Automatic selection of object recognition methods using reinforcement learning
Nenhuma Miniatura disponível
Citações na Scopus
8
Tipo de produção
Artigo
Data
2010
Autores
Reinaldo Bianchi
RAMISA, A.
DE MANTARAS, R. L.
RAMISA, A.
DE MANTARAS, R. L.
Orientador
Periódico
Studies in Computational Intelligence
Título da Revista
ISSN da Revista
Título de Volume
Citação
BIANCHI, R. RAMISA, A.; DE MANTARAS, R. L. Automatic selection of object recognition methods using reinforcement learning. Studies in Computational Intelligence, v. 262, p. 421-439, 2010.
Texto completo (DOI)
Palavras-chave
Resumo
Selecting which algorithms should be used by a mobile robot computer vision system is a decision that is usually made a priori by the system developer, based on past experience and intuition, not systematically taking into account information that can be found in the images and in the visual process itself to learn which algorithm should be used, in execution time. This paper presents a method that uses Reinforcement Learning to decide which algorithm should be used to recognize objects seen by a mobile robot in an indoor environment, based on simple attributes extracted on-line from the images, such as mean intensity and intensity deviation. Two state-of-the-art object recognition algorithms can be selected: the constellation method proposed by Lowe together with its interest point detector and descriptor, the Scale-Invariant Feature Transform and Nistér and Stewénius Vocabulary Tree approach. A set of empirical evaluations was conducted using a household mobile robots image database, and results obtained shows that the approach adopted here is very promising. © 2010 Springer-Verlag Berlin Heidelberg.