We propose a novel method for object tracking using prototype-based deforma
ble template models. To track an object in an image sequence, we use a crit
erion which combines two terms: the frame-to-frame deviations of the object
shape and the fidelity of the modeled shape to the Input image. The deform
able template model utilizes the prior shape information which is extracted
from the previous frames along with a systematic shape deformation scheme
to model the object shape in a new frame. The following image information I
s used in the tracking process: 1) edge and gradient information: the objec
t boundary consists of pixels with large image gradient, 2) region consiste
ncy: the same object region possesses consistent color and texture througho
ut the sequence, and 3) interframe motion: the boundary of a moving object
is characterized by large interframe motion. The tracking proceeds by optim
izing an objective function which combines both the shape deformation and t
he fidelity of the modeled shape to the current image (in terms of gradient
, texture, and interframe motion). The inherent structure in the deformable
template. together with region, motion, and image gradient cues. makes the
proposed algorithm relatively insensitive to the adverse effects of weak i
mage features and moderate amounts of occlusion.