E-MobileViT: a lightweight model for traffic sign recognition

Abstract Traffic sign recognition is crucial for intelligent transportation and autonomous driving, ensuring road safety and efficient traffic management. This paper proposes a lightweight enhanced MobileViT model (E-MobileViT). It is based on the MobileViT model, combining the advantages of CNN and...

Full description

Saved in:
Bibliographic Details
Main Authors: Shiqi Song, Xinfeng Ye, Sathiamoorthy Manoharan
Format: Article
Language:English
Published: Springer 2025-03-01
Series:Industrial Artificial Intelligence
Subjects:
Online Access:https://doi.org/10.1007/s44244-025-00024-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849389929799352320
author Shiqi Song
Xinfeng Ye
Sathiamoorthy Manoharan
author_facet Shiqi Song
Xinfeng Ye
Sathiamoorthy Manoharan
author_sort Shiqi Song
collection DOAJ
description Abstract Traffic sign recognition is crucial for intelligent transportation and autonomous driving, ensuring road safety and efficient traffic management. This paper proposes a lightweight enhanced MobileViT model (E-MobileViT). It is based on the MobileViT model, combining the advantages of CNN and Transformer. We integrate Efficient Local Attention (ELA) and Convolutional Block Attention Module (CBAM) mechanisms in the model to improve feature extraction. The proposed model improves the feature fusion structure and significantly reduces the number of model parameters. We evaluated the model on the German Traffic Sign Recognition Benchmark (GTSRB), Belgian Traffic Signs Database (BTSD), and China Traffic Signs Database (TSRD) datasets and its accuracy reaches 99.61%, 99.26% and 97.34%, respectively, which outperforms traditional and advanced models. We confirmed the key role of ELA and CBAM mechanisms through ablation experiments. With fewer parameters than mainstream models, our E-MobileViT model is suitable for resource-constrained environments such as mobile devices, providing a balanced solution for traffic sign recognition tasks.
format Article
id doaj-art-9d81c02b6c7d441ebb6f9992ec3cb29c
institution Kabale University
issn 2731-667X
language English
publishDate 2025-03-01
publisher Springer
record_format Article
series Industrial Artificial Intelligence
spelling doaj-art-9d81c02b6c7d441ebb6f9992ec3cb29c2025-08-20T03:41:49ZengSpringerIndustrial Artificial Intelligence2731-667X2025-03-013111510.1007/s44244-025-00024-2E-MobileViT: a lightweight model for traffic sign recognitionShiqi Song0Xinfeng Ye1Sathiamoorthy Manoharan2School of Computer Science, The University of AucklandSchool of Computer Science, The University of AucklandSchool of Computer Science, The University of AucklandAbstract Traffic sign recognition is crucial for intelligent transportation and autonomous driving, ensuring road safety and efficient traffic management. This paper proposes a lightweight enhanced MobileViT model (E-MobileViT). It is based on the MobileViT model, combining the advantages of CNN and Transformer. We integrate Efficient Local Attention (ELA) and Convolutional Block Attention Module (CBAM) mechanisms in the model to improve feature extraction. The proposed model improves the feature fusion structure and significantly reduces the number of model parameters. We evaluated the model on the German Traffic Sign Recognition Benchmark (GTSRB), Belgian Traffic Signs Database (BTSD), and China Traffic Signs Database (TSRD) datasets and its accuracy reaches 99.61%, 99.26% and 97.34%, respectively, which outperforms traditional and advanced models. We confirmed the key role of ELA and CBAM mechanisms through ablation experiments. With fewer parameters than mainstream models, our E-MobileViT model is suitable for resource-constrained environments such as mobile devices, providing a balanced solution for traffic sign recognition tasks.https://doi.org/10.1007/s44244-025-00024-2MobileViTTraffic sign recognitionAttention mechanismsTransformer
spellingShingle Shiqi Song
Xinfeng Ye
Sathiamoorthy Manoharan
E-MobileViT: a lightweight model for traffic sign recognition
Industrial Artificial Intelligence
MobileViT
Traffic sign recognition
Attention mechanisms
Transformer
title E-MobileViT: a lightweight model for traffic sign recognition
title_full E-MobileViT: a lightweight model for traffic sign recognition
title_fullStr E-MobileViT: a lightweight model for traffic sign recognition
title_full_unstemmed E-MobileViT: a lightweight model for traffic sign recognition
title_short E-MobileViT: a lightweight model for traffic sign recognition
title_sort e mobilevit a lightweight model for traffic sign recognition
topic MobileViT
Traffic sign recognition
Attention mechanisms
Transformer
url https://doi.org/10.1007/s44244-025-00024-2
work_keys_str_mv AT shiqisong emobilevitalightweightmodelfortrafficsignrecognition
AT xinfengye emobilevitalightweightmodelfortrafficsignrecognition
AT sathiamoorthymanoharan emobilevitalightweightmodelfortrafficsignrecognition