We use Scaled Gaussian Process
Latent Variable Models (SGPLVM) to learn prior
models of 3D human pose for 3D people
tracking. The SGPLVM simultaneously optimizes
a low dimensional embedding of the high-dimensional
pose data and a density function that both gives
higher probability to points close to training
data and provides a nonlinear probabilistic mapping
from the low-dimensional latent space to the full-dimensional
pose space. The SGPLVM is a natural choice when
only small amounts of training data are available.
We demonstrate our approach with two distinct
motions, golfing and walking.
We show that the SGPLVM sufficiently constrains
the problem such that tracking can be accomplished
with straighforward deterministic optimization.
We propose an approach to incorporating
dynamic models into the human body tracking process
that yields full 3--D reconstructions from monocular
We formulate the tracking problem in terms of
minimizing a differentiable criterion whose differential
structure is rich enough for successful optimization
using a simple hill-climbing approach as opposed
to a multi-hypotheses probabilistic one. In other
words, we avoid the computational complexity of
multi-hypotheses algorithms while obtaining excellent
results under challenging conditions.
To demonstrate this, we focus
on monocular tracking of a golf
swing from ordinary video. It involves both dealing
potentially very different swing styles, recovering
arm motions that are perpendicular to the camera
plane and handling strong self-occlusions.
We use temporal
motion models based on Principal
Component Analysis (PCA)
to formulate the tracking problem as one of minimizing
differentiable objective functions. Our experiments
show that the differential structure of these
objective functions is rich enough to take advantage
of standard deterministic
optimization methods, whose computational requirements
are much smaller than those of probabilistic ones
and can nevertheless yield very good results even
in difficult situations.
We show the effictiveness of
our approach compare to probabilistic
approaches, that while effective, require exponentially
large amounts of computation as the number of
degrees of freedom in the model increases.
Most current gait analysis algorithms
rely on appearance-based methods that do not explicitly
take into account the 3--D nature of the motion.
In this work, we propose an approach that relies
on robust 3--D tracking
and has the potential to overcome the limitations
of appearance-based approaches,
such as their sensitivity to occlusions and changes
in the direction of motion.
Representing motions as linear
sums of principal components has become a widely
accepted animation technique. While powerful,
the simplest version of this approach is not particularly
well suited to modeling the specific style of
an individual whose motion had not yet been recorded
when building the database: It would take an expert
to adjust the PCA weights to obtain a motion style
that is indistinguishable from his. Consequently,
when realism is required, current practice is
to perform a full motion capture session each
time a new person must be considered.
We extend the PCA approach so
that this requirement can be drastically reduced:
For whole classes of motion such as walking or
running, it is enough to observe the newcomer
moving only once at a particular speed using either
an optical motion capture system or a simple pair
of synchronized video cameras. This one observation
is used to compute a set of principal component
weights that best approximates the motion and
to extrapolate in real-time realistic animations
of the same person walking or running at different