An efficient object recognition system for humanoid robot vision

The research of autonomous robots is one of the most important issues in recent years. In the numerous robot researches, the humanoid robot soccer competition is very popular. The robot soccer players rely on their vision systems very heavily when they are in the unpredictable and dynamic environments. This paper proposes a simple and fast 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 finish the functions of robot localization, robot tactic, barrier avoiding,…, etc. It can decrease the computing efforts 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.

1. Introduction

RoboCup [1] is an international joint project to stimulate researches in the field of artificial intelligence, robotics, and related fields. According the rules of RoboCup for 2009 in the humanoid league of kid size [2], the competitions take place on a rectangular field of cm2 area, which contains two goals and two landmark poles, as shown in Figure 1. A goal is placed in the middle of each goal line. One of the goals is colored yellow and the other is colored blue. The goal for the kid size field has 90cm of height for the crossbar, 40cm of height for the goal wall, 150cm of width for the goal wall, and 50cm of depth for the goal wall. The two landmark poles are placed at each side of the two intersection points between the touch line and the center line. The landmark pole is a cylinder and has a diameter of 20cm. It consists of three segments of 20cm height, stacked each other. The lowest and the highest segments are with the same color as the goal of its left side. The ball is the standard size orange tennis ball. All of the above objects are the most critical characteristics in the field, and they are also the key features which we have to pay attention to. Figure 1.

The field of the competitions [2].