6MapNet: Representing soccer players from tracking data by a triplet network

TL;DR

This paper introduces 6MapNet, a triplet network that effectively captures soccer players' movement styles from GPS data, enabling accurate player identification with minimal matches without requiring annotated actions.

Contribution

The novel 6MapNet model uses heatmaps derived from GPS data to quantify player styles without needing annotated actions, improving scalability and efficiency.

Findings

Accurately identifies players with few matches

Uses heatmaps from GPS data for style representation

No need for annotated soccer actions

Abstract

Although the values of individual soccer players have become astronomical, subjective judgments still play a big part in the player analysis. Recently, there have been new attempts to quantitatively grasp players' styles using video-based event stream data. However, they have some limitations in scalability due to high annotation costs and sparsity of event stream data. In this paper, we build a triplet network named 6MapNet that can effectively capture the movement styles of players using in-game GPS data. Without any annotation of soccer-specific actions, we use players' locations and velocities to generate two types of heatmaps. Our subnetworks then map these heatmap pairs into feature vectors whose similarity corresponds to the actual similarity of playing styles. The experimental results show that players can be accurately identified with only a small number of matches by our method.