This paper describes the design and construction of a wearable active vision platform which is able to achieve substantial decoupling of the camera motion from the wearer’s motion. Design issues in sensor placement, robot kinematics and their relation to wearability are discussed and the prototype platform’s performance is evaluated in a number of important visual tasks. The paper also discusse...

In this work, an explicitly task-oriented approach to the active vision problem is presented. The system tries to reduce the most relevant components of the uncertainty in the world model, for the task the robot is currently performing. It is task oriented in the sense that it explicitly considers a task-specific value function. As test-bed for the presented active vision approach, we selected ...

We present a model of scene exploration in which the high-resolution fovea is deployed to interesting regions by selective attention processes. The system switches between exploratory and recognition modes such that in exploration mode, regions of interest are investigated and in recognition mode, a given region is carefully examined as the recognition process is attempted for the particular re...

Active vision is identified by a closed loop linking sensing with acting. Thus, an active vision system's behaviour is directly determined by what it senses. To date however, the responses produced by active vision systems have tended to be relatively low-level, generally designed to facilitate improved sensing, by enhancing the duration or speed of object tracking, for example, or optimising t...

The experienced quality of virtual reality is currently limited by available computational resources, and will be for some time to come. It is essential that these limited resources not be wasted on the acquisition and processing of data that do not contribute significantly to the final percept. Efficient construction of the intermediate views that are the basis of some forms of virtual reality...

In this paper, a new active vision based camera self-calibration technique is proposed. The novelty of this new technique is that it can determine LINEARLY all the FIVE intrinsic parameters of a camera. The basic principle of our new calibration technique is to use the planar information in the scene and to control the camera to undergo several sets of orthogonal planar motions. Then, a set of ...

This paper demonstrates a method of using non-metric visual information derived from an uncalibrated active vision system to navigate an autonomous vehicle through freespace regions detected in a cluttered environment. The structure of 3-space is recovered modulo an affine transformation using an uncalibrated active stereo head carried by the vehicle. The plane at infinity, necessary for recove...

Symmetry is one of the most prominent cues in visual perception as well as in computer vision. We have recently presented the Generalized Symmetry Transform that receives as input an edge map, and outputs a symmetry map, where every point mark the intensity and orientation of the local generalized symmetry. In the context of Computer Vision, this map emphasizes points of high symmetry, which, i...

This paper presents a new constraint, ie., projective transformation constraint, to solve the di cult problem of motion stereo correspondence in the context where the motion is dominated by rotation (for instance, 10 degrees of rotation with 1 cm of translation). Our observation here is that two consecutive images can be related to each other by a 2D projective transformation. Its coe cients ar...

In this paper we describe a surveillance system made up of a fixed camera and a binocular active vision system. The fixed camera is used to provide the system with peripheral motion detection capabilities. The binocular active system is used to track in 3D and reconstruct the trajectories of specific targets. Both are fully integrated and the redundancy is exploited to achieve a higher degree o...