SlideShare uma empresa Scribd logo
1 de 19
Baixar para ler offline
Smart Vision System:
Design of Application
Algorithm-Architecture
      Eric Delfosse
      IBBT-NES-IMEC
What are Smart Vision Systems?

Systems that embed intelligence through advanced
image processing to:

  Enhance visual user experience

  Improve natural interaction

  Facilitate decision making for complex events

  …
Enhance visual user experience
Multi-camera 3D image reconstruction for advanced
surveillance




3D GPS
                                           (IBBT GBO ISYSS)


                                           (IBBT GBO URBAN)
Increase natural interaction


Natural human-machine interface
through gesture recognition




3D (immersive) video              (IBBT GBO Hi-Masquerade)
conferencing
Facilitate decision making for complex events


Event detection for
surveillance applications


                        (IBBT GBO ISYSS)




Traffic sign recognition for
driver assistance

                       (IBBT GBO URBAN)
Different applications, different requirements

                   Throughput
                  High resolution
                  High framerate
Functionality
                                          Accuracy
                                    Reduce false negatives
                                      and false positives


                      …
          Size                         Low Power
                                       Solar energy
                                    Avoid active cooling
                                             ...

                         Cost
These applications require increasingly complex
algorithms

                                                    Exponential algorithmic complexity increase
                                                                                                                                          > 9000
                            3000


                            2500
   Complexity (Ops/pixel)




                            2000


                            1500


                            1000


                             500


                               0
                                                                       enhancement




                                                                                       extraction




                                                                                                    Depth extraction
                                   Edge detection




                                                        AVC encoding




                                                                                                                       Object detection




                                                                                                                                           understanding
                                                                                        Feature
                                                                          Image




                                                                                                                                              Image
                                                                                     Algorithm
Diversity of platform architectures with different
characteristics




                                   PC + GPU
                                 High performance
                                    High power
                             Limited portability (laptop)
                                         …




      Server rack
                                Embedded systems
    Very high performance
       Very high Power          Medium performance
         Non-portable               Low power
              …                   High portability
                                        …
Smart Vision Systems design =
Matching Application – Algorithm - Architecture

                   Application
                 (Requirements)




   Algorithm                        Architecture
  (Complexity)                     (Constraints)
Smart Vision Systems design =
Matching Application – Algorithm - Architecture

                   Application
                 (Requirements)




   Algorithm                        Architecture
  (Complexity)                     (Constraints)
Smart Vision Systems design =
Matching Application – Algorithm - Architecture

                   Application
                 (Requirements)




   Algorithm                                 Architecture
  (Complexity)     Introduce parallelism
                                            (Constraints)
                  Processor optimizations
Complexity - Quality trade-off: reduce complexity with
limited (visual) quality loss
Matching Algorithm and Architecture: the DCT example
f0                           F0


f1                           F1


f2                           F2


f3                           F3


f4                           F4


f5                           F5


f6                           F6


f7                           F7

        Classical DCT                 Butterfly DCT
        64 multiplications           20 multiplications
        64 additions                 26 additions

        High regularity              Low regularity

        Ideal for:                   Ideal for:
Smart Vision Systems design =
Matching Application – Algorithm - Architecture
                   Companies

                   Application
                 (Requirements)




                     IBBT




   Algorithm                        Architecture
  (Complexity)                     (Constraints)
Conclusions

Smart Vision Systems:
  Enable new applications
  Require new complex algorithms
  Use diverse platform architectures



Successful design requires competences on these 3
aspects

   IBBT brings these competences together
Demo’s
Demo 1: 3D video through real-time viewpoint
  interpolation
                              Viewpoint interpolation:
                              a)   stereo capturing
                              b)   depth extraction
                              c)   interpolation




Autostereoscopic displays:
       require multiple
     (interpolated) views
Demo 2: Eye-gaze corrected video chatting
                Webcam


                   Computer
                   Display
Demo 3: Novel 3D Camera prototype and monitoring
application in elderly environment

Mais conteúdo relacionado

Mais procurados

Java me 08-mobile3d
Java me 08-mobile3dJava me 08-mobile3d
Java me 08-mobile3d
Hemanth Raju
 
Practical and Robust Stenciled Shadow Volumes for Hardware-Accelerated Rendering
Practical and Robust Stenciled Shadow Volumes for Hardware-Accelerated RenderingPractical and Robust Stenciled Shadow Volumes for Hardware-Accelerated Rendering
Practical and Robust Stenciled Shadow Volumes for Hardware-Accelerated Rendering
Mark Kilgard
 
Keynote - SPIE Stereoscopic Displays & Applications 2014
Keynote - SPIE Stereoscopic Displays & Applications 2014Keynote - SPIE Stereoscopic Displays & Applications 2014
Keynote - SPIE Stereoscopic Displays & Applications 2014
Gordon Wetzstein
 
Samsung box shc-735 e
Samsung box shc-735 eSamsung box shc-735 e
Samsung box shc-735 e
mayur_32
 
NIAR_VRC_2010
NIAR_VRC_2010NIAR_VRC_2010
NIAR_VRC_2010
fftoledo
 
Monocular simultaneous localization and generalized object mapping with undel...
Monocular simultaneous localization and generalized object mapping with undel...Monocular simultaneous localization and generalized object mapping with undel...
Monocular simultaneous localization and generalized object mapping with undel...
Chen-Han Hsiao
 

Mais procurados (14)

Java me 08-mobile3d
Java me 08-mobile3dJava me 08-mobile3d
Java me 08-mobile3d
 
Modern Graphics Pipeline Overview
Modern Graphics Pipeline OverviewModern Graphics Pipeline Overview
Modern Graphics Pipeline Overview
 
Practical and Robust Stenciled Shadow Volumes for Hardware-Accelerated Rendering
Practical and Robust Stenciled Shadow Volumes for Hardware-Accelerated RenderingPractical and Robust Stenciled Shadow Volumes for Hardware-Accelerated Rendering
Practical and Robust Stenciled Shadow Volumes for Hardware-Accelerated Rendering
 
Keynote - SPIE Stereoscopic Displays & Applications 2014
Keynote - SPIE Stereoscopic Displays & Applications 2014Keynote - SPIE Stereoscopic Displays & Applications 2014
Keynote - SPIE Stereoscopic Displays & Applications 2014
 
Compressive DIsplays: SID Keynote by Ramesh Raskar
Compressive DIsplays: SID Keynote by Ramesh RaskarCompressive DIsplays: SID Keynote by Ramesh Raskar
Compressive DIsplays: SID Keynote by Ramesh Raskar
 
Samsung box shc-735 e
Samsung box shc-735 eSamsung box shc-735 e
Samsung box shc-735 e
 
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro..."High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
 
Keynote at 23rd International Display Workshop
Keynote at 23rd International Display WorkshopKeynote at 23rd International Display Workshop
Keynote at 23rd International Display Workshop
 
Keynote Virtual Efficiency Congress 2012
Keynote Virtual Efficiency Congress 2012Keynote Virtual Efficiency Congress 2012
Keynote Virtual Efficiency Congress 2012
 
NIAR_VRC_2010
NIAR_VRC_2010NIAR_VRC_2010
NIAR_VRC_2010
 
Raskar Mar09 Nesosa
Raskar Mar09 NesosaRaskar Mar09 Nesosa
Raskar Mar09 Nesosa
 
Scv 3080 p
Scv 3080 pScv 3080 p
Scv 3080 p
 
Monocular simultaneous localization and generalized object mapping with undel...
Monocular simultaneous localization and generalized object mapping with undel...Monocular simultaneous localization and generalized object mapping with undel...
Monocular simultaneous localization and generalized object mapping with undel...
 
Scd 2080 p
Scd 2080 pScd 2080 p
Scd 2080 p
 

Destaque

Brokerage2006 wim dewaele ibbt een overzicht van 2 jaren werking & onze plan...
Brokerage2006 wim dewaele  ibbt een overzicht van 2 jaren werking & onze plan...Brokerage2006 wim dewaele  ibbt een overzicht van 2 jaren werking & onze plan...
Brokerage2006 wim dewaele ibbt een overzicht van 2 jaren werking & onze plan...
imec.archive
 
Maduf08 Business Models Olivier Braet
Maduf08 Business Models   Olivier BraetMaduf08 Business Models   Olivier Braet
Maduf08 Business Models Olivier Braet
imec.archive
 
I Lab3 I Lab Testcenteroverview
I Lab3 I Lab TestcenteroverviewI Lab3 I Lab Testcenteroverview
I Lab3 I Lab Testcenteroverview
imec.archive
 
Ict Sd08 Multichannel E Government Leo Van Audenhove
Ict Sd08 Multichannel E Government   Leo Van AudenhoveIct Sd08 Multichannel E Government   Leo Van Audenhove
Ict Sd08 Multichannel E Government Leo Van Audenhove
imec.archive
 
A2 Bforum P1 10 Kul Sam Michiels Stadium
A2 Bforum P1 10 Kul   Sam Michiels   StadiumA2 Bforum P1 10 Kul   Sam Michiels   Stadium
A2 Bforum P1 10 Kul Sam Michiels Stadium
imec.archive
 
Excellence in customer relationships
Excellence in customer relationshipsExcellence in customer relationships
Excellence in customer relationships
Garrett Delcourt
 
Dominique Segers - Demand-driven research in Medical Imaging
Dominique Segers - Demand-driven research in Medical ImagingDominique Segers - Demand-driven research in Medical Imaging
Dominique Segers - Demand-driven research in Medical Imaging
imec.archive
 
Koen Handekyn - Variability in the Cloud
Koen Handekyn - Variability in the CloudKoen Handekyn - Variability in the Cloud
Koen Handekyn - Variability in the Cloud
imec.archive
 
ENoLL 6th Wave Results Ceremony (Jesse Marsh)
ENoLL 6th Wave Results Ceremony (Jesse Marsh)ENoLL 6th Wave Results Ceremony (Jesse Marsh)
ENoLL 6th Wave Results Ceremony (Jesse Marsh)
imec.archive
 
Peter Schelkens - Future Media and Imaging
Peter Schelkens - Future Media and ImagingPeter Schelkens - Future Media and Imaging
Peter Schelkens - Future Media and Imaging
imec.archive
 
Marc De Colvenaer - Vlaams Proeftuinplatform
Marc De Colvenaer - Vlaams ProeftuinplatformMarc De Colvenaer - Vlaams Proeftuinplatform
Marc De Colvenaer - Vlaams Proeftuinplatform
imec.archive
 
Curriculumvitae 100425072655-phpapp01
Curriculumvitae 100425072655-phpapp01Curriculumvitae 100425072655-phpapp01
Curriculumvitae 100425072655-phpapp01
nnasirkful
 
I Minds2009 Wishbone
I Minds2009 WishboneI Minds2009 Wishbone
I Minds2009 Wishbone
imec.archive
 
I Minds2009 Amy Shuen What Is Web 2 0
I Minds2009 Amy Shuen   What Is Web 2 0I Minds2009 Amy Shuen   What Is Web 2 0
I Minds2009 Amy Shuen What Is Web 2 0
imec.archive
 
02 Levenslang Wonen In Levensbestendige Woonwijken
02  Levenslang Wonen In Levensbestendige Woonwijken02  Levenslang Wonen In Levensbestendige Woonwijken
02 Levenslang Wonen In Levensbestendige Woonwijken
imec.archive
 
Steven Logghe & Pieter Audenaert - Mobiroute
Steven Logghe & Pieter Audenaert - MobirouteSteven Logghe & Pieter Audenaert - Mobiroute
Steven Logghe & Pieter Audenaert - Mobiroute
imec.archive
 
Maduf07 Expert Opinion And Potential Estimation Lieven De Marez
Maduf07 Expert Opinion And Potential Estimation   Lieven De MarezMaduf07 Expert Opinion And Potential Estimation   Lieven De Marez
Maduf07 Expert Opinion And Potential Estimation Lieven De Marez
imec.archive
 
Qo E E2 E6 Slotevent Programma
Qo E E2 E6 Slotevent ProgrammaQo E E2 E6 Slotevent Programma
Qo E E2 E6 Slotevent Programma
imec.archive
 

Destaque (20)

موزاییک بندی تصاویر ویدیویی
موزاییک بندی تصاویر ویدیوییموزاییک بندی تصاویر ویدیویی
موزاییک بندی تصاویر ویدیویی
 
Brokerage2006 wim dewaele ibbt een overzicht van 2 jaren werking & onze plan...
Brokerage2006 wim dewaele  ibbt een overzicht van 2 jaren werking & onze plan...Brokerage2006 wim dewaele  ibbt een overzicht van 2 jaren werking & onze plan...
Brokerage2006 wim dewaele ibbt een overzicht van 2 jaren werking & onze plan...
 
Maduf08 Business Models Olivier Braet
Maduf08 Business Models   Olivier BraetMaduf08 Business Models   Olivier Braet
Maduf08 Business Models Olivier Braet
 
I Lab3 I Lab Testcenteroverview
I Lab3 I Lab TestcenteroverviewI Lab3 I Lab Testcenteroverview
I Lab3 I Lab Testcenteroverview
 
Ict Sd08 Multichannel E Government Leo Van Audenhove
Ict Sd08 Multichannel E Government   Leo Van AudenhoveIct Sd08 Multichannel E Government   Leo Van Audenhove
Ict Sd08 Multichannel E Government Leo Van Audenhove
 
A2 Bforum P1 10 Kul Sam Michiels Stadium
A2 Bforum P1 10 Kul   Sam Michiels   StadiumA2 Bforum P1 10 Kul   Sam Michiels   Stadium
A2 Bforum P1 10 Kul Sam Michiels Stadium
 
Excellence in customer relationships
Excellence in customer relationshipsExcellence in customer relationships
Excellence in customer relationships
 
Dominique Segers - Demand-driven research in Medical Imaging
Dominique Segers - Demand-driven research in Medical ImagingDominique Segers - Demand-driven research in Medical Imaging
Dominique Segers - Demand-driven research in Medical Imaging
 
Koen Handekyn - Variability in the Cloud
Koen Handekyn - Variability in the CloudKoen Handekyn - Variability in the Cloud
Koen Handekyn - Variability in the Cloud
 
ENoLL 6th Wave Results Ceremony (Jesse Marsh)
ENoLL 6th Wave Results Ceremony (Jesse Marsh)ENoLL 6th Wave Results Ceremony (Jesse Marsh)
ENoLL 6th Wave Results Ceremony (Jesse Marsh)
 
Peter Schelkens - Future Media and Imaging
Peter Schelkens - Future Media and ImagingPeter Schelkens - Future Media and Imaging
Peter Schelkens - Future Media and Imaging
 
Marc De Colvenaer - Vlaams Proeftuinplatform
Marc De Colvenaer - Vlaams ProeftuinplatformMarc De Colvenaer - Vlaams Proeftuinplatform
Marc De Colvenaer - Vlaams Proeftuinplatform
 
Modal Verbs
Modal VerbsModal Verbs
Modal Verbs
 
Curriculumvitae 100425072655-phpapp01
Curriculumvitae 100425072655-phpapp01Curriculumvitae 100425072655-phpapp01
Curriculumvitae 100425072655-phpapp01
 
I Minds2009 Wishbone
I Minds2009 WishboneI Minds2009 Wishbone
I Minds2009 Wishbone
 
I Minds2009 Amy Shuen What Is Web 2 0
I Minds2009 Amy Shuen   What Is Web 2 0I Minds2009 Amy Shuen   What Is Web 2 0
I Minds2009 Amy Shuen What Is Web 2 0
 
02 Levenslang Wonen In Levensbestendige Woonwijken
02  Levenslang Wonen In Levensbestendige Woonwijken02  Levenslang Wonen In Levensbestendige Woonwijken
02 Levenslang Wonen In Levensbestendige Woonwijken
 
Steven Logghe & Pieter Audenaert - Mobiroute
Steven Logghe & Pieter Audenaert - MobirouteSteven Logghe & Pieter Audenaert - Mobiroute
Steven Logghe & Pieter Audenaert - Mobiroute
 
Maduf07 Expert Opinion And Potential Estimation Lieven De Marez
Maduf07 Expert Opinion And Potential Estimation   Lieven De MarezMaduf07 Expert Opinion And Potential Estimation   Lieven De Marez
Maduf07 Expert Opinion And Potential Estimation Lieven De Marez
 
Qo E E2 E6 Slotevent Programma
Qo E E2 E6 Slotevent ProgrammaQo E E2 E6 Slotevent Programma
Qo E E2 E6 Slotevent Programma
 

Semelhante a 2008 brokerage 04 smart vision system [compatibility mode]

“Tools for Creating Next-Gen Computer Vision Apps on Snapdragon,” a Presentat...
“Tools for Creating Next-Gen Computer Vision Apps on Snapdragon,” a Presentat...“Tools for Creating Next-Gen Computer Vision Apps on Snapdragon,” a Presentat...
“Tools for Creating Next-Gen Computer Vision Apps on Snapdragon,” a Presentat...
Edge AI and Vision Alliance
 
PCI Geomatics Overview
PCI Geomatics OverviewPCI Geomatics Overview
PCI Geomatics Overview
Pci Geomatics
 
Scrambling For Video Surveillance
Scrambling For Video SurveillanceScrambling For Video Surveillance
Scrambling For Video Surveillance
Kobi Magnezi
 
Fujifilm - e2v L3 Vision
Fujifilm - e2v L3 VisionFujifilm - e2v L3 Vision
Fujifilm - e2v L3 Vision
Bernard Genoud
 
Gentek Introduce(en)
Gentek Introduce(en)Gentek Introduce(en)
Gentek Introduce(en)
cloudmmog
 
Discrete cosine transform
Discrete cosine transformDiscrete cosine transform
Discrete cosine transform
Aniruddh Tyagi
 
Discrete cosine transform
Discrete cosine transformDiscrete cosine transform
Discrete cosine transform
aniruddh Tyagi
 
Advanced Silverlight
Advanced SilverlightAdvanced Silverlight
Advanced Silverlight
rsnarayanan
 

Semelhante a 2008 brokerage 04 smart vision system [compatibility mode] (20)

“Tools for Creating Next-Gen Computer Vision Apps on Snapdragon,” a Presentat...
“Tools for Creating Next-Gen Computer Vision Apps on Snapdragon,” a Presentat...“Tools for Creating Next-Gen Computer Vision Apps on Snapdragon,” a Presentat...
“Tools for Creating Next-Gen Computer Vision Apps on Snapdragon,” a Presentat...
 
PCI Geomatics Overview
PCI Geomatics OverviewPCI Geomatics Overview
PCI Geomatics Overview
 
High-Level Synthesis Skill Development Needs - IEDEC
High-Level Synthesis Skill Development Needs - IEDECHigh-Level Synthesis Skill Development Needs - IEDEC
High-Level Synthesis Skill Development Needs - IEDEC
 
Scrambling For Video Surveillance
Scrambling For Video SurveillanceScrambling For Video Surveillance
Scrambling For Video Surveillance
 
IMAGE PROCESSING
IMAGE PROCESSINGIMAGE PROCESSING
IMAGE PROCESSING
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002
 
Imaging automotive 2015 addfor v002
Imaging automotive 2015   addfor v002Imaging automotive 2015   addfor v002
Imaging automotive 2015 addfor v002
 
Hardware Accelerated 2D Rendering for Android
Hardware Accelerated 2D Rendering for AndroidHardware Accelerated 2D Rendering for Android
Hardware Accelerated 2D Rendering for Android
 
Remote Graphical Rendering
Remote Graphical RenderingRemote Graphical Rendering
Remote Graphical Rendering
 
How To Make Multi-Robots Formation Control System
How To Make Multi-Robots Formation Control SystemHow To Make Multi-Robots Formation Control System
How To Make Multi-Robots Formation Control System
 
Fujifilm - e2v L3 Vision
Fujifilm - e2v L3 VisionFujifilm - e2v L3 Vision
Fujifilm - e2v L3 Vision
 
Training Videovigilancia IP: Capture
Training Videovigilancia IP: CaptureTraining Videovigilancia IP: Capture
Training Videovigilancia IP: Capture
 
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
 
Gentek Introduce(en)
Gentek Introduce(en)Gentek Introduce(en)
Gentek Introduce(en)
 
Kinect v1+Processing workshot fabcafe_taipei
Kinect v1+Processing workshot fabcafe_taipeiKinect v1+Processing workshot fabcafe_taipei
Kinect v1+Processing workshot fabcafe_taipei
 
System-on-Chip Programmable Retina
System-on-Chip Programmable RetinaSystem-on-Chip Programmable Retina
System-on-Chip Programmable Retina
 
Discrete cosine transform
Discrete cosine transformDiscrete cosine transform
Discrete cosine transform
 
Discrete cosine transform
Discrete cosine transformDiscrete cosine transform
Discrete cosine transform
 
Advanced Silverlight
Advanced SilverlightAdvanced Silverlight
Advanced Silverlight
 
GLS-1000
GLS-1000GLS-1000
GLS-1000
 

Mais de imec.archive

iMinds-iLab.o, Open Innovation in ICT
iMinds-iLab.o, Open Innovation in ICTiMinds-iLab.o, Open Innovation in ICT
iMinds-iLab.o, Open Innovation in ICT
imec.archive
 
The Connected Smart Cities Network and Living Labs - Towards Horizon 2020 - K...
The Connected Smart Cities Network and Living Labs - Towards Horizon 2020 - K...The Connected Smart Cities Network and Living Labs - Towards Horizon 2020 - K...
The Connected Smart Cities Network and Living Labs - Towards Horizon 2020 - K...
imec.archive
 
Apollon-23/05/2012-9u30- Parallell session: Living Labs added value
Apollon-23/05/2012-9u30- Parallell session: Living Labs added value  Apollon-23/05/2012-9u30- Parallell session: Living Labs added value
Apollon-23/05/2012-9u30- Parallell session: Living Labs added value
imec.archive
 
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across bordersApollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
imec.archive
 
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future InternetApollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
imec.archive
 
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future InternetApollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
imec.archive
 
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future InternetApollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
imec.archive
 
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future InternetApollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
imec.archive
 
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across bordersApollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
imec.archive
 
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation EcosystemsApollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
imec.archive
 
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation EcosystemsApollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
imec.archive
 

Mais de imec.archive (20)

iMinds-iLab.o, Open Innovation in ICT
iMinds-iLab.o, Open Innovation in ICTiMinds-iLab.o, Open Innovation in ICT
iMinds-iLab.o, Open Innovation in ICT
 
Accio presentation closing event
Accio presentation closing eventAccio presentation closing event
Accio presentation closing event
 
PRoF+ Patient Room of the Future
PRoF+ Patient Room of the FuturePRoF+ Patient Room of the Future
PRoF+ Patient Room of the Future
 
Results of the Apollon pilot in homecare and independent living
Results of the Apollon pilot in homecare and independent livingResults of the Apollon pilot in homecare and independent living
Results of the Apollon pilot in homecare and independent living
 
Delivery of feedback on Health, Home Security and Home Energy in Aware Homes ...
Delivery of feedback on Health, Home Security and Home Energy in Aware Homes ...Delivery of feedback on Health, Home Security and Home Energy in Aware Homes ...
Delivery of feedback on Health, Home Security and Home Energy in Aware Homes ...
 
NMMU-Emmanuel Haven Living Lab
NMMU-Emmanuel Haven Living LabNMMU-Emmanuel Haven Living Lab
NMMU-Emmanuel Haven Living Lab
 
The Humanicité workshops
The Humanicité workshopsThe Humanicité workshops
The Humanicité workshops
 
A Real-World Experimentation Platform
A Real-World Experimentation PlatformA Real-World Experimentation Platform
A Real-World Experimentation Platform
 
ENoLL @ AAL Forum 2012
ENoLL @ AAL Forum 2012ENoLL @ AAL Forum 2012
ENoLL @ AAL Forum 2012
 
The Connected Smart Cities Network and Living Labs - Towards Horizon 2020 - K...
The Connected Smart Cities Network and Living Labs - Towards Horizon 2020 - K...The Connected Smart Cities Network and Living Labs - Towards Horizon 2020 - K...
The Connected Smart Cities Network and Living Labs - Towards Horizon 2020 - K...
 
Apollon-23/05/2012-9u30- Parallell session: Living Labs added value
Apollon-23/05/2012-9u30- Parallell session: Living Labs added value  Apollon-23/05/2012-9u30- Parallell session: Living Labs added value
Apollon-23/05/2012-9u30- Parallell session: Living Labs added value
 
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across bordersApollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
 
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future InternetApollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
 
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future InternetApollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
 
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future InternetApollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
 
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future InternetApollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
Apollon - 22/5/12 - 16:00 - Smart Open Cities and the Future Internet
 
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across bordersApollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
Apollon - 22/5/12 - 11:30 - Local SME's - Innovating Across borders
 
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation EcosystemsApollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
 
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation EcosystemsApollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
 
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation EcosystemsApollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
Apollon - 22/5/12 - 09:00 - User-driven Open Innovation Ecosystems
 

2008 brokerage 04 smart vision system [compatibility mode]

  • 1. Smart Vision System: Design of Application Algorithm-Architecture Eric Delfosse IBBT-NES-IMEC
  • 2. What are Smart Vision Systems? Systems that embed intelligence through advanced image processing to: Enhance visual user experience Improve natural interaction Facilitate decision making for complex events …
  • 3. Enhance visual user experience Multi-camera 3D image reconstruction for advanced surveillance 3D GPS (IBBT GBO ISYSS) (IBBT GBO URBAN)
  • 4. Increase natural interaction Natural human-machine interface through gesture recognition 3D (immersive) video (IBBT GBO Hi-Masquerade) conferencing
  • 5. Facilitate decision making for complex events Event detection for surveillance applications (IBBT GBO ISYSS) Traffic sign recognition for driver assistance (IBBT GBO URBAN)
  • 6. Different applications, different requirements Throughput High resolution High framerate Functionality Accuracy Reduce false negatives and false positives … Size Low Power Solar energy Avoid active cooling ... Cost
  • 7. These applications require increasingly complex algorithms Exponential algorithmic complexity increase > 9000 3000 2500 Complexity (Ops/pixel) 2000 1500 1000 500 0 enhancement extraction Depth extraction Edge detection AVC encoding Object detection understanding Feature Image Image Algorithm
  • 8. Diversity of platform architectures with different characteristics PC + GPU High performance High power Limited portability (laptop) … Server rack Embedded systems Very high performance Very high Power Medium performance Non-portable Low power … High portability …
  • 9. Smart Vision Systems design = Matching Application – Algorithm - Architecture Application (Requirements) Algorithm Architecture (Complexity) (Constraints)
  • 10. Smart Vision Systems design = Matching Application – Algorithm - Architecture Application (Requirements) Algorithm Architecture (Complexity) (Constraints)
  • 11. Smart Vision Systems design = Matching Application – Algorithm - Architecture Application (Requirements) Algorithm Architecture (Complexity) Introduce parallelism (Constraints) Processor optimizations
  • 12. Complexity - Quality trade-off: reduce complexity with limited (visual) quality loss
  • 13. Matching Algorithm and Architecture: the DCT example f0 F0 f1 F1 f2 F2 f3 F3 f4 F4 f5 F5 f6 F6 f7 F7 Classical DCT Butterfly DCT 64 multiplications 20 multiplications 64 additions 26 additions High regularity Low regularity Ideal for: Ideal for:
  • 14. Smart Vision Systems design = Matching Application – Algorithm - Architecture Companies Application (Requirements) IBBT Algorithm Architecture (Complexity) (Constraints)
  • 15. Conclusions Smart Vision Systems: Enable new applications Require new complex algorithms Use diverse platform architectures Successful design requires competences on these 3 aspects IBBT brings these competences together
  • 17. Demo 1: 3D video through real-time viewpoint interpolation Viewpoint interpolation: a) stereo capturing b) depth extraction c) interpolation Autostereoscopic displays: require multiple (interpolated) views
  • 18. Demo 2: Eye-gaze corrected video chatting Webcam Computer Display
  • 19. Demo 3: Novel 3D Camera prototype and monitoring application in elderly environment