In conventional model-based coding schemes, predefined static models are ge
nerally used. These models cannot adapt to new situations, and hence, they
have to be very specific and cannot be generated from a single generic mode
l even though they are very similar. In this letter, we present a model-gen
eration technique that can gradually build a model and dynamically modify i
t according to new video frames scanned. The proposed technique is robust t
o the object's orientation in the view and can be efficiently implemented w
ith a parallel processing technique. As a result, the proposed technique is
more attractive to the practical use of model-based coding techniques in r
eal applications.