Estimating Positions of Students in a Classroom from Camera Images Captured by the Lecturer's PC

We propose to estimate the position of each student in a classroom by observing the classroom with a camera attached on the notebook or tablet PC of the lecturer. The position of each student in the classroom is useful to keep observing his/her learning behavior as well as taking attendance, continuously during the lecture. Although there are many previous works on estimating positions of humans from camera images in the field of computer vision, the arrangement of humans in a classroom is quite different from usual scenes. Since students in a classroom sit on closely-spaced seats, they appear with many overlaps among their regions in camera images. To cope with this difficulty, we keep observing students to capture their faces once they appear, and recover the positions in the classroom with the geometric constraint that requires those positions to be distributed on the same plane parallel to the floor.