Cargando…

Unsupervised Monocular Depth Estimation Method Based on Uncertainty Analysis and Retinex Algorithm

Depth estimation of a single image presents a classic problem for computer vision, and is important for the 3D reconstruction of scenes, augmented reality, and object detection. At present, most researchers are beginning to focus on unsupervised monocular depth estimation. This paper proposes soluti...

Descripción completa

Detalles Bibliográficos
Autores principales: Song, Chuanxue, Qi, Chunyang, Song, Shixin, Xiao, Feng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7570747/
https://www.ncbi.nlm.nih.gov/pubmed/32967069
http://dx.doi.org/10.3390/s20185389
_version_ 1783597018669645824
author Song, Chuanxue
Qi, Chunyang
Song, Shixin
Xiao, Feng
author_facet Song, Chuanxue
Qi, Chunyang
Song, Shixin
Xiao, Feng
author_sort Song, Chuanxue
collection PubMed
description Depth estimation of a single image presents a classic problem for computer vision, and is important for the 3D reconstruction of scenes, augmented reality, and object detection. At present, most researchers are beginning to focus on unsupervised monocular depth estimation. This paper proposes solutions to the current depth estimation problem. These solutions include a monocular depth estimation method based on uncertainty analysis, which solves the problem in which a neural network has strong expressive ability but cannot evaluate the reliability of an output result. In addition, this paper proposes a photometric loss function based on the Retinex algorithm, which solves the problem of pulling around pixels due to the presence of moving objects. We objectively compare our method to current mainstream monocular depth estimation methods and obtain satisfactory results.
format Online
Article
Text
id pubmed-7570747
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-75707472020-10-28 Unsupervised Monocular Depth Estimation Method Based on Uncertainty Analysis and Retinex Algorithm Song, Chuanxue Qi, Chunyang Song, Shixin Xiao, Feng Sensors (Basel) Letter Depth estimation of a single image presents a classic problem for computer vision, and is important for the 3D reconstruction of scenes, augmented reality, and object detection. At present, most researchers are beginning to focus on unsupervised monocular depth estimation. This paper proposes solutions to the current depth estimation problem. These solutions include a monocular depth estimation method based on uncertainty analysis, which solves the problem in which a neural network has strong expressive ability but cannot evaluate the reliability of an output result. In addition, this paper proposes a photometric loss function based on the Retinex algorithm, which solves the problem of pulling around pixels due to the presence of moving objects. We objectively compare our method to current mainstream monocular depth estimation methods and obtain satisfactory results. MDPI 2020-09-21 /pmc/articles/PMC7570747/ /pubmed/32967069 http://dx.doi.org/10.3390/s20185389 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 Letter
Song, Chuanxue
Qi, Chunyang
Song, Shixin
Xiao, Feng
Unsupervised Monocular Depth Estimation Method Based on Uncertainty Analysis and Retinex Algorithm
title Unsupervised Monocular Depth Estimation Method Based on Uncertainty Analysis and Retinex Algorithm
title_full Unsupervised Monocular Depth Estimation Method Based on Uncertainty Analysis and Retinex Algorithm
title_fullStr Unsupervised Monocular Depth Estimation Method Based on Uncertainty Analysis and Retinex Algorithm
title_full_unstemmed Unsupervised Monocular Depth Estimation Method Based on Uncertainty Analysis and Retinex Algorithm
title_short Unsupervised Monocular Depth Estimation Method Based on Uncertainty Analysis and Retinex Algorithm
title_sort unsupervised monocular depth estimation method based on uncertainty analysis and retinex algorithm
topic Letter
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7570747/
https://www.ncbi.nlm.nih.gov/pubmed/32967069
http://dx.doi.org/10.3390/s20185389
work_keys_str_mv AT songchuanxue unsupervisedmonoculardepthestimationmethodbasedonuncertaintyanalysisandretinexalgorithm
AT qichunyang unsupervisedmonoculardepthestimationmethodbasedonuncertaintyanalysisandretinexalgorithm
AT songshixin unsupervisedmonoculardepthestimationmethodbasedonuncertaintyanalysisandretinexalgorithm
AT xiaofeng unsupervisedmonoculardepthestimationmethodbasedonuncertaintyanalysisandretinexalgorithm