Grant: Engage Grants Program
University of Ottawa
$25,000.00
Towards an automated human detection scheme using automatic teller machines video
FY 2012-13
Summary
Automatic Teller Machines (ATM) have now become an integrated part of people's daily lives. Unfortunately,
ATM frauds are also on the rise. Criminals have found ways to steal, duplicate, or otherwise extract debit card
information from customers, using a variety of techniques. Fortunately, ATM are now equipped with cameras
in or around the machine, which create an opportunity for monitoring who is actually performing banking
operations, and taking action in suspicious cases.
This project will contribute to the development of a video-based analytics system for human detection that can
help to detect and locate people at ATM before engaging more sophisticated face detection and recognition. As
such, it will improve the security system performance and reduce false positives. The methods that will be
developed will also be used for queue detection and people counting which will then help organizations, such
as banks, to better manage their human resources allocation, leading to enhanced customer experience while
also preventing and reducing ATM fraud.
Existing solutions for detection of suspicious activities involve expensive video analytic camera hardware
which creates a barrier for wide adoption. This research aims at developing a software-based video analytic
solution to automatically extract, analyze, match and locate human body features using ATM and bank video
surveillance data. The information extracted from surveillance cameras is subject to severe constraints due to
bandwidth limitation. Therefore, image processing algorithms, video analytics, classification schemes and
machine learning techniques will be combined and refined with the objective to enhance subject identification
in low quality video surveillance images. This work will provide solutions for automated human detection, face
detection, segmentation and features extraction, and for reliable classification and matching of individuals.
This project will ultimately lead to new products development and groundbreaking technology. It will benefit
numerous applications, including fraud and counterfeit debit cards detection, and subject identification.
Program
Engage Grants Program
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
435196-2012
Name nom
Payeur, Pierre
Department département
Electrical Engineering and Computer Science , School of
Organization id
28
Institution établissement
University of Ottawa
Province en
Ontario
Province fr
Ontario
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
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
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
2605
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Pattern analysis and machine intelligence
Research subject fr
Analyse de formes et intelligence artificielle
Partie
1
Nb partie
1
Application title
Towards an automated human detection scheme using automatic teller machines video
Keyword
NSERC
Application summary
Automatic Teller Machines (ATM) have now become an integrated part of people's daily lives. Unfortunately,
ATM frauds are also on the rise. Criminals have found ways to steal, duplicate, or otherwise extract debit card
information from customers, using a variety of techniques. Fortunately, ATM are now equipped with cameras
in or around the machine, which create an opportunity for monitoring who is actually performing banking
operations, and taking action in suspicious cases.
This project will contribute to the development of a video-based analytics system for human detection that can
help to detect and locate people at ATM before engaging more sophisticated face detection and recognition. As
such, it will improve the security system performance and reduce false positives. The methods that will be
developed will also be used for queue detection and people counting which will then help organizations, such
as banks, to better manage their human resources allocation, leading to enhanced customer experience while
also preventing and reducing ATM fraud.
Existing solutions for detection of suspicious activities involve expensive video analytic camera hardware
which creates a barrier for wide adoption. This research aims at developing a software-based video analytic
solution to automatically extract, analyze, match and locate human body features using ATM and bank video
surveillance data. The information extracted from surveillance cameras is subject to severe constraints due to
bandwidth limitation. Therefore, image processing algorithms, video analytics, classification schemes and
machine learning techniques will be combined and refined with the objective to enhance subject identification
in low quality video surveillance images. This work will provide solutions for automated human detection, face
detection, segmentation and features extraction, and for reliable classification and matching of individuals.
This project will ultimately lead to new products development and groundbreaking technology. It will benefit
numerous applications, including fraud and counterfeit debit cards detection, and subject identification.