Sports Camera Calibration via Synthetic Data

Calibrating sports cameras is important for autonomous broadcasting and sports analysis. Here we propose a highly automatic method for calibrating sports cameras from a single image using synthetic data. First, we develop a novel camera pose engine that generates camera poses by randomly sampling camera parameters. The camera pose engine has only three significant free parameters so that it can effectively generate diverse camera poses and corresponding edge (i.e. field marking) images. Then, we learn compact feature descriptors via a siamese network and build a feature-pose database. After that, we use a novel generative adversarial network (GAN) model to detect field markings in real images. Finally, we query an initial camera pose from the feature-pose database and refine the camera pose by using distance images. We evaluate our method on both synthetic and real data. Our method not only demonstrates the robustness on the synthetic data but also achieves state-of-the-art accuracy on a standard soccer dataset and very high performance on a volleyball dataset.