Cargando…

Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam

Simultaneous localization and mapping (SLAM) technology can be used to locate and build maps in unknown environments, but the constructed maps often suffer from poor readability and interactivity, and the primary and secondary information in the map cannot be accurately grasped. For intelligent robo...

Descripción completa

Detalles Bibliográficos
Autores principales: Sun, Ying, Hu, Jun, Yun, Juntong, Liu, Ying, Bai, Dongxu, Liu, Xin, Zhao, Guojun, Jiang, Guozhang, Kong, Jianyi, Chen, Baojia
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9571389/
https://www.ncbi.nlm.nih.gov/pubmed/36236676
http://dx.doi.org/10.3390/s22197576
_version_ 1784810352298426368
author Sun, Ying
Hu, Jun
Yun, Juntong
Liu, Ying
Bai, Dongxu
Liu, Xin
Zhao, Guojun
Jiang, Guozhang
Kong, Jianyi
Chen, Baojia
author_facet Sun, Ying
Hu, Jun
Yun, Juntong
Liu, Ying
Bai, Dongxu
Liu, Xin
Zhao, Guojun
Jiang, Guozhang
Kong, Jianyi
Chen, Baojia
author_sort Sun, Ying
collection PubMed
description Simultaneous localization and mapping (SLAM) technology can be used to locate and build maps in unknown environments, but the constructed maps often suffer from poor readability and interactivity, and the primary and secondary information in the map cannot be accurately grasped. For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them. Our proposed method can not only reduce the absolute positional errors (APE) and improve the positioning performance of the system but also construct the object-oriented dense semantic point cloud map and output point cloud model of each object to reconstruct each object in the indoor scene. In fact, eight categories of objects are used for detection and semantic mapping using coco weights in our experiments, and most objects in the actual scene can be reconstructed in theory. Experiments show that the number of points in the point cloud is significantly reduced. The average positioning error of the eight categories of objects in Technical University of Munich (TUM) datasets is very small. The absolute positional error of the camera is also reduced with the introduction of semantic constraints, and the positioning performance of the system is improved. At the same time, our algorithm can segment the point cloud model of objects in the environment with high accuracy.
format Online
Article
Text
id pubmed-9571389
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-95713892022-10-17 Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam Sun, Ying Hu, Jun Yun, Juntong Liu, Ying Bai, Dongxu Liu, Xin Zhao, Guojun Jiang, Guozhang Kong, Jianyi Chen, Baojia Sensors (Basel) Article Simultaneous localization and mapping (SLAM) technology can be used to locate and build maps in unknown environments, but the constructed maps often suffer from poor readability and interactivity, and the primary and secondary information in the map cannot be accurately grasped. For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them. Our proposed method can not only reduce the absolute positional errors (APE) and improve the positioning performance of the system but also construct the object-oriented dense semantic point cloud map and output point cloud model of each object to reconstruct each object in the indoor scene. In fact, eight categories of objects are used for detection and semantic mapping using coco weights in our experiments, and most objects in the actual scene can be reconstructed in theory. Experiments show that the number of points in the point cloud is significantly reduced. The average positioning error of the eight categories of objects in Technical University of Munich (TUM) datasets is very small. The absolute positional error of the camera is also reduced with the introduction of semantic constraints, and the positioning performance of the system is improved. At the same time, our algorithm can segment the point cloud model of objects in the environment with high accuracy. MDPI 2022-10-06 /pmc/articles/PMC9571389/ /pubmed/36236676 http://dx.doi.org/10.3390/s22197576 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 Article
Sun, Ying
Hu, Jun
Yun, Juntong
Liu, Ying
Bai, Dongxu
Liu, Xin
Zhao, Guojun
Jiang, Guozhang
Kong, Jianyi
Chen, Baojia
Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam
title Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam
title_full Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam
title_fullStr Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam
title_full_unstemmed Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam
title_short Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam
title_sort multi-objective location and mapping based on deep learning and visual slam
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9571389/
https://www.ncbi.nlm.nih.gov/pubmed/36236676
http://dx.doi.org/10.3390/s22197576
work_keys_str_mv AT sunying multiobjectivelocationandmappingbasedondeeplearningandvisualslam
AT hujun multiobjectivelocationandmappingbasedondeeplearningandvisualslam
AT yunjuntong multiobjectivelocationandmappingbasedondeeplearningandvisualslam
AT liuying multiobjectivelocationandmappingbasedondeeplearningandvisualslam
AT baidongxu multiobjectivelocationandmappingbasedondeeplearningandvisualslam
AT liuxin multiobjectivelocationandmappingbasedondeeplearningandvisualslam
AT zhaoguojun multiobjectivelocationandmappingbasedondeeplearningandvisualslam
AT jiangguozhang multiobjectivelocationandmappingbasedondeeplearningandvisualslam
AT kongjianyi multiobjectivelocationandmappingbasedondeeplearningandvisualslam
AT chenbaojia multiobjectivelocationandmappingbasedondeeplearningandvisualslam