A stabilized snake constraint for tracking object boundaries

A discrete dynamic model for tracking contours in object boundaries is presented. An active contour in this objective is optimized by a dynamic programming algorithm, for which a new constraint that has simple and stable properties is introduced. The internal energy of the model depends on local behavior of the contour, while the external energy is derived from image features. The algorithm is able to stabilize boundary tracking and well maintain position consistency of snake´s control points between two consecutive frames. The authors prove the constraint is useful to stabilize not only the normal motion of the tracked curve but also a planar motion of the curve