Vehicle detection and classification by voiceprint recognition based on single acoustic sensor under bridge expansion joint

Vehicle detection and classification (VDC) is a crucial aspect of bridge engineering, as vehicles exert significant dynamic loads on bridges. Various contact and noncontact methods have been proposed for VDC, but finding a durable and cost-effective sensing approach remains challenging for practical...

Full description

Saved in:
Bibliographic Details
Main Authors: Pan, Yue, Dong, Yiqing, Wang, Dalei, Di, Jin, Chen, Airong
Other Authors: School of Civil and Environmental Engineering
Format: Article
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/180769
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-180769
record_format dspace
spelling sg-ntu-dr.10356-1807692024-10-23T05:21:48Z Vehicle detection and classification by voiceprint recognition based on single acoustic sensor under bridge expansion joint Pan, Yue Dong, Yiqing Wang, Dalei Di, Jin Chen, Airong School of Civil and Environmental Engineering Engineering Acoustic sensing Deep learning Vehicle detection and classification (VDC) is a crucial aspect of bridge engineering, as vehicles exert significant dynamic loads on bridges. Various contact and noncontact methods have been proposed for VDC, but finding a durable and cost-effective sensing approach remains challenging for practical bridge applications. In this study, we propose a voiceprint recognition (VPR) method for VDC using a single microphone, offering flexibility and affordability. The distinctive acoustic signatures generated by vehicles impacting bridge expansion joints (BEJs) are captured and utilized for VDC. We optimize a threshold-based algorithm for vehicle detection and a deep learning-based VPR model for vehicle classification. In addition, cascading VPR models enable fine-grained vehicle classification, including lanes and axle types. We validate the proposed method on an actual bridge. The short-term energy (STE) thresholding algorithm achieves a detection accuracy and recall of 90.0% and 91.6%, respectively. The ConFormer model achieves an area under the curve (AuC) of 0.925 for vehicle classification. These results highlight the method as an easy-to-implement and cost-effective solution for efficient VDC surveys. Future work can focus on expanding datasets and incorporating multiple microphones to further enhance the system's capabilities. This work was supported in part by the National Natural Science Foundation of China under Grant 52208198, Grant 52238005, and Grant 52192663; in part by the National Key Research and Development Program of China under Grant 2021YFF0501004; and in part by the Interdisciplinary Project in Ocean Research of Tongji University under Grant 2023-1-YB-03. 2024-10-23T05:17:02Z 2024-10-23T05:17:02Z 2024 Journal Article Pan, Y., Dong, Y., Wang, D., Di, J. & Chen, A. (2024). Vehicle detection and classification by voiceprint recognition based on single acoustic sensor under bridge expansion joint. IEEE Transactions On Instrumentation and Measurement, 73, 1-15. https://dx.doi.org/10.1109/TIM.2024.3428610 0018-9456 https://hdl.handle.net/10356/180769 10.1109/TIM.2024.3428610 2-s2.0-85198713333 73 1 15 en IEEE Transactions on Instrumentation and Measurement © 2024 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering
Acoustic sensing
Deep learning
spellingShingle Engineering
Acoustic sensing
Deep learning
Pan, Yue
Dong, Yiqing
Wang, Dalei
Di, Jin
Chen, Airong
Vehicle detection and classification by voiceprint recognition based on single acoustic sensor under bridge expansion joint
description Vehicle detection and classification (VDC) is a crucial aspect of bridge engineering, as vehicles exert significant dynamic loads on bridges. Various contact and noncontact methods have been proposed for VDC, but finding a durable and cost-effective sensing approach remains challenging for practical bridge applications. In this study, we propose a voiceprint recognition (VPR) method for VDC using a single microphone, offering flexibility and affordability. The distinctive acoustic signatures generated by vehicles impacting bridge expansion joints (BEJs) are captured and utilized for VDC. We optimize a threshold-based algorithm for vehicle detection and a deep learning-based VPR model for vehicle classification. In addition, cascading VPR models enable fine-grained vehicle classification, including lanes and axle types. We validate the proposed method on an actual bridge. The short-term energy (STE) thresholding algorithm achieves a detection accuracy and recall of 90.0% and 91.6%, respectively. The ConFormer model achieves an area under the curve (AuC) of 0.925 for vehicle classification. These results highlight the method as an easy-to-implement and cost-effective solution for efficient VDC surveys. Future work can focus on expanding datasets and incorporating multiple microphones to further enhance the system's capabilities.
author2 School of Civil and Environmental Engineering
author_facet School of Civil and Environmental Engineering
Pan, Yue
Dong, Yiqing
Wang, Dalei
Di, Jin
Chen, Airong
format Article
author Pan, Yue
Dong, Yiqing
Wang, Dalei
Di, Jin
Chen, Airong
author_sort Pan, Yue
title Vehicle detection and classification by voiceprint recognition based on single acoustic sensor under bridge expansion joint
title_short Vehicle detection and classification by voiceprint recognition based on single acoustic sensor under bridge expansion joint
title_full Vehicle detection and classification by voiceprint recognition based on single acoustic sensor under bridge expansion joint
title_fullStr Vehicle detection and classification by voiceprint recognition based on single acoustic sensor under bridge expansion joint
title_full_unstemmed Vehicle detection and classification by voiceprint recognition based on single acoustic sensor under bridge expansion joint
title_sort vehicle detection and classification by voiceprint recognition based on single acoustic sensor under bridge expansion joint
publishDate 2024
url https://hdl.handle.net/10356/180769
_version_ 1814777761050394624