TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications

Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. It is still challenging to recognize and position a high-speed and tiny ball accurately from an ordinary video. In this paper, we develop a deep learning network, called TrackNet, to track the tennis ball from broadcast videos in which the ball images are small, blurry, and sometimes with afterimage tracks or even invisible. The proposed heatmap-based deep learning network is trained to not only recognize the ball image from a single frame but also learn flying patterns from consecutive frames. The network is evaluated on the video of the men's singles final at the 2017 Summer Universiade, which is available on YouTube. The precision, recall, and $F1$ -measure reach 99.7%, 97.3%, and 98.5%, respectively. To prevent overfitting, 9 additional videos are partially labeled together with a subset from the previous dataset to implement 10-fold cross-validation, and the precision, recall, and $F_{1}$ -measure are 95.3%, 75.7%, and 84.3%, respectively. The source code and dataset are available at https://nol.cs.nctu.edu.tw:234/open-source/TrackNet/.