afb747039710f977d50ab0052021-09-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S209580992100326Xhttps://doaj.org/toc/2095-8099This paper synchronizes control theory with computer vision by formalizing object tracking as a sequential decision-making process. A reinforcement learning (RL) agent successfully tracks an interface between two liquids, which is often a critical variable to track in many chemical, petrochemical, metallurgical, and oil industries. This method utilizes less than 100 images for creating an environment, from which the agent generates its own data without the need for expert knowledge. Unlike supervised learning (SL) methods that rely on a huge number of parameters, this approach requires far fewer parameters, which naturally reduces its maintenance cost. Besides its frugal nature, the agent is robust to environmental uncertainties such as occlusion, intensity changes, and excessive noise. From a closed-loop control context, an interface location-based deviation is chosen as the optimization goal during training. The methodology showcases RL for real-time object-tracking applications in the oil sands industry. Along with a presentation of the interface tracking problem, this paper provides a detailed review of one of the most effective RL methodologies: actor–critic policy.Oguzhan DogruKirubakaran VelswamyBiao HuangElsevierarticleInterface trackingObject trackingOcclusionReinforcement learningUniform manifold approximation and projectionEngineering (General). Civil engineering (General)TA1-2040ENEngineering, Vol 7, Iss 9, Pp 1248-1261 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Interface tracking Object tracking Occlusion Reinforcement learning Uniform manifold approximation and projection Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	Interface tracking Object tracking Occlusion Reinforcement learning Uniform manifold approximation and projection Engineering (General). Civil engineering (General) TA1-2040 Oguzhan Dogru Kirubakaran Velswamy Biao Huang Actor–Critic Reinforcement Learning and Application in Developing Computer-Vision-Based Interface Tracking
description	This paper synchronizes control theory with computer vision by formalizing object tracking as a sequential decision-making process. A reinforcement learning (RL) agent successfully tracks an interface between two liquids, which is often a critical variable to track in many chemical, petrochemical, metallurgical, and oil industries. This method utilizes less than 100 images for creating an environment, from which the agent generates its own data without the need for expert knowledge. Unlike supervised learning (SL) methods that rely on a huge number of parameters, this approach requires far fewer parameters, which naturally reduces its maintenance cost. Besides its frugal nature, the agent is robust to environmental uncertainties such as occlusion, intensity changes, and excessive noise. From a closed-loop control context, an interface location-based deviation is chosen as the optimization goal during training. The methodology showcases RL for real-time object-tracking applications in the oil sands industry. Along with a presentation of the interface tracking problem, this paper provides a detailed review of one of the most effective RL methodologies: actor–critic policy.
format	article
author	Oguzhan Dogru Kirubakaran Velswamy Biao Huang
author_facet	Oguzhan Dogru Kirubakaran Velswamy Biao Huang
author_sort	Oguzhan Dogru
title	Actor–Critic Reinforcement Learning and Application in Developing Computer-Vision-Based Interface Tracking
title_short	Actor–Critic Reinforcement Learning and Application in Developing Computer-Vision-Based Interface Tracking
title_full	Actor–Critic Reinforcement Learning and Application in Developing Computer-Vision-Based Interface Tracking
title_fullStr	Actor–Critic Reinforcement Learning and Application in Developing Computer-Vision-Based Interface Tracking
title_full_unstemmed	Actor–Critic Reinforcement Learning and Application in Developing Computer-Vision-Based Interface Tracking
title_sort	actor–critic reinforcement learning and application in developing computer-vision-based interface tracking
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/a624e2d1afb747039710f977d50ab005
work_keys_str_mv	AT oguzhandogru actorcriticreinforcementlearningandapplicationindevelopingcomputervisionbasedinterfacetracking AT kirubakaranvelswamy actorcriticreinforcementlearningandapplicationindevelopingcomputervisionbasedinterfacetracking AT biaohuang actorcriticreinforcementlearningandapplicationindevelopingcomputervisionbasedinterfacetracking
_version_	1718429976263393280

Actor–Critic Reinforcement Learning and Application in Developing Computer-Vision-Based Interface Tracking

Ejemplares similares