Monocular Depth Estimation Using Deep Learning: A Review

Masoumian, Armin; Rashwan, Hatem A; Cristiano, Julian; Asif, M Salman; Puig, Domenec

Pertany a la col·lecció PC:SerieArticles

TÍTOL:

Monocular Depth Estimation Using Deep Learning: A Review - imarina:9280435

Handle:

https://hdl.handle.net/20.500.11797/imarina9280435

Autor/s de la URV:	Abdellatif Fatahallah Ibrahim Mahmoud, Hatem / CRISTIANO RODRÍGUEZ, JULIÁN EFRÉN / Masoumian, Armin / Puig Valls, Domènec Savi
Autor segons l'article:	Masoumian, Armin; Rashwan, Hatem A; Cristiano, Julian; Asif, M Salman; Puig, Domenec
Adreça de correu electrònic de l'autor:	hatem.abdellatif@urv.cat armin.masoumian@estudiants.urv.cat armin.masoumian@estudiants.urv.cat domenec.puig@urv.cat
Identificador de l'autor:	0000-0001-5421-1637 0000-0002-0562-4205
Any de publicació de la revista:	2022
Tipus de publicació:	Journal Publications
Referència de l'ítem segons les normes APA:	Masoumian, Armin; Rashwan, Hatem A; Cristiano, Julian; Asif, M Salman; Puig, Domenec (2022). Monocular Depth Estimation Using Deep Learning: A Review. Sensors, 22(14), 5353-. DOI: 10.3390/s22145353
Referència a l'article segons font original:	Sensors. 22 (14): 5353-
Resum:	In current decades, significant advancements in robotics engineering and autonomous vehicles have improved the requirement for precise depth measurements. Depth estimation (DE) is a traditional task in computer vision that can be appropriately predicted by applying numerous procedures. This task is vital in disparate applications such as augmented reality and target tracking. Conventional monocular DE (MDE) procedures are based on depth cues for depth prediction. Various deep learning techniques have demonstrated their potential applications in managing and supporting the traditional ill-posed problem. The principal purpose of this paper is to represent a state-of-the-art review of the current developments in MDE based on deep learning techniques. For this goal, this paper tries to highlight the critical points of the state-of-the-art works on MDE from disparate aspects. These aspects include input data shapes and training manners such as supervised, semi-supervised, and unsupervised learning approaches in combination with applying different datasets and evaluation indicators. At last, limitations regarding the accuracy of the DL-based MDE models, computational time requirements, real-time inference, transferability, input images shape and domain adaptation, and generalization are discussed to open new directions for future research.
DOI de l'article:	10.3390/s22145353
Enllaç font original:	https://www.mdpi.com/1424-8220/22/14/5353
Versió de l'article dipositat:	info:eu-repo/semantics/publishedVersion
Accès a la llicència d'ús:	https://creativecommons.org/licenses/by/3.0/es/
Departament:	Enginyeria Informàtica i Matemàtiques
URL Document de llicència:	https://repositori.urv.cat/ca/proteccio-de-dades/
Àrees temàtiques:	Zootecnia / recursos pesqueiros Química Medicine (miscellaneous) Medicina veterinaria Medicina iii Medicina ii Medicina i Materiais Matemática / probabilidade e estatística Linguística e literatura Letras / linguística Interdisciplinar Instruments & instrumentation Instrumentation Information systems Geografía Geociências Farmacia Engineering, electrical & electronic Engenharias iv Engenharias iii Engenharias ii Engenharias i Electrochemistry Electrical and electronic engineering Educação física Ciências biológicas iii Ciências biológicas ii Ciências biológicas i Ciências ambientais Ciências agrárias i Ciência de alimentos Ciência da computação Chemistry, analytical Biotecnología Biodiversidade Biochemistry Atomic and molecular physics, and optics Astronomia / física Arquitetura, urbanismo e design Analytical chemistry
Paraules clau:	Supervised, semi-supervised, and unsupervised learning Supervised Single image depth estimation Semi-supervised Multi-task learning Monocular depth estimation Forecasting Deep learning Camera Augmented reality And unsupervised learning
Entitat:	Universitat Rovira i Virgili
Data d'alta del registre:	2024-09-21

Descripció:	In current decades, significant advancements in robotics engineering and autonomous vehicles have improved the requirement for precise depth measurements. Depth estimation (DE) is a traditional task in computer vision that can be appropriately predicted by applying numerous procedures. This task is vital in disparate applications such as augmented reality and target tracking. Conventional monocular DE (MDE) procedures are based on depth cues for depth prediction. Various deep learning techniques have demonstrated their potential applications in managing and supporting the traditional ill-posed problem. The principal purpose of this paper is to represent a state-of-the-art review of the current developments in MDE based on deep learning techniques. For this goal, this paper tries to highlight the critical points of the state-of-the-art works on MDE from disparate aspects. These aspects include input data shapes and training manners such as supervised, semi-supervised, and unsupervised learning approaches in combination with applying different datasets and evaluation indicators. At last, limitations regarding the accuracy of the DL-based MDE models, computational time requirements, real-time inference, transferability, input images shape and domain adaptation, and generalization are discussed to open new directions for future research.
Tipus:	Journal Publications
Coautor:	Universitat Rovira i Virgili
Títol:	Monocular Depth Estimation Using Deep Learning: A Review
Matèria:	Analytical Chemistry,Atomic and Molecular Physics, and Optics,Biochemistry,Chemistry, Analytical,Electrical and Electronic Engineering,Electrochemistry,Engineering, Electrical & Electronic,Information Systems,Instrumentation,Instruments & Instrumentation,Medicine (Miscellaneous) Supervised, semi-supervised, and unsupervised learning Supervised Single image depth estimation Semi-supervised Multi-task learning Monocular depth estimation Forecasting Deep learning Camera Augmented reality And unsupervised learning Zootecnia / recursos pesqueiros Química Medicine (miscellaneous) Medicina veterinaria Medicina iii Medicina ii Medicina i Materiais Matemática / probabilidade e estatística Linguística e literatura Letras / linguística Interdisciplinar Instruments & instrumentation Instrumentation Information systems Geografía Geociências Farmacia Engineering, electrical & electronic Engenharias iv Engenharias iii Engenharias ii Engenharias i Electrochemistry Electrical and electronic engineering Educação física Ciências biológicas iii Ciências biológicas ii Ciências biológicas i Ciências ambientais Ciências agrárias i Ciência de alimentos Ciência da computação Chemistry, analytical Biotecnología Biodiversidade Biochemistry Atomic and molecular physics, and optics Astronomia / física Arquitetura, urbanismo e design Analytical chemistry
Data:	2022
Autor:	Masoumian, Armin Rashwan, Hatem A Cristiano, Julian Asif, M Salman Puig, Domenec
Drets:	info:eu-repo/semantics/openAccess

Cerca el teu registre a:

Fitxers disponibles
Fitxer	Descripció	Format
DocumentPrincipal	DocumentPrincipal	application/pdf

Tots els objectes d'aquesta col·lecció

Informació