We present a robust algorithm for point tracking on deformable objects. The key elements are the use of orientation selective rank features (ranklets), local filter adaptation and...
Fabrizio Smeraldi, Alessio Del Bue, Lourdes de Aga...
Background model and tracking became critical components for many vision-based applications. Typically, background modeling and object tracking are mutually independent in many ap...
This paper presents a physical model-based method for recovering and tracking nonrigid motion of elastic objects. The proposed method recovers the motion in terms of actual physic...
Yong Zhang, Dmitry B. Goldgof, Sudeep Sarkar, Leon...
The biggest single obstacle to building effective augmented reality (AR) systems is the lack of accurate wide-area sensors for trackers that report the locations and orientations ...
This work introduces a new pattern recognition model for segmenting and tracking lip contours in video sequences. We formulate the problem as a general nonrigid object tracking me...