Grant: Engage Grants Program
McGill University
$25,000.00
Parking Occupancy Study from Mobile License Plate Recognition Data
FY 2012-13
Summary
License plate recognition (LPR) systems are currently used to assist parking and law enforcement officers in
identifying parking violations, gathering evidence, and surveying information about parking behavior around a
city. Genetec, the supporting organization for this project, is the world-leading provider of LPR systems. The
aim of this project is to develop a suite of algorithms for post-processing LPR data to extract statistics, patterns,
and trends which will be compiled into a parking occupancy study. The study will include statistics such as the
typical duration that a car remains parked, the rate at which spots turnover in different parts of the city, the
average number of spots which are filled, and predictions of busy periods. One challenging aspect of this work
is the noise or uncertainty inherent to the data. Each LPR record contains the license plate string, a timestamp,
and the GPS coordinates where the record was obtained, as well as other metadata. Existing computer vision
algorithms which extract the license plate string from images are not perfect. The license plate strings may
include errors (e.g., '8' instead of 'B'), and the algorithms may make false detections (e.g., mistaking text on a
bumper sticker or sign for a license plate). There is also uncertainty inherent in the reported GPS coordinates.
The statistical techniques developed in this project will aim to produce accurate estimates of occupancy
statistics from this noisy data. Pattern recognition algorithms will extract patterns which may not be
immediately obvious to the human eye, and they will also be used in conjunction with roadmap data to help
visualize the results.
Program
Engage Grants Program
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
429988-2012
Name nom
Rabbat, Michael
Department département
Electrical and Computer Engineering
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2012
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2514
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Digital signal processing
Research subject fr
Traitement des signaux numériques
Partie
1
Nb partie
1
Application title
Parking Occupancy Study from Mobile License Plate Recognition Data
Keyword
NSERC
Application summary
License plate recognition (LPR) systems are currently used to assist parking and law enforcement officers in
identifying parking violations, gathering evidence, and surveying information about parking behavior around a
city. Genetec, the supporting organization for this project, is the world-leading provider of LPR systems. The
aim of this project is to develop a suite of algorithms for post-processing LPR data to extract statistics, patterns,
and trends which will be compiled into a parking occupancy study. The study will include statistics such as the
typical duration that a car remains parked, the rate at which spots turnover in different parts of the city, the
average number of spots which are filled, and predictions of busy periods. One challenging aspect of this work
is the noise or uncertainty inherent to the data. Each LPR record contains the license plate string, a timestamp,
and the GPS coordinates where the record was obtained, as well as other metadata. Existing computer vision
algorithms which extract the license plate string from images are not perfect. The license plate strings may
include errors (e.g., '8' instead of 'B'), and the algorithms may make false detections (e.g., mistaking text on a
bumper sticker or sign for a license plate). There is also uncertainty inherent in the reported GPS coordinates.
The statistical techniques developed in this project will aim to produce accurate estimates of occupancy
statistics from this noisy data. Pattern recognition algorithms will extract patterns which may not be
immediately obvious to the human eye, and they will also be used in conjunction with roadmap data to help
visualize the results.