Multilayered Presentation Architecture in Intelligent eLearning Systems

Abstract

eLearning systems have become essential in enabling lectures from experts accessible to masses spread across distant geographic location. The digital representation of different components in the instructor’s environment, such as the presentation screen and the instructor’s video, in a remote location is often spatially disconnected. This results in missing out spatially related gestural cues such as pointing at the screen by the instructor. This paper discusses a method of creating a spatially connected, close to natural view of the instructor’s environment by overlaying the instructor’s video defined by his contour over the presentation screen content. This technique involves a calibration step required to match the camera perspectives of the different video components. We present a real-time and robust calibration technique allowing for automatic recalibration in a dynamic classroom scenario which involves changes in camera position and pan, tilt and zoom parameters.