Visual attention and novelty detection: experiments with automatic scale selection

• Autor(a) principal: Nehmzow, Ulrich
• Data de Publicação: 2006
• Outros Autores: Vieira Neto, Hugo
• Tipo de documento: Artigo de conferência
• Idioma: por
• Título da fonte: Repositório Institucional da UTFPR (da Universidade Tecnológica Federal do Paraná (RIUT))
• Texto Completo: http://repositorio.utfpr.edu.br/jspui/handle/1/660
• topic: Robôs móveis; Redes neurais (Computação); Visão por computador; Mobile robots; Computer vision; Neural networks (Computer science)

We present experiments with an autonomous inspection robot, whose task was to highlight novel features in its environment using camera images. Experiments were conducted with two different attention mechanisms — saliency map and multiscale Harris detector — and two different novelty detection mechanisms — the Grow-When- Required neural network and incremental PCA. For both mechanisms we compared fixed-scale image encoding with automatically scaled image patches. Results show that using automatic scale selection provides a more efficient representation of the visual input space, but that performance is generally better using a fixed-scale image encoding.