Thammasat University Smart Classroom Project : Persons and seats detection system

  • 0

Persons and seats detection system

Thammasat University Smart Classroom Project

DISCRIPTION

▶ Smart Classroom

This research was created as part of the project "Innovative All-around Learning toward Smart Campus Creation" by Dr. Somrudee Deepaisarn and team under the larger-scheme of AI Ready City Networking in RUN Project conceptualized by Prof. Dr. Virach Sornlertlamvanich.

• Our proposed system is an end-to-end camera-based human physical distancing recording system. The system itself takes a video file as input and stores the physical location of the seat and people in every fixed timestamp.

• We implemented the algorithm with the weighted and pre- trained YOLOv3 model of which we specifically selected the function that can be utilized to perform human body detection as follows:

• We have implemented the system for the location estimation of the persons and seats using the camera-based system in order to work out the actual human and seat locations in the classroom.

• As a result of the performance evaluation compared against the accepted value (i.e. the actual physical the distance measured in the classroom),the average error of seat location computed using the proposed system is ±5.25 cm with a standard deviation of 4.64 cm.

Leave a Comment:

Your email address will not be published. Required fields are marked *