Spiral Particle Distribution for Template based Tracking

Autor:	Pleština, Vladimir, Papić, Vladan
Jazyk:	angličtina
Rok vydání:	2019
Předmět:	particle filter template-based tracking spiral particle distribution
Popis:	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.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=57a035e5b1ae::d3b4e6215a5a21953624db64e3d8c94c https://www.bib.irb.hr/1020847 Zobrazit plný text záznamu