SlideShare a Scribd company logo
1 of 19
Download to read offline
3D Scene Accessibility For The Blind
 Via Auditory-Multitouch Interfaces
    Juan D. Gomez, Sinan Mohammed, Guido Bologna and Thierry Pun



            UNIVERSITY OF GENEVA,
       COMPUTER VISION & MULTIMEDIA LAB
                     CVML


                         University   Computer vision &
                         of Geneva     Multimedia Lab




        28-30 November 2011 in Brussels, Belgium
“Object Detection”
The annual PASCAL Visual Objects Challenge
“Object Detection”
The annual PASCAL Visual Objects Challenge
V. Hedau, D. Hoiem, D.Forsyth,
“Recovering the Spatial Layout of Cluttered Rooms”
   IEEE International Conference on Computer Vision (ICCV), 2009.
S.Y. Bao, M. Sun, S.Savarese.
       “Coherent Object Detection And
        Scene Layout Understanding”
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
Gomez, J., Mohammed, S., Bologna, G. and Pun, T.
“Toward 3D Scene Understanding via Audio-description:
     Kinect-iPad fusion for the visually impaired”
 International Conference on Computers and Accessibility (ASSETS), 2011.



              Preliminary Target Scene
                         Triangle                Circle




                                        Square
                            Cylinder




                      40 cm
Gomez, J., Bologna, G. and Pun, T.
         “A virtual ceiling mounted depth-camera
                using orthographic kinect ”
      IEEE International Conference on Computer Vision (ICCV), 2011.




One-Shot Semiautomatic Kinect Calibration




Before Calibration                                         After Calibration
Gomez, J., Mohammed, S., Bologna, G. and Pun, T.
          “Toward 3D Scene Understanding via Audio-description:
               Kinect-iPad fusion for the visually impaired”
            International Conference on Computers and Accessibility (ASSETS), 2011.




Elements Extraction Via Depth-Based Segmentation




                                                     Layers in which an object was detected after scanning
Layering across the Depth




       Objectless Image
Gomez, J., Mohammed, S., Bologna, G. and Pun, T.
“Toward 3D Scene Understanding via Audio-description:
     Kinect-iPad fusion for the visually impaired”
 International Conference on Computers and Accessibility (ASSETS), 2011.



     Neural-Based Object Recognition

                                     4 features per Object:

                                     Features’ values range from 0 to 1. [0,1].
                                     Weights equal to 1, features are of same importance.
                                     All features are scale-invariant.
                                     All features are rotation-invariant.




                                    | 1 – (majorAxisLength – minorAxisLength) / majorAxisLength |

                                    perimeter / (majorAxisLength* pi)

                                    | ((pi * Radius2 )-area) / area |

                                    | 1 - | pi*majorAxisLength – perimeter | / perimeter |
Gomez, J., Mohammed, S., Bologna, G. and Pun, T.
          “Toward 3D Scene Understanding via Audio-description:
               Kinect-iPad fusion for the visually impaired”
            International Conference on Computers and Accessibility (ASSETS), 2011.



                    Early Scenary Description




                                   So far:
           Frontal-view gives just relative layout understanding.
   A top-view of the scene is quite desirable to grasp scene distribution.
Wheras frontal distances (depths) are known, lateral distances are still missed.

           How to deliver all this information to the blind user?
Gomez, J., Mohammed, S., Bologna, G. and Pun, T.
           “Toward 3D Scene Understanding via Audio-description:
                Kinect-iPad fusion for the visually impaired”
             International Conference on Computers and Accessibility (ASSETS), 2011.



Delivering Visual Information via Finger-Triggered Audio




    Natural Top-view of the scene     Artificial Top-view of the scene   Traget sensation to be achieved onto iPad




                      iPad holding Artificial Top-view          Target sensation of Spatial Audio
Gomez, J., Bologna, G. and Pun, T.
                 “A virtual ceiling mounted depth-camera
                        using orthographic kinect ”
             IEEE International Conference on Computer Vision (ICCV), 2011.


Deceptive Object Location Caused by Perspective
     Causes Mistaken Spatial Sonification
   And Top-View is Unreacheble despite Depth




  Vanishing Point and Scene Optical Geometry
                                                                       Example
Gomez, J., Bologna, G. and Pun, T.
                                “A virtual ceiling mounted depth-camera
                                       using orthographic kinect ”
                             IEEE International Conference on Computer Vision (ICCV), 2011.



                      Orthographic Vs Perspective Cameras




A perspective camera (bottom-right): Objects further away appear smaller in size, besides the positions vary with the distance.
                An orthographic camera (top-left): Objects preserve natural proportions on size and position.
Gomez, J., Bologna, G. and Pun, T.
        “A virtual ceiling mounted depth-camera
               using orthographic kinect ”
     IEEE International Conference on Computer Vision (ICCV), 2011.



Top-View Based on Virtual Orthographic Cam
Gomez, J., Bologna, G. and Pun, T.
        “A virtual ceiling mounted depth-camera
               using orthographic kinect ”
     IEEE International Conference on Computer Vision (ICCV), 2011.



Top-View Based on Virtual Orthographic Cam
Gomez, J., Bologna, G. and Pun, T.
                              “A virtual ceiling mounted depth-camera
                                     using orthographic kinect ”
                          IEEE International Conference on Computer Vision (ICCV), 2011.



             Top-View Based on Virtual Orthographic Cam




                                                                     Artificial Top-view using virtual orthographic Kinect and
Natural depth map from avobe using virtual orthographic Kinect                       Object recognition methods.
Gomez, J., Mohammed, S., Bologna, G. and Pun, T.
           “Scene accessibility for the blind
 via computer-vision and multi-touch interfaces”
   Conference on Open Accessibility Everywhere (AEGIS), 2011.

Experiments With Blinfoleded Users




 Original Layout             User Guess               Centroids Shifting
Gomez, J., Mohammed, S., Bologna, G. and Pun, T.
                                “Scene accessibility for the blind
                     via computer-vision and multi-touch interfaces”
                         Conference on Open Accessibility Everywhere (AEGIS), 2011.



                                               Results




 X axis represents 30 different scenes with four elements each. Y axis represents the average of the distances (cm)
                           between the original and the final location of the four objects.
              This average distance has been normalized dividing its value by the diagonal (244 cm).
The colors of the bars (scenes) vary according to their exploration time that goes from 0 to 10 minutes (colormap).
                   Each bar shows on top the standard deviation of the four elements’ relocation.
Gomez, J., Mohammed, S., Bologna, G. and Pun, T.
                        “Scene accessibility for the blind
               via computer-vision and multi-touch interfaces”
                  Conference on Open Accessibility Everywhere (AEGIS), 2011.

                                  Conclusions
  The mean error distance on objects’ replacement for all the experiments was 3.3%
 with respect to the diagonal of the table. This is around 8.5 cm of separation between
                      an original object position and its relocation.

  In both cases i.e. scenes with three and four objects, this distance remained
                                   more or less invariant.

       The exploration time varied according the number of elements on the table.
 In average for a scene composed of three elements, 3.4 minutes were enough to build
its layout in mind, whereas for scenes with four elements this time reached 5.4 minutes.

This difference was given due to the increase in the number of sound-colors associations
       to be learned; the results showed no misclassifications of objects though.

          The results presented in this work reveal that the participants
         were capable of grasping general spatial structure of the sonified
               environments and accurately estimate scene layouts.

More Related Content

What's hot

11.lookn learn an ar system of linked video
11.lookn learn an ar system of linked video11.lookn learn an ar system of linked video
11.lookn learn an ar system of linked videoAlexander Decker
 
Lookn learn an ar system of linked video
Lookn learn an ar system of linked videoLookn learn an ar system of linked video
Lookn learn an ar system of linked videoAlexander Decker
 
Real time hand gesture recognition system for dynamic applications
Real time hand gesture recognition system for dynamic applicationsReal time hand gesture recognition system for dynamic applications
Real time hand gesture recognition system for dynamic applicationsijujournal
 
Real time hand gesture recognition system for dynamic applications
Real time hand gesture recognition system for dynamic applicationsReal time hand gesture recognition system for dynamic applications
Real time hand gesture recognition system for dynamic applicationsijujournal
 
Top Cited Articles in Computer Graphics and Animation
Top Cited Articles in Computer Graphics and AnimationTop Cited Articles in Computer Graphics and Animation
Top Cited Articles in Computer Graphics and Animationijcga
 

What's hot (6)

Computer Vision
Computer VisionComputer Vision
Computer Vision
 
11.lookn learn an ar system of linked video
11.lookn learn an ar system of linked video11.lookn learn an ar system of linked video
11.lookn learn an ar system of linked video
 
Lookn learn an ar system of linked video
Lookn learn an ar system of linked videoLookn learn an ar system of linked video
Lookn learn an ar system of linked video
 
Real time hand gesture recognition system for dynamic applications
Real time hand gesture recognition system for dynamic applicationsReal time hand gesture recognition system for dynamic applications
Real time hand gesture recognition system for dynamic applications
 
Real time hand gesture recognition system for dynamic applications
Real time hand gesture recognition system for dynamic applicationsReal time hand gesture recognition system for dynamic applications
Real time hand gesture recognition system for dynamic applications
 
Top Cited Articles in Computer Graphics and Animation
Top Cited Articles in Computer Graphics and AnimationTop Cited Articles in Computer Graphics and Animation
Top Cited Articles in Computer Graphics and Animation
 

Viewers also liked

assisting device for visually impaired person
assisting device for visually impaired personassisting device for visually impaired person
assisting device for visually impaired personPushpa Gothwal
 
All about WEARABLE TECHNOLOGY...By..GEORGE KURIAN POTTACKAL
All about WEARABLE TECHNOLOGY...By..GEORGE KURIAN POTTACKALAll about WEARABLE TECHNOLOGY...By..GEORGE KURIAN POTTACKAL
All about WEARABLE TECHNOLOGY...By..GEORGE KURIAN POTTACKALgeorgekurianpottackal
 
Smart blind stick
Smart blind stickSmart blind stick
Smart blind stickvarsh12345
 
Touchless technology Seminar Presentation
Touchless technology Seminar PresentationTouchless technology Seminar Presentation
Touchless technology Seminar PresentationAparna Nk
 

Viewers also liked (6)

3D printing
3D printing3D printing
3D printing
 
assisting device for visually impaired person
assisting device for visually impaired personassisting device for visually impaired person
assisting device for visually impaired person
 
All about WEARABLE TECHNOLOGY...By..GEORGE KURIAN POTTACKAL
All about WEARABLE TECHNOLOGY...By..GEORGE KURIAN POTTACKALAll about WEARABLE TECHNOLOGY...By..GEORGE KURIAN POTTACKAL
All about WEARABLE TECHNOLOGY...By..GEORGE KURIAN POTTACKAL
 
Smart blind stick
Smart blind stickSmart blind stick
Smart blind stick
 
Finger reader
Finger readerFinger reader
Finger reader
 
Touchless technology Seminar Presentation
Touchless technology Seminar PresentationTouchless technology Seminar Presentation
Touchless technology Seminar Presentation
 

Similar to 27 3 d scene accesibility for the blind via

光学シースルーHMDの高性能化に向けたCV技術活用事例
光学シースルーHMDの高性能化に向けたCV技術活用事例光学シースルーHMDの高性能化に向けたCV技術活用事例
光学シースルーHMDの高性能化に向けたCV技術活用事例Yuta Itoh
 
Using Augmented Reality to Create Empathic Experiences
Using Augmented Reality to Create Empathic ExperiencesUsing Augmented Reality to Create Empathic Experiences
Using Augmented Reality to Create Empathic ExperiencesMark Billinghurst
 
NIPS2009: Understand Visual Scenes - Part 2
NIPS2009: Understand Visual Scenes - Part 2NIPS2009: Understand Visual Scenes - Part 2
NIPS2009: Understand Visual Scenes - Part 2zukun
 
Unleashing the Potentials of Immersive Augmented Reality for Software Enginee...
Unleashing the Potentials of Immersive Augmented Reality for Software Enginee...Unleashing the Potentials of Immersive Augmented Reality for Software Enginee...
Unleashing the Potentials of Immersive Augmented Reality for Software Enginee...Leonel Merino
 
Empathic Computing: New Approaches to Gaming
Empathic Computing: New Approaches to GamingEmpathic Computing: New Approaches to Gaming
Empathic Computing: New Approaches to GamingMark Billinghurst
 
The Reality of Augmented Reality: Are we there yet?
The Reality of Augmented Reality: Are we there yet?The Reality of Augmented Reality: Are we there yet?
The Reality of Augmented Reality: Are we there yet?Mark Billinghurst
 
Human-Computer Interfaces: When will new ones become technically and economic...
Human-Computer Interfaces: When will new ones become technically and economic...Human-Computer Interfaces: When will new ones become technically and economic...
Human-Computer Interfaces: When will new ones become technically and economic...Jeffrey Funk
 
Future Research Directions for Augmented Reality
Future Research Directions for Augmented RealityFuture Research Directions for Augmented Reality
Future Research Directions for Augmented RealityMark Billinghurst
 
Natural Interaction for Augmented Reality Applications
Natural Interaction for Augmented Reality ApplicationsNatural Interaction for Augmented Reality Applications
Natural Interaction for Augmented Reality ApplicationsMark Billinghurst
 
Introduction to UVR Lab 2.0
Introduction to UVR Lab 2.0Introduction to UVR Lab 2.0
Introduction to UVR Lab 2.0Woontack Woo
 
Tangible AR Interface
Tangible AR InterfaceTangible AR Interface
Tangible AR InterfaceJongHyoun
 
Video Browsing By Direct Manipulation - Draft 1
Video Browsing By Direct Manipulation - Draft 1Video Browsing By Direct Manipulation - Draft 1
Video Browsing By Direct Manipulation - Draft 1Vashira Ravipanich
 
Beautiful Mind: iPhone Anatomy & Architecture
Beautiful Mind: iPhone Anatomy & ArchitectureBeautiful Mind: iPhone Anatomy & Architecture
Beautiful Mind: iPhone Anatomy & ArchitectureBess Ho
 
COSC 426 Lect. 8: AR Research Directions
COSC 426 Lect. 8: AR Research DirectionsCOSC 426 Lect. 8: AR Research Directions
COSC 426 Lect. 8: AR Research DirectionsMark Billinghurst
 
Initial Project Presentation
Initial Project Presentation  Initial Project Presentation
Initial Project Presentation Colm Walsh
 
Unfolding Data - Interaction Design for Visualizations of Geospatial Data
Unfolding Data - Interaction Design for Visualizations of Geospatial DataUnfolding Data - Interaction Design for Visualizations of Geospatial Data
Unfolding Data - Interaction Design for Visualizations of Geospatial DataTill Nagel
 

Similar to 27 3 d scene accesibility for the blind via (20)

Mobile interactions
Mobile interactionsMobile interactions
Mobile interactions
 
光学シースルーHMDの高性能化に向けたCV技術活用事例
光学シースルーHMDの高性能化に向けたCV技術活用事例光学シースルーHMDの高性能化に向けたCV技術活用事例
光学シースルーHMDの高性能化に向けたCV技術活用事例
 
Using Augmented Reality to Create Empathic Experiences
Using Augmented Reality to Create Empathic ExperiencesUsing Augmented Reality to Create Empathic Experiences
Using Augmented Reality to Create Empathic Experiences
 
NIPS2009: Understand Visual Scenes - Part 2
NIPS2009: Understand Visual Scenes - Part 2NIPS2009: Understand Visual Scenes - Part 2
NIPS2009: Understand Visual Scenes - Part 2
 
Unleashing the Potentials of Immersive Augmented Reality for Software Enginee...
Unleashing the Potentials of Immersive Augmented Reality for Software Enginee...Unleashing the Potentials of Immersive Augmented Reality for Software Enginee...
Unleashing the Potentials of Immersive Augmented Reality for Software Enginee...
 
Empathic Computing: New Approaches to Gaming
Empathic Computing: New Approaches to GamingEmpathic Computing: New Approaches to Gaming
Empathic Computing: New Approaches to Gaming
 
The Reality of Augmented Reality: Are we there yet?
The Reality of Augmented Reality: Are we there yet?The Reality of Augmented Reality: Are we there yet?
The Reality of Augmented Reality: Are we there yet?
 
Human-Computer Interfaces: When will new ones become technically and economic...
Human-Computer Interfaces: When will new ones become technically and economic...Human-Computer Interfaces: When will new ones become technically and economic...
Human-Computer Interfaces: When will new ones become technically and economic...
 
Future Research Directions for Augmented Reality
Future Research Directions for Augmented RealityFuture Research Directions for Augmented Reality
Future Research Directions for Augmented Reality
 
Natural Interaction for Augmented Reality Applications
Natural Interaction for Augmented Reality ApplicationsNatural Interaction for Augmented Reality Applications
Natural Interaction for Augmented Reality Applications
 
Alvaro Cassinelli / Meta Perception Group leader
Alvaro Cassinelli / Meta Perception Group leaderAlvaro Cassinelli / Meta Perception Group leader
Alvaro Cassinelli / Meta Perception Group leader
 
Introduction to UVR Lab 2.0
Introduction to UVR Lab 2.0Introduction to UVR Lab 2.0
Introduction to UVR Lab 2.0
 
Tangible AR Interface
Tangible AR InterfaceTangible AR Interface
Tangible AR Interface
 
Video Browsing By Direct Manipulation - Draft 1
Video Browsing By Direct Manipulation - Draft 1Video Browsing By Direct Manipulation - Draft 1
Video Browsing By Direct Manipulation - Draft 1
 
Beautiful Mind: iPhone Anatomy & Architecture
Beautiful Mind: iPhone Anatomy & ArchitectureBeautiful Mind: iPhone Anatomy & Architecture
Beautiful Mind: iPhone Anatomy & Architecture
 
COSC 426 Lect. 8: AR Research Directions
COSC 426 Lect. 8: AR Research DirectionsCOSC 426 Lect. 8: AR Research Directions
COSC 426 Lect. 8: AR Research Directions
 
Initial Project Presentation
Initial Project Presentation  Initial Project Presentation
Initial Project Presentation
 
1.pdf
1.pdf1.pdf
1.pdf
 
Unfolding Data - Interaction Design for Visualizations of Geospatial Data
Unfolding Data - Interaction Design for Visualizations of Geospatial DataUnfolding Data - Interaction Design for Visualizations of Geospatial Data
Unfolding Data - Interaction Design for Visualizations of Geospatial Data
 
Can You See What I See?
Can You See What I See?Can You See What I See?
Can You See What I See?
 

More from AEGIS-ACCESSIBLE Projects

Aegis concertation - 2nd International AEGIS conference
Aegis concertation - 2nd International AEGIS conferenceAegis concertation - 2nd International AEGIS conference
Aegis concertation - 2nd International AEGIS conferenceAEGIS-ACCESSIBLE Projects
 
Mobile applications (Panagiotis Tsoris, Steficon)
Mobile applications (Panagiotis Tsoris, Steficon)Mobile applications (Panagiotis Tsoris, Steficon)
Mobile applications (Panagiotis Tsoris, Steficon)AEGIS-ACCESSIBLE Projects
 
ViPi platform technologies and integration pathway (Karel Van Isacker, Phoeni...
ViPi platform technologies and integration pathway (Karel Van Isacker, Phoeni...ViPi platform technologies and integration pathway (Karel Van Isacker, Phoeni...
ViPi platform technologies and integration pathway (Karel Van Isacker, Phoeni...AEGIS-ACCESSIBLE Projects
 
Basic ICT Training curriculum (Andy Burton, NTU)
Basic ICT Training curriculum (Andy Burton, NTU)Basic ICT Training curriculum (Andy Burton, NTU)
Basic ICT Training curriculum (Andy Burton, NTU)AEGIS-ACCESSIBLE Projects
 
General introduction of the ViPi project (Karel Van Isacker, PhoenixKM)
General introduction of the ViPi project (Karel Van Isacker, PhoenixKM)General introduction of the ViPi project (Karel Van Isacker, PhoenixKM)
General introduction of the ViPi project (Karel Van Isacker, PhoenixKM)AEGIS-ACCESSIBLE Projects
 
Semantic Content Management enhancements (George Milis, G.M EuroCy Innovation...
Semantic Content Management enhancements (George Milis, G.M EuroCy Innovation...Semantic Content Management enhancements (George Milis, G.M EuroCy Innovation...
Semantic Content Management enhancements (George Milis, G.M EuroCy Innovation...AEGIS-ACCESSIBLE Projects
 
Gelijke kansen op informatie, toegankelijke documenten en communicatiekanalen...
Gelijke kansen op informatie, toegankelijke documenten en communicatiekanalen...Gelijke kansen op informatie, toegankelijke documenten en communicatiekanalen...
Gelijke kansen op informatie, toegankelijke documenten en communicatiekanalen...AEGIS-ACCESSIBLE Projects
 
AEGIS SP4 story - building an accessible mobile application
AEGIS SP4 story - building an accessible mobile applicationAEGIS SP4 story - building an accessible mobile application
AEGIS SP4 story - building an accessible mobile applicationAEGIS-ACCESSIBLE Projects
 
AEGIS SP3 story - building an accessible web application
AEGIS SP3 story - building an accessible web applicationAEGIS SP3 story - building an accessible web application
AEGIS SP3 story - building an accessible web applicationAEGIS-ACCESSIBLE Projects
 
Conference proceedings 2011 AEGIS International Workshop and Conference
Conference proceedings 2011 AEGIS International Workshop and ConferenceConference proceedings 2011 AEGIS International Workshop and Conference
Conference proceedings 2011 AEGIS International Workshop and ConferenceAEGIS-ACCESSIBLE Projects
 

More from AEGIS-ACCESSIBLE Projects (20)

Newsletter 7 AEGIS project
Newsletter 7 AEGIS projectNewsletter 7 AEGIS project
Newsletter 7 AEGIS project
 
Veritas newsletter no 5 final
Veritas newsletter no 5 finalVeritas newsletter no 5 final
Veritas newsletter no 5 final
 
Aegis concertation - 2nd International AEGIS conference
Aegis concertation - 2nd International AEGIS conferenceAegis concertation - 2nd International AEGIS conference
Aegis concertation - 2nd International AEGIS conference
 
Mobile applications (Panagiotis Tsoris, Steficon)
Mobile applications (Panagiotis Tsoris, Steficon)Mobile applications (Panagiotis Tsoris, Steficon)
Mobile applications (Panagiotis Tsoris, Steficon)
 
ViPi platform technologies and integration pathway (Karel Van Isacker, Phoeni...
ViPi platform technologies and integration pathway (Karel Van Isacker, Phoeni...ViPi platform technologies and integration pathway (Karel Van Isacker, Phoeni...
ViPi platform technologies and integration pathway (Karel Van Isacker, Phoeni...
 
Basic ICT Training curriculum (Andy Burton, NTU)
Basic ICT Training curriculum (Andy Burton, NTU)Basic ICT Training curriculum (Andy Burton, NTU)
Basic ICT Training curriculum (Andy Burton, NTU)
 
ViPi Survey (Andy Burton, NTU)
ViPi Survey (Andy Burton, NTU)ViPi Survey (Andy Burton, NTU)
ViPi Survey (Andy Burton, NTU)
 
General introduction of the ViPi project (Karel Van Isacker, PhoenixKM)
General introduction of the ViPi project (Karel Van Isacker, PhoenixKM)General introduction of the ViPi project (Karel Van Isacker, PhoenixKM)
General introduction of the ViPi project (Karel Van Isacker, PhoenixKM)
 
Semantic Content Management enhancements (George Milis, G.M EuroCy Innovation...
Semantic Content Management enhancements (George Milis, G.M EuroCy Innovation...Semantic Content Management enhancements (George Milis, G.M EuroCy Innovation...
Semantic Content Management enhancements (George Milis, G.M EuroCy Innovation...
 
Gelijke kansen op informatie, toegankelijke documenten en communicatiekanalen...
Gelijke kansen op informatie, toegankelijke documenten en communicatiekanalen...Gelijke kansen op informatie, toegankelijke documenten en communicatiekanalen...
Gelijke kansen op informatie, toegankelijke documenten en communicatiekanalen...
 
AEGIS SP4 story - building an accessible mobile application
AEGIS SP4 story - building an accessible mobile applicationAEGIS SP4 story - building an accessible mobile application
AEGIS SP4 story - building an accessible mobile application
 
AEGIS SP3 story - building an accessible web application
AEGIS SP3 story - building an accessible web applicationAEGIS SP3 story - building an accessible web application
AEGIS SP3 story - building an accessible web application
 
ACCESSIBLE newsletter n° 6
ACCESSIBLE newsletter n° 6ACCESSIBLE newsletter n° 6
ACCESSIBLE newsletter n° 6
 
AEGIS Newsletter n° 6
AEGIS Newsletter n° 6AEGIS Newsletter n° 6
AEGIS Newsletter n° 6
 
VERITAS newsletter n° 3
VERITAS newsletter n° 3VERITAS newsletter n° 3
VERITAS newsletter n° 3
 
VERITAS newsletter n° 2
VERITAS newsletter n° 2VERITAS newsletter n° 2
VERITAS newsletter n° 2
 
VERITAS newsletter n° 4
VERITAS newsletter n° 4VERITAS newsletter n° 4
VERITAS newsletter n° 4
 
Conference proceedings 2011 AEGIS International Workshop and Conference
Conference proceedings 2011 AEGIS International Workshop and ConferenceConference proceedings 2011 AEGIS International Workshop and Conference
Conference proceedings 2011 AEGIS International Workshop and Conference
 
Aegis concertation certh
Aegis concertation certhAegis concertation certh
Aegis concertation certh
 
Veritas iti aegis_conf
Veritas iti aegis_confVeritas iti aegis_conf
Veritas iti aegis_conf
 

Recently uploaded

9599632723 Top Call Girls in Delhi at your Door Step Available 24x7 Delhi
9599632723 Top Call Girls in Delhi at your Door Step Available 24x7 Delhi9599632723 Top Call Girls in Delhi at your Door Step Available 24x7 Delhi
9599632723 Top Call Girls in Delhi at your Door Step Available 24x7 DelhiCall Girls in Delhi
 
A305_A2_file_Batkhuu progress report.pdf
A305_A2_file_Batkhuu progress report.pdfA305_A2_file_Batkhuu progress report.pdf
A305_A2_file_Batkhuu progress report.pdftbatkhuu1
 
It will be International Nurses' Day on 12 May
It will be International Nurses' Day on 12 MayIt will be International Nurses' Day on 12 May
It will be International Nurses' Day on 12 MayNZSG
 
Insurers' journeys to build a mastery in the IoT usage
Insurers' journeys to build a mastery in the IoT usageInsurers' journeys to build a mastery in the IoT usage
Insurers' journeys to build a mastery in the IoT usageMatteo Carbone
 
Call Girls In Holiday Inn Express Gurugram➥99902@11544 ( Best price)100% Genu...
Call Girls In Holiday Inn Express Gurugram➥99902@11544 ( Best price)100% Genu...Call Girls In Holiday Inn Express Gurugram➥99902@11544 ( Best price)100% Genu...
Call Girls In Holiday Inn Express Gurugram➥99902@11544 ( Best price)100% Genu...lizamodels9
 
Understanding the Pakistan Budgeting Process: Basics and Key Insights
Understanding the Pakistan Budgeting Process: Basics and Key InsightsUnderstanding the Pakistan Budgeting Process: Basics and Key Insights
Understanding the Pakistan Budgeting Process: Basics and Key Insightsseri bangash
 
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...Dipal Arora
 
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...lizamodels9
 
Mondelez State of Snacking and Future Trends 2023
Mondelez State of Snacking and Future Trends 2023Mondelez State of Snacking and Future Trends 2023
Mondelez State of Snacking and Future Trends 2023Neil Kimberley
 
Monte Carlo simulation : Simulation using MCSM
Monte Carlo simulation : Simulation using MCSMMonte Carlo simulation : Simulation using MCSM
Monte Carlo simulation : Simulation using MCSMRavindra Nath Shukla
 
The Coffee Bean & Tea Leaf(CBTL), Business strategy case study
The Coffee Bean & Tea Leaf(CBTL), Business strategy case studyThe Coffee Bean & Tea Leaf(CBTL), Business strategy case study
The Coffee Bean & Tea Leaf(CBTL), Business strategy case studyEthan lee
 
Monthly Social Media Update April 2024 pptx.pptx
Monthly Social Media Update April 2024 pptx.pptxMonthly Social Media Update April 2024 pptx.pptx
Monthly Social Media Update April 2024 pptx.pptxAndy Lambert
 
The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...
The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...
The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...Aggregage
 
Regression analysis: Simple Linear Regression Multiple Linear Regression
Regression analysis:  Simple Linear Regression Multiple Linear RegressionRegression analysis:  Simple Linear Regression Multiple Linear Regression
Regression analysis: Simple Linear Regression Multiple Linear RegressionRavindra Nath Shukla
 
Unlocking the Secrets of Affiliate Marketing.pdf
Unlocking the Secrets of Affiliate Marketing.pdfUnlocking the Secrets of Affiliate Marketing.pdf
Unlocking the Secrets of Affiliate Marketing.pdfOnline Income Engine
 
Call Girls in Gomti Nagar - 7388211116 - With room Service
Call Girls in Gomti Nagar - 7388211116  - With room ServiceCall Girls in Gomti Nagar - 7388211116  - With room Service
Call Girls in Gomti Nagar - 7388211116 - With room Servicediscovermytutordmt
 
MONA 98765-12871 CALL GIRLS IN LUDHIANA LUDHIANA CALL GIRL
MONA 98765-12871 CALL GIRLS IN LUDHIANA LUDHIANA CALL GIRLMONA 98765-12871 CALL GIRLS IN LUDHIANA LUDHIANA CALL GIRL
MONA 98765-12871 CALL GIRLS IN LUDHIANA LUDHIANA CALL GIRLSeo
 
HONOR Veterans Event Keynote by Michael Hawkins
HONOR Veterans Event Keynote by Michael HawkinsHONOR Veterans Event Keynote by Michael Hawkins
HONOR Veterans Event Keynote by Michael HawkinsMichael W. Hawkins
 
0183760ssssssssssssssssssssssssssss00101011 (27).pdf
0183760ssssssssssssssssssssssssssss00101011 (27).pdf0183760ssssssssssssssssssssssssssss00101011 (27).pdf
0183760ssssssssssssssssssssssssssss00101011 (27).pdfRenandantas16
 
B.COM Unit – 4 ( CORPORATE SOCIAL RESPONSIBILITY ( CSR ).pptx
B.COM Unit – 4 ( CORPORATE SOCIAL RESPONSIBILITY ( CSR ).pptxB.COM Unit – 4 ( CORPORATE SOCIAL RESPONSIBILITY ( CSR ).pptx
B.COM Unit – 4 ( CORPORATE SOCIAL RESPONSIBILITY ( CSR ).pptxpriyanshujha201
 

Recently uploaded (20)

9599632723 Top Call Girls in Delhi at your Door Step Available 24x7 Delhi
9599632723 Top Call Girls in Delhi at your Door Step Available 24x7 Delhi9599632723 Top Call Girls in Delhi at your Door Step Available 24x7 Delhi
9599632723 Top Call Girls in Delhi at your Door Step Available 24x7 Delhi
 
A305_A2_file_Batkhuu progress report.pdf
A305_A2_file_Batkhuu progress report.pdfA305_A2_file_Batkhuu progress report.pdf
A305_A2_file_Batkhuu progress report.pdf
 
It will be International Nurses' Day on 12 May
It will be International Nurses' Day on 12 MayIt will be International Nurses' Day on 12 May
It will be International Nurses' Day on 12 May
 
Insurers' journeys to build a mastery in the IoT usage
Insurers' journeys to build a mastery in the IoT usageInsurers' journeys to build a mastery in the IoT usage
Insurers' journeys to build a mastery in the IoT usage
 
Call Girls In Holiday Inn Express Gurugram➥99902@11544 ( Best price)100% Genu...
Call Girls In Holiday Inn Express Gurugram➥99902@11544 ( Best price)100% Genu...Call Girls In Holiday Inn Express Gurugram➥99902@11544 ( Best price)100% Genu...
Call Girls In Holiday Inn Express Gurugram➥99902@11544 ( Best price)100% Genu...
 
Understanding the Pakistan Budgeting Process: Basics and Key Insights
Understanding the Pakistan Budgeting Process: Basics and Key InsightsUnderstanding the Pakistan Budgeting Process: Basics and Key Insights
Understanding the Pakistan Budgeting Process: Basics and Key Insights
 
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
 
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
 
Mondelez State of Snacking and Future Trends 2023
Mondelez State of Snacking and Future Trends 2023Mondelez State of Snacking and Future Trends 2023
Mondelez State of Snacking and Future Trends 2023
 
Monte Carlo simulation : Simulation using MCSM
Monte Carlo simulation : Simulation using MCSMMonte Carlo simulation : Simulation using MCSM
Monte Carlo simulation : Simulation using MCSM
 
The Coffee Bean & Tea Leaf(CBTL), Business strategy case study
The Coffee Bean & Tea Leaf(CBTL), Business strategy case studyThe Coffee Bean & Tea Leaf(CBTL), Business strategy case study
The Coffee Bean & Tea Leaf(CBTL), Business strategy case study
 
Monthly Social Media Update April 2024 pptx.pptx
Monthly Social Media Update April 2024 pptx.pptxMonthly Social Media Update April 2024 pptx.pptx
Monthly Social Media Update April 2024 pptx.pptx
 
The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...
The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...
The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...
 
Regression analysis: Simple Linear Regression Multiple Linear Regression
Regression analysis:  Simple Linear Regression Multiple Linear RegressionRegression analysis:  Simple Linear Regression Multiple Linear Regression
Regression analysis: Simple Linear Regression Multiple Linear Regression
 
Unlocking the Secrets of Affiliate Marketing.pdf
Unlocking the Secrets of Affiliate Marketing.pdfUnlocking the Secrets of Affiliate Marketing.pdf
Unlocking the Secrets of Affiliate Marketing.pdf
 
Call Girls in Gomti Nagar - 7388211116 - With room Service
Call Girls in Gomti Nagar - 7388211116  - With room ServiceCall Girls in Gomti Nagar - 7388211116  - With room Service
Call Girls in Gomti Nagar - 7388211116 - With room Service
 
MONA 98765-12871 CALL GIRLS IN LUDHIANA LUDHIANA CALL GIRL
MONA 98765-12871 CALL GIRLS IN LUDHIANA LUDHIANA CALL GIRLMONA 98765-12871 CALL GIRLS IN LUDHIANA LUDHIANA CALL GIRL
MONA 98765-12871 CALL GIRLS IN LUDHIANA LUDHIANA CALL GIRL
 
HONOR Veterans Event Keynote by Michael Hawkins
HONOR Veterans Event Keynote by Michael HawkinsHONOR Veterans Event Keynote by Michael Hawkins
HONOR Veterans Event Keynote by Michael Hawkins
 
0183760ssssssssssssssssssssssssssss00101011 (27).pdf
0183760ssssssssssssssssssssssssssss00101011 (27).pdf0183760ssssssssssssssssssssssssssss00101011 (27).pdf
0183760ssssssssssssssssssssssssssss00101011 (27).pdf
 
B.COM Unit – 4 ( CORPORATE SOCIAL RESPONSIBILITY ( CSR ).pptx
B.COM Unit – 4 ( CORPORATE SOCIAL RESPONSIBILITY ( CSR ).pptxB.COM Unit – 4 ( CORPORATE SOCIAL RESPONSIBILITY ( CSR ).pptx
B.COM Unit – 4 ( CORPORATE SOCIAL RESPONSIBILITY ( CSR ).pptx
 

27 3 d scene accesibility for the blind via

  • 1. 3D Scene Accessibility For The Blind Via Auditory-Multitouch Interfaces Juan D. Gomez, Sinan Mohammed, Guido Bologna and Thierry Pun UNIVERSITY OF GENEVA, COMPUTER VISION & MULTIMEDIA LAB CVML University Computer vision & of Geneva Multimedia Lab 28-30 November 2011 in Brussels, Belgium
  • 2. “Object Detection” The annual PASCAL Visual Objects Challenge
  • 3. “Object Detection” The annual PASCAL Visual Objects Challenge
  • 4. V. Hedau, D. Hoiem, D.Forsyth, “Recovering the Spatial Layout of Cluttered Rooms” IEEE International Conference on Computer Vision (ICCV), 2009.
  • 5. S.Y. Bao, M. Sun, S.Savarese. “Coherent Object Detection And Scene Layout Understanding” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
  • 6. Gomez, J., Mohammed, S., Bologna, G. and Pun, T. “Toward 3D Scene Understanding via Audio-description: Kinect-iPad fusion for the visually impaired” International Conference on Computers and Accessibility (ASSETS), 2011. Preliminary Target Scene Triangle Circle Square Cylinder 40 cm
  • 7. Gomez, J., Bologna, G. and Pun, T. “A virtual ceiling mounted depth-camera using orthographic kinect ” IEEE International Conference on Computer Vision (ICCV), 2011. One-Shot Semiautomatic Kinect Calibration Before Calibration After Calibration
  • 8. Gomez, J., Mohammed, S., Bologna, G. and Pun, T. “Toward 3D Scene Understanding via Audio-description: Kinect-iPad fusion for the visually impaired” International Conference on Computers and Accessibility (ASSETS), 2011. Elements Extraction Via Depth-Based Segmentation Layers in which an object was detected after scanning Layering across the Depth Objectless Image
  • 9. Gomez, J., Mohammed, S., Bologna, G. and Pun, T. “Toward 3D Scene Understanding via Audio-description: Kinect-iPad fusion for the visually impaired” International Conference on Computers and Accessibility (ASSETS), 2011. Neural-Based Object Recognition 4 features per Object: Features’ values range from 0 to 1. [0,1]. Weights equal to 1, features are of same importance. All features are scale-invariant. All features are rotation-invariant. | 1 – (majorAxisLength – minorAxisLength) / majorAxisLength | perimeter / (majorAxisLength* pi) | ((pi * Radius2 )-area) / area | | 1 - | pi*majorAxisLength – perimeter | / perimeter |
  • 10. Gomez, J., Mohammed, S., Bologna, G. and Pun, T. “Toward 3D Scene Understanding via Audio-description: Kinect-iPad fusion for the visually impaired” International Conference on Computers and Accessibility (ASSETS), 2011. Early Scenary Description So far: Frontal-view gives just relative layout understanding. A top-view of the scene is quite desirable to grasp scene distribution. Wheras frontal distances (depths) are known, lateral distances are still missed. How to deliver all this information to the blind user?
  • 11. Gomez, J., Mohammed, S., Bologna, G. and Pun, T. “Toward 3D Scene Understanding via Audio-description: Kinect-iPad fusion for the visually impaired” International Conference on Computers and Accessibility (ASSETS), 2011. Delivering Visual Information via Finger-Triggered Audio Natural Top-view of the scene Artificial Top-view of the scene Traget sensation to be achieved onto iPad iPad holding Artificial Top-view Target sensation of Spatial Audio
  • 12. Gomez, J., Bologna, G. and Pun, T. “A virtual ceiling mounted depth-camera using orthographic kinect ” IEEE International Conference on Computer Vision (ICCV), 2011. Deceptive Object Location Caused by Perspective Causes Mistaken Spatial Sonification And Top-View is Unreacheble despite Depth Vanishing Point and Scene Optical Geometry Example
  • 13. Gomez, J., Bologna, G. and Pun, T. “A virtual ceiling mounted depth-camera using orthographic kinect ” IEEE International Conference on Computer Vision (ICCV), 2011. Orthographic Vs Perspective Cameras A perspective camera (bottom-right): Objects further away appear smaller in size, besides the positions vary with the distance. An orthographic camera (top-left): Objects preserve natural proportions on size and position.
  • 14. Gomez, J., Bologna, G. and Pun, T. “A virtual ceiling mounted depth-camera using orthographic kinect ” IEEE International Conference on Computer Vision (ICCV), 2011. Top-View Based on Virtual Orthographic Cam
  • 15. Gomez, J., Bologna, G. and Pun, T. “A virtual ceiling mounted depth-camera using orthographic kinect ” IEEE International Conference on Computer Vision (ICCV), 2011. Top-View Based on Virtual Orthographic Cam
  • 16. Gomez, J., Bologna, G. and Pun, T. “A virtual ceiling mounted depth-camera using orthographic kinect ” IEEE International Conference on Computer Vision (ICCV), 2011. Top-View Based on Virtual Orthographic Cam Artificial Top-view using virtual orthographic Kinect and Natural depth map from avobe using virtual orthographic Kinect Object recognition methods.
  • 17. Gomez, J., Mohammed, S., Bologna, G. and Pun, T. “Scene accessibility for the blind via computer-vision and multi-touch interfaces” Conference on Open Accessibility Everywhere (AEGIS), 2011. Experiments With Blinfoleded Users Original Layout User Guess Centroids Shifting
  • 18. Gomez, J., Mohammed, S., Bologna, G. and Pun, T. “Scene accessibility for the blind via computer-vision and multi-touch interfaces” Conference on Open Accessibility Everywhere (AEGIS), 2011. Results X axis represents 30 different scenes with four elements each. Y axis represents the average of the distances (cm) between the original and the final location of the four objects. This average distance has been normalized dividing its value by the diagonal (244 cm). The colors of the bars (scenes) vary according to their exploration time that goes from 0 to 10 minutes (colormap). Each bar shows on top the standard deviation of the four elements’ relocation.
  • 19. Gomez, J., Mohammed, S., Bologna, G. and Pun, T. “Scene accessibility for the blind via computer-vision and multi-touch interfaces” Conference on Open Accessibility Everywhere (AEGIS), 2011. Conclusions The mean error distance on objects’ replacement for all the experiments was 3.3% with respect to the diagonal of the table. This is around 8.5 cm of separation between an original object position and its relocation. In both cases i.e. scenes with three and four objects, this distance remained more or less invariant. The exploration time varied according the number of elements on the table. In average for a scene composed of three elements, 3.4 minutes were enough to build its layout in mind, whereas for scenes with four elements this time reached 5.4 minutes. This difference was given due to the increase in the number of sound-colors associations to be learned; the results showed no misclassifications of objects though. The results presented in this work reveal that the participants were capable of grasping general spatial structure of the sonified environments and accurately estimate scene layouts.