Evolving High-Dimensional, Adaptive Camera-Based Speed Sensors

R. Salomon (Germany)


Intelligent Agents, Robotics, Computer Vision


This paper reviews some attempts that exploit a phe nomenon, also known as motion parallax, to estimate the distance of closest approach of a moving object. Despite their success, the existing methods lack some desirable properties, such as reasonable scalability and online learn ing. To overcomethese practically-relevantlimitations, this paper proposes a new model that is based on Hebbian learn ing. Due to its scalability and online learning capabilities, this model is especially suited to mobile robots.

Important Links:

Go Back