Puck localization and multi-task event recognition in broadcast hockey videos

TL;DR

This paper presents a multi-task neural network for accurate puck localization and event recognition in broadcast hockey videos, leveraging temporal context and player positions to improve performance.

Contribution

Introduces a novel multi-task network that combines puck localization with event recognition using expert annotations and spatial attention mechanisms.

Findings

Achieves 73.1% AUC in puck localization

Localizes puck at 5 fps in 720p videos

Multi-task learning enhances event recognition accuracy

Abstract

Puck localization is an important problem in ice hockey video analytics useful for analyzing the game, determining play location, and assessing puck possession. The problem is challenging due to the small size of the puck, excessive motion blur due to high puck velocity and occlusions due to players and boards. In this paper, we introduce and implement a network for puck localization in broadcast hockey video. The network leverages expert NHL play-by-play annotations and uses temporal context to locate the puck. Player locations are incorporated into the network through an attention mechanism by encoding player positions with a Gaussian-based spatial heatmap drawn at player positions. Since event occurrence on the rink and puck location are related, we also perform event recognition by augmenting the puck localization network with an event recognition head and training the network through multi-task learning. Experimental results demonstrate that the network is able to localize the puck with an AUC of $73.1 \%$ on the test set. The puck location can be inferred in 720p broadcast videos at $5$ frames per second. It is also demonstrated that multi-task learning with puck location improves event recognition accuracy.