Share Email Print

Proceedings Paper

Vehicle monitoring under Vehicular Ad-Hoc Networks (VANET) parameters employing illumination invariant correlation filters for the Pakistan motorway police
Author(s): A. Gardezi; T. Umer; F. Butt; R. C. D. Young; C. R. Chatwin
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

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 enhancements 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.

Paper Details

Date Published: 20 April 2016
PDF: 13 pages
Proc. SPIE 9845, Optical Pattern Recognition XXVII, 984508 (20 April 2016); doi: 10.1117/12.2228295
Show Author Affiliations
A. Gardezi, COMSATS Institute of Information Technology (Pakistan)
T. Umer, COMSATS Institute of Information Technology (Pakistan)
F. Butt, COMSATS Institute of Information Technology (Pakistan)
R. C. D. Young, Univ. of Sussex (United Kingdom)
C. R. Chatwin, Univ. of Sussex (United Kingdom)

Published in SPIE Proceedings Vol. 9845:
Optical Pattern Recognition XXVII
David Casasent; Mohammad S. Alam, Editor(s)

© SPIE. Terms of Use
Back to Top