Research Article

An Ontology-Based Framework for Complex Urban Object Recognition through Integrating Visual Features and Interpretable Semantics

Table 2

Demo of generating semantics and rules in ontology.

DefinitionDescription 1: generally, the covered materials are asphalt or bitumen.
Description 2: a majority of street contains yellow or white center lines
Description 3: a road in a city or town that has houses or other buildings on one or both sides (from Merriam-Webster)

Semantics (RDF triples)Triple 1 from description 1: street covers asphalt
Triple 2 from description 1: street covers bitumen
Triple 3 from description 2: street contains center_line
Triple 4 from description 3: street isA road
Triple 5 from description 3: house isOnSidesOf street
Triple 6 from description 3: building isOnSidesOf street

Rule set by SWRLRule 1 from triple 4: isA(?image_object, ?road) => isA(?image_object, ?street)
Rule 2 from triple 1 and 5: isOnSidesOf(?house, ?image_object) ∧ covers(?image_object, ?asphalt) => isA(?image_object, ?street)
Rule 3 from triple 1 and 6: isOnSidesOf(?building, ?image_object) ∧ covers(?image_object, ?asphalt) => isA(?image_object, ?street)
Rule 4 from triple 2 and 5: isOnSidesOf(?house, ?image_object) ∧ covers(?image_object, ?bitumen) => isA(?image_object, ?street)
Rule 5 from triple 1 and 3 and 5: isOnSidesOf(?house, ?image_object) ∧ covers(?image_object, ?asphalt) ∧ contains(?image_object, ?center_line) => isA(?image_object, ?street)