Today’s robotics applications require complex, real-time, high-bandwidth sensor systems. Although many such systems have been developed [12][14][17][10], integrating them into an autonomous agent architecture remains an area of active research. We will discuss how active perception systems can be integrated with agent architectures to perform complex tasks. We present an active stereo vision sy...

Active vision requires the integration of information coming from the retina with that generated internally within the brain, especially by saccadic eye movements. Just as visual information reaches cortex via the lateral geniculate nucleus of the thalamus, this internal information reaches the cerebral cortex through other higher-order nuclei of the thalamus. This review summarizes recent work...

robot can get quite far with a simple vision system that is In 1991, Ballard [1] described the implications of haytuned to a particular distance. ing a visual system that could actively position the camera coordinates in response to physical stimuli. In humanoid robotic systems, or in any animate vision system that inter11. SOCIAL CONSTRAINTS acts with people, social dynamics provide additional...

Achieving the rst step of a framework for humanrobot interaction, we have designed a binocular tracking system which uses disparity and velocity information for the detection and pursuit of moving objects in cluttered environments without a-priori knowledge of the target shape or texture. The implemented system robustly tracks in real-time deformable objects such as human hands and faces, takin...

In this paper we describe how the combination of several vision sensors can be used to track multiple human targets in a typical surveillance situation. The experimental system devised is made up of a xed camera and a binocular active vision system. The xed camera is used to provide the system with peripheral motion detection capabilities. The human activity is monitored by extracting several p...

Our work on Active Vision has recently focused on the computational modelling of navigational tasks where our investigations were guided by the idea of approaching vision for behavioral systems in form of modules that are directly related to perceptual tasks These studies led us to branch in various directions and inquire into the problems that have to be addressed in order to obtain an overall...

In computer vision real–time tracking of moving objects in natural scenes has become more and more important. In this paper we describe a complete system for data driven tracking of moving objects. We apply the system to tracking pedestrians in natural scenes. No specialized hardware is used. To achieve the necessary efficiency several principles of active vision, namely selection in space, tim...

In this paper we describe the use of a steerable camera and active vision system in the real-time recovery of trajectories of objects moving on a planar surface in the scene. The system first selfcalibrates the transformation from camera platform joint angles to scene plane coordinates by active observation of static scene geometry which has been stored as a model. The transformation is encoded...

In this paper, we propose an observable-area model of the scene for real-time cooperative object tracking by multiple cameras. The knowledge of partners’ abilities is necessary for cooperative action whatever task is defined. In particular, for the tracking a moving object in the scene, every Active Vision Agent (AVA), a rational model of the network-connected computer with an active camera, sh...

In this paper, we address the ability of a computer vision system to perceive the motion of an object (possibly a robot manipulator) in its field of view. We derive a quantitative measure of motion perceptibility, which relates the magnitude of the rate of change in an object’s position to the magnitude of the rate of change in the image of that object. We then show how motion perceptibility ca...