IPS: A Ubiquitous Indoor Positioning System






Floorplan construction from motion traces

Although GPS has been considered a ubiquitous outdoor localization technology, it cannot be used in indoor environments due the requirement of maintaining a line of sight with satellites; We are still far from a similar technology for indoor environments. While a number of technologies have been proposed for indoor localization, such as ultrasonic, RFID, GSM and WiFi-based techniques, they are either providing a coarse grained location information, require dedicated infrastructure and/or an expensive calibration. This affect their ubiquitous deployment. A ubiquitous indoor positioning system is envisioned to be deployed on a large scale worldwide, with minimum overhead, to work with heterogeneous devices, and to allow users to roam seamlessly from indoor to outdoor environments. Such a system will enable a wide set of applications including worldwide seamless direction finding between indoor locations, enhancing first responders’ safety by providing anywhere localization and floor plans, and providing a richer environment for location-aware social networking applications.

Our goal in the ubiquitous Indoor Positioning System project (IPS) is to develop a true ubiquitous indoor localization system that works in indoor places as well as outdoor spaces. It can be used in any building, with zero setup and calibration overhead, and works with commodity mobile devices. IPS adapts a crowdsourcing based approach that transparently and anonymously collects sensor data from normal users and visitors moving inside the building. The design of IPS includes novel algorithms for generating accurate user traces and constructing a training information database for different localization techniques as needed. A cloud-based IPS service  performs multi-modal sensor fusion between all the collected sensor data to accurately track the user’s motion inside the building. IPS also employs the inertial sensors (accelerometer, magnetometer) for identifying typical user activities for indoor spaces (climbing stairs, riding an escalator or using an elevator). Those activities are used for estimating the locations of the points of interest (stairs, elevators, escalators) inside the building, which can be used also to reset the accumulated error in motion.

IPS also addresses the problem of automatic construction of a worldwide indoor floorplans database by leveraging the embedded sensors in today’s cell phones, such as accelerometers, compasses, and cameras, as a distributed floor plan generation tool. By collecting motion traces from users moving inside the building, IPS constructs a  floorplan that captures many details like the number of rooms and corridors, their locations among others. The project also targets discovering higher level semantic information about the discovered spaces, such as the space owner.

Sponsors

This project is funded by a Google Research Award, a joint TWAS-AAS-Microsoft Award and a research grant from ITIDA.

People

  • Prof. Moustafa Youssef
  • Moustafa Alzantot
  • Reem El-Khouly
  • Amal Lotfy
  • Moustafa Elhamshary
  • Nesma Mohssen
  • Rana Momtaz
  • Heba Aly
  • Rizanne Elbakly
  • Reham Mohamed
  • Heba Abdelnasser

Collaborators:

Talks:

Videos and Media Coverage:

NaviRize:

 

CrowdInside:

UnLoc:

List of Publications

Conference Publications

  1. A Robust Zero-Calibration RF-based Localization System for Realistic Environments
    Rizanne Elbakly, Moustafa Youssef
    IEEE International Conference on Sensing, Communication and Networking (SECON 2016).
    Download: PDF.
  2. Towards Truly Ubiquitous Indoor Localization on a Worldwide Scale – Vision Paper
    Moustafa Youssef
    The 23rd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2015).
    PDF
  3. A Calibration-free RF Localization System
    Rizanne Elbakly, Moustafa Youssef
    The 23rd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2015), Short paper.
    PDF
  4. Activity Recognition of Railway Passengers by Fusion of Low-Power Sensors in Mobile Phones
    Moustafa Elhamshary, Akira Uchiyama, Hirozumi Yamaguchi, Tero Higashino and Moustafa Youssef
    The 23rd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2015), Short paper.
    PDF
  5. SemanticSLAM: Using Environment Landmarks for Unsupervised Indoor Localization
    Heba Abdelnasser, Reham Mohamed, Ahmed Elgohary, Moustafa Farid, He Wang, Souvik Sen, Romit Choudhury, Moustafa Youssef
    IEEE Transactions on Mobile Computing 2015.
    Download: PDF
  6. SemSense: Automatic Construction of Semantic Indoor Floorplans
    Moustafa Elhamshary, Moustafa Youssef
    International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2015.
    Download: PDF
  7. CheckInside: A Fine-grained Indoor Location-based Social Network
    Moustafa Elhamshary, Moustafa Youssef
    The 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp ’14). Acceptance Rate 20.7%.
    Download: PDF

  8. It’s the Human that Matters: Accurate User Orientation Estimation for Mobile Computing Applications
    Nesma Mohssen, Rana Momtaz, Heba Aly, Moustafa Youssef
    The 11th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (Mobiquotous 2014). Acceptance Rate 19.3%.
    Download: PDF

  9. CrowdInside: Automatic Construction of Indoor Floorplan
    Moustafa Alzantot, Moustafa Youssef
    The 20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL GIS 2012). Acceptance Rate 15.4%.
    Download: PDF

  10. No Need to War-Drive: Unsupervised Indoor Localization
    He Wang, Souvik Sen,Ahmed Elgohary,Moustafa Alzantot, Moustafa Youssef, Romit Roy Choudhury
    The 10th International Conference on Mobile Systems, Applications and Services (MobiSys’12). Acceptance rate 17%.
    Download: PDF


  11. UPTIME: Ubiquitous Pedestrian Tracking using Mobile Phones
    Moustafa Alzantot, Moustafa Youssef
    IEEE Wireless Communications and Networking Conference (WCNC 2012), Paris, France, April 1-4, 2012.
    Download: PDF

Posters and Demos

  1. Demonstrating CrowdInside : A System for the Automatic Construction of Indoor Floor-plans (Demo)
    Moustafa Alzantot, Moustafa Youssef
    IEEE International Conference on Pervasive Computing and Communications (PerCom 2013)
    Download: PDF
  2. Unsupervised Indoor Localization (Demo)
    He Wang,  Souvik Sen, Alex Mariakakis, Romit Roy Choudhury, Ahmed Elgohary, Moustafa Farid, Moustafa Youssef
    The 10th International Conference on Mobile Systems, Applications and Services (MobiSys’12).
    Download: PDF 
  3. IPS: Ubiquitous Indoor Positioning System (Poster)
    Moustafa Alzantot, Reem elkholy, Amal Lotfy, Moustafa Youssef
    The Eighth Annual International Conference on Mobile and Ubiquitous Systems:Computing, Networking and Services (MobiQuitous 2011)
    Download: PDF