Autonomous Lecture Recording with a PTZ Camera While Complying with Cinematographic Rules

Abstract

Nowadays, many lectures and presentations are recorded and broadcasted for teleteaching applications. When no human camera crew is present, the most obvious choice is for static cameras. In order to enhance the viewing experience, more advanced systems automatically track and steer the camera towards the lecturer. In this paper we propose an even more advanced system that tracks the lecturer while taking cinematographic rules into account. On top of that, the lecturer can be filmed in different types of shots. Our system is able to detect and track the position of the lecturer, even with non-static backgrounds and in difficult illumination. We developed an action axis determination system, needed to apply cinematographic rules and to steer the Pan-Tilt-Zoom (PTZ) camera towards the lecturer.

Protocols and software for simplified educational video capture and editing

“…(Wulff and Fecke 2012) developed a cost-effective solution for automatic camera control for lecture recordings. (Hulens et al 2014) proposed an even more advanced system that tracks the lecturer while taking cinematographic rules into account. Some software such as Camstudio (Nickthegeek et al 2013) record all screen and audio activity on the computer and combine them with web camera stream to create video tutorials for school or college class.…”

You’ve Got the Moves, We’ve Got the Motion – Understanding and Designing for Cinematographic Camera Motion Control

“…Autonomous pan-and-tilt cameras are used to autonomously record academic lectures. In the work of Hulens et al [22], the Rule of Thirds 2 is borrowed from cinematography and integrated into the tracking. Zhang and colleagues [36] presented a tele-conferencing system incorporating video and context analysis.…”

TrackLine: Refining touch-to-track Interaction for Camera Motion Control on Mobile Devices

“…They identified core tasks and summarized twenty years of research-driven tool development and evaluation. Besides traditional cinematography, further work was conducted in automated lecture recording [12,[18][19][20], tele-conferencing [10,21] or event broadcasting [1,2,4,9]. Regarding high-level control in particular, as in our case, the most prominent approaches are Through-the-Lens [7], image-based [14] or constraint-based [8,13] control.…”

“…In [16] a computer-vision supported crane was evaluated by following a target that was moved by an industrial robot. In [12] a motorized slider was used to move an action figure, which served as a tracking target for a computer vision based panning system. Without standardized tasks at hand, a system's capabilities are also often documented by picture series as in [15] or by referencing a video as in [11].…”