Grant: Engage Grants Program
Concordia University
$25,000.00
Error Correction for Depth Sensing using Deep Learning
EF 2016-17
Résumé
Airy 3D, a Montreal start-up company, is pioneering the development of low form factor, low power, singlesensor depth sensing technology. Depth sensing technology has been used for 3D scanning, for gesturerecognition as well as in robotics for robot navigation and location. A common limitation of depth sensingdevices, especially based on optical technology, is the high measurement errors. We are collaborating closelywith Airy 3D to develop together a novel approach base on deep learning to address these errors.We are proposing a system that learns the error function of the device by learning the correlations betweenneighbouring pixels using a deep learning framework and a large database of scanned objects. At run-time anerror correction step is added in real-time based on the network trained in the off-line learning step. This willmake the sensor more accurate, thus reducing the calibration cost and implicitly the manufacturing cost of thedevice. This method can have a high impact as depth sensing is becoming more and more ubiquitous.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
506136-2016
Name nom
Popa, Tiberiu
Department département
Computer Science and Software Engineering
Organization id
70
Institution établissement
Concordia University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
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
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
2707
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Graphics
Research subject fr
Infographie
Partie
1
Nb partie
1
Application title
Error Correction for Depth Sensing using Deep Learning
Keyword
NSERC
Application summary
Airy 3D, a Montreal start-up company, is pioneering the development of low form factor, low power, singlesensor depth sensing technology. Depth sensing technology has been used for 3D scanning, for gesturerecognition as well as in robotics for robot navigation and location. A common limitation of depth sensingdevices, especially based on optical technology, is the high measurement errors. We are collaborating closelywith Airy 3D to develop together a novel approach base on deep learning to address these errors.We are proposing a system that learns the error function of the device by learning the correlations betweenneighbouring pixels using a deep learning framework and a large database of scanned objects. At run-time anerror correction step is added in real-time based on the network trained in the off-line learning step. This willmake the sensor more accurate, thus reducing the calibration cost and implicitly the manufacturing cost of thedevice. This method can have a high impact as depth sensing is becoming more and more ubiquitous.