Cargando…

Deep Learning-Based Monocular Depth Estimation Methods—A State-of-the-Art Review

Monocular depth estimation from Red-Green-Blue (RGB) images is a well-studied ill-posed problem in computer vision which has been investigated intensively over the past decade using Deep Learning (DL) approaches. The recent approaches for monocular depth estimation mostly rely on Convolutional Neura...

Descripción completa

Detalles Bibliográficos
Autores principales: Khan, Faisal, Salahuddin, Saqib, Javidnia, Hossein
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7219073/
https://www.ncbi.nlm.nih.gov/pubmed/32316336
http://dx.doi.org/10.3390/s20082272
_version_ 1783532923597619200
author Khan, Faisal
Salahuddin, Saqib
Javidnia, Hossein
author_facet Khan, Faisal
Salahuddin, Saqib
Javidnia, Hossein
author_sort Khan, Faisal
collection PubMed
description Monocular depth estimation from Red-Green-Blue (RGB) images is a well-studied ill-posed problem in computer vision which has been investigated intensively over the past decade using Deep Learning (DL) approaches. The recent approaches for monocular depth estimation mostly rely on Convolutional Neural Networks (CNN). Estimating depth from two-dimensional images plays an important role in various applications including scene reconstruction, 3D object-detection, robotics and autonomous driving. This survey provides a comprehensive overview of this research topic including the problem representation and a short description of traditional methods for depth estimation. Relevant datasets and 13 state-of-the-art deep learning-based approaches for monocular depth estimation are reviewed, evaluated and discussed. We conclude this paper with a perspective towards future research work requiring further investigation in monocular depth estimation challenges.
format Online
Article
Text
id pubmed-7219073
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-72190732020-05-22 Deep Learning-Based Monocular Depth Estimation Methods—A State-of-the-Art Review Khan, Faisal Salahuddin, Saqib Javidnia, Hossein Sensors (Basel) Review Monocular depth estimation from Red-Green-Blue (RGB) images is a well-studied ill-posed problem in computer vision which has been investigated intensively over the past decade using Deep Learning (DL) approaches. The recent approaches for monocular depth estimation mostly rely on Convolutional Neural Networks (CNN). Estimating depth from two-dimensional images plays an important role in various applications including scene reconstruction, 3D object-detection, robotics and autonomous driving. This survey provides a comprehensive overview of this research topic including the problem representation and a short description of traditional methods for depth estimation. Relevant datasets and 13 state-of-the-art deep learning-based approaches for monocular depth estimation are reviewed, evaluated and discussed. We conclude this paper with a perspective towards future research work requiring further investigation in monocular depth estimation challenges. MDPI 2020-04-16 /pmc/articles/PMC7219073/ /pubmed/32316336 http://dx.doi.org/10.3390/s20082272 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Review
Khan, Faisal
Salahuddin, Saqib
Javidnia, Hossein
Deep Learning-Based Monocular Depth Estimation Methods—A State-of-the-Art Review
title Deep Learning-Based Monocular Depth Estimation Methods—A State-of-the-Art Review
title_full Deep Learning-Based Monocular Depth Estimation Methods—A State-of-the-Art Review
title_fullStr Deep Learning-Based Monocular Depth Estimation Methods—A State-of-the-Art Review
title_full_unstemmed Deep Learning-Based Monocular Depth Estimation Methods—A State-of-the-Art Review
title_short Deep Learning-Based Monocular Depth Estimation Methods—A State-of-the-Art Review
title_sort deep learning-based monocular depth estimation methods—a state-of-the-art review
topic Review
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7219073/
https://www.ncbi.nlm.nih.gov/pubmed/32316336
http://dx.doi.org/10.3390/s20082272
work_keys_str_mv AT khanfaisal deeplearningbasedmonoculardepthestimationmethodsastateoftheartreview
AT salahuddinsaqib deeplearningbasedmonoculardepthestimationmethodsastateoftheartreview
AT javidniahossein deeplearningbasedmonoculardepthestimationmethodsastateoftheartreview