Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/24425

Title: Vehicle make and model recognition in CCTV footage
Authors: Saravi, Sara
Edirisinghe, Eran A.
Keywords: VMMR
CCTV footage
Make and Model Recognition
Local Energy Shape Histogram (LESH)
Coherent Point Drift (CPD)
Issue Date: 2013
Publisher: © IEEE
Citation: SARAVI, S. and EDIRISINGHE, E., 2013. Vehicle make and model recognition in CCTV footage. IN: Proceedings of 2013 18th International Conference on Digital Signal Processing (DSP 2013), Santorini, Greece, 1-3 July 2013, DOI: 10.1109/ICDSP.2013.6622720.
Abstract: This paper presents a novel approach to Vehicle Make & Model Recognition in CCTV video footage. CPD (coherent Point Drift) is used to effectively remove skew of vehicles detected as CCTV cameras are not specifically configured for the VMMR (Vehicle Make and Model Recognition) task and may capture vehicles at different approaching angles. Also a novel ROI (Region Of Interest) segmentation is proposed. A LESH (Local Energy Shape Histogram) feature based approach is used for vehicle make and model recognition with the novelty that temporal processing is used to improve reliability. A number of further algorithms are used to maximize the reliability of the fnal outcome. Experimental results are provided to prove that the proposed system demonstrates accuracy over 95% when tested in real CCTV footage with no prior camera calibration.
Description: © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Version: Accepted for publication
DOI: 10.1109/ICDSP.2013.6622720
URI: https://dspace.lboro.ac.uk/2134/24425
Publisher Link: http://dx.doi.org/10.1109/ICDSP.2013.6622720
ISBN: 9781467358071
ISSN: 1546-1874
Appears in Collections:Conference Papers and Presentations (Computer Science)

Files associated with this item:

File Description SizeFormat
Vehicle Make and Model Recognition for CCTV Camera Footage.pdfAccepted version619.99 kBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.