A General Framework for Jersey Number Recognition in Sports Video

TL;DR

This paper introduces a new dataset and framework for recognizing jersey numbers in sports videos, adapting scene text recognition methods to improve long-term player tracking across hockey and soccer.

Contribution

It presents a novel jersey number dataset, adapts scene text recognition models for sports, and explores cross-sport generalization and tracklet-level recognition.

Findings

Achieved 91.4% accuracy on hockey jersey images.

Achieved 87.4% accuracy on soccer jersey tracklets.

Demonstrated effective adaptation of scene text recognition models.

Abstract

Jersey number recognition is an important task in sports video analysis, partly due to its importance for long-term player tracking. It can be viewed as a variant of scene text recognition. However, there is a lack of published attempts to apply scene text recognition models on jersey number data. Here we introduce a novel public jersey number recognition dataset for hockey and study how scene text recognition methods can be adapted to this problem. We address issues of occlusions and assess the degree to which training on one sport (hockey) can be generalized to another (soccer). For the latter, we also consider how jersey number recognition at the single-image level can be aggregated across frames to yield tracklet-level jersey number labels. We demonstrate high performance on image- and tracklet-level tasks, achieving 91.4% accuracy for hockey images and 87.4% for soccer tracklets. Code, models, and data are available at https://github.com/mkoshkina/jersey-number-pipeline.