Mice and larvae tracking using a particle filter with an auto-adjustable observation model

  • Authors:

  • Hemerson Pistori;Valguima Victoria Viana Aguiar Odakura;João Bosco Oliveira Monteiro;Wesley Nunes Gonçalves;Antonia Railda Roel;Jonathan de Andrade Silva;Bruno Brandoli Machado

  • Affiliations:

  • Biotechnology Department, Dom Bosco Catholic University, Campo Grande, MS, Brazil and Federal University of Mato Grosso do Sul, Campo Grande, MS, Brazil;Faculty of Exact Science and Technology, Federal University of Grande Dourados, Dourados, MS, Brazil;Biotechnology Department, Dom Bosco Catholic University, Campo Grande, MS, Brazil;São Paulo University, São Carlos, SP, Brazil;Biotechnology Department, Dom Bosco Catholic University, Campo Grande, MS, Brazil;São Paulo University, São Carlos, SP, Brazil;São Paulo University, São Carlos, SP, Brazil

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 2010

Quantified Score

Hi-index 0.10

Visualization

Abstract

This paper proposes a novel way to combine different observation models in a particle filter framework. This, so called, auto-adjustable observation model, enhance the particle filter accuracy when the tracked objects overlap without infringing a great runtime penalty to the whole tracking system. The approach has been tested under two important real world situations related to animal behavior: mice and larvae tracking. The proposal was compared to some state-of-art approaches and the results show, under the datasets tested, that a good trade-off between accuracy and runtime can be achieved using an auto-adjustable observation model.