The increasing number of vision-based tracking systems deployed in production has necessitated fast, robust cam- era calibration. In the domain of sport, the majority of cur- rent work focuses on sports where lines and intersections are easy to extract, and appearance is relatively consistent across venues. However, for more challenging sports like basketball, those techniques are not sufficient. In this paper, we propose an end-to-end approach for single moving cam- era calibration across challenging scenarios in sports. Our method contains three key modules: 1) area-based court segmentation, 2) camera pose estimation with embedded templates, 3) homography prediction via a spatial trans- form network (STN). All three modules are connected, en- abling end-to-end training. We evaluate our method on a new college basketball dataset and demonstrate the state of the art performance in variable and dynamic environments. We also validate our method on the World Cup 2014 dataset to show its competitive performance against the state-of- the-art methods. Lastly, we show that our method is two orders of magnitude faster than the previous state of the art on both datasets.
© Copyright 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE. Published by IEEE. All rights reserved.