Connectionist Decision Systems for a Visual Search Problem
IIZUKA ´94, Fukuoka, Japan August 1-7, 1994, Invited paper
Uwe R. Zimmer - contact author
Visual Search has been investigated by many researchers inspired by the
biological fact, that the sensory elements on the mammal retina are not
distributed. Therefore the focus of attention (the area of the retina
highest density of sensory elements) has to be directed in a way to
gather data according to certain criteria.
The work discussed in this article concentrates on applying a laser range
instead of a silicon retina. The laser range finder is maximal focused at
time, but therefore a low-resolution total-scene-image, available with
camera-like devices from scratch on, cannot be used here. By adapting a
of algorithms, the edge-scanning module steering the laser range finder
to trace a detected edge. Based on the data scanned so far, two questions
to be answered. First: "Should the actual (edge-) scanning be interrupted
order to give another area of interest a chance of being investigated?" and
second: "Where to start a new edge-scanning, after being interrupted?".
These two decision-problems might be solved by a range of decision
correctness of the decisions depends widely on the actual environment and
underlying rules may not be well initialized with a-priori knowledge. So
present a version of a reinforcement decision system together with an
scheme for efficiently controlling highly focused devices.
| Other Publications