Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Idea to Innovation

University of British Columbia

$121,000.00

Depth sensing technology using super-resolution sensor fusion

EF 2011-12

Résumé
Today's 3D imaging systems consist of 5 key components: illumination, optics/lens, image sensor, electronics and interfacing, and image processing software. The technology we are developing under this I2I project applies to the image processing software. The output of the project will be a set of C++ libraries and a separate set of GPU libraries, with functionality that takes as input a low resolution 3D data set and a high resolution 2D image data set and outputs either (a) a segmented scene and/or (b) an accurate high resolution 3D depth map data set. The eventual product that end-users will use would incorporate the 5 components of a 3D imaging system where the UBC technology would be a major part of the image processing software workflow. The technology does require a high resolution 2D image of a scene, which can be obtained either directly from the existing 3D image acquisition hardware (if possible), or via introduction of a simple and inexpensive camera sensor as an additional component. A proposed start-up company would develop initial products based on the technology. While this may be a complete 3D acquisition system, it is more likely to be an image processing software package, based on the C++ and GPU libraries, that is tailored to the specific application and hardware needs (e.g. real time vs. post production processing; very low resolution sparse data vs. high resolution, highly accurate data as inputs). The technology will be implemented as image processing software that is compatible with virtually all 3D acquisition equipment that posesses or is augmented with a high resolution standard camera. Key benefits of the technology are higher resolution and accuracy of depth maps with lower data acquisition times and high quality scene segmentation. A cursory examination of trends in the imaging industry highlights the importance and rapidly growing demand for 3D imaging across a wide range of sectors - such as consumer devices and media content (gaming, movies, TV, etc.), medical imaging and diagnostics, factory automation and autonomous vehicles. As our technology is compatible with any 3D image acquisition hardware system, the scope of the opportunity is quite broad.
Programme
Idea to Innovation
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
413017-2011
Name nom
Lawrence, Peter
Department département
Electrical and Computer Engineering
Organization id
2
Institution établissement
University of British Columbia
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2011
Award amount
121000
Program id
I2IPJ
Program nane en
Idea to Innovation
Program name fr
De l'idée à l'innovation
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
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
Depth sensing technology using super-resolution sensor fusion
Keyword
NSERC
Application summary
Today's 3D imaging systems consist of 5 key components: illumination, optics/lens, image sensor, electronics and interfacing, and image processing software. The technology we are developing under this I2I project applies to the image processing software. The output of the project will be a set of C++ libraries and a separate set of GPU libraries, with functionality that takes as input a low resolution 3D data set and a high resolution 2D image data set and outputs either (a) a segmented scene and/or (b) an accurate high resolution 3D depth map data set. The eventual product that end-users will use would incorporate the 5 components of a 3D imaging system where the UBC technology would be a major part of the image processing software workflow. The technology does require a high resolution 2D image of a scene, which can be obtained either directly from the existing 3D image acquisition hardware (if possible), or via introduction of a simple and inexpensive camera sensor as an additional component. A proposed start-up company would develop initial products based on the technology. While this may be a complete 3D acquisition system, it is more likely to be an image processing software package, based on the C++ and GPU libraries, that is tailored to the specific application and hardware needs (e.g. real time vs. post production processing; very low resolution sparse data vs. high resolution, highly accurate data as inputs). The technology will be implemented as image processing software that is compatible with virtually all 3D acquisition equipment that posesses or is augmented with a high resolution standard camera. Key benefits of the technology are higher resolution and accuracy of depth maps with lower data acquisition times and high quality scene segmentation. A cursory examination of trends in the imaging industry highlights the importance and rapidly growing demand for 3D imaging across a wide range of sectors - such as consumer devices and media content (gaming, movies, TV, etc.), medical imaging and diagnostics, factory automation and autonomous vehicles. As our technology is compatible with any 3D image acquisition hardware system, the scope of the opportunity is quite broad.