Adoption of Convolutional Neural Network Algorithm Combined with Augmented Reality in Building Data Visualization and Intelligent Detection

Wei, M; Tang, J; Tang, H; Zhao, R; Gai, X; Lin, R

Adoption of Convolutional Neural Network Algorithm Combined with Augmented Reality in Building Data Visualization and Intelligent Detection

Wei, M Tang, J Tang, H Zhao, R

Gai, X Lin, R

Permalink

Publisher:: Hindawi Limited
Publication Type:: Journal Article
Citation:: Complexity, 2021, 2021, pp. 1-13
Issue Date:: 2021-06-29

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (2.75 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Wei, M
dc.contributor.author	Tang, J
dc.contributor.author	Tang, H
dc.contributor.author	Zhao, R https://orcid.org/0000-0003-0287-0870
dc.contributor.author	Gai, X
dc.contributor.author	Lin, R
dc.date.accessioned	2022-03-15T01:54:49Z
dc.date.available	2022-03-15T01:54:49Z
dc.date.issued	2021-06-29
dc.identifier.citation	Complexity, 2021, 2021, pp. 1-13
dc.identifier.issn	1076-2787
dc.identifier.issn	1099-0526
dc.identifier.uri	http://hdl.handle.net/10453/155232
dc.description.abstract	<jats:p>It aims to improve the degree of visualization of building data, ensure the ability of intelligent detection, and effectively solve the problems encountered in building data processing. Convolutional neural network and augmented reality technology are adopted, and a building visualization model based on convolutional neural network and augmented reality is proposed. The performance of the proposed algorithm is further confirmed by performance verification on public datasets. It is found that the building target detection model based on convolutional neural network and augmented reality has obvious advantages in algorithm complexity and recognition accuracy. It is 25 percent more accurate than the latest model. The model can make full use of mobile computing resources, avoid network delay and dependence, and guarantee the real-time requirement of data processing. Moreover, the model can also well realize the augmented reality navigation and interaction effect of buildings in outdoor scenes. To sum up, this study provides a research idea for the identification, data processing, and intelligent detection of urban buildings.</jats:p>
dc.language	en
dc.publisher	Hindawi Limited
dc.relation.ispartof	Complexity
dc.relation.isbasedon	10.1155/2021/5161111
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0102 Applied Mathematics, 0103 Numerical and Computational Mathematics, 0802 Computation Theory and Mathematics
dc.subject.classification	Fluids & Plasmas
dc.title	Adoption of Convolutional Neural Network Algorithm Combined with Augmented Reality in Building Data Visualization and Intelligent Detection
dc.type	Journal Article
utslib.citation.volume	2021
utslib.for	0102 Applied Mathematics
utslib.for	0103 Numerical and Computational Mathematics
utslib.for	0802 Computation Theory and Mathematics
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	open_access	*
dc.date.updated	2022-03-15T01:54:37Z
pubs.publication-status	Published
pubs.volume	2021

Abstract:

It aims to improve the degree of visualization of building data, ensure the ability of intelligent detection, and effectively solve the problems encountered in building data processing. Convolutional neural network and augmented reality technology are adopted, and a building visualization model based on convolutional neural network and augmented reality is proposed. The performance of the proposed algorithm is further confirmed by performance verification on public datasets. It is found that the building target detection model based on convolutional neural network and augmented reality has obvious advantages in algorithm complexity and recognition accuracy. It is 25 percent more accurate than the latest model. The model can make full use of mobile computing resources, avoid network delay and dependence, and guarantee the real-time requirement of data processing. Moreover, the model can also well realize the augmented reality navigation and interaction effect of buildings in outdoor scenes. To sum up, this study provides a research idea for the identification, data processing, and intelligent detection of urban buildings.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/155232