Deep Learning-Based Method for Detecting Traffic Flow Parameters Under Snowfall

In recent years, advancements in computer vision have yielded new prospects for intelligent transportation applications, specifically in the realm of automated traffic flow data collection. Within this emerging trend, the ability to swiftly and accurately detect vehicles and extract traffic flow par...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheng Jian, Tiancheng Xie, Xiaojian Hu, Jian Lu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Journal of Imaging
Subjects:
Online Access:https://www.mdpi.com/2313-433X/10/12/301
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050334558257152
author Cheng Jian
Tiancheng Xie
Xiaojian Hu
Jian Lu
author_facet Cheng Jian
Tiancheng Xie
Xiaojian Hu
Jian Lu
author_sort Cheng Jian
collection DOAJ
description In recent years, advancements in computer vision have yielded new prospects for intelligent transportation applications, specifically in the realm of automated traffic flow data collection. Within this emerging trend, the ability to swiftly and accurately detect vehicles and extract traffic flow parameters from videos captured during snowfall conditions has become imperative for numerous future applications. This paper proposes a new analytical framework designed to extract traffic flow parameters from traffic flow videos recorded under snowfall conditions. The framework encompasses four distinct stages aimed at addressing the challenges posed by image degradation and the diminished accuracy of traffic flow parameter recognition caused by snowfall. The initial two stages propose a deep learning network for removing snow particles and snow streaks, resulting in an 8.6% enhancement in vehicle recognition accuracy after snow removal, specifically under moderate snow conditions. Additionally, the operation speed is significantly enhanced. Subsequently, the latter two stages encompass yolov5-based vehicle recognition and the employment of the virtual coil method for traffic flow parameter estimation. Following rigorous testing, the accuracy of traffic flow parameter estimation reaches 97.2% under moderate snow conditions.
format Article
id doaj-art-3c1d298377ad40e6bc473ffb3fc63c45
institution DOAJ
issn 2313-433X
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Journal of Imaging
spelling doaj-art-3c1d298377ad40e6bc473ffb3fc63c452025-08-20T02:53:30ZengMDPI AGJournal of Imaging2313-433X2024-11-01101230110.3390/jimaging10120301Deep Learning-Based Method for Detecting Traffic Flow Parameters Under SnowfallCheng Jian0Tiancheng Xie1Xiaojian Hu2Jian Lu3Nanjing LES Information Technology Co., Ltd., Nanjing 211189, ChinaJiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, Nanjing 211189, ChinaJiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, Nanjing 211189, ChinaJiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, Nanjing 211189, ChinaIn recent years, advancements in computer vision have yielded new prospects for intelligent transportation applications, specifically in the realm of automated traffic flow data collection. Within this emerging trend, the ability to swiftly and accurately detect vehicles and extract traffic flow parameters from videos captured during snowfall conditions has become imperative for numerous future applications. This paper proposes a new analytical framework designed to extract traffic flow parameters from traffic flow videos recorded under snowfall conditions. The framework encompasses four distinct stages aimed at addressing the challenges posed by image degradation and the diminished accuracy of traffic flow parameter recognition caused by snowfall. The initial two stages propose a deep learning network for removing snow particles and snow streaks, resulting in an 8.6% enhancement in vehicle recognition accuracy after snow removal, specifically under moderate snow conditions. Additionally, the operation speed is significantly enhanced. Subsequently, the latter two stages encompass yolov5-based vehicle recognition and the employment of the virtual coil method for traffic flow parameter estimation. Following rigorous testing, the accuracy of traffic flow parameter estimation reaches 97.2% under moderate snow conditions.https://www.mdpi.com/2313-433X/10/12/301snow removaldeep learning networkvirtual coiltraffic flow parameter estimationvehicle detection
spellingShingle Cheng Jian
Tiancheng Xie
Xiaojian Hu
Jian Lu
Deep Learning-Based Method for Detecting Traffic Flow Parameters Under Snowfall
Journal of Imaging
snow removal
deep learning network
virtual coil
traffic flow parameter estimation
vehicle detection
title Deep Learning-Based Method for Detecting Traffic Flow Parameters Under Snowfall
title_full Deep Learning-Based Method for Detecting Traffic Flow Parameters Under Snowfall
title_fullStr Deep Learning-Based Method for Detecting Traffic Flow Parameters Under Snowfall
title_full_unstemmed Deep Learning-Based Method for Detecting Traffic Flow Parameters Under Snowfall
title_short Deep Learning-Based Method for Detecting Traffic Flow Parameters Under Snowfall
title_sort deep learning based method for detecting traffic flow parameters under snowfall
topic snow removal
deep learning network
virtual coil
traffic flow parameter estimation
vehicle detection
url https://www.mdpi.com/2313-433X/10/12/301
work_keys_str_mv AT chengjian deeplearningbasedmethodfordetectingtrafficflowparametersundersnowfall
AT tianchengxie deeplearningbasedmethodfordetectingtrafficflowparametersundersnowfall
AT xiaojianhu deeplearningbasedmethodfordetectingtrafficflowparametersundersnowfall
AT jianlu deeplearningbasedmethodfordetectingtrafficflowparametersundersnowfall