A WiSARD-based multi-term memory framework for online tracking of objects

Daniel N Do Nascimiento (1) , Rafael Lima de Carvalho (2, 1) , Felix Mora-Camino (2) , Priscila V. M. Lima (3) , Felipe M G Franca (1)

1 COPPE-UFRJ - Instituto Alberto Luiz Coimbra de Pós-Graduação e Pesquisa de Engenharia
2 MAIAA - ENAC - Laboratoire de Mathématiques Appliquées, Informatique et Automatique pour l'Aérien
3 UFRJ - Universidade Federal do Rio de Janeiro

In this paper it is proposed a generic object tracker with real- time performance. The proposed tracker is inspired on the hierarchical short-term and medium-term memories for which patterns are stored as discriminators of a WiSARD weightless neural network. This approach is evaluated through benchmark video sequences published by Babenko et al. Experiments show that the WiSARD-based approach outperforms most of the previous results in the literature, with respect to the same dataset.

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

Daniel N Do Nascimiento, Rafael Lima de Carvalho, Felix Mora-Camino, Priscila V. M. Lima, Felipe M G Franca. A WiSARD-based multi-term memory framework for online tracking of objects. ESANN 2015, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2015, Bruges, Belgium. pp.978-287587014-8, ⟨10.13140/RG.2.1.3387.5687⟩. ⟨hal-01193153⟩