Grant: Engage Grants Program
University of Ottawa
$25,000.00
Audio analytics for intelligent cameras
FY 2010-11
Summary
The objective of this collaborative research is to develop the first version of an intelligent audio analytics
application, as part of an intelligent camera surveillance system. The partner company is iWatchLife, a
surveillance software provider offering self-monitoring software to deploy low-cost, flexible and robust
surveillance solutions for residences and small organizations. iWatchLife products currently make use of
advanced video analytics, which looks at the video motion detected, and uses advanced computer algorithms to
classify the motion. Using such a tool has several advantages such as alerting the customer for the types of
video events that he has selected and for the areas and times that he has selected. The solution also reduces the
bandwidth required for the transmission of video, because fewer images or video clips need to be monitored or
analyzed, when compared to continuous video streaming. While video-only event detection and classification
can offer good performance under several scenarios, it has some obvious limitations too, such as:
1. cameras and/or detection algorithms not performing as well in dark conditions, and
2. cameras do not normally cover or monitor all angles within a room, or all rooms within a house.
Intelligent audio analytics would offer an alternative or a strong complement to iWatchLife's video analytics
tools. A camera with a microphone is obviously immune to the lighting conditions and it can detect sounds
from reasonably remote areas. In addition, even for conditions where the current video analytics tool performs
well, there is also a strong potential benefit to make detections and classification using ""multimodal""
information (i.e. using both the information from the audio and video). Therefore, the long-term objective of
the collaboration with iWatchLife is to develop a comprehensive audio analytics tool which will also interact
and be integrated with the currently available video analytics tool.
Program
Engage Grants Program
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
401991-2010
Name nom
Bouchard, Martin
Department département
Information Technology and Engineering, 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
2010
Competition year année de concours
2010
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
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
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
Audio analytics for intelligent cameras
Keyword
NSERC
Application summary
The objective of this collaborative research is to develop the first version of an intelligent audio analytics
application, as part of an intelligent camera surveillance system. The partner company is iWatchLife, a
surveillance software provider offering self-monitoring software to deploy low-cost, flexible and robust
surveillance solutions for residences and small organizations. iWatchLife products currently make use of
advanced video analytics, which looks at the video motion detected, and uses advanced computer algorithms to
classify the motion. Using such a tool has several advantages such as alerting the customer for the types of
video events that he has selected and for the areas and times that he has selected. The solution also reduces the
bandwidth required for the transmission of video, because fewer images or video clips need to be monitored or
analyzed, when compared to continuous video streaming. While video-only event detection and classification
can offer good performance under several scenarios, it has some obvious limitations too, such as:
1. cameras and/or detection algorithms not performing as well in dark conditions, and
2. cameras do not normally cover or monitor all angles within a room, or all rooms within a house.
Intelligent audio analytics would offer an alternative or a strong complement to iWatchLife's video analytics
tools. A camera with a microphone is obviously immune to the lighting conditions and it can detect sounds
from reasonably remote areas. In addition, even for conditions where the current video analytics tool performs
well, there is also a strong potential benefit to make detections and classification using ""multimodal""
information (i.e. using both the information from the audio and video). Therefore, the long-term objective of
the collaboration with iWatchLife is to develop a comprehensive audio analytics tool which will also interact
and be integrated with the currently available video analytics tool.