Associative Embedding for Game-Agnostic Team Discrimination

TL;DR

This paper introduces a CNN-based associative embedding method for game-agnostic team discrimination in sports, enabling accurate and generalizable team labeling without prior knowledge of team appearance.

Contribution

It presents a novel lightweight segmentation approach that assigns consistent embeddings to team players, allowing immediate and game-agnostic team separation in sports analytics.

Findings

High accuracy in team labeling across various basketball games

Effective generalization to new games and arenas

Robust performance despite player occlusions and interactions

Abstract

Assigning team labels to players in a sport game is not a trivial task when no prior is known about the visual appearance of each team. Our work builds on a Convolutional Neural Network (CNN) to learn a descriptor, namely a pixel-wise embedding vector, that is similar for pixels depicting players from the same team, and dissimilar when pixels correspond to distinct teams. The advantage of this idea is that no per-game learning is needed, allowing efficient team discrimination as soon as the game starts. In principle, the approach follows the associative embedding framework introduced in arXiv:1611.05424 to differentiate instances of objects. Our work is however different in that it derives the embeddings from a lightweight segmentation network and, more fundamentally, because it considers the assignment of the same embedding to unconnected pixels, as required by pixels of distinct players from the same team. Excellent results, both in terms of team labelling accuracy and generalization to new games/arenas, have been achieved on panoramic views of a large variety of basketball games involving players interactions and occlusions. This makes our method a good candidate to integrate team separation in many CNN-based sport analytics pipelines.