Grant: Engage Grants Program
École Polytechnique de Montréal
$25,000.00
Head tracking and detection for people counting and wait time evaluation
EF 2012-13
Résumé
The partner company is Solink Corporation, a company working in real-time retail intelligence across nearly
every vertical from banks, to independent retail stores and large chains. To expand beyond the fraud prevention
and banking filed and based on current and existing client requests, Solink is working toward a solution for
retail intelligence, traffic monitoring, queue management, and customer behavior analysis. For example, the
dwell-time indicator measures how long customers spend looking at a specific display, determining the success
of such displays. In addition, by tracking lines throughout the store, queue management let the retailer know
when additional staff is needed at checkout stations or can alert customers and staff alike as to how long a wait
in line will be. This project will allow Solink to develop a solution that can help the retailer understands the
customers' behavior from entrance to exit, identifying opportunities for improvement as well as scaling best
practices throughout the entire facility. Our investigations will therefore focus on researching methods and
algorithms that can be quickly used in the company software for detecting and tracking customers to count
them and evaluate the wait time in queues.
We will develop new methods to track a head in the context of a non-cooperative environment and where the
videos are low resolution to count the number of people and to determine wait times. The research will be
conducted in two phases. First, we will focus on head detection using features that are not too facial features
dependent, and then we will focus on tracking, accounting for changes of appearance and occlusions.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
443521-2012
Name nom
Bilodeau, GuillaumeAlexandre
Department département
Génie informatique et génie logiciel
Organization id
64
Institution établissement
École Polytechnique de Montréal
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
2603
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Computer vision
Research subject fr
Vision artificielle
Partie
1
Nb partie
1
Application title
Head tracking and detection for people counting and wait time evaluation
Keyword
NSERC
Application summary
The partner company is Solink Corporation, a company working in real-time retail intelligence across nearly
every vertical from banks, to independent retail stores and large chains. To expand beyond the fraud prevention
and banking filed and based on current and existing client requests, Solink is working toward a solution for
retail intelligence, traffic monitoring, queue management, and customer behavior analysis. For example, the
dwell-time indicator measures how long customers spend looking at a specific display, determining the success
of such displays. In addition, by tracking lines throughout the store, queue management let the retailer know
when additional staff is needed at checkout stations or can alert customers and staff alike as to how long a wait
in line will be. This project will allow Solink to develop a solution that can help the retailer understands the
customers' behavior from entrance to exit, identifying opportunities for improvement as well as scaling best
practices throughout the entire facility. Our investigations will therefore focus on researching methods and
algorithms that can be quickly used in the company software for detecting and tracking customers to count
them and evaluate the wait time in queues.
We will develop new methods to track a head in the context of a non-cooperative environment and where the
videos are low resolution to count the number of people and to determine wait times. The research will be
conducted in two phases. First, we will focus on head detection using features that are not too facial features
dependent, and then we will focus on tracking, accounting for changes of appearance and occlusions.