Comparative Analysis of Background Subtraction and CNN Algorithms for Mid-Block Traffic Data Collection and Classification

Comparative Analysis of Background Subtraction and CNN Algorithms for Mid-Block Traffic Data Collection and Classification

Classification of vehicles in the traffic stream is a pre-requisite for planning and designing the facilities for road-users. Considering the importance and gaining popularity of automated systems in this field, the aim of this article is to compare two algorithms- one using the Background Subtracti...

Full description

Bibliographic Details
Main Authors: Ubaid Illahi, Mohammad Shafi Mir
Format: Article
Language:English
Published: International Journal of Mathematical, Engineering and Management Sciences 2020-12-01
Series:International Journal of Mathematical, Engineering and Management Sciences
Subjects:
computer vision
traffic data
object detection
background subtraction
convolutional neural network
Online Access:https://www.ijmems.in/volumes/volume5/number6/107-IJMEMS-20-101-5-6-1440-1451-2020.pdf
id doaj-6e38a20c765b4571929403cec27c750b
record_format Article
spelling doaj-6e38a20c765b4571929403cec27c750b2020-11-25T03:41:18ZengInternational Journal of Mathematical, Engineering and Management SciencesInternational Journal of Mathematical, Engineering and Management Sciences2455-77492455-77492020-12-01561440145110.33889/IJMEMS.2020.5.6.107Comparative Analysis of Background Subtraction and CNN Algorithms for Mid-Block Traffic Data Collection and Classification Ubaid Illahi0Mohammad Shafi Mir1Department of Civil Engineering, National Institute of Technology Srinagar, UT of Jammu & Kashmir, India.Department of Civil Engineering, National Institute of Technology Srinagar, UT of Jammu & Kashmir, India.Classification of vehicles in the traffic stream is a pre-requisite for planning and designing the facilities for road-users. Considering the importance and gaining popularity of automated systems in this field, the aim of this article is to compare two algorithms- one using the Background Subtraction (BS) technique and the other using Convolutional Neural Network (CNN) with a primary focus on an increased number of vehicle classifications. To check the reliability of these algorithms, the outputs produced were validated against the data obtained from Kachkoot Toll Plaza, India. The results were analyzed using drop-line diagrams and confusion matrices. The overall efficiency of the CNN-based algorithm (0.98) was found to be better than the BS-based algorithm (0.95). The comparison presented in this paper will be useful for transportation professionals and agencies.https://www.ijmems.in/volumes/volume5/number6/107-IJMEMS-20-101-5-6-1440-1451-2020.pdfcomputer visiontraffic dataobject detectionbackground subtractionconvolutional neural network
collection DOAJ
language English
format Article
sources DOAJ
author Ubaid Illahi
Mohammad Shafi Mir
spellingShingle Ubaid Illahi
Mohammad Shafi Mir
Comparative Analysis of Background Subtraction and CNN Algorithms for Mid-Block Traffic Data Collection and Classification
International Journal of Mathematical, Engineering and Management Sciences
computer vision
traffic data
object detection
background subtraction
convolutional neural network
author_facet Ubaid Illahi
Mohammad Shafi Mir
author_sort Ubaid Illahi
title Comparative Analysis of Background Subtraction and CNN Algorithms for Mid-Block Traffic Data Collection and Classification
title_short Comparative Analysis of Background Subtraction and CNN Algorithms for Mid-Block Traffic Data Collection and Classification
title_full Comparative Analysis of Background Subtraction and CNN Algorithms for Mid-Block Traffic Data Collection and Classification
title_fullStr Comparative Analysis of Background Subtraction and CNN Algorithms for Mid-Block Traffic Data Collection and Classification
title_full_unstemmed Comparative Analysis of Background Subtraction and CNN Algorithms for Mid-Block Traffic Data Collection and Classification
title_sort comparative analysis of background subtraction and cnn algorithms for mid-block traffic data collection and classification
publisher International Journal of Mathematical, Engineering and Management Sciences
series International Journal of Mathematical, Engineering and Management Sciences
issn 2455-7749
2455-7749
publishDate 2020-12-01
description Classification of vehicles in the traffic stream is a pre-requisite for planning and designing the facilities for road-users. Considering the importance and gaining popularity of automated systems in this field, the aim of this article is to compare two algorithms- one using the Background Subtraction (BS) technique and the other using Convolutional Neural Network (CNN) with a primary focus on an increased number of vehicle classifications. To check the reliability of these algorithms, the outputs produced were validated against the data obtained from Kachkoot Toll Plaza, India. The results were analyzed using drop-line diagrams and confusion matrices. The overall efficiency of the CNN-based algorithm (0.98) was found to be better than the BS-based algorithm (0.95). The comparison presented in this paper will be useful for transportation professionals and agencies.
topic computer vision
traffic data
object detection
background subtraction
convolutional neural network
url https://www.ijmems.in/volumes/volume5/number6/107-IJMEMS-20-101-5-6-1440-1451-2020.pdf
work_keys_str_mv AT ubaidillahi comparativeanalysisofbackgroundsubtractionandcnnalgorithmsformidblocktrafficdatacollectionandclassification
AT mohammadshafimir comparativeanalysisofbackgroundsubtractionandcnnalgorithmsformidblocktrafficdatacollectionandclassification
_version_ 1724530504047263744

Similar Items