Ice Hockey Puck Localization Using Contextual Cues

TL;DR

This paper introduces PLUCC, a novel context-aware method for detecting ice hockey pucks in broadcast videos, leveraging player behavior cues to improve accuracy amidst challenges like occlusion and motion blur.

Contribution

The paper proposes a new approach that explicitly models player behavior cues for improved puck detection, outperforming previous appearance and motion-based methods.

Findings

Achieved 12.2% higher average precision over baselines.

Introduced Rink Space Localization Error (RSLE) for perspective-invariant evaluation.

Demonstrated the importance of contextual cues in puck detection.

Abstract

Puck detection in ice hockey broadcast videos poses significant challenges due to the puck's small size, frequent occlusions, motion blur, broadcast artifacts, and scale inconsistencies due to varying camera zoom and broadcast camera viewpoints. Prior works focus on appearance-based or motion-based cues of the puck without explicitly modelling the cues derived from player behaviour. Players consistently turn their bodies and direct their gaze toward the puck. Motivated by this strong contextual cue, we propose Puck Localization Using Contextual Cues (PLUCC), a novel approach for scale-aware and context-driven single-frame puck detections. PLUCC consists of three components: (a) a contextual encoder, which utilizes player orientations and positioning as helpful priors; (b) a feature pyramid encoder, which extracts multiscale features from the dual encoders; and (c) a gating decoder that combines latent features with a channel gating mechanism. For evaluation, in addition to standard average precision, we propose Rink Space Localization Error (RSLE), a scale-invariant homography-based metric for removing perspective bias from rink space evaluation. The experimental results of PLUCC on the PuckDataset dataset demonstrated state-of-the-art detection performance, surpassing previous baseline methods by an average precision improvement of 12.2% and RSLE average precision of 25%. Our research demonstrates the critical role of contextual understanding in improving puck detection performance, with broad implications for automated sports analysis.