Author_Institution :
Sch. of Comput. Sci. & Technol., Shenyang Aerosp. Univ., Shenyang, China
Abstract :
Fast flying ping-pong usually generates motion blur in the process of image capture, which impacts, and even interferes in, the process of exact detecting and tracking of the sphere position. In this paper, motion blur of flying ping-pong, as well as the demands by an adversarial ping-pong robot, is analyzed, and after that we propose an integrated method called CS-BS-EF, which stands for a comprehensive integration and optimization of three in being methods, i.e., color segmentation, background subtraction and ellipse fitting, and overcomes the drawbacks of each single. This method is computational efficient because it does not need any deblurring at all. Now, CS-BS-EF is used for detecting the smear scope and calculating the exact position and direction of the flying ping-pong. The experimental results show that CS-BS-EF is capable of surmounting the effect of smear, and detecting and tracking high-speed flying ping-pong with comparative accuracy, anti-interfering, instantaneity.
Keywords :
image colour analysis; image segmentation; object detection; object tracking; CS-BS-EF; adversarial ping-pong robot; background subtraction; color segmentation; ellipse fitting; high-speed flying ping-pong detection; high-speed flying ping-pong tracking; image capture; motion blur; smear scope detection; Educational institutions; Fitting; Image color analysis; Image segmentation; Real-time systems; Robots; Tracking; motion blur; object tracking; ping-pong; robot;
Conference_Titel :
Mechatronic Sciences, Electric Engineering and Computer (MEC), Proceedings 2013 International Conference on