Toward Robust Features for Remote Audio-Visual Classroom.
Isaac Schlittenhart, Jason Winters, Kyle Springer, Atsushi Inoue · 2011
We present two studies on robustness of feature extractions for an remote classroom intelligent autopilot: (1) robust fea-ture extractions and (2) a simple automated calibration of we-bcams. For the robust feature extractions, use of quantified vectors is studied as feature extractions of fuzzy classifiers in Perceptual State Machine, i.e. our core Computational Intel-ligence model for this intelligent autopilot. The simple auto-mated calibration of devices is studied mainly for the sake of maximizing device utility. Those studies have shown promis-ing results for actual use of this intelligent autopilot in ordi-nary classrooms that are not necessarily ideal for teleconfer-ence lectures.