SlideShare a Scribd company logo
1 of 30
Download to read offline
Firma convenzione
Politecnico di Milano e Veneranda Fabbrica
del Duomo di Milano
Aula Magna – Rettorato
Mercoledì 27 maggio 2015
A Location-Based Virtual Reality
Application for Mountain Peak Detection
Antonio La Salandra - Piero Fraternali - Darian Frajberg
LocWeb2018 | WWW 2018 Workshop
Lyon, April 24, 2018
Department of Electronics, Information and Bioengineering
Introduction and motivation
User Generated Content publicly available on the web is a
valuable resource for the extraction of data useful for scientific
and social purposes
• Facebook: ~300M daily photo uploads
• Twitter: ~500M tweets sent per day
• Instagram: ~95M photos and videos shared per day
Smartphones are the most used means of acquiring and sharing
data
Department of Electronics, Information and Bioengineering
Introduction and motivation
Citizen Science can be described as the process of active
engagement of citizens and communities to collaborate to solve
common social issues
Mobile Outdoor Applications are powerful means of promoting
the collection of geo-referenced data useful to support scientific
researches
Several mobile applications have been released for environmental
monitoring purposes by following the citizen science paradigm:
plant study, climate change, noise pollution, bird migration…
Department of Electronics, Information and Bioengineering
The SnowWatch Project
Our contribution: monitoring of mountain snow coverage, and
hence of water availability, through the analysis of low-cost
multimedia content
Department of Electronics, Information and Bioengineering
From 2D to 3D visualization of geo-located data
Augmented Reality (AR) and
Virtual Reality (VR) enable the
visualization of geo-located
data from the classic 2D planar
representation to 3D immersive
environments
Department of Electronics, Information and Bioengineering
The PeakLens Application
PeakLens is an AR location-based mobile app developed for
collecting photos of mountains for the SnowWatch data set
Department of Electronics, Information and Bioengineering
The PeakLens Application
The application is used as a
means of engaging users in the
collection of data by providing
them with a peak identification
service in real-time
It was released for Android in
February 2017 and it has already
achieved about 200k installs, 4
stars’ ratings and most positive
feedbacks
Department of Electronics, Information and Bioengineering
PeakLensVR
PeakLensVR aims at boosting the community of PeakLens users
and SnowWatch contributors
• It enables the acquisition of geo-located, geo-referenced,
timestamped panoramic photos of mountain landscapes by
using a mobile phone
• It extends the peak identification service to cope with such
images
• It enables the visualization of captured panoramas enriched with
information about peaks in view in a virtual reality environment
Department of Electronics, Information and Bioengineering
PeakLensVR – Processing Pipeline
Overview of PeakLensVR main processing steps and modules
Department of Electronics, Information and Bioengineering
PeakLensVR – Scene acquisition
A sequence of photos is taken with the smartphone camera
Department of Electronics, Information and Bioengineering
Data about user geographical position, smartphone spatial
orientation and camera parameters are saved as photo
metadata to be used in the next phases of the processing
pipeline
• Geographical coordinates: latitude and longitude
• Spatial orientation: azimuth, pitch and roll
• Camera parameters: horizontal and vertical field of views,
frame width and height
PeakLensVR – Scene acquisition
Department of Electronics, Information and Bioengineering
PeakLensVR – Panorama composition
Image sequence and sensor data are used to compose the
panoramic image
Department of Electronics, Information and Bioengineering
PeakLensVR – Panoramic image enrichment with peaks
PeakLens integrate geo-data from different sources and expose
them through an API
Main data sources:
• OpenStreetMap
• NASA SRTM DEM
Server-side
Department of Electronics, Information and Bioengineering
PeakLensVR – Panoramic image enrichment with peaks
Different DEM and POI data representations are accessible
through the PeakLens API
Department of Electronics, Information and Bioengineering
PeakLensVR – Panoramic image enrichment with peaks
Sensor-based peak positioning
GPS Coordinates
Peaks + Skyline JSON
Orientation data + Camera parameters
Panorama augmented with peak data
Department of Electronics, Information and Bioengineering
PeakLensVR – Panoramic image enrichment with peaks
Content-based position refinement
Skyline extraction
+
Skyline matching
Department of Electronics, Information and Bioengineering
PeakLensVR – Panoramic image enrichment with peaks
Sensor-based vs Content-based image alignment
Department of Electronics, Information and Bioengineering
PeakLensVR – Visualization and sharing
VR mode visualization by using a Google Cardboard VR headset
Department of Electronics, Information and Bioengineering
PeakLensVR – Visualization and sharing
Fullscreen immersive mode visualization on smartphone
Department of Electronics, Information and Bioengineering
PeakLensVR – Visualization and sharing
Sharing and visualization on Facebook 360 platform
Department of Electronics, Information and Bioengineering
Experimental Study: Goal
• Sensor-based peak positioning errors
• Accuracy of peak positions identified by using sensors
• Smartphone sensor precision
• Content-based position refinement errors
• Improvements introduced with respect to the sensor-
based approach
• Precision of the final peak positioning
Department of Electronics, Information and Bioengineering
Experimental Study: Dataset
• N. Panoramic Photos: 10
• Location: Como lake area
in North Italy and Pollino
National Park in South Italy
• Horizontal Field of View:
96 – 360 degree
• N. Peaks: 1 – 11
• Photos have been taken in
various weather conditions,
with different exposures
and, in some of them, with
objects partially occluding
the skyline
Department of Electronics, Information and Bioengineering
Experimental Study: Ground truth
Manually computed with the support of an online service we developed, that given
the geographical coordinates of the view point, returns a digital representation of
the panorama visible from that point, enriched with the labels of each visible peak
placed in the correct position
Department of Electronics, Information and Bioengineering
Experimental Study: Results
Sensor-based and Content-based Euclidean Degree Error (EDE) comparison
Department of Electronics, Information and Bioengineering
Experimental Study: Results
Classification of the frequency distribution of peaks with respect to their
EDE after the sensor-based and the content-based matching approaches
Department of Electronics, Information and Bioengineering
Experimental Study: Results
Sensor-based: 35% of peaks have EDE < 3° and 17,5% have EDE > 6°
Department of Electronics, Information and Bioengineering
Experimental Study: Results
Content-based: 85% of peaks have EDE < 3° and 0% have EDE > 6°
Department of Electronics, Information and Bioengineering
Conclusions
• The application prototyped during this work may become a
new channel for the acquisition of geo-located, geo-
referenced and timestamped panoramic photos useful to
environmental monitoring purposes
• The content-based alignment technique developed during the
SnowWatch project has been proved to work with panoramic
images involving an average 54% improvement compared
with the sensor-based peak positioning approach
Department of Electronics, Information and Bioengineering
Future work
• The introduction of the crowdsourcing module and the
refinement of the sharing mechanism, to allow users to
contribute by sharing their own photos with the community
• The rendition in VR mode of other objects of interest, such as
trails and huts, besides peaks
• The creation of an online platform that aggregates the user-
generated panoramas to automatically produce maps and
virtual tours in mountain areas
Department of Electronics, Information and Bioengineering
Q&A
Thank you for your attention
Questions?
A Location-Based Virtual Reality Application
for Mountain Peak Detection
Antonio La Salandra - Piero Fraternali - Darian Frajberg
antonio.lasalandra | piero.fraternali | darian.frajberg
@polimi.it

More Related Content

Similar to A Location-Based Virtual Reality Application for Mountain Peak Detection

Heterogeneous information integration for mountain augmented reality mobile apps
Heterogeneous information integration for mountain augmented reality mobile appsHeterogeneous information integration for mountain augmented reality mobile apps
Heterogeneous information integration for mountain augmented reality mobile appsDarian Frajberg
 
Applying Computer Vision Techniques to Web Public Images for the Environmenta...
Applying Computer Vision Techniques to Web Public Images for the Environmenta...Applying Computer Vision Techniques to Web Public Images for the Environmenta...
Applying Computer Vision Techniques to Web Public Images for the Environmenta...PasiniPolimi
 
IRJET- Application of MCNN in Object Detection
IRJET-  	  Application of MCNN in Object DetectionIRJET-  	  Application of MCNN in Object Detection
IRJET- Application of MCNN in Object DetectionIRJET Journal
 
Program for 2015 ieee international conference on consumer electronics taiw...
Program for 2015 ieee international conference on consumer electronics   taiw...Program for 2015 ieee international conference on consumer electronics   taiw...
Program for 2015 ieee international conference on consumer electronics taiw...supra_uny
 
An Autonomic Approach to Real-Time Predictive Analytics using Open Data and ...
An Autonomic Approach to Real-Time Predictive Analytics using Open Data and ...An Autonomic Approach to Real-Time Predictive Analytics using Open Data and ...
An Autonomic Approach to Real-Time Predictive Analytics using Open Data and ...Wassim Derguech
 
Scientific Knowledge from Geospatial Observations
Scientific Knowledge from Geospatial ObservationsScientific Knowledge from Geospatial Observations
Scientific Knowledge from Geospatial Observations George Percivall
 
"Complementing Snow Cover Estimation with Analysis of Web Public Images"
"Complementing Snow Cover Estimation with Analysis of Web Public Images""Complementing Snow Cover Estimation with Analysis of Web Public Images"
"Complementing Snow Cover Estimation with Analysis of Web Public Images"PasiniPolimi
 
Wireless Sensor Network for AgriTech Applications
Wireless Sensor Network for AgriTech Applications Wireless Sensor Network for AgriTech Applications
Wireless Sensor Network for AgriTech Applications IoTForum | TiE Bangalore
 
Geospatial Analysis and Internet of Things in Environmental Informatics
Geospatial Analysis and Internet of Things in Environmental InformaticsGeospatial Analysis and Internet of Things in Environmental Informatics
Geospatial Analysis and Internet of Things in Environmental InformaticsAndreas Kamilaris
 
Radiometric Calibration of Digital Images
Radiometric Calibration of Digital ImagesRadiometric Calibration of Digital Images
Radiometric Calibration of Digital ImagesSean Thibert
 
FraPPE: a vocabulary to represent heterogeneous spatio-temporal data to suppo...
FraPPE: a vocabulary to represent heterogeneous spatio-temporal data to suppo...FraPPE: a vocabulary to represent heterogeneous spatio-temporal data to suppo...
FraPPE: a vocabulary to represent heterogeneous spatio-temporal data to suppo...Marco Balduini
 
ICC2017 UUUI sessions 5604-2
ICC2017 UUUI sessions 5604-2ICC2017 UUUI sessions 5604-2
ICC2017 UUUI sessions 5604-2UUUI ICA
 
Arturo Sanchez-Azofeifa_Challenges and opportunities in the implementation of...
Arturo Sanchez-Azofeifa_Challenges and opportunities in the implementation of...Arturo Sanchez-Azofeifa_Challenges and opportunities in the implementation of...
Arturo Sanchez-Azofeifa_Challenges and opportunities in the implementation of...TERN Australia
 
ZaneRicksResume8-14
ZaneRicksResume8-14ZaneRicksResume8-14
ZaneRicksResume8-14Zane Ricks
 
Satellite Image Classification and Analysis using Machine Learning with ISRO ...
Satellite Image Classification and Analysis using Machine Learning with ISRO ...Satellite Image Classification and Analysis using Machine Learning with ISRO ...
Satellite Image Classification and Analysis using Machine Learning with ISRO ...IRJET Journal
 
Data Ecosystems for Geospatial Data
Data Ecosystems for Geospatial DataData Ecosystems for Geospatial Data
Data Ecosystems for Geospatial DataSlim Turki, Dr.
 

Similar to A Location-Based Virtual Reality Application for Mountain Peak Detection (20)

Heterogeneous information integration for mountain augmented reality mobile apps
Heterogeneous information integration for mountain augmented reality mobile appsHeterogeneous information integration for mountain augmented reality mobile apps
Heterogeneous information integration for mountain augmented reality mobile apps
 
Applying Computer Vision Techniques to Web Public Images for the Environmenta...
Applying Computer Vision Techniques to Web Public Images for the Environmenta...Applying Computer Vision Techniques to Web Public Images for the Environmenta...
Applying Computer Vision Techniques to Web Public Images for the Environmenta...
 
Resume_updated_job
Resume_updated_jobResume_updated_job
Resume_updated_job
 
IRJET- Application of MCNN in Object Detection
IRJET-  	  Application of MCNN in Object DetectionIRJET-  	  Application of MCNN in Object Detection
IRJET- Application of MCNN in Object Detection
 
Program for 2015 ieee international conference on consumer electronics taiw...
Program for 2015 ieee international conference on consumer electronics   taiw...Program for 2015 ieee international conference on consumer electronics   taiw...
Program for 2015 ieee international conference on consumer electronics taiw...
 
An Autonomic Approach to Real-Time Predictive Analytics using Open Data and ...
An Autonomic Approach to Real-Time Predictive Analytics using Open Data and ...An Autonomic Approach to Real-Time Predictive Analytics using Open Data and ...
An Autonomic Approach to Real-Time Predictive Analytics using Open Data and ...
 
Scientific Knowledge from Geospatial Observations
Scientific Knowledge from Geospatial ObservationsScientific Knowledge from Geospatial Observations
Scientific Knowledge from Geospatial Observations
 
"Complementing Snow Cover Estimation with Analysis of Web Public Images"
"Complementing Snow Cover Estimation with Analysis of Web Public Images""Complementing Snow Cover Estimation with Analysis of Web Public Images"
"Complementing Snow Cover Estimation with Analysis of Web Public Images"
 
Wireless Sensor Network for AgriTech Applications
Wireless Sensor Network for AgriTech Applications Wireless Sensor Network for AgriTech Applications
Wireless Sensor Network for AgriTech Applications
 
Geospatial Analysis and Internet of Things in Environmental Informatics
Geospatial Analysis and Internet of Things in Environmental InformaticsGeospatial Analysis and Internet of Things in Environmental Informatics
Geospatial Analysis and Internet of Things in Environmental Informatics
 
Radiometric Calibration of Digital Images
Radiometric Calibration of Digital ImagesRadiometric Calibration of Digital Images
Radiometric Calibration of Digital Images
 
FraPPE: a vocabulary to represent heterogeneous spatio-temporal data to suppo...
FraPPE: a vocabulary to represent heterogeneous spatio-temporal data to suppo...FraPPE: a vocabulary to represent heterogeneous spatio-temporal data to suppo...
FraPPE: a vocabulary to represent heterogeneous spatio-temporal data to suppo...
 
Seminario Ernesto Bonomi, 24-05-2012
Seminario Ernesto Bonomi,  24-05-2012Seminario Ernesto Bonomi,  24-05-2012
Seminario Ernesto Bonomi, 24-05-2012
 
1st FIG Young Surveyors European Meeting
1st FIG Young Surveyors European Meeting1st FIG Young Surveyors European Meeting
1st FIG Young Surveyors European Meeting
 
ICC2017 UUUI sessions 5604-2
ICC2017 UUUI sessions 5604-2ICC2017 UUUI sessions 5604-2
ICC2017 UUUI sessions 5604-2
 
Arturo Sanchez-Azofeifa_Challenges and opportunities in the implementation of...
Arturo Sanchez-Azofeifa_Challenges and opportunities in the implementation of...Arturo Sanchez-Azofeifa_Challenges and opportunities in the implementation of...
Arturo Sanchez-Azofeifa_Challenges and opportunities in the implementation of...
 
ZaneRicksResume8-14
ZaneRicksResume8-14ZaneRicksResume8-14
ZaneRicksResume8-14
 
Satellite Image Classification and Analysis using Machine Learning with ISRO ...
Satellite Image Classification and Analysis using Machine Learning with ISRO ...Satellite Image Classification and Analysis using Machine Learning with ISRO ...
Satellite Image Classification and Analysis using Machine Learning with ISRO ...
 
SmartGeo/Eiagrid portal (Guido Satta, CRS4)
SmartGeo/Eiagrid portal (Guido Satta, CRS4)SmartGeo/Eiagrid portal (Guido Satta, CRS4)
SmartGeo/Eiagrid portal (Guido Satta, CRS4)
 
Data Ecosystems for Geospatial Data
Data Ecosystems for Geospatial DataData Ecosystems for Geospatial Data
Data Ecosystems for Geospatial Data
 

Recently uploaded

AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024The Digital Insurer
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDropbox
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024The Digital Insurer
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businesspanagenda
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...apidays
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024The Digital Insurer
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
Cyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfCyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfOverkill Security
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 

Recently uploaded (20)

AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Cyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfCyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdf
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 

A Location-Based Virtual Reality Application for Mountain Peak Detection

  • 1. Firma convenzione Politecnico di Milano e Veneranda Fabbrica del Duomo di Milano Aula Magna – Rettorato Mercoledì 27 maggio 2015 A Location-Based Virtual Reality Application for Mountain Peak Detection Antonio La Salandra - Piero Fraternali - Darian Frajberg LocWeb2018 | WWW 2018 Workshop Lyon, April 24, 2018
  • 2. Department of Electronics, Information and Bioengineering Introduction and motivation User Generated Content publicly available on the web is a valuable resource for the extraction of data useful for scientific and social purposes • Facebook: ~300M daily photo uploads • Twitter: ~500M tweets sent per day • Instagram: ~95M photos and videos shared per day Smartphones are the most used means of acquiring and sharing data
  • 3. Department of Electronics, Information and Bioengineering Introduction and motivation Citizen Science can be described as the process of active engagement of citizens and communities to collaborate to solve common social issues Mobile Outdoor Applications are powerful means of promoting the collection of geo-referenced data useful to support scientific researches Several mobile applications have been released for environmental monitoring purposes by following the citizen science paradigm: plant study, climate change, noise pollution, bird migration…
  • 4. Department of Electronics, Information and Bioengineering The SnowWatch Project Our contribution: monitoring of mountain snow coverage, and hence of water availability, through the analysis of low-cost multimedia content
  • 5. Department of Electronics, Information and Bioengineering From 2D to 3D visualization of geo-located data Augmented Reality (AR) and Virtual Reality (VR) enable the visualization of geo-located data from the classic 2D planar representation to 3D immersive environments
  • 6. Department of Electronics, Information and Bioengineering The PeakLens Application PeakLens is an AR location-based mobile app developed for collecting photos of mountains for the SnowWatch data set
  • 7. Department of Electronics, Information and Bioengineering The PeakLens Application The application is used as a means of engaging users in the collection of data by providing them with a peak identification service in real-time It was released for Android in February 2017 and it has already achieved about 200k installs, 4 stars’ ratings and most positive feedbacks
  • 8. Department of Electronics, Information and Bioengineering PeakLensVR PeakLensVR aims at boosting the community of PeakLens users and SnowWatch contributors • It enables the acquisition of geo-located, geo-referenced, timestamped panoramic photos of mountain landscapes by using a mobile phone • It extends the peak identification service to cope with such images • It enables the visualization of captured panoramas enriched with information about peaks in view in a virtual reality environment
  • 9. Department of Electronics, Information and Bioengineering PeakLensVR – Processing Pipeline Overview of PeakLensVR main processing steps and modules
  • 10. Department of Electronics, Information and Bioengineering PeakLensVR – Scene acquisition A sequence of photos is taken with the smartphone camera
  • 11. Department of Electronics, Information and Bioengineering Data about user geographical position, smartphone spatial orientation and camera parameters are saved as photo metadata to be used in the next phases of the processing pipeline • Geographical coordinates: latitude and longitude • Spatial orientation: azimuth, pitch and roll • Camera parameters: horizontal and vertical field of views, frame width and height PeakLensVR – Scene acquisition
  • 12. Department of Electronics, Information and Bioengineering PeakLensVR – Panorama composition Image sequence and sensor data are used to compose the panoramic image
  • 13. Department of Electronics, Information and Bioengineering PeakLensVR – Panoramic image enrichment with peaks PeakLens integrate geo-data from different sources and expose them through an API Main data sources: • OpenStreetMap • NASA SRTM DEM Server-side
  • 14. Department of Electronics, Information and Bioengineering PeakLensVR – Panoramic image enrichment with peaks Different DEM and POI data representations are accessible through the PeakLens API
  • 15. Department of Electronics, Information and Bioengineering PeakLensVR – Panoramic image enrichment with peaks Sensor-based peak positioning GPS Coordinates Peaks + Skyline JSON Orientation data + Camera parameters Panorama augmented with peak data
  • 16. Department of Electronics, Information and Bioengineering PeakLensVR – Panoramic image enrichment with peaks Content-based position refinement Skyline extraction + Skyline matching
  • 17. Department of Electronics, Information and Bioengineering PeakLensVR – Panoramic image enrichment with peaks Sensor-based vs Content-based image alignment
  • 18. Department of Electronics, Information and Bioengineering PeakLensVR – Visualization and sharing VR mode visualization by using a Google Cardboard VR headset
  • 19. Department of Electronics, Information and Bioengineering PeakLensVR – Visualization and sharing Fullscreen immersive mode visualization on smartphone
  • 20. Department of Electronics, Information and Bioengineering PeakLensVR – Visualization and sharing Sharing and visualization on Facebook 360 platform
  • 21. Department of Electronics, Information and Bioengineering Experimental Study: Goal • Sensor-based peak positioning errors • Accuracy of peak positions identified by using sensors • Smartphone sensor precision • Content-based position refinement errors • Improvements introduced with respect to the sensor- based approach • Precision of the final peak positioning
  • 22. Department of Electronics, Information and Bioengineering Experimental Study: Dataset • N. Panoramic Photos: 10 • Location: Como lake area in North Italy and Pollino National Park in South Italy • Horizontal Field of View: 96 – 360 degree • N. Peaks: 1 – 11 • Photos have been taken in various weather conditions, with different exposures and, in some of them, with objects partially occluding the skyline
  • 23. Department of Electronics, Information and Bioengineering Experimental Study: Ground truth Manually computed with the support of an online service we developed, that given the geographical coordinates of the view point, returns a digital representation of the panorama visible from that point, enriched with the labels of each visible peak placed in the correct position
  • 24. Department of Electronics, Information and Bioengineering Experimental Study: Results Sensor-based and Content-based Euclidean Degree Error (EDE) comparison
  • 25. Department of Electronics, Information and Bioengineering Experimental Study: Results Classification of the frequency distribution of peaks with respect to their EDE after the sensor-based and the content-based matching approaches
  • 26. Department of Electronics, Information and Bioengineering Experimental Study: Results Sensor-based: 35% of peaks have EDE < 3° and 17,5% have EDE > 6°
  • 27. Department of Electronics, Information and Bioengineering Experimental Study: Results Content-based: 85% of peaks have EDE < 3° and 0% have EDE > 6°
  • 28. Department of Electronics, Information and Bioengineering Conclusions • The application prototyped during this work may become a new channel for the acquisition of geo-located, geo- referenced and timestamped panoramic photos useful to environmental monitoring purposes • The content-based alignment technique developed during the SnowWatch project has been proved to work with panoramic images involving an average 54% improvement compared with the sensor-based peak positioning approach
  • 29. Department of Electronics, Information and Bioengineering Future work • The introduction of the crowdsourcing module and the refinement of the sharing mechanism, to allow users to contribute by sharing their own photos with the community • The rendition in VR mode of other objects of interest, such as trails and huts, besides peaks • The creation of an online platform that aggregates the user- generated panoramas to automatically produce maps and virtual tours in mountain areas
  • 30. Department of Electronics, Information and Bioengineering Q&A Thank you for your attention Questions? A Location-Based Virtual Reality Application for Mountain Peak Detection Antonio La Salandra - Piero Fraternali - Darian Frajberg antonio.lasalandra | piero.fraternali | darian.frajberg @polimi.it