Cargando…

Scene Classification in the Environmental Art Design by Using the Lightweight Deep Learning Model under the Background of Big Data

On the basis of scene visual understanding technology, the research aims to further improve the classification efficiency and classification accuracy of art design scenes. The lightweight deep learning (DL) model based on big data is used as the main method to achieve real-time detection and recogni...

Descripción completa

Detalles Bibliográficos
Autor principal: Liu, Lu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9208967/
https://www.ncbi.nlm.nih.gov/pubmed/35733573
http://dx.doi.org/10.1155/2022/9066648
_version_ 1784729830245269504
author Liu, Lu
author_facet Liu, Lu
author_sort Liu, Lu
collection PubMed
description On the basis of scene visual understanding technology, the research aims to further improve the classification efficiency and classification accuracy of art design scenes. The lightweight deep learning (DL) model based on big data is used as the main method to achieve real-time detection and recognition of multiple targets and classification of the multilabel scene. This research introduces the related foundations of the DL network and the lightweight object detection involved. The data for a multilabel scene classifier are constructed and the design of the convolutional neural network (CNN) model is described. On public datasets, the effectiveness of the lightweight object detection algorithm is verified to ensure its feasibility in the classification of actual scenes. The simulation results indicate that compared with the YOLOv3-Tiny model, the improved IRDA-YOLOv3 model reduces the number of parameters by 56.2%, the amount of computation by 46.3%, and the forward computation time of the network by 0.2 ms. It means that the IRDA-YOLOv3 network obtained after the improvement can realize the lightweight of the network. In the scene classification of complex traffic roads, the classification model of the multilabel scene can predict all kinds of semantic information of a single image and the classification accuracy for the four scenes is more than 90%. In summary, the discussed classification method based on the lightweight DL model is suitable for complex practical scenes. The constructed lightweight network improves the representational ability of the network and has certain research value for scene classification problems.
format Online
Article
Text
id pubmed-9208967
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-92089672022-06-21 Scene Classification in the Environmental Art Design by Using the Lightweight Deep Learning Model under the Background of Big Data Liu, Lu Comput Intell Neurosci Research Article On the basis of scene visual understanding technology, the research aims to further improve the classification efficiency and classification accuracy of art design scenes. The lightweight deep learning (DL) model based on big data is used as the main method to achieve real-time detection and recognition of multiple targets and classification of the multilabel scene. This research introduces the related foundations of the DL network and the lightweight object detection involved. The data for a multilabel scene classifier are constructed and the design of the convolutional neural network (CNN) model is described. On public datasets, the effectiveness of the lightweight object detection algorithm is verified to ensure its feasibility in the classification of actual scenes. The simulation results indicate that compared with the YOLOv3-Tiny model, the improved IRDA-YOLOv3 model reduces the number of parameters by 56.2%, the amount of computation by 46.3%, and the forward computation time of the network by 0.2 ms. It means that the IRDA-YOLOv3 network obtained after the improvement can realize the lightweight of the network. In the scene classification of complex traffic roads, the classification model of the multilabel scene can predict all kinds of semantic information of a single image and the classification accuracy for the four scenes is more than 90%. In summary, the discussed classification method based on the lightweight DL model is suitable for complex practical scenes. The constructed lightweight network improves the representational ability of the network and has certain research value for scene classification problems. Hindawi 2022-06-13 /pmc/articles/PMC9208967/ /pubmed/35733573 http://dx.doi.org/10.1155/2022/9066648 Text en Copyright © 2022 Lu Liu. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Liu, Lu
Scene Classification in the Environmental Art Design by Using the Lightweight Deep Learning Model under the Background of Big Data
title Scene Classification in the Environmental Art Design by Using the Lightweight Deep Learning Model under the Background of Big Data
title_full Scene Classification in the Environmental Art Design by Using the Lightweight Deep Learning Model under the Background of Big Data
title_fullStr Scene Classification in the Environmental Art Design by Using the Lightweight Deep Learning Model under the Background of Big Data
title_full_unstemmed Scene Classification in the Environmental Art Design by Using the Lightweight Deep Learning Model under the Background of Big Data
title_short Scene Classification in the Environmental Art Design by Using the Lightweight Deep Learning Model under the Background of Big Data
title_sort scene classification in the environmental art design by using the lightweight deep learning model under the background of big data
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9208967/
https://www.ncbi.nlm.nih.gov/pubmed/35733573
http://dx.doi.org/10.1155/2022/9066648
work_keys_str_mv AT liulu sceneclassificationintheenvironmentalartdesignbyusingthelightweightdeeplearningmodelunderthebackgroundofbigdata