Title :
Multiple Mice Tracking using a Combination of Particle Filter and K-Means
Author :
Gonçalves, Wesley Nunes ; Monteiro, J.B.O. ; De Silva, Jonathan Andrade ; Machado, Bruno Brandoli ; Pistori, Hemerson ; Odakura, Valguima
Author_Institution :
Dom Bosco Catholic Univ., Campo Grande
Abstract :
This paper presents a new approach to multiple objects tracking that combines particle filters and k-means. The approach has been tested under an important real world situation, related to pharmacological development, which has also proved to serve as an interesting ground-truth dataset provider for the evaluation of tracking algorithms. The obtained results are then compared to other models. The promising results of these experiments are presented.
Keywords :
computer vision; particle filtering (numerical methods); target tracking; computer vision; k-means; multiple mice tracking; particle filters; Animal behavior; Application software; Computer graphics; Computer vision; Humans; Laboratories; Mice; Particle filters; Particle tracking; Predictive models;
Conference_Titel :
Computer Graphics and Image Processing, 2007. SIBGRAPI 2007. XX Brazilian Symposium on
Conference_Location :
Minas Gerais
Print_ISBN :
978-0-7695-2996-7
DOI :
10.1109/SIBGRAPI.2007.39