nextuppreviouscontents
Next:Attention and Change Detection Up:Visual-motor Systems Previous:VLSI Smart Sensors

Attention and View-Based Object Recognition

A. Domercq, J.J. Clark

Our main goal in this project is to understand the process of visual attention, which is the process by which the human brain selects information to be analyzed further. In particular, we are interested in the application of attentional processes to the implementation of view-based object recognition schemes. In this approach, objects are recognized by comparing their appearance from a given viewpoint to (interpolated) views which have been previously recorded. Attention promises to improve this process by minimizing irrelevant inputs and by increasing viewpoint invariance. In such active view-based object recognition techniques, hypotheses as to an object's identity alter the way in which further information regarding the object is gathered. Such approaches to object recognition hold the promise of real-time performance, due to their directed nature which reduces the amount of information that needs to be processed. Another advantage of active view-based recognition schemes is that of robustness to variations in the scene, due to the fixation of attention on only relevant scene information. At the moment, we have implemented the low level attentional shift algorithms based on hard-wired measures of saliency (colour and saturation), and have used these to guide the motion of a video camera via a Directed Perception Pan-Tilt unit.
 


Annual Report

Fri Nov 26 23:00:32 GMT 1999