Reasoning about Depth and Motion from an Observer's Viewpoint

Abstract

The goal of this paper is to present a logic-based formalism for representing knowledge about objects in space and their movements, and show how this knowledge could be built up from the viewpoint of an observer immersed in a dynamic world. In this paper space is represented using functions that extract attributes of depth, size and distance from snapshots of the world. These attributes compose a novel spatial reasoning system named Depth Profile Calculus (DP C). Transitions between qualitative relations involving these attributes are represented by an extension of this calculus called Dynamic Depth Profile Calculus (DDP C). We argue that knowledge about objects in the world could be built up via a process of abduction on DDP C relations.

Reasoning about Space and Images

“…Following these ideas Santos and Shanahan [14], Santos [3], dos Santos et al [5] presented a theory aiming at the automatic scene understanding from a robot's viewpoint. In particular, Santos [3] presents formalism capable to interpret events such as approaching, receding, or coalescing from pairs of subsequent images obtained by a mobile robot's stereo pair. In order to further interpret these image-related events, an abductive procedure was developed for hypothesizing on the possible changes that might have occurred with the domain objects that could explain the image events.…”

“…Traditionally, however, QSR formalisms are independent from an observer's viewpoint, which makes them not applicable to computer vision or robotic problems. There is, however, a growing interest in the development of dynamic formalisms about space in which qualitative changes observed by a mobile robot are the building blocks of the system [2][3][4].…”

Interpretação de imagens com raciocínio espacial qualitativo probabilístico.

“…Buscando uma aplicação com dados reais, estendeu-se com uma abordagem probabilís-tica um sistema de auto localização previamente desenvolvido em trabalhos anteriores (SANTOS; DEE; FENELON, 2008;SANTOS;FENELON, 2009). O sistema trata do problema referente ao robô inferir sua localização qualitativa a partir da sua percepção visual das relações dos elementos alvos no ambiente.…”

“…Porém, também é possível raciocinar sobre sombras a partir do ponto de vista de um observador. Com o PQRS podemos inferir informações tais como percepção de profundidade e a localização relativa do observador, ambas descritas em (SANTOS; DEE; FENELON, 2008;SANTOS;FENELON, 2009). Por ser relevante a esse trabalho a seguir descreveremos somente a localização relativa.…”

Inductive Learning Spatial Attention

“…In previous works (Santos and Shanahan, 2002;Santos and Shanahan, 2003;Santos, 2007;dos Santos et al, 2008) we have concentrated on developing systems capable of generating explanations for computer vision data using abductive reasoning. Abduction was proposed by Charles Peirce as the inference that rules the first stage of scientific inquiries and of any interpretive process (Peirce, 1958), i.e., the process of suggesting hypotheses to explain a given phenomenon.…”