University of Sussex
Browse
Vehicle monitoring under Vehicular Ad-Hoc Networks 2016.pdf (779.51 kB)

Vehicle monitoring under Vehicular Ad-Hoc Networks (VANET) parameters employing illumination invariant correlation filters for the Pakistan motorway police

Download (779.51 kB)
conference contribution
posted on 2023-06-09, 01:09 authored by A Gardezi, T Umer, F Butt, Rupert YoungRupert Young, Chris ChatwinChris Chatwin
A spatial domain optimal trade-off Maximum Average Correlation Height (SPOT-MACH) filter has been previously developed and shown to have advantages over frequency domain implementations in that it can be made locally adaptive to spatial variations in the input image background clutter and normalised for local intensity changes. The main concern for using the SPOT-MACH is its computationally intensive nature. However, in the past enhancement techniques were proposed for the SPOT-MACH to make its execution time comparable to its frequency domain counterpart. In this paper a novel approach is discussed which uses VANET parameters coupled with the SPOT-MACH in order to minimise the extensive processing of the large video dataset acquired from the Pakistan motorways surveillance system. The use of VANET parameters gives us an estimation criterion of the flow of traffic on the Pakistan motorway network and acts as a precursor to the training algorithm. The use of VANET in this scenario would contribute heavily towards the computational complexity minimization of the proposed monitoring system.

History

Publication status

  • Published

File Version

  • Accepted version

Journal

Proceedings of SPIE Defense + Security 2016 on Optical Pattern Recognition; Baltimore, MD , United States; 17-21 April 2016

Publisher

SPIE

Issue

984508

Volume

XXVII

Page range

1-13

ISBN

9781510600867

Department affiliated with

  • Engineering and Design Publications

Research groups affiliated with

  • Industrial Informatics and Signal Processing Research Group Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2016-05-09

First Open Access (FOA) Date

2017-07-13

First Compliant Deposit (FCD) Date

2017-07-13

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC