Page 206 - DCAP208_Management Support Systems

Unit 12: Applications of Neural Network

Notes
Did u know? It is generally recognised that traditional implementation of radiosity is
computationally very expensive and therefore not feasible for use in VR systems where
practical data sets are of huge complexity.

In the original thesis, we introduce two new methods and several hybrid techniques to the
radiosity research community on using radiosity in VR applications.
For example, in figure 12.9, flyby, walkthrough and a virtual space are first introduced and in
figure 12.10, we showcase one of the two novel methods which was proposed using Neural
Network technology.

Figure 12.9: Introduction to Flyby, Walkthrough and Virtual Space

Figure 12.10: ROVER

Source: http://tralvex.com/pub/nap/#CoEvolution of Neural Networks for Control of Pursuit & Evasion

12.2.5 Using HMM’s for Audio-to-Visual Conversion

One emerging application which exploits the correlation between audio and video is speech-
driven facial animation. The goal of speech-driven facial animation is to synthesize realistic
video sequences from acoustic speech. Much of the previous research has implemented this
audio-to-visual conversion strategy with existing techniques such as vector quantization and
neural networks. Here, they examine how this conversion process can be accomplished with
hidden Markov models (HMM).
(a) Tracking Demo: The parabolic contour is fit to each frame of the video sequence using a
modified deformable template algorithm. The height between the two contours, and the
width between the corners of the mouth can be extracted from the templates to form our
visual parameter sets.

LOVELY PROFESSIONAL UNIVERSITY 199