Graph-Based Multi-Camera Soccer Player Tracker
This addresses tracking challenges in sports analytics for soccer, but it is incremental as it builds on existing multi-camera methods with specific adaptations.
The paper tackles the problem of tracking soccer players in long-shot multi-camera videos by focusing on player dynamics and interactions, overcoming calibration errors with a novel tracker operating on raw detection heat maps, and achieves improved performance using synthetic data for training.
The paper presents a multi-camera tracking method intended for tracking soccer players in long shot video recordings from multiple calibrated cameras installed around the playing field. The large distance to the camera makes it difficult to visually distinguish individual players, which adversely affects the performance of traditional solutions relying on the appearance of tracked objects. Our method focuses on individual player dynamics and interactions between neighborhood players to improve tracking performance. To overcome the difficulty of reliably merging detections from multiple cameras in the presence of calibration errors, we propose the novel tracking approach, where the tracker operates directly on raw detection heat maps from multiple cameras. Our model is trained on a large synthetic dataset generated using Google Research Football Environment and fine-tuned using real-world data to reduce costs involved with ground truth preparation.