Online tracking of multiple objects using WiSARD

Rafael Lima de Carvalho (1, 2) , Danilo S. C. Carvalho (1) , Felix Mora-Camino (3) , Priscila V. M. Lima (4) , Felipe M. G. França (1)

1 COPPE-UFRJ - Instituto Alberto Luiz Coimbra de Pós-Graduação e Pesquisa de Engenharia
2 UFT - Universidade Federal do Tocantins
3 MAIAA-AUTO - ENAC Equipe MAIAA-AUTO
4 UFRJ - Universidade Federal do Rio de Janeiro

This paper evaluates the WiSARD weightless model as a classification system on the problem of tracking multiple objects in real- time. Exploring the structure of this model, the proposed solution applies a re-learning stage in order to avoid interferences caused by background noise or variations in the target shape. Once the tracker finds a target at the first time, it applies only local searches around the neighborhood in order to have fast response. This approach is evaluated through some experiments on real-world video data.

Domaines: Sciences de l'ingénieur [physics]; Automatique / Robotique

Rafael Lima de Carvalho, Danilo S. C. Carvalho, Felix Mora-Camino, Priscila V. M. Lima, Felipe M. G. França. Online tracking of multiple objects using WiSARD. ESANN 2014, 22st European Symposium on Artificial Neural Networks, Computational Intelligence And Machine Learning, Apr 2014, Bruges, Belgium. pp 541-546. ⟨hal-01059678⟩