Reasoning about scene descriptions

DiManzo, M.; Adorni, Giovanni; Giunchiglia, Fausto

doi:10.1109/proc.1986.13579

Cited by 18 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In NLP, the focus is on how to simulate situations according to the context besides the prototypical meaning of space-related prepositions. [15][16][17] In GIS, data are selected according to the user's queries in order to show, process, and analyze spatial data. 9 In AI and robotics, spatial-relation problems are concerned mainly with recognition of a spatial situation from the view of an agent or robot in search of its goal location.…”

Section: Related Researchmentioning

confidence: 99%

Hierarchical spatial relation based on a contiguity graph

Choe

Park

Pyo

2005

Int. J. Intell. Syst.

View full text Add to dashboard Cite

Autonomous agents traversing a natural space need to be knowledgeable of its space configuration. The existing space models in geographic information systems and robotics, however, deal with only the topological relations among numerous types of spatial relations. We aim to develop an enhanced space model that elaborates the spatial relations with respect to their relevant physical relations. Specifically, the spatial relations in a space configuration are further characterized with the gravitation as a potential factor to affect the space configuration. The resulting space model is capable of capturing an extended set of spatial relations over existing models such as a four-intersection model.

show abstract

Section: Related Researchmentioning

confidence: 99%

Hierarchical spatial relation based on a contiguity graph

Choe

Park

Pyo

2005

Int. J. Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…NALIG [4], [5], is an early example that was aimed at recreating static 2D scenes. One of the major goals of the project was to study relationships between space and prepositions.…”

Section: Text-to-scene Conversionmentioning

confidence: 99%

Information Extraction to Generate Visual Simulations of Car Accidents from Written Descriptions

Nugues

Dupuy²,

Egges

2003

Computational Science and Its Applications — ICCSA 2003

View full text Add to dashboard Cite

Abstract. This paper describes a system to create animated 3D scenes of car accidents from written reports. The text-to-scene conversion process consists of two stages. An information extraction module creates a tabular description of the accident and a visual simulator generates and animates the scene. We outline the overall structure of the text-to-scene conversion and the template structure. We then describe the information extraction system: the detection of the static objects and the vehicles, their initial directions, the chain of events, and the collisions. We show snapshots of the car animation output and we conclude with the results we obtained.

show abstract

“…One or more conceptualizations correspond to a natural language spatial preposition (Waltz & Boggess, 1979;Adorni, DiManzo & Giunchiglia, 1983, 1984bDiManzo, Adorni & Giunchiglia, 1986). Any conceptualization is a nonambiguous but imprecise translation of the input.…”

Section: Attribute Grammars For Hcimentioning

confidence: 99%

“…A more detailed discussion of the treatment of spatial relationships can be found in DiManzo et al (1986).…”

Section: Not(container(y))phorizontal -Contact(x Y))mentioning

confidence: 99%