Cargando…

Identification and Tracking of Vehicles between Multiple Cameras on Bridges Using a YOLOv4 and OSNet-Based Method

The estimation of vehicle loads is a rising research hotspot in bridge structure health monitoring (SHM). Traditional methods, such as the bridge weight-in-motion system (BWIM), are widely used but they fail to record the locations of vehicles on the bridges. Computer vision-based approaches are pro...

Descripción completa

Detalles Bibliográficos
Autores principales: Jin, Tao, Ye, Xiaowei, Li, Zhexun, Huo, Zhaoyu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10301447/
https://www.ncbi.nlm.nih.gov/pubmed/37420677
http://dx.doi.org/10.3390/s23125510
_version_ 1785064814191575040
author Jin, Tao
Ye, Xiaowei
Li, Zhexun
Huo, Zhaoyu
author_facet Jin, Tao
Ye, Xiaowei
Li, Zhexun
Huo, Zhaoyu
author_sort Jin, Tao
collection PubMed
description The estimation of vehicle loads is a rising research hotspot in bridge structure health monitoring (SHM). Traditional methods, such as the bridge weight-in-motion system (BWIM), are widely used but they fail to record the locations of vehicles on the bridges. Computer vision-based approaches are promising ways for vehicle tracking on bridges. Nevertheless, keeping track of vehicles from the video frames of multiple cameras without an overlapped visual field poses a challenge for the tracking of vehicles across the whole bridge. In this study, a method that was You Only Look Once v4 (YOLOv4)- and Omni-Scale Net (OSNet)-based was proposed to realize vehicle detecting and tracking across multiple cameras. A modified IoU-based tracking method was proposed to track a vehicle in adjacent video frames from the same camera, which takes both the appearance of vehicles and overlapping rates between the vehicle bounding boxes into consideration. The Hungary algorithm was adopted to match vehicle photos in various videos. Moreover, a dataset with 25,080 images of 1727 vehicles for vehicle identification was established to train and evaluate four models. Field validation experiments based on videos from three surveillance cameras were conducted to validate the proposed method. Experimental results show that the proposed method has an accuracy of 97.7% in terms of vehicle tracking in the visual field of a single camera and over 92.5% in tracking across multiple cameras, which can contribute to the acquisition of the temporal–spatial distribution of vehicle loads on the whole bridge.
format Online
Article
Text
id pubmed-10301447
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-103014472023-06-29 Identification and Tracking of Vehicles between Multiple Cameras on Bridges Using a YOLOv4 and OSNet-Based Method Jin, Tao Ye, Xiaowei Li, Zhexun Huo, Zhaoyu Sensors (Basel) Article The estimation of vehicle loads is a rising research hotspot in bridge structure health monitoring (SHM). Traditional methods, such as the bridge weight-in-motion system (BWIM), are widely used but they fail to record the locations of vehicles on the bridges. Computer vision-based approaches are promising ways for vehicle tracking on bridges. Nevertheless, keeping track of vehicles from the video frames of multiple cameras without an overlapped visual field poses a challenge for the tracking of vehicles across the whole bridge. In this study, a method that was You Only Look Once v4 (YOLOv4)- and Omni-Scale Net (OSNet)-based was proposed to realize vehicle detecting and tracking across multiple cameras. A modified IoU-based tracking method was proposed to track a vehicle in adjacent video frames from the same camera, which takes both the appearance of vehicles and overlapping rates between the vehicle bounding boxes into consideration. The Hungary algorithm was adopted to match vehicle photos in various videos. Moreover, a dataset with 25,080 images of 1727 vehicles for vehicle identification was established to train and evaluate four models. Field validation experiments based on videos from three surveillance cameras were conducted to validate the proposed method. Experimental results show that the proposed method has an accuracy of 97.7% in terms of vehicle tracking in the visual field of a single camera and over 92.5% in tracking across multiple cameras, which can contribute to the acquisition of the temporal–spatial distribution of vehicle loads on the whole bridge. MDPI 2023-06-12 /pmc/articles/PMC10301447/ /pubmed/37420677 http://dx.doi.org/10.3390/s23125510 Text en © 2023 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
Jin, Tao
Ye, Xiaowei
Li, Zhexun
Huo, Zhaoyu
Identification and Tracking of Vehicles between Multiple Cameras on Bridges Using a YOLOv4 and OSNet-Based Method
title Identification and Tracking of Vehicles between Multiple Cameras on Bridges Using a YOLOv4 and OSNet-Based Method
title_full Identification and Tracking of Vehicles between Multiple Cameras on Bridges Using a YOLOv4 and OSNet-Based Method
title_fullStr Identification and Tracking of Vehicles between Multiple Cameras on Bridges Using a YOLOv4 and OSNet-Based Method
title_full_unstemmed Identification and Tracking of Vehicles between Multiple Cameras on Bridges Using a YOLOv4 and OSNet-Based Method
title_short Identification and Tracking of Vehicles between Multiple Cameras on Bridges Using a YOLOv4 and OSNet-Based Method
title_sort identification and tracking of vehicles between multiple cameras on bridges using a yolov4 and osnet-based method
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10301447/
https://www.ncbi.nlm.nih.gov/pubmed/37420677
http://dx.doi.org/10.3390/s23125510
work_keys_str_mv AT jintao identificationandtrackingofvehiclesbetweenmultiplecamerasonbridgesusingayolov4andosnetbasedmethod
AT yexiaowei identificationandtrackingofvehiclesbetweenmultiplecamerasonbridgesusingayolov4andosnetbasedmethod
AT lizhexun identificationandtrackingofvehiclesbetweenmultiplecamerasonbridgesusingayolov4andosnetbasedmethod
AT huozhaoyu identificationandtrackingofvehiclesbetweenmultiplecamerasonbridgesusingayolov4andosnetbasedmethod