A Fast Vehicle Counting and Traffic Volume Estimation Method Based on Convolutional Neural Network

Vehicle counting and traffic volume estimation on traffic videos has gained extensive attention from multimedia and computer vision communities. Recent vehicle counting and volume estimation methods, including detection based and time-spatial image (TSI) based methods have achieved significant impro...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Henglong Yang, Youmei Zhang, Yu Zhang, Hailong Meng, Shuang Li, Xianglin Dai
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Vehicle counting traffic volume estimation time-spatial image density map attention mechanism Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/450760c665e44accb6b1f0a5619e90d8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:450760c665e44accb6b1f0a5619e90d8
record_format	dspace
spelling	oai:doaj.org-article:450760c665e44accb6b1f0a5619e90d82021-11-18T00:06:14ZA Fast Vehicle Counting and Traffic Volume Estimation Method Based on Convolutional Neural Network2169-353610.1109/ACCESS.2021.3124675https://doaj.org/article/450760c665e44accb6b1f0a5619e90d82021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9597503/https://doaj.org/toc/2169-3536Vehicle counting and traffic volume estimation on traffic videos has gained extensive attention from multimedia and computer vision communities. Recent vehicle counting and volume estimation methods, including detection based and time-spatial image (TSI) based methods have achieved significant improvements. However, how to balance the accuracy and speed is still a challenge to this task. In this paper, we design a fast and accurate vehicle counting and traffic volume estimation method. Firstly, traffic videos are converted to TSIs and we annotate the vehicle locations in TSIs manually. Then, we design a simple TSI density map estimation network which utilizes attention mechanism to strengthen the features in the traffic locations for vehicle counting. Finally, we use the parameters obtained from the vehicle counting network to further estimate the traffic volume. Experiments on UA-DETRAC dataset demonstrate that the vehicle counting network not only takes a balance between counting accuracy and speed, but also well estimates the traffic volume when the video data is insufficient.Henglong YangYoumei ZhangYu ZhangHailong MengShuang LiXianglin DaiIEEEarticleVehicle countingtraffic volume estimationtime-spatial imagedensity mapattention mechanismElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 150522-150531 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Vehicle counting traffic volume estimation time-spatial image density map attention mechanism Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Vehicle counting traffic volume estimation time-spatial image density map attention mechanism Electrical engineering. Electronics. Nuclear engineering TK1-9971 Henglong Yang Youmei Zhang Yu Zhang Hailong Meng Shuang Li Xianglin Dai A Fast Vehicle Counting and Traffic Volume Estimation Method Based on Convolutional Neural Network
description	Vehicle counting and traffic volume estimation on traffic videos has gained extensive attention from multimedia and computer vision communities. Recent vehicle counting and volume estimation methods, including detection based and time-spatial image (TSI) based methods have achieved significant improvements. However, how to balance the accuracy and speed is still a challenge to this task. In this paper, we design a fast and accurate vehicle counting and traffic volume estimation method. Firstly, traffic videos are converted to TSIs and we annotate the vehicle locations in TSIs manually. Then, we design a simple TSI density map estimation network which utilizes attention mechanism to strengthen the features in the traffic locations for vehicle counting. Finally, we use the parameters obtained from the vehicle counting network to further estimate the traffic volume. Experiments on UA-DETRAC dataset demonstrate that the vehicle counting network not only takes a balance between counting accuracy and speed, but also well estimates the traffic volume when the video data is insufficient.
format	article
author	Henglong Yang Youmei Zhang Yu Zhang Hailong Meng Shuang Li Xianglin Dai
author_facet	Henglong Yang Youmei Zhang Yu Zhang Hailong Meng Shuang Li Xianglin Dai
author_sort	Henglong Yang
title	A Fast Vehicle Counting and Traffic Volume Estimation Method Based on Convolutional Neural Network
title_short	A Fast Vehicle Counting and Traffic Volume Estimation Method Based on Convolutional Neural Network
title_full	A Fast Vehicle Counting and Traffic Volume Estimation Method Based on Convolutional Neural Network
title_fullStr	A Fast Vehicle Counting and Traffic Volume Estimation Method Based on Convolutional Neural Network
title_full_unstemmed	A Fast Vehicle Counting and Traffic Volume Estimation Method Based on Convolutional Neural Network
title_sort	fast vehicle counting and traffic volume estimation method based on convolutional neural network
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/450760c665e44accb6b1f0a5619e90d8
work_keys_str_mv	AT henglongyang afastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT youmeizhang afastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT yuzhang afastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT hailongmeng afastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT shuangli afastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT xianglindai afastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT henglongyang fastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT youmeizhang fastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT yuzhang fastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT hailongmeng fastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT shuangli fastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork AT xianglindai fastvehiclecountingandtrafficvolumeestimationmethodbasedonconvolutionalneuralnetwork
_version_	1718425221839454208

A Fast Vehicle Counting and Traffic Volume Estimation Method Based on Convolutional Neural Network

Ejemplares similares