Reproduced with the kind permissions of the copyright owner. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Abstract Thi...

This paper introduces the Neural Active Vision System NAVIS. It it able to explore visually its environment, locates interesting 2D and 3D objects and recognizes them under control of several invariance capabilities. Emphasis has been put on the system’s biological plausibility as well as on its computational costs and the integration aspects. The integration of several processing units is sche...

One of the main claims of the active vision framework is that finding data on the basis of task requirements is more efficient than reconstructing the whole scene by performing a complete visual scan. To be successful, this approach requires that agents learn visual routines to direct overt attention to locations with the information needed to accomplish the task. In ecological conditions, lear...

We describe an evolutionary vision system capable of autonomously scanning through an image while zooming in and out and changing filtering strategy in order to perform shape discrimination. The system consists of a small artificial retina controlled by an evolutionary recurrent neural network without hidden units. We show that such a simple active-vision system can successfully recognize diffe...

Humans employ an active visual system to gather visual data from the surrounding environment. In addition to continually re-focusing the lens and adjusting the iris to control the exposure of light on to the retina, the eye constantly moves so that specific information can be focused on to the fovea – the part of the retina capable of defining fine detail. The target location when the eye moves...

A wavelet decomposition for multiscale edge detection is used to separate border edges from texture in an image, toward the goal of a complete segmentation by Active Perception for robotic exploration of a scene. The physical limitations of the image acquisition system and the robotic system provide the limitations on the range of scales which we consider. We link edges through scale space, usi...