Date of Award
8-2018
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Electrical and Computer Engineering (Holcomb Dept. of)
Committee Member
Adam Hoover
Committee Member
Jacob Sorber
Committee Member
Ian Walker
Abstract
Reliable and accurate room-level occupancy-tracking systems can enable many new advances in sensors and applications of modern smart buildings. This allows buildings to be more capable of adapting to the needs of their occupants in their day-to-day activities and better optimize certain resources, such as power and air conditioning, to do so. Unfortunately, existing occupancy-tracking systems are plagued by large size, high energy consumption, and, unsurprisingly, short battery lifetimes.
In this paper, we present Waldo, a batteryless, room-level occupancy monitoring sensor that harvests energy from indoor ambient light reflections, and uses changes in these reflections to detect when people enter and exit a room. Waldo is mountable at the top of a doorframe, allowing for detection of a person and the direction they are traveling at the entry and exit point of a room. We evaluated the Waldo sensor in an office-style setting under mixed lighting conditions (natural and artificial) on both sides of the doorway with subjects exhibiting varying physical characteristics such as height, hair color, gait, and clothing. 651 number of controlled experiments were ran on 6 doorways with 12 individuals and achieved a total detection accuracy of 97.38%. Further, it judged the direction of movement correctly with an accuracy of 95.42%. This paper also evaluates and discusses various practical factors that can impact the performance of the current system in actual deployments.
This work demonstrates that ambient light reflections provide both a promising low-cost, long-term sustainable option for monitoring how people use buildings and an exciting new research direction for batteryless computing.
Recommended Citation
Desai, Harsh, "Waldo: Batteryless Occupancy Monitoring with Reflected Ambient Light" (2018). All Theses. 3244.
https://open.clemson.edu/all_theses/3244