Vision is an active process. We do not see the world directly; rather, we construct a representation of it from sensory inputs in combination with internal, nonvisual signals. In the case of spatial perception, our representation of the visual scene must take into account our own movements. This allows us to perceive the world as stationary despite the constant eye movements that produce new im...

This chapter discusses the relationship between covert visual attention and overt movements of the eyes. One of the most frequently emphasised facts concerning visual attention is the ability to attend covertly to a location in the visual field without directing the eyes to that location. Based on this, the “mental spotlight” metaphor has been widely prevalent and has given rise to much experim...

Recent studies that consider how vision is used in everyday life have led to a new perspective in visual science, in which more emphasis is placed on the active role of the viewer.

We present a mapping approach to scene understanding based on active stereo vision. We generalise traditional static multi-camera rectification techniques to enable active epipolar rectification and intuitive representation of the results. The approach is shown to enable the use of any static stereo algorithms with active multi-camera systems. In particular, we show the use of the framework to ...

Perception in intelligent systems is closely coupled with action and the actual environment the system is situated in. Embodied robots exploit by means of sensory-motor coordination the environment in simplifying a complex visually guided task, yielding successful robust perceptual behavior. This active vision approach enables robots to sequentially and interactively select and analyze only the...

A low-cost active vision head with ten degrees of freedom is presented which has been build from oo-the-shelf parts. A modular design using a separate pan-tilt unit and two integrated CCD-cameras mounted on a vergence platform allows the variation of intrinsic and extrinsic parameters of the system using the basic competences of the low-level modules. In this paper we will present the stereo he...

This paper focuses on learning of object models for an active robot vision system. One of its main attributes is the generation of hybrid models of 3D objects, integrating implicit representations by neural networks and explicit descriptions by semantic networks. On both levels of the vision system, subsymbolic neural learning as well as symbolic semantic learning can be done completely unsuper...

Active cameras provide a navigating vehicle with the ability to fixate and track features over extended periods of time, and wide fields of view. While it is relatively straightforward to apply fixating vision to tactical, short-term navigation tasks, using serial fixation on a succession of features to provide global information for strategic navigation is more involved. However, active vision...

A new study has found that artificial occlusion of central vision leads to rapid emergence, and long-term maintenance of a new preferred retinal locus of fixation. These findings have important implications for the understanding of visual and oculomotor plasticity as well as for the development of rehabilitation techniques.

This paper reviews aspects of the design and construction of an active wearable camera, and describes progress in equipping it with visual processing for reactive tasks like orientation stabilisation, slaving from head movements, and 2D tracking. The paper goes on to describe a first application of frame-rate simultaneous localisation and mapping (SLAM) to the wearable camera. Though relevant f...