The goal of active vision is to change intrinsic or extrinsic properties of the sensor in order to get new and improved information. In the case of 3-D object modeling from vision, this can mean moving the camera to view the scene from a new angle or to get a close-up view of an object that has been localized and is being modeled. We discuss using active vision to improve the speed and utility ...

We propose and demonstrate a new paradigm for active vision research that draws upon recent advances in the fields of artificial life and computer graphics. A software alternative to the prevailing hardware vision mindset, animat vision prescribes artificial animals, or animats, situated in physics-based virtual worlds as autonomous virtual robots with active perception systems. To be operative...

In this paper a basic conceptual architecture aimed at the design of Computer Vision System is qualitatively described The pro posed architecture addresses the design of vision systems in a modular fashion using modules with three distinct units or components a process ing network or diagnostics unit a control unit and a communications unit The control of the system at the modules level is desi...

This paper presents a software skeleton system for experiments in integration and control of real time active vision systems. This skeleton has been constructed by a consortium of six laboratories as part of a long term basic research investigation of issues of integration and control of real time vision. The first chapter describes the problems of integration and control and the context for th...

The development of computational solutions for simulation of visual behavior deals with the problem of integration and co-operation between different computational processes for control of active vision systems. In general these computational processes could emulate different and specific artificial visual behavior and their integration presents distinct facets and problems. The first is the in...

Accurate oculomotor control is one of the essential pre-requisites of successful visuomotor coordination. Given the variable nonlinearities of the geometry of binocular vision as well as the possible nonlinearities of the oculomotor plant, it is desirable to accomplish accurate oculomotor control through learning approaches. In this paper, we investigate learning control for a biomimetic active...

In order to do useful things a mobile robot needs some sort of global information about the environment it is operating in. In this paper an approach is described where the global information is not cast in a model of the geometry of the environment but in a model of all sensory data of the robot. As a primary sensing system we used computer vision. The model gives a probability distribution ov...

This paper deals with the 3D structure estimation and exploration of static scenes using active vision. Our method is based on the structure from controlled motion approach that constrains camera motions to obtain an optimal estimation of the 3D structure of a geometrical primitive. Since this approach involves to gaze on the considered primitive, we have developed perceptual strategies able to...

We present a modular architecture for image understanding and active computer vision which consists of the following major components: Sensor and actor interfaces required for data–driven active vision are encapsulated to hide machine–dependent parts; image segmentation is implemented in object–oriented programming as a hierarchy of image operator classes, guaranteeing simple and uniform interf...

Performance on visual tasks such as classification can be enhanced by employing active vision systems. Such systems do not passively receive observations, but have to some extent control over the observations they perceive. There are two general approaches to active vision. The first approach to active vision is a probabilistic approach, in which reducing uncertainty on a part of the world stat...