Ir arriba
Información del artículo

Online topological segmentation of visual sequences using the algebraic connectivity of graphs

J. Boal, A. Sánchez

In the context of topological mapping, the automatic segmentation of an environment into meaningful and distinct locations is still regarded as an open problem. This paper presents an algorithm to extract places online from image sequences based on the algebraic connectivity of graphs or Fiedler value, which provides an insight into how well connected several consecutive observations are. The main contribution of the proposed method is that it is a theoretically supported alternative to tuning thresholds on similarities, which is a difficult task and environment dependent. It can accommodate any type of feature detector and matching procedure, as it only requires non-negative similarities as input, and is therefore able to deal with descriptors of variable length, to which statistical techniques are difficult to apply. The method has been validated in an office environment using exclusively visual information. Two different types of features, a bag-of-words model built from SIFT keypoints, and a more complex fingerprint based on vertical lines, color histograms, and a few Star keypoints, are employed to demonstrate that the method can be applied to both fixed and variable length descriptors with similar results.


Palabras clave: Computer vision; Mobile robots; Robot localization; SLAM; Topological modeling of robots


Robótica. Volumen: 34 Numero: 10 Páginas: 2400-2413

Índice de impacto JCR y cuartil Scopus: JCR impact factor: 1.554 (2016); 1.184 (2018).

Referencia DOI: DOI icon 10.1017/S0263574715000053    

Publicado en papel: Octubre 2016. Publicado on-line: Febrero 2015.



Cita:
J. Boal, A. Sánchez. Online topological segmentation of visual sequences using the algebraic connectivity of graphs. Robótica. vol. 34, no. 10, pp. 2400-2413, Octubre 2016. [Online: Febrero 2015]


    Líneas de investigación:
  • *Robots móviles y visión artificial

pdf  Previsualizar
pdf Solicitar el artículo completo a los autores



Aviso legal  |  Política de cookies |  Política de Privacidad

© Universidad Pontificia Comillas, Escuela Técnica Superior de Ingeniería - ICAI, Instituto de Investigación Tecnológica

Calle de Santa Cruz de Marcenado, 26 - 28015 Madrid, España - Tel: (+34) 91 5422 800