Different approaches on the implementation of implicit polynomials in visual tracking /

Official URL: http://risc01.sabanciuniv.edu/record=b1147835 (Table of Contents)

Visual tracking has emerged as an important component of systems in several application areas including vision-based control, human-computer interfaces, surveillance, agricultural automation, medical imaging and visual reconstruction. The central challenge in visual tracking is to keep track of the pose and location of one or more objects through a sequence of frames. Implicit algebraic 2D curves and 3D surfaces are among the most powerful representations and have proven very useful in many model-based applications in the past two decades. With this approach, objects in 2D images are described by their silhouettes and then represented by 2D implicit polynomial curves. In our work, we tried different approaches in order to efficiently apply the powerful implicit algebraic 2D curve representation to the phenomenon of visual tracking. Through the proposed concepts and algorithms, we tried to reduce the computational burden of fitting algorithms. Besides showing the usage of this representation on boundary data simulations, use of the implicit polynomial as a representative of the target region is also experimented on real videos.