| |
Abstract:
We have constructed an inexpensive, video-based, motorized
tracking system that learns to track a head. It uses real time
graphical user input as a supervisory signal to train a
convolutional neural network. The inputs to the neural network
consist of normalized luminance and chrominance images and motion
information from frame differences. Subsampled images are also used
to provide scale invariance. During the online training phase, the
neural network adjusts the input weights depending upon the
reliability of the different channels in the surrounding
environment. This allows the system to robustly track a head even
when other objects are moving within a cluttered background.
|
