Automatic Capture of Significant Points in a Computer Based Presentation

Abstract

We describe an automatic classroom capture system that detects and records significant (stable) points in lectures by sampling and analyzing a sequence of screen capture frames from a PC used for presentations, application demonstrations, etc. The system uses visual inspection techniques to scan the screen capture stream to identify points to store. Unlike systems that only detect and store slide presentation transitions, this system detects and stores significant frames in any style of lecture using any program. The system is transparent to the lecturer and requires no software or training. It has been tested extensively on lectures with multiple applications and pen-based annotations and has successfully identified "significant" frames (frames that represent stable events such as a new slide, bullet, figure, inked comment, drawing, code entry, application entry etc.). The system can analyze over 20000 frames and typically identifies and stores about 100 significant frames within minutes of the end of a lecture. A time stamp for each saved frame is recorded and will in the future be used to compile these frames into a jMANIC [16] multimedia record of the class.

Automatic capture and presentation creation from multimedia lectures

“…During the 2006-2007 academic year, data were captured using only the computer capture system. In addition, the computer capture system was demonstrated at a number of conferences (including [10]) and other venues. The computer capture system was also tested with the UP delivery system in a software engineering class in Fall 2007 [4].…”

“…The set of all sampled images from these classes serve as a significant base of experimental data that can be used to refine and evaluate the algorithms. The work reported in [10] and [11] describe our analysis of the quality of the captured and stored images in terms of duplicated and/or missed images, noise, etc.…”

“…As noted, the captured content can also be sent to students using a modified UP system [4]. The PAOL capture algorithms are described in greater detail and with greater comparison with similar systems in [10] and [11].…”

Portable Lecture Capture that Captures the Complete Lecture

“…Over 20 years [5], [16], [17], [18], [19] of surveys, discussions, and focus groups show that viewers want to identify gestures, emphases, etc. and are less concerned with the size, resolution, and overall quality of the video as long as clear, detailed, and synchronized whiteboard and/or projected images can be found.…”

Whiteboard Content Extraction and Analysis for the Classroom Environment

“…PAOL automatically captures and indexes lectures from any combination of computer and whiteboard content. Whiteboard content capture compliments the PAOL computer content capture [1] and, with captured video and indexes, provides a complete record of classroom activities.…”