Cargando…

A Critical Review of Deep Learning-Based Multi-Sensor Fusion Techniques

In this review, we provide a detailed coverage of multi-sensor fusion techniques that use RGB stereo images and a sparse LiDAR-projected depth map as input data to output a dense depth map prediction. We cover state-of-the-art fusion techniques which, in recent years, have been deep learning-based m...

Descripción completa

Detalles Bibliográficos
Autores principales: Marsh, Benedict, Sadka, Abdul Hamid, Bahai, Hamid
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9737943/
https://www.ncbi.nlm.nih.gov/pubmed/36502065
http://dx.doi.org/10.3390/s22239364
_version_ 1784847415020355584
author Marsh, Benedict
Sadka, Abdul Hamid
Bahai, Hamid
author_facet Marsh, Benedict
Sadka, Abdul Hamid
Bahai, Hamid
author_sort Marsh, Benedict
collection PubMed
description In this review, we provide a detailed coverage of multi-sensor fusion techniques that use RGB stereo images and a sparse LiDAR-projected depth map as input data to output a dense depth map prediction. We cover state-of-the-art fusion techniques which, in recent years, have been deep learning-based methods that are end-to-end trainable. We then conduct a comparative evaluation of the state-of-the-art techniques and provide a detailed analysis of their strengths and limitations as well as the applications they are best suited for.
format Online
Article
Text
id pubmed-9737943
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97379432022-12-11 A Critical Review of Deep Learning-Based Multi-Sensor Fusion Techniques Marsh, Benedict Sadka, Abdul Hamid Bahai, Hamid Sensors (Basel) Review In this review, we provide a detailed coverage of multi-sensor fusion techniques that use RGB stereo images and a sparse LiDAR-projected depth map as input data to output a dense depth map prediction. We cover state-of-the-art fusion techniques which, in recent years, have been deep learning-based methods that are end-to-end trainable. We then conduct a comparative evaluation of the state-of-the-art techniques and provide a detailed analysis of their strengths and limitations as well as the applications they are best suited for. MDPI 2022-12-01 /pmc/articles/PMC9737943/ /pubmed/36502065 http://dx.doi.org/10.3390/s22239364 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/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 (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Review
Marsh, Benedict
Sadka, Abdul Hamid
Bahai, Hamid
A Critical Review of Deep Learning-Based Multi-Sensor Fusion Techniques
title A Critical Review of Deep Learning-Based Multi-Sensor Fusion Techniques
title_full A Critical Review of Deep Learning-Based Multi-Sensor Fusion Techniques
title_fullStr A Critical Review of Deep Learning-Based Multi-Sensor Fusion Techniques
title_full_unstemmed A Critical Review of Deep Learning-Based Multi-Sensor Fusion Techniques
title_short A Critical Review of Deep Learning-Based Multi-Sensor Fusion Techniques
title_sort critical review of deep learning-based multi-sensor fusion techniques
topic Review
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9737943/
https://www.ncbi.nlm.nih.gov/pubmed/36502065
http://dx.doi.org/10.3390/s22239364
work_keys_str_mv AT marshbenedict acriticalreviewofdeeplearningbasedmultisensorfusiontechniques
AT sadkaabdulhamid acriticalreviewofdeeplearningbasedmultisensorfusiontechniques
AT bahaihamid acriticalreviewofdeeplearningbasedmultisensorfusiontechniques
AT marshbenedict criticalreviewofdeeplearningbasedmultisensorfusiontechniques
AT sadkaabdulhamid criticalreviewofdeeplearningbasedmultisensorfusiontechniques
AT bahaihamid criticalreviewofdeeplearningbasedmultisensorfusiontechniques