A Real-Time Object Recognition System Using Adaptive Resolution Method for Humanoid Robot Vision Development

摘要

The research of autonomous robots is one of the most important challenges in recent years. Among the numerous robot researches, the humanoid robot soccer competition is very popular. The robot soccer players rely on their vision systems very intensively when they are in the unpredictable and dynamic environments. This work proposes a simple and real-time object recognition system for the RoboCup soccer humanoid league rules of the 2009 competition. This vision system can help the robot to collect various environment information as the terminal data to complete the functions of robot localization, robot tactic, barrier avoiding, etc. It can reduce the computing complexity by using our proposed approach, adaptive resolution method (ARM), to recognize the critical objects in the contest field by object features which can be obtained easily. The experimental results indicate that the proposed approach can increase the real-time and accurate recognition efficiency.