Design and implementation of FPGA based automatic lecture recording system

摘要

Tele-teaching and distance-learning concept is getting much consideration these days since it poses easy access and availability of well-known instructors' lectures and presentations. In relation to video lectures, one of the utmost important concerns is professional video recording. Video recording inside lecture halls requires experienced camera-work professionals, who can record video lecture in an eye-catching way that keep the viewer concentration. To eliminate the overhead of expensive camera-work professionals, recently, image recognition algorithms combined with camera controllers make automatic lecture recording possible. In this article, we present real time implementation of the field programmable gate arrays (FPGA) based automatic lecture recording system. The system comprises of FPGA board, which can take input from analog and/or digital video camera, the ARM processor unit, and camera mounted stepper motor. Real time Image recognition algorithms are used to detect the region of interest (ROI) boundaries, instructor's face, and instructor's movement direction. The stepper motor rotates the mounted camera as directed by the FPGA controller to follow the lecturer and board. Further, the proposed system is designed in a compatible manner that can take input from a variety of video formats. Successful video lecture recording at Hanyang University lecture hall validated the performance of the system.