Analysis of object detection methods to detect traffic flow

Johan Le Roux; Dustin Van Der Haar

doi:10.1109/ICABCD.2019.8851054

Analysis of object detection methods to detect traffic flow

Johan Le Roux, Dustin Van Der Haar

Academy of Computer Science and Software Engineering

University of Johannesburg

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Traffic analysis has received more interest as smart cities become a reality. A key component of traffic analysis is detecting the amount of cars that pass certain points. However, limited research exists that explores methods for the car detection component in these systems. This paper will discuss different computer vision methods that can be used for the detection and analysis of vehicles on the road for active traffic flow analysis and implements them in an experiment to find the best method for the task of car detection. MobileNet and Haar-Cascade based methods are implemented and a compared according to performance and accuracy levels in real-world scenarios. Lastly, the results achieved from the experimental model will be discussed giving detail to why Haar cascade gives better performance and accuracy in most scenarios with an average frame rate of over 40 fps on HD video.

Original language	English
Title of host publication	icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems
Editors	Manoj Maharaj, Upasana Gitanjali Singh
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538692363
DOIs	https://doi.org/10.1109/ICABCD.2019.8851054
Publication status	Published - Aug 2019
Event	2nd International Conference on Advances in Big Data, Computing and Data Communication Systems, icABCD 2019 - Winterton, South Africa Duration: 5 Aug 2019 → 6 Aug 2019

Publication series

Name	icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems

Conference

Conference	2nd International Conference on Advances in Big Data, Computing and Data Communication Systems, icABCD 2019
Country/Territory	South Africa
City	Winterton
Period	5/08/19 → 6/08/19

Keywords

Computer Vision
Object Detection
Traffic Monitoring System

ASJC Scopus subject areas

Information Systems and Management
Safety, Risk, Reliability and Quality
Computer Networks and Communications
Computer Science Applications
Computer Vision and Pattern Recognition
Information Systems
Signal Processing

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICABCD.2019.8851054

Cite this

Le Roux, J., & Van Der Haar, D. (2019). Analysis of object detection methods to detect traffic flow. In M. Maharaj, & U. G. Singh (Eds.), icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems Article 8851054 (icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICABCD.2019.8851054

Le Roux, Johan ; Van Der Haar, Dustin. / Analysis of object detection methods to detect traffic flow. icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems. editor / Manoj Maharaj ; Upasana Gitanjali Singh. Institute of Electrical and Electronics Engineers Inc., 2019. (icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems).

@inproceedings{5d842ef4f04d4c0ca6c806ee6371c427,

title = "Analysis of object detection methods to detect traffic flow",

abstract = "Traffic analysis has received more interest as smart cities become a reality. A key component of traffic analysis is detecting the amount of cars that pass certain points. However, limited research exists that explores methods for the car detection component in these systems. This paper will discuss different computer vision methods that can be used for the detection and analysis of vehicles on the road for active traffic flow analysis and implements them in an experiment to find the best method for the task of car detection. MobileNet and Haar-Cascade based methods are implemented and a compared according to performance and accuracy levels in real-world scenarios. Lastly, the results achieved from the experimental model will be discussed giving detail to why Haar cascade gives better performance and accuracy in most scenarios with an average frame rate of over 40 fps on HD video.",

keywords = "Computer Vision, Object Detection, Traffic Monitoring System",

author = "{Le Roux}, Johan and {Van Der Haar}, Dustin",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems, icABCD 2019 ; Conference date: 05-08-2019 Through 06-08-2019",

year = "2019",

month = aug,

doi = "10.1109/ICABCD.2019.8851054",

language = "English",

series = "icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Manoj Maharaj and Singh, {Upasana Gitanjali}",

booktitle = "icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems",

address = "United States",

}

Le Roux, J & Van Der Haar, D 2019, Analysis of object detection methods to detect traffic flow. in M Maharaj & UG Singh (eds), icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems., 8851054, icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems, Institute of Electrical and Electronics Engineers Inc., 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems, icABCD 2019, Winterton, South Africa, 5/08/19. https://doi.org/10.1109/ICABCD.2019.8851054

Analysis of object detection methods to detect traffic flow. / Le Roux, Johan; Van Der Haar, Dustin.
icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems. ed. / Manoj Maharaj; Upasana Gitanjali Singh. Institute of Electrical and Electronics Engineers Inc., 2019. 8851054 (icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Analysis of object detection methods to detect traffic flow

AU - Le Roux, Johan

AU - Van Der Haar, Dustin

PY - 2019/8

Y1 - 2019/8

N2 - Traffic analysis has received more interest as smart cities become a reality. A key component of traffic analysis is detecting the amount of cars that pass certain points. However, limited research exists that explores methods for the car detection component in these systems. This paper will discuss different computer vision methods that can be used for the detection and analysis of vehicles on the road for active traffic flow analysis and implements them in an experiment to find the best method for the task of car detection. MobileNet and Haar-Cascade based methods are implemented and a compared according to performance and accuracy levels in real-world scenarios. Lastly, the results achieved from the experimental model will be discussed giving detail to why Haar cascade gives better performance and accuracy in most scenarios with an average frame rate of over 40 fps on HD video.

AB - Traffic analysis has received more interest as smart cities become a reality. A key component of traffic analysis is detecting the amount of cars that pass certain points. However, limited research exists that explores methods for the car detection component in these systems. This paper will discuss different computer vision methods that can be used for the detection and analysis of vehicles on the road for active traffic flow analysis and implements them in an experiment to find the best method for the task of car detection. MobileNet and Haar-Cascade based methods are implemented and a compared according to performance and accuracy levels in real-world scenarios. Lastly, the results achieved from the experimental model will be discussed giving detail to why Haar cascade gives better performance and accuracy in most scenarios with an average frame rate of over 40 fps on HD video.

KW - Computer Vision

KW - Object Detection

KW - Traffic Monitoring System

UR - http://www.scopus.com/inward/record.url?scp=85073570270&partnerID=8YFLogxK

U2 - 10.1109/ICABCD.2019.8851054

DO - 10.1109/ICABCD.2019.8851054

M3 - Conference contribution

AN - SCOPUS:85073570270

T3 - icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems

BT - icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems

A2 - Maharaj, Manoj

A2 - Singh, Upasana Gitanjali

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems, icABCD 2019

Y2 - 5 August 2019 through 6 August 2019

ER -

Le Roux J, Van Der Haar D. Analysis of object detection methods to detect traffic flow. In Maharaj M, Singh UG, editors, icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems. Institute of Electrical and Electronics Engineers Inc. 2019. 8851054. (icABCD 2019 - 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems). doi: 10.1109/ICABCD.2019.8851054

Analysis of object detection methods to detect traffic flow

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this