|
|
|
CONTOUR BASED OBJECT TRACKING
|
|
Summary:
High level vision tasks for video processing, such as recognition and
understanding, require tracking of complete objects. In this paper, we
propose a contour tracking method for video acquired using mobile
cameras, which can track the complete objects. The proposed method can
track multiple objects, adapt to changing visual features, and handle
occlusions. Our approach has two major components related to visual
features and object shape. Visual features (color, texture) are modeled
by semi-parametric models, where the mixing parameters are
computed using independent opinion polling. The shape prior, which is
used to fill missing observations for occluded objects, is modeled
using parametric models. We formulate the contour energy as a
variational calculus problem, which results in a system of nonlinear
partial integro-differential equations of order one. The energy is
minimized in the gradient descent direction evaluated in the contour
vicinity defined by a band. In this regard, it can be viewed as the
generalization of formerly proposed contour based methods. The
performance of the proposed method is demonstrated on real sequences
with and without complete object occlusions.
|
Supporting
Agency:
|
Related
Publications:
|
|
|
