Multi-Camera Asynchronous Ball Localization and Trajectory Prediction with Factor Graphs and Human Poses
This work addresses the challenge of precise ball tracking for agile robots in sports like tennis, representing an incremental improvement with domain-specific applications.
The paper tackles the problem of real-time 3D tennis ball localization and trajectory prediction in high-speed sports by combining multi-camera systems, factor graphs, and human pose data, achieving a 63.6% reduction in landing position prediction error compared to a baseline.
The rapid and precise localization and prediction of a ball are critical for developing agile robots in ball sports, particularly in sports like tennis characterized by high-speed ball movements and powerful spins. The Magnus effect induced by spin adds complexity to trajectory prediction during flight and bounce dynamics upon contact with the ground. In this study, we introduce an innovative approach that combines a multi-camera system with factor graphs for real-time and asynchronous 3D tennis ball localization. Additionally, we estimate hidden states like velocity and spin for trajectory prediction. Furthermore, to enhance spin inference early in the ball's flight, where limited observations are available, we integrate human pose data using a temporal convolutional network (TCN) to compute spin priors within the factor graph. This refinement provides more accurate spin priors at the beginning of the factor graph, leading to improved early-stage hidden state inference for prediction. Our result shows the trained TCN can predict the spin priors with RMSE of 5.27 Hz. Integrating TCN into the factor graph reduces the prediction error of landing positions by over 63.6% compared to a baseline method that utilized an adaptive extended Kalman filter.