Title: Active Hidden Models for Tracking with Kernel Projections

Authors: Samuel Epstein and Margrit Betke

Date: March 10, 2009

We introduce Active Hidden Models (AHM) that utilize kernel methods
traditionally associated with classification.  We use AHMs to track
deformable objects in video sequences by leveraging kernel
projections.  We introduce the `` subset projection'' method which
improves the efficiency of our tracking approach by a factor of
ten. We successfu lly tested our method on facial tracking with
extreme head movements (including full 180-degree head rotation), fa
cial expressions, and deformable objects.  Given a kernel and a set of
training observations, we derive unbiased e stimates of the accuracy
of the AHM tracker.  Kernels are generally used in classification
methods to make trainin g data linearly separable.  We prove that the
optimal (minimum variance) tracking kernels are those that make the
training observations linearly dependent.