Edge-computing video analytics for real-time traffic monitoring in a smart city

Johan Barthélemy, Nicolas Verstaevel, Hugh Forehead, Pascal Perez

Research output: Contribution to journalArticle

1 Downloads (Pure)

Abstract

The increasing development of urban centers brings serious challenges for trafficmanagement. In this paper, we introduce a smart visual sensor, developed for a pilot project taking place in the Australian city of Liverpool (NSW). The project’s aim was to design and evaluate an edge-computing device using computer vision and deep neural networks to track in real-time multi-modal transportation while ensuring citizens’ privacy. The performance of the sensor was evaluated on a town center dataset. We also introduce the interoperable Agnosticity framework designed to collect, store and access data from multiple sensors, with results from two real-world experiments.

Original languageEnglish
Article number2048
Number of pages23
JournalSensors
Volume19
Issue number9
DOIs
Publication statusPublished - 1 May 2019

Fingerprint

Urban Renewal
Privacy
traffic
Equipment and Supplies
Monitoring
sensors
Sensors
Multimodal transportation
privacy
computer vision
Computer vision
Datasets
Smart city
Experiments

Keywords

  • CCTV
  • Edge-computing
  • IoT
  • Smart city
  • Traffic monitoring
  • Video analytic

Cite this

Barthélemy, Johan ; Verstaevel, Nicolas ; Forehead, Hugh ; Perez, Pascal. / Edge-computing video analytics for real-time traffic monitoring in a smart city. In: Sensors. 2019 ; Vol. 19, No. 9.
@article{0558301bccf44a6b9af53a4de0121e18,
title = "Edge-computing video analytics for real-time traffic monitoring in a smart city",
abstract = "The increasing development of urban centers brings serious challenges for trafficmanagement. In this paper, we introduce a smart visual sensor, developed for a pilot project taking place in the Australian city of Liverpool (NSW). The project’s aim was to design and evaluate an edge-computing device using computer vision and deep neural networks to track in real-time multi-modal transportation while ensuring citizens’ privacy. The performance of the sensor was evaluated on a town center dataset. We also introduce the interoperable Agnosticity framework designed to collect, store and access data from multiple sensors, with results from two real-world experiments.",
keywords = "CCTV, Edge-computing, IoT, Smart city, Traffic monitoring, Video analytic",
author = "Johan Barth{\'e}lemy and Nicolas Verstaevel and Hugh Forehead and Pascal Perez",
year = "2019",
month = "5",
day = "1",
doi = "10.3390/s19092048",
language = "English",
volume = "19",
journal = "Sensors",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "9",

}

Edge-computing video analytics for real-time traffic monitoring in a smart city. / Barthélemy, Johan; Verstaevel, Nicolas; Forehead, Hugh; Perez, Pascal.

In: Sensors, Vol. 19, No. 9, 2048, 01.05.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Edge-computing video analytics for real-time traffic monitoring in a smart city

AU - Barthélemy, Johan

AU - Verstaevel, Nicolas

AU - Forehead, Hugh

AU - Perez, Pascal

PY - 2019/5/1

Y1 - 2019/5/1

N2 - The increasing development of urban centers brings serious challenges for trafficmanagement. In this paper, we introduce a smart visual sensor, developed for a pilot project taking place in the Australian city of Liverpool (NSW). The project’s aim was to design and evaluate an edge-computing device using computer vision and deep neural networks to track in real-time multi-modal transportation while ensuring citizens’ privacy. The performance of the sensor was evaluated on a town center dataset. We also introduce the interoperable Agnosticity framework designed to collect, store and access data from multiple sensors, with results from two real-world experiments.

AB - The increasing development of urban centers brings serious challenges for trafficmanagement. In this paper, we introduce a smart visual sensor, developed for a pilot project taking place in the Australian city of Liverpool (NSW). The project’s aim was to design and evaluate an edge-computing device using computer vision and deep neural networks to track in real-time multi-modal transportation while ensuring citizens’ privacy. The performance of the sensor was evaluated on a town center dataset. We also introduce the interoperable Agnosticity framework designed to collect, store and access data from multiple sensors, with results from two real-world experiments.

KW - CCTV

KW - Edge-computing

KW - IoT

KW - Smart city

KW - Traffic monitoring

KW - Video analytic

UR - http://www.scopus.com/inward/record.url?scp=85065670219&partnerID=8YFLogxK

U2 - 10.3390/s19092048

DO - 10.3390/s19092048

M3 - Article

C2 - 31052514

AN - SCOPUS:85065670219

VL - 19

JO - Sensors

JF - Sensors

SN - 1424-8220

IS - 9

M1 - 2048

ER -