Qualitative directions in egocentric spatial reference frame

Baruah, Rupam; Hazarika, Shyamanta M.

doi:10.1109/isda.2012.6416599

Cited by 4 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, orientation relations correspond to coneshaped regions, and lines separating the regions belong to only one of these regions. This is the basic difference to relations proposed in [7] and [8].…”

Section: Spatial Representationmentioning

confidence: 73%

“…None of the above supports orientation relations which typically appear in natural language scene descriptions and in robotics among others. In this work, a representation of orientation relations based on a combination of modified versions of the relations proposed in [7,8] is proposed. The proposed representation is combined with a tractable reasoning mechanism over specific sets of relations, containing basic relations of both sets that are parts of the mechanism.…”

Section: Background and Related Workmentioning

confidence: 99%

“…This approach is similar to the approach used in [1] for cardinal directional relations, as part of the SOWL model. In [7] and [8] orientation relations are defined between objects based on cone-shaped regions around objects. In both cases lines separating the cone-shaped regions are also different relations, similar to the star calculus proposed in [5].…”

Section: Spatial Representationmentioning

confidence: 99%

“…Egocentric orientation relations are analysed into two sets of relations; The first set represents the directional orientation relation between two objects (e.g., "same" or "opposite" direction). This set of relations is a modified form of the relations proposed in [7]. The second set represents the positional orientation relations in terms of the egocentric reference frame of each object (e.g., "front" or "behind").…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Reasoning over Spatial Orientation Relations Using Rules

Batsakis

Antoniou

Tachmazidis

2015

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Abstract. Representation of spatial information for the Semantic Web often involves qualitative defined information (i.e., information described using natural language terms such as "Left"), since precise arithmetic descriptions using coordinates and angles are not always available. A basic aspect of spatial information is directional relations, thus embedding directional spatial relations into ontologies along with their semantics and reasoning rules is an important practical issue. This work proposes a new representation for directional spatial information in ontologies by means of OWL properties and reasoning rules in SWRL embedded into the ontology. The proposed representation is based on the combination of object orientations (e.g., same direction or opposite) and cone shaped directional relations of positions using an egocentric reference (e.g., left or right of an object). The proposed representation is to the best of our knowledge a novel one, and in this work, the proposed representation is analysed, implemented and evaluated.

show abstract

Section: Spatial Representationmentioning

confidence: 73%

Section: Background and Related Workmentioning

confidence: 99%

Section: Spatial Representationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Reasoning over Spatial Orientation Relations Using Rules

Batsakis

Antoniou

Tachmazidis

2015

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

show abstract

“…Such abstractions are quite common in QSR [8]. For representation of relative direction, we have used a qualitative direction algebra proposed by the authors [12]. A pro jection based spatial model in an egocentric [9] frame of reference is used for handling spatial orientation.…”

Section: Representation Of Qualitative Featuresmentioning

confidence: 99%

Recognition of motion events of directed points using a language based framework

Baruah

Hazarika

2013

2013 1st International Conference on Emerging Trends and Applications in Computer Science

Self Cite

View full text Add to dashboard Cite

In this paper, we have proposed a framework for representation and recogniti on of motion events of s patial objects abstracted as directed points . The framework combines qualitati ve s patial reasoning wi th formal grammars in order to recognize motion events in an input stream. Motion events are represented by three qualitati ve attri butes, namely, orientati on, directi on and distance. It has been shown that by using spatio-tempor al continuity of qualitati ve relati ons, it is possible to use regular grammars for event recogniti on. The novelty of the approach is that any number of qualitati ve relation sets can be combined with formal grammars and hierarchies of abstractions can be created to make the knowledge representation cl oser to human cognition.

show abstract