Homography Transformation Research Articles

TRACKING THE BALL AND PLAYERS FROM MULTIPLE FOOTBALL VIDEOS

This paper deals with tracking players and the ball in multiple soccer video sequences taken from fixed cameras located around the stadium. One of the major obstacle in player tracking occurs when occlusion between people results in insufficient observation information. If a player blob is not visible in some of the input videos due to occlusion, one solution is to check whether he is visible in others. This check is helped by the homography transformation induced by the play-ground because the players' positions can be represented on a virtual planar soccer field and can be mapped into any video image through a corresponding homography between the virtual field and the video image. Therefore, the position estimate of the player is exploited to predict and check the visibility in each of the video images. Measurements are taken from those visible images. On the other hand, before initiating tracking, we do a color correction in order to enhance the measurement and matching process because each of the video produces different RGB values for the same scene object due to different camera position and color sensor characteristics. After tracking players, ball tracking is carried out by eliminating the image blobs of players and accumulating the ideally ball-only images. We implemented our tracking algorithm, and experiments for sets of multiple real videos showed promising results.