Ball Tracking in Soccer Video Using Kalman Filter
In the present work, tracking the soccer ball has been studied. For this purpose, it is necessary to detect exact position of the ball in the playfield and then track it Ball position on the field plays an important role in determining which event has occurred in the game. Therefore, Ball trajectory that can be obtained via tracking is useful for identifying and detecting main events of soccer games. Cleaning morphological method is applied to detect the ball. This method is real-time and automatic; it yields superior results in comparison with other common methods such as Template Matching and Circular Hough Transform (CHT)~. By applying the proposed method, only one candidate for the ball position is obtained; hence, it is more reliable than other methods. The tracking is performed using Kalman Filter in which the ball position in consecutive frames is obtained using size and color features. This tracking method can be useful in situation that cameras are not fixed and the moving problem in the screen coordinates occurs. The results illustrate that the proposed method is fast, effective, and reliable.
component object tracking motion detection object detection
J. Hosseinkhani A. H. Bakhtiari H. Soltanian-Zadeh M. Kamarei
CIPCE, Department of Electrical and Computer Engineering University of Tehran, Tehran, Iran
国际会议
重庆
英文
596-599
2011-08-20（万方平台首次上网日期，不代表论文的发表时间）