Design and Development of an image processing system for humanoid robot team playing soccer in RoboCup KSL league

שלחו לחבר
שנה
2015

תכנון ופיתוח מערכת ראייה ועיבוד תמונה לקבוצת רובוטים המשחקים כדורגל בליגת KSL בתחרות רובוקאפ

תיאור הפרויקט:

RoboCupTM is an international research and education initiative. Its goal is to foster artificial intelligence and robotics research by providing a standard problem where a wide range of technologies can be examined and integrated. 
The focus of the RoboCup activities is competitive soccer. 
In this league, autonomous robots with a human-like body plan and human-like senses play soccer against each other. Dynamic walking, running, and kicking the ball while maintaining balance, visual perception of the ball, other players, and the field, self-localization, and team play are among the many issues investigated in the Humanoid League.

תכולת הפרויקט:

The students will design image processing system for a soccer playing robot team including ball identification, goal identification, geometric features on the field, other robots on the field, the team goal-keeper, distance to various objects, using of edge detection filters, phase and angle conversion filters, color identification and calibration, object movements and more. In addition, the students will build a GUI for robots position identification. 

מקורות:

1. Gonzalez, R.C. and Woods, R.E., Digital Image Processing, Pearson Prentice-Hall, New Jersy, 2008.
2. Budden D., Fenn S., Mendes A, and Chalup S. Evaluation of Color Modelsfor Computer Vision Using Cluster Validation Techniques. Proc. of RoboCup 2012,  pp. 261-272, 2012.
3. Morrison J., Chown E., and Silver B. Implementing a Real-Time Hough Transform on a Mobile Robot. Proc. of RoboCup 2012,  pp. 322-331, 2012.
4. Sven Behnke, Jürgen Müller, Michael Schreiber: Toni: A Soccer Playing Humanoid Robot. In: RoboCup 2005: 59-704.
5. Laowattana D., et al.: Team KMUTT, Team description paper. Robocup 2009, Humanoid League (2009)
6. Lu H., Huang D., Xiong D., Li X., and Zheng Z. A Robust Place Recognition Algorithm Based on Omnidirectional Vision for Mobile Robots. Proc. of RoboCup 2012,  pp. 286-297, 2012.