Posted on by

Football Playing Field Registration Using Distance Maps

Introduction

In football, the playing field registration problem can be thought of as the homography estimation between the playing field plane and the visible area of
the image. Existing approaches rely on the identification of significant keypoints in the image, such as the corners or intersections of the playing
field lines, which are then used for the initial estimate of the homography. Finding the exact location of such keypoints can be very challenging, and
that is why the initial homography estimates are not accurate enough and need to be refined iteratively. We propose distance maps, a technique that
utilizes distance transform to predict the location of imaginary lines spread evenly over the playing field. Intersections of these lines can be
used to find more accurate homography estimates. We also introduce the Calib360 playing field registration dataset, that can provide a sufficient amount of
training data with accurate ground truth labels.

 

The source code of our method can be found at – https://github.com/IgorJanos/stuFieldReg-official

The official repository of the Calib360 dataset can be found at – https://github.com/IgorJanos/stuCalib360

The best pre-trained models can be downloaded at – https://vggnas.fiit.stuba.sk/download/janos/fieldreg/fieldreg-experiments.tar.gz

You can find our original paper at – … URL …

Dataset

We propose the Calib360 dataset, which contains 300,000 training images with accurate homography annotations, which we have constructed from equirectangular panoramas. In panoramas, we annotate the positions of known keypoints of the football playing field model.

Next, from the annotated keypoints we extract the panoramic camera position and orientation with respect to the playing field. Once the camera parameters are extracted, we can generate unlimited number of different views of the playing field by adjusting the viewing angles and field of view. These generated images are perfect for training of neural networks because they all conform to the pinhole camera model and contain accurate annotations.

Results

Estimated playing field registration by our method (first column), by the method of Nie et al. (2021, second column), by the method of Chu et al. (2022, third column), and by the method of Theiner et al. (2023, fourth column).