BlurBall: Joint Ball and Motion Blur Estimation for Table Tennis Ball Tracking
This work addresses motion blur challenges in racket sports analytics, offering incremental improvements in detection and trajectory prediction for real-time applications.
The paper tackles the problem of motion blur in table tennis ball tracking by introducing a new labeling strategy that places the ball at the center of the blur streak and annotates blur attributes, releasing a dataset and a model called BlurBall that achieves state-of-the-art results in detection accuracy.
Motion blur reduces the clarity of fast-moving objects, posing challenges for detection systems, especially in racket sports, where balls often appear as streaks rather than distinct points. Existing labeling conventions mark the ball at the leading edge of the blur, introducing asymmetry and ignoring valuable motion cues correlated with velocity. This paper introduces a new labeling strategy that places the ball at the center of the blur streak and explicitly annotates blur attributes. Using this convention, we release a new table tennis ball detection dataset. We demonstrate that this labeling approach consistently enhances detection performance across various models. Furthermore, we introduce BlurBall, a model that jointly estimates ball position and motion blur attributes. By incorporating attention mechanisms such as Squeeze-and-Excitation over multi-frame inputs, we achieve state-of-the-art results in ball detection. Leveraging blur not only improves detection accuracy but also enables more reliable trajectory prediction, benefiting real-time sports analytics.