WSEAS Transactions on Computers
Print ISSN: 1109-2750, E-ISSN: 2224-2872
Volume 18, 2019
Spiral Particle Distribution for Template based Tracking
Authors: ,
Abstract: This paper presents a new approach for tracking template-based objects based on spiral particle distribution algorithm. Proposed algorithm uses points on Archimedean spiral as possible location of object in next frame. Before applying algorithm, the system is provided with off-line learning of training data. After that, start point is initialized and algorithm for tracking is applied. Tracking starts from initialization location and searches for the best matching point on spiral as a new starting point in the next frame. In this work our algorithm is explained and compared with basic particle filter tracking algorithm. Experiment is demonstrated with real data on Croatian popular amateur game.