Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Multimodale Indoor-Lokalisierung fuer Android basierte mobile Endgeräte

Multimodale Indoor-Lokalisierung fuer Android basierte mobile Endgeräte
by

Stephan Linzner

on 28 June 2010

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Multimodale Indoor-Lokalisierung fuer Android basierte mobile Endgeräte

“Location changes everything. This one input – our
coordinates – has the potential to change all the
outputs. Where we shop, who we talk to, what we
read, what we search for, where we go – they all
change once we merge location and the Web.”
Location Matters! Mathew Honan, WIRED magazine, 19.1.2009 Multimodale Indoor-Lokalisierung auf
Android basierten mobilen Endgeraeten Location Fingerprinting Smartspace Framework Performance Evaluation Future Work Ubiquitary wireless infrastructure Today, Almost everybody will carry a mobile device by 2020 880 million global smartphone users by 2013 Location for outdoor environments is provided by the Global Positioning System (GPS) There is no solution for indoors yet... and... + allows Fine grained sensor profiling of any environment GSM/CDMA 319 million chipsets sold in 2008, with 862 million installed base Wifi Total: 4137 Open: 735 Closed: 3402 Indoor-Localization of mobile devices Use Cases Library Museum Conference Why it works... How it works... We can do better... Radio Map GSM/CDMA RSS Wifi RSS Drawbacks... Signal Strength Difference Scoring / Adjusting Quantization of orientation Time interferences Mobile device interferences Blocking-Effect interferences Algorithms Deterministic: Nearest Neighbour in Signal Space (NNSS)
K Nearest Neighbour in Signal Space (KNNSS)
Euklidean-Distance
Mahalanobis-Distance
Similarity Matching Algorithm (SMA)

Optimierungen:
Orientation Reduction


Bayesian interference
Hidden Markov Model (HHM)
Markov Lokalization
Monte Carlo Lokalization



Probability: Private home/house Features Off-the-shelf mobile devices
Use of existing infrastructure
- Wifi
- GSM
- Marker
Passive use of infrastructure
Adaptivity
Extensibility
- Sensors
- Data processing
- Localization algorithms

Indoor-Localization-Framework for the android plattform
Implemented as an android service
Provides developers with location providers for:
- Wifi LFPT
- GSM LFPT
- Marker (Fixed Position)
- Display (Fixed Position)
- Motion Detection
Passive use of infrastrucure
Autonomous-Learning
Open Source (ca. 6000 LOC)
Extensible

Requirements Wifi and GSM LFPT components
Input-Method components
- QR-Code
- Dialog
- Display (POI)
Motion detection component
Finite state machine
- Fixed position signals
- Motion signals Indoor-Localization overview
Implementation Context-aware state transitions Location listeners
Log listeners Architecture Finite State Machine Sensing Framework Parameters Wifi Installation:
• Size: 133m^2
• Grid: 5x5m
• Data: Wifi RSS of all APs in dBm

TRP:
• Count TPs: 39
• LFPTs per TP: 5
• Total measurements: 125
• Orientation: ori0 (0 − 90◦ )

RTP:
• Count RPs: 19
• Count RPs/TPs: 14
• Count RPs beliebig: 5
• Orientation: ori0 (0 − 90◦ )
Installation:
• Size: 133m^2
• Grid: 5x5m
• Data: GSM RSS, active CID +
RSS neighbor CIDs in dBm

TRP:
• Count TPs: 39
• LFPTs per TP: 4
• Total measurements: 100
• Orientation: ori0 (0 − 90◦ )

RTP:
• Count RPs: 16
• Count RPs/TPs: 16
• Orientation: ori0 (0 − 90◦ )
Parameters GSM Wifi + GSM, 3 floors Wifi, 3rd floor GSM, Sand Installation:
• Size: 133m^2
• Grid: 5x5m
• Data: Wifi RSS of all APs in dBm

TRP:
• Count TPs: 13
• LFPTs per TP: 5
• Total measurements: 125
• Orientation: ori0 (0 − 90◦ )

RTP:
• Count RPs: 13
• Count RPs/TPs: 13
• Orientation: ori0 (0 − 90◦ )
Parameters Wifi Installation:
• Size: 1280m^2
• Grid: 40-80m
• Data: GSM RSS, active + neighbor CIDS
in dBm

TRP:
• Count TPs: 6
• LFPTs per TP: 4
• Total measurements: 100
• Orientation: ori0 (0 − 90◦ )

RTP:
• Count RPs: 6
• Count RPs/TPs: 6
• Orientation: ori0 (0 − 90◦ )
Parameters GSM Location Results Performance Diploma Thesis

Tuebingen, 28.6.2010
Stephan Linzner, onlythoughtworks@googlemail.com, @onlythoughtwork

EBERHARD -KARLS -UNIVERSITAET TUEBINGEN
Wilhelm-Schickard-Institut fuer Informatik
Lehrstuhl Rechnerarchitektur

https://github.com/otw/SmartSpace Implementation of new:
- Sensors
- Algorithms
- Data filters

Geo-Mapping
- Seamless indoor/outdoor integration
- Unify implementation for android location
providers (facade, wrapper)

Outsourcing of localization to the cloud
- Google App Engine Backend (already in the works)

Implementation of pedestrian navigation component
Develop smarter localization algorithms
- Technology (Context-aware, accuracy)
- Performance (Lazy loading, fastest technology)
- Energy (Most efficient technology) equipped with multiple sensors
A new generation of mobile phones Wifi
GSM/CDMA
Bluetooth
Accelerometer
Electric Compass
Gyroscope
Camera
Light
Infrared
Audio
enables Wifi, 3 floors match RP: Total, Hit, Miss Wifi, 3 floors: Precesion Wifi, 3 floors: Accuracy Wifi, 3rd floor: Precision Wifi, 3rd floor: Accuracy GSM, Sand RP: Total, Hit, Miss and... but... G1 Droid X Nexus One
Full transcript