Continuous image interpretation by a moving viewer (robot vision)

摘要

The roles played by vision in each function needed for autonomous navigation is briefly discussed. The analysis, representation, and integration of vision data acquired continuously while the robot is moving are then described. Two key ideas for image interpretation, namely, the use of prior knowledge on the structure of environment and fusion of vision information with the other sensory data, are also discussed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>