Abstract
[Japanese | Thesis | Researches in Minoh Lab | Minoh Lab]


Automatic Imaging Method for Lectures Based on Location and Speech Volume of Objects


We propose an automatic imaging method for lectures based on the location and the speech volume of a lecturer and students.

The method focuses on user's understanding of a lecture by obtaining presentation information. The method controls cameras and selects video images from the cameras based on ``Dynamic Situation'', which is estimated by the location and the speech volume of a lecturer and students. For browsing the video image, the method can segment and index the video image based on the dynamic situation.

We verified the method through the experiments on distance learning and lecture recording. The result is rated highly on the questionnaire survey.


Go back to Thesis Page