Evaluation of Stopping Criterion in Contour Tracing Algorithms

Under the conditions of fasting moving, shape changing and partial occlusion of target, Now mostly tracing algorithms are difficult to get accurate contour of target, for these problems, a novel contour tracing algorithm based on particle filter and fast level set is proposed. Firstly, the particle filter algorithm is adopted to estimate moving target's boundary contour. Then, according to the nearest neighbour decision method, a new the velocity function of fast level set is found, the strongpoint of the function is that the tracking algorithm is fit for target and background changing. Finally, the contour tracing is realized by evolving the zero level set curves using fast level set algorithm. Experiments for representative image sequences show that this algorithm can trace the rigid and non-rigid target contour under the complex environments. The result indicates that this algorithm is robust and accurate compared with other tracing algorithms. Evaluation of contour tracing algorithms and how the start and Stopping Criteria’s used in various contour tracing algorithms. Concentrated to show the stopping criteria’s, and which criteria is the best to find contour of pixels of an image and comparison of different stopping criteria’s. The resulting contours can be used to create 3D reconstructions.