Open AccessRoom Categorization Based on a Hierarchical Representation of Space
Author(s) -
Ursic Peter,
Domen Tabernik,
Marko Boben,
Danijel Skočaj,
Aleš Leonardis,
Matej Kristan
Publication year - 2013
Publication title -
international journal of advanced robotic systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.394
H-Index - 46
eISSN - 1729-8814
pISSN - 1729-8806
DOI - 10.5772/55534
Subject(s) - categorization , computer science , representation (politics) , hierarchy , context (archaeology) , artificial intelligence , range (aeronautics) , sonar , space (punctuation) , robot , spatial contextual awareness , scale (ratio) , fidelity , machine learning , pattern recognition (psychology) , politics , political science , law , operating system , paleontology , telecommunications , materials science , physics , quantum mechanics , economics , market economy , composite material , biology
For successful operation in real‐world environments, a mobile robot requires an effective spatial model. The model should be compact, should possess large expressive power and should scale well with respect to the number of modelled categories. In this paper we propose a new compositional hierarchical representation of space that is based on learning statistically significant observations, in terms of the frequency of occurrence of various shapes in the environment. We have focused on a two‐dimensional space, since many robots perceive their surroundings in two dimensions with the use of a laser range finder or sonar. We also propose a new low‐level image descriptor, by which we demonstrate the performance of our representation in the context of a room categorization problem. Using only the lower layers of the hierarchy, we obtain state‐of‐the‐art categorization results in two different experimental scenarios. We also present a large, freely available, dataset, which is intended for room categorization experiments based on data obtained with a laser range finder