Usage
  • 41 views
  • 39 downloads

Multiple Occupant Indoor Localization

  • Author / Creator
    Vatanpour Azghandi, Masoud
  • Recognizing the indoor activities of people is a key functionality of smart homes, since it is a prerequisite for any supportive action in service of the occupants. In this thesis, we investigate the multiple occupant localization problem in indoor environments. We developed a method based on the use of inexpensive passive infrared motion sensors together with Radio Frequency IDentification (RFID) readers. In our method, the former type of sensors, placed throughout the space, recognize movement and RFID readers, placed selectively at key locations, unambiguously recognize individuals’ locations (some or all of the occupants are assumed to be wearing passive RFID tags) as they pass through their coverage area. Due to their high cost and generally cumbersome placement requirements, RFID readers must be judiciously placed. Thus, we study the placement of the readers such that the occupants trajectory ambiguity is reduced. We rely on a heat-map representing the frequency with which individuals visit locations as they move through the indoor space and on models of coverage for the Passive InfraRed (PIR) sensors and RFID readers and develop a heuristic for the RFID reader placement. We also revisit the problem of cost-efficient PIR sensor placement for high-quality in- door localization, extending it for sensors with diverse coverage footprints, and the oc- clusion effects due to obstructions typically found in indoor environments. The objective is the placement of the smallest number of sensors with the right combination of foot- prints. Given the vast search space of possible placement and footprint combinations, we adopt an evolutionary technique. We demonstrate that our technique performs faster and/or produces more accurate results when compared to previously proposed greedy methods. Furthermore, our technique is flexible in that adding new sensor footprints can be trivially accomplished. We evaluate the effectiveness of our method in both RFID reader and PIR sensor placement under different occupancy conditions with simulations.

  • Subjects / Keywords
  • Graduation date
    2016-06
  • Type of Item
    Thesis
  • Degree
    Master of Science
  • DOI
    https://doi.org/10.7939/R3251FT16
  • License
    This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.
  • Language
    English
  • Institution
    University of Alberta
  • Degree level
    Master's
  • Department
    • Department of Computing Science
  • Supervisor / co-supervisor and their department(s)
    • Stroulia, Eleni (Computing Science)
    • Nikolaidis, Ioanis (Computing Science)
  • Examining committee members and their departments
    • Friggstad, Zac (Computing Science)
    • Zhang, Hong (Computing Science)