A Study on how Humans Describe Relative Positions of Image Objects

Abstract

Information describing the layout of objects in space is commonly conveyed through the use of linguistic terms denoting spatial relations that hold between the objects. Though progress has been made in the understanding and modelling of many individual relations, a better understanding of how human subjects use spatial relations together in natural language to is required. This paper outlines the design and completion of an experiment resulting in the collection of 1920 spoken descriptions from 32 human subjects; they describe the relative positions of a variety of objects within an image space. We investigate the spatial relations that the subjects express in their descriptions, and the terms through which they do so, in an effort to determine variations and commonalities. Analysis of the descriptions determines that common elements of spatial perception do indeed exist between subjects, and that the subjects are quite consistent with each other in the use of spatial relations.

Relações Espaciais Obtidas a Partir de Descrições de Localização em Linguagem Natural em Ambientes Indoor e Outdoor

“…A classificação dos termos de relações espaciais foi realizada a partir das classes: topológica, direcional e de distância, já existentes em estudos sobre relações espaciais (Bruns & Egenhofer, 1998;Shariff et al, 1998;Wang et al, 2008;Coventry, 2013). A classificação dos termos de relação espacial encontrados colaborará com aplicações computacionais na distinção dos termos que podem ser utilizados para cada classe.…”

Efficient computation of objects' spatial relations in digital images

“…Two objects are randomly selected from the pool, randomly resized, rotated and placed in a digital image. The procedure, which is similar as that followed by Wang et al in [9], is repeated 800 times. 800 synthetic images are therefore created.…”

Qualitative distances and qualitative description of images for indoor scene description and recognition in robotics

“…Some studies on how people describe images can be found in the literature [Jörgensen, 1998;Laine-Hernandez and Westman, 2006;Greisdorf and O'Connor, 2002;Wang et al, 2008]. The main objective of most of these studies is analysing people's image descriptions for image retrieval in databases.…”

“…Research by Wang et al [2008] on how humans describe relative positions of image objects show that the relations of direction (right, left, above, below ), topology (overlap, separate, touch, in, out, etc.) and distance (far, near, etc.)…”