Attention and Visual Search : Active Robotic Vision Systems that Search

摘要

Visual attention is a multi-faceted phenomenon, playing different roles in different situations and for different processing mechanisms. Regardless, attention is a mechanism that optimizes the search processes inherent in vision. This perspective leads to sound theoretical foundation for studies of attention in both machine and in the brain. The development of this foundation and the many ways in which attentional processes manifest themselves will be overviewed. One particular example of a practical robotic vision system that employs some of these attentional processes will be described. A difficult problem for robotic vision systems is visual search for a given target in an arbitrary 3D space. A solution to this problem will be described that optimizes the probability of finding the target given a fixed cost limit in terms of total number of robotic actions the robot requires to find its visual target. A robotic realization will be shown.