|
Not far away from home: A relational distance-based approach to understand images of houses AbstractAugmenting vision systems with high-level knowledge and reasoning can improve lower-level vision processes, such as object detection, with richer and more structured information. In this paper we tackle the problem of delimiting conceptual elements of street views based on spatial relations between lowerlevel components, e.g. the element ‘house’ is composed of windows and a door in a spatial arrangement. We use structured data: each concept can be seen as a graph representing spatial relations between components, e.g. in terms of right, up, close. We employ distances between logical interpretations to match parts of images with known examples and describe experimental results.
[Edit] |