Grant: Research Tools and Instruments - Category 1 (<$150,000)
Simon Fraser University
$112,922.00
Vision based Autonomous Navigation and Human Robot Interaction (HRI) for a Team of Flying Robots
FY 2014-15
Summary
We propose to purchase a high-quality indoor motion-capture system to track the locations of a team of flying robots and humans as they interact, cameras for data collection by a team of robots, and computer servers and storage to process these data. This equipment will support the applicants' individual and joint research programs. Each of our team has recently demonstrated world-leading new capabilities in multi-camera tracking and SLAM (Tan), in vision-mediated human-robot interaction (Vaughan), and human activity recognition from video (Mori). The proposed equipment will support our new joint work, where we (i) control a team of flying robots to observe moving people from several viewpoints (ii) reconstruct a 3D view of each person and extract a skeleton pose estimate in real time, (iii) categorize the people's activity, and (iv) use the activity information to help the robots improve their camera placement.The key piece of proposed equipment is an indoor motion capture system to provide ground-truth measurements that allow us to analyze and evaluate the performance of our system. When proven indoors, our goal is to have the robot system work outdoors. Multi-view stereo and 3D modeling of people and the environment is a rapidly-growing area with great commercial promise. The new ubiquity of camera-equipped mobile devices means that our algorithms could be used immediately by hundreds of millions of people. The use of robots as automated camera platform is just starting commercially, and will be very valuable. Finally, accurately capturing the pose of a freely-moving person has major applications in health diagnosis, entertainment, and human-robot interfaces.
Program
Research Tools and Instruments - Category 1 (<$150,000)
Recipient
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
472804-2015
Name nom
Tan, Ping
Department département
Computing Science, School of
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2015
Award amount
112922
Program id
EQPEQ
Program name en
Research Tools and Instruments - Category 1 (<$150,000)
Program name fr
Outils et instruments de recherche - catégorie 1 (<150 000$)
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
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
Vision based Autonomous Navigation and Human Robot Interaction (HRI) for a Team of Flying Robots
Keyword
NSERC
Application summary
We propose to purchase a high-quality indoor motion-capture system to track the locations of a team of flying robots and humans as they interact, cameras for data collection by a team of robots, and computer servers and storage to process these data. This equipment will support the applicants' individual and joint research programs. Each of our team has recently demonstrated world-leading new capabilities in multi-camera tracking and SLAM (Tan), in vision-mediated human-robot interaction (Vaughan), and human activity recognition from video (Mori). The proposed equipment will support our new joint work, where we (i) control a team of flying robots to observe moving people from several viewpoints (ii) reconstruct a 3D view of each person and extract a skeleton pose estimate in real time, (iii) categorize the people's activity, and (iv) use the activity information to help the robots improve their camera placement.The key piece of proposed equipment is an indoor motion capture system to provide ground-truth measurements that allow us to analyze and evaluate the performance of our system. When proven indoors, our goal is to have the robot system work outdoors. Multi-view stereo and 3D modeling of people and the environment is a rapidly-growing area with great commercial promise. The new ubiquity of camera-equipped mobile devices means that our algorithms could be used immediately by hundreds of millions of people. The use of robots as automated camera platform is just starting commercially, and will be very valuable. Finally, accurately capturing the pose of a freely-moving person has major applications in health diagnosis, entertainment, and human-robot interfaces.