Automating camera management for lecture room environments
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Building an intelligent camera management system
MULTIMEDIA '01 Proceedings of the ninth ACM international conference on Multimedia
Lessons learned from eClass: Assessing automated capture and access in the classroom
ACM Transactions on Computer-Human Interaction (TOCHI)
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Podcasting computer science E-1
Proceedings of the 38th SIGCSE technical symposium on Computer science education
Lecture video capture for the masses
Proceedings of the 12th annual SIGCSE conference on Innovation and technology in computer science education
An automated end-to-end lecture capture and broadcasting system
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Restoration of out-of-focus lecture video by automatic slide matching
Proceedings of the international conference on Multimedia
Multimedia multi-device educational presentations preserved as interactive multi-video objects
Proceedings of the 19th Brazilian symposium on Multimedia and the web
Hi-index | 0.00 |
Although recording and streaming lecture videos is becoming popular, large-scale lecture recording is still a difficult task for many universities. Auto lecture recording systems with robotic tripod or smart sensors are too expensive to be standard equipment in many classrooms. A simple solution of human-operated recording is also resource intensive from the perspective of hiring, training, and managing operators. A possible solution for the problem is the combination of recording with a stationary high-definition camcorder and post-processing of camerawork generation that traces regions of interest. However, automatic recording systems in high-definition are still uncommon and expensive. In this paper, we describe the automated lecture recording system developed in our lab based on years of experience in manual lecture recording in classrooms. In the system, we use an AVCHD camcorder and microserver for automated recording. The camcorder makes high-definition video capture boards unnecessary since it records videos as files on its filesystem; capturing now becomes an easy task of copying files. With this idea, we can make the system small and cost effective. Lectures are automatically recorded according to the schedule specified by iCalendar data, and recorded videos are automatically processed with a camerawork engine we have developed to generate NTSC resolution videos.