N. Srinivasa et R. Sharma, EFFICIENT LEARNING OF VAM-BASED REPRESENTATION OF 3D TARGETS AND ITS ACTIVE VISION APPLICATIONS, Neural networks, 11(1), 1998, pp. 153-171
There has been a considerable interest in using active vision for vari
ous applications. This interest is primarily because active vision can
enhance machine vision capabilities by dynamically changing the camer
a parameters based on the content of the scene. An important issue in
active vision is that of representing 3D targets in a manner that is i
nvariant to changing camera configurations. This paper addresses this
representation issue for a robotic active vision system. An efficient
Vector Associative Map (VAM)-based learning scheme is proposed to lear
n a joint-based representation. Computer simulations and experiments a
re first performed to evaluate the effectiveness of this scheme using
the University of Illinois Active Vision System (UIAVS). The invarianc
e property of the learned representation is then exploited to develop
several robotic applications. These include, detecting moving targets,
saccade control, planning saccade sequences and controlling a robot m
anipulator. (C) 1998 Elsevier Science Ltd. All rights reserved.