SlideShare une entreprise Scribd logo
1  sur  26
Télécharger pour lire hors ligne
A Vision-Based Mobile Platform
 for Seamless Indoor/Outdoor
          Positioning
               Guillaume GALES
                 Eric MCCLEAN
               John MCDONALD

         DEPARTMENT OF COMPUTER SCIENCE
     NATIONAL UNIVERSITY OF IRELAND MAYNOOTH
Introduction

 Internet access



                   Accelerometer

                   GPS / Compass

                   Camera




        2
Introduction
           Vision-based platform
               for positioning

                Internet access


    Position
Camera pose




                       3
Introduction
Vision-based platform
    for positioning


    Georeferenced façade
          database


     Façade recognition
          system




 Client applications


           4
Introduction
Vision-based platform
    for positioning




 Client applications

          5
Example of AR application
Mobile client side
                                       Rendering

Server side
          Façade                   Widget
        extraction                 Retrieval

Database                         Authoring client
    Façade
   Matching


                       6
Example of application




          7
Outline


Vison-based platform
• Façade extraction
• Georeferenced façade database
• Façade recognition system
• Camera pose estimation
Applications
• Augmented reality
• Navigation
• Positioning
Conclusion and perspectives



                             8
Vison-based platform
Façade Extraction


Key of the vision-based platform
 • Georeferenced façades are the frame of references of 3D content
Input: image of a façade
Output: homography between the façade and its image
Advantages:
 • Robust matching (invariant to rotation and perspective changes)
 • Façade normalization (used to build a representation of the environment)
 • Camera pose estimation (used by the visualization system)



                                    10
Façade Extraction




        11
Georeferenced façade database



 For each street, take pictures of façades
 Automatic façade extraction, matching and stitching
  • Geometrical constraint makes matching robust
  • Invariance to rotation and perspective changes




                           12
Georeferenced façade database




              13
Georeferenced façade database




              14
Façade recognition system



Candidate selection
• GPS coordinates
• Bag-of-word description for selecting
   candidates
Similarity constraint




                                           Figure 2: Database infrastructure for computing planar facade mo-
                                                                                                    ¸
                                           saics. The individual facades are stitched together into planes to
                                                                    ¸
                                      15   build a frame of reference for authoring.
Camera pose estimation
  intrinsics are known
  extrinsics are given by the façade extraction algorithm
  (homography between plane and its image decomposed
  into rotation and translation)
              2            3
              0   0   sh sh
    ⇥      ⇤ 60   h    h  07
x=K R     t 640
                            7
                  0    0  05
              1   1    1  1                      0
    2                 3
      0   0   sh sh
 = H 40   h   h   05            H                             sh
      1   1    1  1

                                                 h


                                             1
                                         H           Façade
 Camera
                                    16
Applications
Augmented reality

Extension of façade to 3D: frame of reference




                          18
Augmented reality
Desktop application
• Easy and intuitive interface to use for non expert users
• Predefined list of 3D models




                                         19
National University of                National University of   National University of
            Ireland Maynooth
                  Ireland           Augmented reality
                                                  Ireland Maynooth
                                                        Ireland
                                                                           Ireland Maynooth
                                                                                 Ireland



T
 horing is an important stage in the workflow of creat-
gmented reality applications. In this paper we describe
sed database infrastructure for authoring and storing 3D
 use in urban environments. It provides frames of ref-
 he environment as well as a mechanism to match new
h the facades and thus retrieving associated 3D content.
        ¸
 ucture is flexible in that we can add different 3D “lay-
tent on top of the facades and hence opens many pos-
                      ¸
                  Façade Extraction
  augmented reality applications in urban environments.
e the system provides a representation suitable for both
                  Pose Estimation
 automatic content authoring.
ds: Augmented Reality, Infrastructure, Authoring,
                  Façade Matching
ed Database, Content Storing and Retrieving.

DUCTION
                  Widget Retrieval useful in-
mented reality applications provide rich and
o their users about their surrounding environment. To
e augmented reality applications, an efficient infrastruc-
red. Such infrastructures involve:
ng a map of the environment ;
g content ;
ving content.
aper we propose an infrastructure that makes authoring
ve and flexible. Our goal is to create a platform for mo-       20
Results




   21
Navigation
         Vision-based platform
             for positioning

                  +
         Path finding algorithm




            Outdoor/Indoor
         navigation application


    22
Positioning
Accurate positioning (ongoing work)




                         23
Conclusion and
 perspectives
Conclusion and perspectives



Vision-based platform for positioning
• Georeferenced façade database
• Façade recognition system
Mobile applications
• Augmented reality
   -   Authoring solution
   -   User generated content
   -   Collaborative GI (HTML5)
• Navigation (Ongoing)
• Optimisations



                                  25
Acknowledgment

Research presented in this paper was funded by a Strategic
Research Cluster grant (07/SRC/I1169) by Science
Foundation Ireland under the National Development Plan.
The authors gratefully acknowledge this support.
Thank you for your attention




                          26

Contenu connexe

En vedette

An Authoring Solution for a Façade-Based AR Platform: Infrastructure, Annota...
An Authoring Solution for  a Façade-Based AR Platform: Infrastructure, Annota...An Authoring Solution for  a Façade-Based AR Platform: Infrastructure, Annota...
An Authoring Solution for a Façade-Based AR Platform: Infrastructure, Annota...Guillaume Gales
 
Constant colour matting with foreground estimation
Constant colour matting with foreground estimationConstant colour matting with foreground estimation
Constant colour matting with foreground estimationGuillaume Gales
 
Pixel matching for binocular stereovision by propagation of feature points ma...
Pixel matching for binocular stereovision by propagation of feature points ma...Pixel matching for binocular stereovision by propagation of feature points ma...
Pixel matching for binocular stereovision by propagation of feature points ma...Guillaume Gales
 
A Region-Based Randomized Voting Scheme for Stereo Matching
A Region-Based Randomized Voting Scheme for Stereo MatchingA Region-Based Randomized Voting Scheme for Stereo Matching
A Region-Based Randomized Voting Scheme for Stereo MatchingGuillaume Gales
 
Pixel Matching from Stereo Images (Callan seminar)
Pixel Matching from Stereo Images (Callan seminar)Pixel Matching from Stereo Images (Callan seminar)
Pixel Matching from Stereo Images (Callan seminar)Guillaume Gales
 
Beyond Augmented Reality: Ubiquitous Media Experiences
Beyond Augmented Reality: Ubiquitous Media ExperiencesBeyond Augmented Reality: Ubiquitous Media Experiences
Beyond Augmented Reality: Ubiquitous Media ExperiencesLightning Laboratories
 
HCI 3e - Ch 20: Ubiquitous computing and augmented realities
HCI 3e - Ch 20:  Ubiquitous computing and augmented realitiesHCI 3e - Ch 20:  Ubiquitous computing and augmented realities
HCI 3e - Ch 20: Ubiquitous computing and augmented realitiesAlan Dix
 
Augmented Reality (AR) - The Future of Mobile Applications?
Augmented Reality (AR) - The Future of Mobile Applications? Augmented Reality (AR) - The Future of Mobile Applications?
Augmented Reality (AR) - The Future of Mobile Applications? Carin Campanario
 
Sixth Sense Technology
Sixth Sense TechnologySixth Sense Technology
Sixth Sense TechnologyNavin Kumar
 

En vedette (11)

An Authoring Solution for a Façade-Based AR Platform: Infrastructure, Annota...
An Authoring Solution for  a Façade-Based AR Platform: Infrastructure, Annota...An Authoring Solution for  a Façade-Based AR Platform: Infrastructure, Annota...
An Authoring Solution for a Façade-Based AR Platform: Infrastructure, Annota...
 
Constant colour matting with foreground estimation
Constant colour matting with foreground estimationConstant colour matting with foreground estimation
Constant colour matting with foreground estimation
 
Pixel matching for binocular stereovision by propagation of feature points ma...
Pixel matching for binocular stereovision by propagation of feature points ma...Pixel matching for binocular stereovision by propagation of feature points ma...
Pixel matching for binocular stereovision by propagation of feature points ma...
 
A Region-Based Randomized Voting Scheme for Stereo Matching
A Region-Based Randomized Voting Scheme for Stereo MatchingA Region-Based Randomized Voting Scheme for Stereo Matching
A Region-Based Randomized Voting Scheme for Stereo Matching
 
Pixel Matching from Stereo Images (Callan seminar)
Pixel Matching from Stereo Images (Callan seminar)Pixel Matching from Stereo Images (Callan seminar)
Pixel Matching from Stereo Images (Callan seminar)
 
Beyond Augmented Reality: Ubiquitous Media Experiences
Beyond Augmented Reality: Ubiquitous Media ExperiencesBeyond Augmented Reality: Ubiquitous Media Experiences
Beyond Augmented Reality: Ubiquitous Media Experiences
 
HCI 3e - Ch 20: Ubiquitous computing and augmented realities
HCI 3e - Ch 20:  Ubiquitous computing and augmented realitiesHCI 3e - Ch 20:  Ubiquitous computing and augmented realities
HCI 3e - Ch 20: Ubiquitous computing and augmented realities
 
Augmented Reality (AR) - The Future of Mobile Applications?
Augmented Reality (AR) - The Future of Mobile Applications? Augmented Reality (AR) - The Future of Mobile Applications?
Augmented Reality (AR) - The Future of Mobile Applications?
 
Indoor Navigation
Indoor NavigationIndoor Navigation
Indoor Navigation
 
Sixth Sense Technology
Sixth Sense TechnologySixth Sense Technology
Sixth Sense Technology
 
Augmented Reality ppt
Augmented Reality pptAugmented Reality ppt
Augmented Reality ppt
 

Similaire à A Vision-Based Mobile Platform for Seamless Indoor/Outdoor Positioning

Handheld augmented reality_for_underground_infrast
Handheld augmented reality_for_underground_infrastHandheld augmented reality_for_underground_infrast
Handheld augmented reality_for_underground_infrastHelloWorld121381
 
Understanding the world in 3D with AI.pdf
Understanding the world in 3D with AI.pdfUnderstanding the world in 3D with AI.pdf
Understanding the world in 3D with AI.pdfQualcomm Research
 
CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...
CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...
CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...Si Chen
 
OpenStreetMap in 3D - current developments
OpenStreetMap in 3D - current developmentsOpenStreetMap in 3D - current developments
OpenStreetMap in 3D - current developmentsvirtualcitySYSTEMS GmbH
 
Aurea Vision & Aurea Consulting: technology proposal
Aurea Vision & Aurea Consulting: technology proposalAurea Vision & Aurea Consulting: technology proposal
Aurea Vision & Aurea Consulting: technology proposalAnna Doroshenko
 
307069674-Augmented-Reality-in-civil-engineering.pptx
307069674-Augmented-Reality-in-civil-engineering.pptx307069674-Augmented-Reality-in-civil-engineering.pptx
307069674-Augmented-Reality-in-civil-engineering.pptxmohammedtawfeeq29
 
GWT 2014: Energy Conference - 02 Le soluzioni Geospaziali per il mondo energy
GWT 2014: Energy Conference - 02 Le soluzioni Geospaziali per il mondo energyGWT 2014: Energy Conference - 02 Le soluzioni Geospaziali per il mondo energy
GWT 2014: Energy Conference - 02 Le soluzioni Geospaziali per il mondo energyPlanetek Italia Srl
 
fyp presentation of group 43011 final.pptx
fyp presentation of group 43011 final.pptxfyp presentation of group 43011 final.pptx
fyp presentation of group 43011 final.pptxIIEE - NEDUET
 
Interior Designing Mobile Application based on Markerless Augmented Reality (AR)
Interior Designing Mobile Application based on Markerless Augmented Reality (AR)Interior Designing Mobile Application based on Markerless Augmented Reality (AR)
Interior Designing Mobile Application based on Markerless Augmented Reality (AR)IRJET Journal
 
Introduction to mago3D, an Open Source Based Digital Twin Platform
Introduction to mago3D, an Open Source Based Digital Twin PlatformIntroduction to mago3D, an Open Source Based Digital Twin Platform
Introduction to mago3D, an Open Source Based Digital Twin PlatformSANGHEE SHIN
 
"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...Edge AI and Vision Alliance
 
356 358,tesma411,ijeast
356 358,tesma411,ijeast356 358,tesma411,ijeast
356 358,tesma411,ijeastaissmsblogs
 
Critical Infrastructure Monitoring Using UAV Imagery
Critical Infrastructure Monitoring Using UAV ImageryCritical Infrastructure Monitoring Using UAV Imagery
Critical Infrastructure Monitoring Using UAV Imageryaditess
 
ETDP 2015 D2 Mars Rover Image Based Localization Using 3D Point Cloud Models ...
ETDP 2015 D2 Mars Rover Image Based Localization Using 3D Point Cloud Models ...ETDP 2015 D2 Mars Rover Image Based Localization Using 3D Point Cloud Models ...
ETDP 2015 D2 Mars Rover Image Based Localization Using 3D Point Cloud Models ...Comit Projects Ltd
 
Simultaneous Mapping and Navigation For Rendezvous in Space Applications
Simultaneous Mapping and Navigation For Rendezvous in Space ApplicationsSimultaneous Mapping and Navigation For Rendezvous in Space Applications
Simultaneous Mapping and Navigation For Rendezvous in Space ApplicationsNandakishor Jahagirdar
 
Current State of mago3D, an Open Source Based Digital Twin Platform
Current State of mago3D, an Open Source Based Digital Twin PlatformCurrent State of mago3D, an Open Source Based Digital Twin Platform
Current State of mago3D, an Open Source Based Digital Twin PlatformSANGHEE SHIN
 
Clayvision-Yuichiro Takeuchi and Ken Perlin-Works
Clayvision-Yuichiro Takeuchi and Ken Perlin-WorksClayvision-Yuichiro Takeuchi and Ken Perlin-Works
Clayvision-Yuichiro Takeuchi and Ken Perlin-WorksDarshan Mehta
 

Similaire à A Vision-Based Mobile Platform for Seamless Indoor/Outdoor Positioning (20)

Handheld augmented reality_for_underground_infrast
Handheld augmented reality_for_underground_infrastHandheld augmented reality_for_underground_infrast
Handheld augmented reality_for_underground_infrast
 
Understanding the world in 3D with AI.pdf
Understanding the world in 3D with AI.pdfUnderstanding the world in 3D with AI.pdf
Understanding the world in 3D with AI.pdf
 
CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...
CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...
CrowdMap: Accurate Reconstruction of Indoor Floor Plan from Crowdsourced Sens...
 
OpenStreetMap in 3D - current developments
OpenStreetMap in 3D - current developmentsOpenStreetMap in 3D - current developments
OpenStreetMap in 3D - current developments
 
Aurea Vision & Aurea Consulting: technology proposal
Aurea Vision & Aurea Consulting: technology proposalAurea Vision & Aurea Consulting: technology proposal
Aurea Vision & Aurea Consulting: technology proposal
 
307069674-Augmented-Reality-in-civil-engineering.pptx
307069674-Augmented-Reality-in-civil-engineering.pptx307069674-Augmented-Reality-in-civil-engineering.pptx
307069674-Augmented-Reality-in-civil-engineering.pptx
 
GWT 2014: Energy Conference - 02 Le soluzioni Geospaziali per il mondo energy
GWT 2014: Energy Conference - 02 Le soluzioni Geospaziali per il mondo energyGWT 2014: Energy Conference - 02 Le soluzioni Geospaziali per il mondo energy
GWT 2014: Energy Conference - 02 Le soluzioni Geospaziali per il mondo energy
 
fyp presentation of group 43011 final.pptx
fyp presentation of group 43011 final.pptxfyp presentation of group 43011 final.pptx
fyp presentation of group 43011 final.pptx
 
EN_3DLS_Oil_Gas_Offshore
EN_3DLS_Oil_Gas_OffshoreEN_3DLS_Oil_Gas_Offshore
EN_3DLS_Oil_Gas_Offshore
 
Interior Designing Mobile Application based on Markerless Augmented Reality (AR)
Interior Designing Mobile Application based on Markerless Augmented Reality (AR)Interior Designing Mobile Application based on Markerless Augmented Reality (AR)
Interior Designing Mobile Application based on Markerless Augmented Reality (AR)
 
Introduction to mago3D, an Open Source Based Digital Twin Platform
Introduction to mago3D, an Open Source Based Digital Twin PlatformIntroduction to mago3D, an Open Source Based Digital Twin Platform
Introduction to mago3D, an Open Source Based Digital Twin Platform
 
"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...
 
356 358,tesma411,ijeast
356 358,tesma411,ijeast356 358,tesma411,ijeast
356 358,tesma411,ijeast
 
Critical Infrastructure Monitoring Using UAV Imagery
Critical Infrastructure Monitoring Using UAV ImageryCritical Infrastructure Monitoring Using UAV Imagery
Critical Infrastructure Monitoring Using UAV Imagery
 
ETDP 2015 D2 Mars Rover Image Based Localization Using 3D Point Cloud Models ...
ETDP 2015 D2 Mars Rover Image Based Localization Using 3D Point Cloud Models ...ETDP 2015 D2 Mars Rover Image Based Localization Using 3D Point Cloud Models ...
ETDP 2015 D2 Mars Rover Image Based Localization Using 3D Point Cloud Models ...
 
Simultaneous Mapping and Navigation For Rendezvous in Space Applications
Simultaneous Mapping and Navigation For Rendezvous in Space ApplicationsSimultaneous Mapping and Navigation For Rendezvous in Space Applications
Simultaneous Mapping and Navigation For Rendezvous in Space Applications
 
CV-RAKESH KUMAR
CV-RAKESH KUMARCV-RAKESH KUMAR
CV-RAKESH KUMAR
 
DSM Extraction from Pleiades Images using MICMAC
DSM Extraction from Pleiades Images using MICMAC DSM Extraction from Pleiades Images using MICMAC
DSM Extraction from Pleiades Images using MICMAC
 
Current State of mago3D, an Open Source Based Digital Twin Platform
Current State of mago3D, an Open Source Based Digital Twin PlatformCurrent State of mago3D, an Open Source Based Digital Twin Platform
Current State of mago3D, an Open Source Based Digital Twin Platform
 
Clayvision-Yuichiro Takeuchi and Ken Perlin-Works
Clayvision-Yuichiro Takeuchi and Ken Perlin-WorksClayvision-Yuichiro Takeuchi and Ken Perlin-Works
Clayvision-Yuichiro Takeuchi and Ken Perlin-Works
 

A Vision-Based Mobile Platform for Seamless Indoor/Outdoor Positioning

  • 1. A Vision-Based Mobile Platform for Seamless Indoor/Outdoor Positioning Guillaume GALES Eric MCCLEAN John MCDONALD DEPARTMENT OF COMPUTER SCIENCE NATIONAL UNIVERSITY OF IRELAND MAYNOOTH
  • 2. Introduction Internet access Accelerometer GPS / Compass Camera 2
  • 3. Introduction Vision-based platform for positioning Internet access Position Camera pose 3
  • 4. Introduction Vision-based platform for positioning Georeferenced façade database Façade recognition system Client applications 4
  • 5. Introduction Vision-based platform for positioning Client applications 5
  • 6. Example of AR application Mobile client side Rendering Server side Façade Widget extraction Retrieval Database Authoring client Façade Matching 6
  • 8. Outline Vison-based platform • Façade extraction • Georeferenced façade database • Façade recognition system • Camera pose estimation Applications • Augmented reality • Navigation • Positioning Conclusion and perspectives 8
  • 10. Façade Extraction Key of the vision-based platform • Georeferenced façades are the frame of references of 3D content Input: image of a façade Output: homography between the façade and its image Advantages: • Robust matching (invariant to rotation and perspective changes) • Façade normalization (used to build a representation of the environment) • Camera pose estimation (used by the visualization system) 10
  • 12. Georeferenced façade database For each street, take pictures of façades Automatic façade extraction, matching and stitching • Geometrical constraint makes matching robust • Invariance to rotation and perspective changes 12
  • 15. Façade recognition system Candidate selection • GPS coordinates • Bag-of-word description for selecting candidates Similarity constraint Figure 2: Database infrastructure for computing planar facade mo- ¸ saics. The individual facades are stitched together into planes to ¸ 15 build a frame of reference for authoring.
  • 16. Camera pose estimation intrinsics are known extrinsics are given by the façade extraction algorithm (homography between plane and its image decomposed into rotation and translation) 2 3 0 0 sh sh ⇥ ⇤ 60 h h 07 x=K R t 640 7 0 0 05 1 1 1 1 0 2 3 0 0 sh sh = H 40 h h 05 H sh 1 1 1 1 h 1 H Façade Camera 16
  • 18. Augmented reality Extension of façade to 3D: frame of reference 18
  • 19. Augmented reality Desktop application • Easy and intuitive interface to use for non expert users • Predefined list of 3D models 19
  • 20. National University of National University of National University of Ireland Maynooth Ireland Augmented reality Ireland Maynooth Ireland Ireland Maynooth Ireland T horing is an important stage in the workflow of creat- gmented reality applications. In this paper we describe sed database infrastructure for authoring and storing 3D use in urban environments. It provides frames of ref- he environment as well as a mechanism to match new h the facades and thus retrieving associated 3D content. ¸ ucture is flexible in that we can add different 3D “lay- tent on top of the facades and hence opens many pos- ¸ Façade Extraction augmented reality applications in urban environments. e the system provides a representation suitable for both Pose Estimation automatic content authoring. ds: Augmented Reality, Infrastructure, Authoring, Façade Matching ed Database, Content Storing and Retrieving. DUCTION Widget Retrieval useful in- mented reality applications provide rich and o their users about their surrounding environment. To e augmented reality applications, an efficient infrastruc- red. Such infrastructures involve: ng a map of the environment ; g content ; ving content. aper we propose an infrastructure that makes authoring ve and flexible. Our goal is to create a platform for mo- 20
  • 21. Results 21
  • 22. Navigation Vision-based platform for positioning + Path finding algorithm Outdoor/Indoor navigation application 22
  • 25. Conclusion and perspectives Vision-based platform for positioning • Georeferenced façade database • Façade recognition system Mobile applications • Augmented reality - Authoring solution - User generated content - Collaborative GI (HTML5) • Navigation (Ongoing) • Optimisations 25
  • 26. Acknowledgment Research presented in this paper was funded by a Strategic Research Cluster grant (07/SRC/I1169) by Science Foundation Ireland under the National Development Plan. The authors gratefully acknowledge this support. Thank you for your attention 26