Using genetic algorithms for real-time object detection

Abstract

This article presents a new approach to mobile robot vision systems based on genetic algorithms. The major contribution of the proposal is the real-time adaptation of genetic algorithms, which are generally used offline. In order to achieve this goal, the execution time must be as short as possible. The scope of the System is the robotic football competition Robocup whitin the Standard Platform category. The system developed detects and estimates distance and orientation to key elements on a football field, such as the ball and goals. Different experiments have been carried out whitin an official Robocup environment