University of Sussex
Browse

File(s) under permanent embargo

Automated vehicle occupancy monitoring

journal contribution
posted on 2023-06-08, 15:01 authored by Philip M Birch, Rupert C D Young, Frederic Claret-Tournier, Chris ChatwinChris Chatwin
There are an increasing number of high-occupancy-vehicle lanes throughout the world. In these lanes each vehicle is required to have two or more occupants. These laws are currently manually enforced. This paper presents a new system for automating the enforcement process, using color image segmentation techniques to find the windshield area, and face detection to count the number of occupants within a vehicle.

History

Publication status

  • Published

File Version

  • Published version

Journal

Optical Engineering

ISSN

0091-3286

Publisher

Society of Photo-Optical Instrumentation Engineers

Issue

8

Volume

43

Page range

1828-1832

Department affiliated with

  • Engineering and Design Publications

Notes

This paper demonstrates the world's first attempt at automatically counting people within a vehicle as an automatic method for policing high occupancy lanes. It used a segmentation technique to locate the windscreen of vehicles and a neural network to locate the people within the segmented image that I developed. This work was part of a DTI Link (GR/R18611/01) on which I was the researcher. The project was with Leeds Council, Golden River Traffic, LOE, and Photonic Consultancy. This project later developed into the company Vehicle Occupancy Ltd. http://www.vehicleoccupancy.com

Full text available

  • No

Peer reviewed?

  • Yes

Legacy Posted Date

2015-07-02

First Compliant Deposit (FCD) Date

2015-07-02

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC