In this paper, we propose a conceptual framework for assessing the salience of landmarks for navigation. Landmark salience is derived as a result of the observer's point of view, both physical and cognitive, the surrounding environment, and the objects contained therein. This is in contrast to the currently held view that salience is an inherent property of some spatial feature. Salience, in our approach, is expressed as a three-valued Saliency Vector. The components that determine this vector are Perceptual Salience, which defines the exogenous (or passive) potential of an object or region for acquisition of visual attention, Cognitive Salience, which is an endogenous (or active) mode of orienting attention, triggered by informative cues providing advance information about the target location, and Contextual Salience, which is tightly coupled to modality and task to be performed. This separation between voluntary and involuntary direction of visual attention in dependence of the context allows defining a framework that accounts for the interaction between observer, environment, and landmark. We identify the low-level factors that contribute to each type of salience and suggest a probabilistic approach for their integration. Finally, we discuss the implications, consider restrictions, and explore the scope of the framework.

No abstract

No abstract

No abstract

Abstract. People use verbal descriptions and graphical depictions to communicate spatial information, thus externalizing their spatial mental representations. In many situations, such as in emergency response, the ability to translate the content of verbal descriptions into a sketch map could greatly assist with the interpretation of the message. In this paper, we present an outline of a semi-automatic framework enabling seamless transition between verbal descriptions and graphical sketches of precinct-scale urban environments. The proposed framework relies on a three-step approach: NL parsing, with spatial named entity and spatial relation recognition in natural language text; the construction of a spatial Property Graph capturing the spatial relationships between pairs of entities; and the sketch drawing step where the identified entities are dynamically placed on a canvas in a manner that minimizes conflicts between the verbalized spatial relationships, thus providing a plausible representation of the described environment. The approach is manually demonstrated on a natural language description of a university campus, and the opportunities and challenges of the suggested framework are discussed. The paper concludes by highlighting the contributions of the framework and by providing insights for its actual implementation.