Page 210 - DCAP208_Management Support Systems
P. 210
Unit 12: Applications of Neural Network
Faces are tracked robustly by integrating motion and model-based tracking. Notes
(a) Tracking in low resolution and poor lighting conditions.
Figure 12.15: Tracking in Low Resolution
Source: http://tralvex.com/pub/nap/#CoEvolution of Neural Networks for Control of Pursuit & Evasion
(b) Tracking two people simultaneously: lock is maintained on the faces despite unreliable
motion-based body tracking.
Figure 12.16: Tracking Two People Simultaneously
Source: http://tralvex.com/pub/nap/#CoEvolution of Neural Networks for Control of Pursuit & Evasion
12.2.10 A Three Layer Feedforward Neural Network
A three layer feedforward neural network with two input nodes and one output node is trained
with backpropagation using some sample points inside a circle in the 2D plane. The evolution of
decision regions formed during the training are shown in the following MPEG movies.
Figure 12.17: Sequence 3, Sequence 10
Source: http://tralvex.com/pub/nap/#CoEvolution of Neural Networks for Control of Pursuit & Evasion
LOVELY PROFESSIONAL UNIVERSITY 203
