We describe the implementation of a biologically motivated model of the human visual system (HVS) on the Paragon XP/S. The approach involves the simulation of the two major pathways (magno-(M), and par-vocellular (P)) of processing visual stimuli including (i) retinal sampling, (ii) active foveation and (iii) object recognition. Theory suggests a vision model based on the competition of active ...

This report documents the design and implementation of a binocular, foveated active vision system as part of the Cog project at the MIT Artificial Intelligence Laboratory. The active vision system features a 3 degree of freedom mechanical platform that supports four color cameras, a motion control system, and a parallel network of digital signal processors for image processing. To demonstrate t...

In this paper we introduce adaptive vision techniques used, for example, in video-conferencing applications. Radial Basis Function (RBF) networks have been trained for gesture-based communication with colour/motion cues to direct face detection and capture ‘attentional frames’. These focus the processing for Visually Mediated Interaction via an appearance-based approach with Gabor filter coeffi...

The field of computer vision has been growing steadily and attracting the interest of both researchers and the industry. Especially in the last decade, enormous advances have been made with regard to automated and reliable recognition of image or video content, such as face, object and motion recognition [1–3] and gesture and activity recognition [4, 5]. Additionally, recent advances in 3D scen...

This paper deals with the mechanical aspects of robot vision and focuses on the design and implementation of a high-performance system. The system is called CeDAR (Cable Drive Active vision Robot). As part of the research at the Robotic Systems Laboratory (RSL) to develop real-world vision systems, CeDAR is designed for speed and accuracy through its novel use of cables in zerobacklash transmis...

Motion parallax, the relative motion of 3D space at different distances experienced by a moving agent, is one of the most informative cues. While motion parallax is typically investigated during navigation, it also occurs in most robotic head/eye systems during rotations of the cameras. In these systems, as in the eyes of many species, the optical nodal points do not lie on the axes of rotation...

Foveated image sensors have a variable spatial resolution enabling a significant reduction in image size and data volume. In this work, the requirements for a foveated sensor within an active vision system are analysed. Based on these requirements, the constraints on the resolution mapping function are determined, and a range of Cartesian based mapping schemes investigated. The results demonstr...

In this paper, the application of CNN associative memories for 3D object recognition is presented. The main idea is to analyse the optical flow in an image sequence of an object. Several features of the optical flow between two succeeding images are calculated and merged to a time series of features for the whole image sequence. These features show several object specific characteristics and ar...

The project described in this paper designed and implemented a hand-eye calibration method for manipulators under observation by stereo cameras. This method has been utilized on Johnson Space Center's Robonaut, and on a planetary manipulator mock-up at the Jet Propulsion Laboratory. The intent of this calibration is to improve the manipulator's hand-eye coordination. The approach uses kinematic...

We describe a set of simulations to evolve omnidirectional active vision, an artificial retina scanning over images taken via an omnidirectional camera, being applied to a car driving task. While the retina can immediately access features in any direction, it is asked to select behaviorally-relevant features so as to drive the car on the road. Neural controllers which direct both the retinal mo...