Perceptual Context in Cognitive Hierarchies

TL;DR

This paper formalizes perceptual context within cognitive hierarchies, demonstrating its role in top-down information flow and applying it to improve visual pose tracking with minimal sensors.

Contribution

It introduces a formal model of perceptual context and integrates it into cognitive hierarchies, including a novel approach for visual pose tracking using a 2D camera.

Findings

Context improves belief state prediction in hierarchies

Formalization enables new applications in vision tasks

Effective pose tracking with minimal sensor data

Abstract

Cognition does not only depend on bottom-up sensor feature abstraction, but also relies on contextual information being passed top-down. Context is higher level information that helps to predict belief states at lower levels. The main contribution of this paper is to provide a formalisation of perceptual context and its integration into a new process model for cognitive hierarchies. Several simple instantiations of a cognitive hierarchy are used to illustrate the role of context. Notably, we demonstrate the use context in a novel approach to visually track the pose of rigid objects with just a 2D camera.