CourtMotion: Learning Event-Driven Motion Representations from Skeletal Data for Basketball

TL;DR

CourtMotion introduces a novel framework combining skeletal data processing with advanced neural architectures to analyze and predict basketball game events, significantly enhancing accuracy over traditional position-only models.

Contribution

The paper presents a two-stage approach using Graph Neural Networks and Transformers to connect physical motion patterns with tactical basketball events, advancing event understanding from skeletal data.

Findings

35% reduction in trajectory prediction error

Significant improvements in downstream basketball analytics tasks

Pretrained model enhances multiple event detection and classification tasks

Abstract

This paper presents CourtMotion, a spatiotemporal modeling framework for analyzing and predicting game events and plays as they develop in professional basketball. Anticipating basketball events requires understanding both physical motion patterns and their semantic significance in the context of the game. Traditional approaches that use only player positions fail to capture crucial indicators such as body orientation, defensive stance, or shooting preparation motions. Our two-stage approach first processes skeletal tracking data through Graph Neural Networks to capture nuanced motion patterns, then employs a Transformer architecture with specialized attention mechanisms to model player interactions. We introduce event projection heads that explicitly connect player movements to basketball events like passes, shots, and steals, training the model to associate physical motion patterns with their tactical purposes. Experiments on NBA tracking data demonstrate significant improvements over position-only baselines: 35% reduction in trajectory prediction error compared to state-of-the-art position-based models and consistent performance gains across key basketball analytics tasks. The resulting pretrained model serves as a powerful foundation for multiple downstream tasks, with pick detection, shot taker identification, assist prediction, shot location classification, and shot type recognition demonstrating substantial improvements over existing methods.