| We describe a general technique for specifying trajectories of controllable imaging parameters in an active vision system so that temporal integration processes are optimized. The technique assumes that a Kalman lter is used to perform the temporal integration of measurements and is based on determining, at each point in time, the set of imaging parameter values that minimizes the trace of th...

In this paper we demonstrate four real-time reactive responses to movement in everyday scenes using an active head/eye platform. We first describe the design and realization of a high bandwidth four degree-of-freedom head/eye platform and visual feedback loop for the exploration of motion processing within active vision. The vision system divides processing into two scales and two broad functio...

In this paper, an omnidirectionnal range sensor is reported. This active vision sensor combines a CCD camera and a laser diode. We use two methods to obtain the depth of the scene: a calibration method and a least square method. We describe the prototype we made. Experimental results are presented. A comparative test shows that this sensor seems to be as accurate as a laser telemeter but less s...

We present a real-time cooperative multi-target tracking system. The system consists of a group of Active Vision Agents (AVAs), where an AVA is a logical model of a network-connected computer with an active camera. All AVAs cooperatively track their target objects by dynamically exchanging object information with each other. In this paper, we address the technologies employed in the system and ...

applied to this structure which is seen by a single view. The location and orientation of the plane mirror must be known. They are estimated easily as the mirror is xed relative to a calibration block. Due to limitation of the geometry, only a fraction of an object and its corresponding image in a plane mirror can be simultaneously visible in a single view. This fraction is usually less than 1/...

In this paper we present the design and implementation of a novel low-cost active vision system for robotic applications. The system is comprised of two parts: A 4-DOF trinocular active camera head and a DSP-based image acquisition and processing board. Design issues and tradeoos are discussed. The performance of the system is evaluated by running an edge-based object tracking algorithm that is...

Modern robotics applications are becoming more complex, due to increasing numbers of resources to be controlled. An excellent example of this is the use of active vision in tasks which previously relied solely on static imaging. Although there are many advantages of active over passive vision [1,2], it is known that the control of active vision devices (AVD’s) is both complex and computationall...

In active vision scenarios, the motion of the observer induces an apparent motion in the image plane. One approach for camera motion compensation is the use of panoramic images, representing the scene at the different positions of the camera. In this work, an approach to build spherical panoramic views from a pan-tilt camera is described, which is based on background updating techniques. Intere...

This paper is about the interface between continuous and discrete robot control. We advocate encapsulating continuous actions and their related sensing strategies into structures called situation speciic activities, which can be manipulated by a symbolic reactive planner. The approach addresses the problem of turning symbolic actions into continuous activities, and the problem of mapping contin...

This paper presents the sensing plan of VIRTUE; an active vision system based around a VIRtual TrinocUlar stEreo-head. VIRTUE is used to build polyhedral volumetric models of unknown objects based on recovered 3-D line segments. Partial models and a viewpoint enumeration scheme are used to guide the image acquisition process and to determine `where to look next'. Results of the active vision re...