Artigo de evento
URI permanente para esta coleçãohttps://repositorio.fei.edu.br/handle/FEI/5120
Navegar
3 resultados
Resultados da Pesquisa
Artigo de evento 1 Citação(ões) na Scopus Probabilistic logic encoding of spatial domains(2010-07-20) Paulo Santos; HUMMEL, B.; FENELON, V.; COZMAN, F. G.This paper presents a formalisation of a spatial domain in terms of a qualitative spatial reasoning formalism, encoded in a probabilistic description logic. The QSR formalism chosen is a subset of a cardinal direction calculus and the probabilistic description logic used has the relational structures of the well-known ALC language, allied with the inference methods of Bayesian Networks. We consider a scenario consisting of a road navigated by an experimental vehicle equipped with three on-board sensors: A digital map, a GPS and a video camera. This paper presents experiments where the proposed formalism is used to answer queries about driving directions, lanes and vehicles.Artigo de evento 0 Citação(ões) na Scopus Holes, knots and shapes: a spatial ontology of a puzzle(2011-09-27) Paulo Santos; CABALAR, P.In this paper we propose a spatial ontology for reasoning about holes, rigid objects and strings, taking a classical puzzle as a motivating example. In this ontology the domain is composed of spatial regions whereby a theory about holes is defined over a mereological basis. We also assume primitives for representing shapes of objects (including the string). From these primitives we propose a sufficient condition for object's penetrability through holes. Additionally, a string is represented as a data structure defined upon a sequence of sections limited by points where the string crosses itself or points where it passes through a hole. This paper first appeared as as technical report [7] and presents the initial framework that was further developed in [8, 2].Artigo de evento 0 Citação(ões) na Scopus Representation and retrieval of images by means of spatial relations between objects(2019-03-25) NUNES, D.; FERREIRA, L. A.; Paulo Santos; PEASE, A.Copyright held by the author(s).The present work addresses the challenge of integrating low-level information with high-level knowledge (known as semantic gap) that exists in content-based image retrieval by introducing an approach to describe images by means of spatial relations. The proposed approach is called Image Retrieval using Region Analysis (IRRA) and relies on decomposing images into pairs of objects. This method generates a representation composed of n triples, each one containing: a noun, a preposition and, another noun. This representation paves the way to enable image retrieval based on spatial relations. Results for an indoor/outdoor classifier shows that neural networks alone are capable of achieving 88% in precision and recall, but when combined with ontology this result increases in 10 percentage points, reaching 98% of precision and recall.