Abstract
This paper proposes a fast colour-based object recognition and localization for soccer robots. The traditional HSL colour model is modified for better colour segmentation and edge detection in a colour coded environment. The object recognition is based on only the edge pixels to speed up the computation. The edge pixels are detected by intelligently scanning a small part of whole image pixels which is distributed over the image. A fast method for line and circle centre detection is also discussed. For object localization, 26 key points are defined on the soccer field. While two or more key points can be seen from the robot camera view, the three rotation angles are adjusted to achieve a precise localization of robots and other objects. If no key point is detected, the robot position is estimated according to the history of robot movement and the feedback from the motors and sensors. The experiments on NAO and RoboErectus teen-size humanoid robots show that the proposed vision system is robust and accurate under different lighting conditions and can effectively and precisely locate robots and other objects.
Highlights
All the RoboCup real robot soccer competitions of different leagues, such as humanoid, standard platform and middle size, take place in a colour coded environment
Many other types of sensors, such as sonar, infrared, and laser range finder can be used to improve the accuracy of object detection and localization
Our vision system has been implemented in RoboErectus (RE) [5] and Aldebaran NAO humanoid robot [4]
Summary
All the RoboCup real robot soccer competitions of different leagues, such as humanoid, standard platform and middle size, take place in a colour coded environment. One or two cameras are used for object detection and localization. Many other types of sensors, such as sonar, infrared, and laser range finder can be used to improve the accuracy of object detection and localization. The main focus of this paper is how to use camera(s) to detect and locate robots and objects. The objects of interest in soccer robot vision system include an orange ball, blue and yellow goals, white lines, robots, poles, etc. T. Yang et al / A fast vision system for soccer robot segmentation of colour while the environment is not too dark or too bright. If two or more key points are seen in the robot camera view, the space relationship of these key points is employed to adjust the rotation angles used in object localization.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
