Court Detection Using Masked Perspective Fields Network

Court detection is an important step in sports video analytics. Its goal is to find a projective transformation matrix which projects a standard court to the one visible in the video frame. The inverse of the transformation matrix allows the pixels in the video frame to be projected back to the standard court, hence, provides measurements in the physical world coordinates. Instead of finding the transformation matrix directly, we design a deep fully convolutional neural network to estimate a Perspective Fields (PF) between the court in the source image and the court in a reference image. Our network has two branches, one outputs the PF, the other outputs the court lines which serves as the mask to guide the network to focus on the relevant parts of the input images, thereby finding the transformation pertaining to the court only. Our network is sport-agnostic, which means it is easily generalizable to different types of sports.