Description/Abstract/Artist Statement
The classroom occupancy detection system aims to limit the spread of COVID-19 and support mitigation efforts advised by national and international health organizations by enforcing social distancing in classroom environments. Utilizing the RaspberryPi computer and its compatible camera module, the system accomplishes this by capturing an overhead image of a classroom and assessing the image for violations. Here, violations are defined as the presence of adjacent occupied seats. As such, for an acceptable state to be detected, there must be at least one vacant seat between all students seated in the classroom. The system communicates the classroom’s state with two light-emitting diode circuits, illuminating a green LED to denote an acceptable state and a red LED to denote one or more violations. System performance was evaluated under three test case scenarios with a simulated classroom environment. The test case results revealed that the system can accurately detect acceptable conditions, as well as the presence of one or more seating violations. However, the inability to account for human behaviors and complex seating layouts limits the system’s real-world functionality. Despite its current limitations, this project suggests that image processing techniques may be a feasible solution to support social distancing in the classroom.
Faculty Advisor/Mentor
Ayman Elmesalami, Soad Ibrahim
College Affiliation
College of Sciences
Presentation Type
Oral Presentation
Disciplines
Other Computer Sciences
Session Title
Colleges of Sciences UG Research #1
Location
Zoom
Start Date
3-19-2022 1:00 PM
End Date
3-19-2022 2:00 PM
Upload File
wf_yes
Included in
COVID-19 Classroom Occupancy Detection System
Zoom
The classroom occupancy detection system aims to limit the spread of COVID-19 and support mitigation efforts advised by national and international health organizations by enforcing social distancing in classroom environments. Utilizing the RaspberryPi computer and its compatible camera module, the system accomplishes this by capturing an overhead image of a classroom and assessing the image for violations. Here, violations are defined as the presence of adjacent occupied seats. As such, for an acceptable state to be detected, there must be at least one vacant seat between all students seated in the classroom. The system communicates the classroom’s state with two light-emitting diode circuits, illuminating a green LED to denote an acceptable state and a red LED to denote one or more violations. System performance was evaluated under three test case scenarios with a simulated classroom environment. The test case results revealed that the system can accurately detect acceptable conditions, as well as the presence of one or more seating violations. However, the inability to account for human behaviors and complex seating layouts limits the system’s real-world functionality. Despite its current limitations, this project suggests that image processing techniques may be a feasible solution to support social distancing in the classroom.