15th Triennial World Congress of the International Federation of Automatic Control
  Barcelona, 21–26 July 2002 
VISUAL TRACKING FOR MOVING OBJECT BY INVARIANT ACTIVE CONTOUR MODEL
Won Kim and Ju-Jang Lee
Department of Electrical Engineering and Computer Science
Korea Advance Institute of Science and Technology
373-1 Kusong-dong, Yusong-gu, Taejon, Korea, 305-701
E-mail: kimwon@odyssey.kaist.ac.kr, jjlee@ee.kaist.ac.kr

In case where strong a priori knowledge about the object being analyzed is available, it can be embedded into the formulation of the snake model. When prior knowledge of shape is available for a specific application, information concerning the shape of the desired objects can be incorporated into the formulation of the snake model as an active contour model. This active contour model can have more robust tracking performance for the weak edge cases because the snaxels of active contour model on weak edges can estimate the likelihood from a priori knowledge about target’s shape and the relations with neighbor snaxels. In this paper we show Five points algorithm can be applied to design invariant energy and the effectiveness of the snake designed on this new concept in robuster tracking for moving object in visual space than the standard snake.
Keywords: Snake; Active Contour Models; Visual Tracking; Invariant
Session slot T-Tu-E20: Application of Robotics/Area code 1d : Robotics