GoalieNet: A Multi-Stage Network for Joint Goalie, Equipment, and Net Pose Estimation in Ice Hockey

TL;DR

GoalieNet is a multi-stage neural network designed to accurately estimate goalie, equipment, and net poses in ice hockey, addressing the unique challenges of padded and obscured goalie keypoints.

Contribution

This paper introduces GoalieNet, a novel multi-stage deep learning model specifically tailored for joint pose estimation of goalies, their equipment, and the net in ice hockey.

Findings

Achieves 84% average keypoint accuracy on NHL data

Detects over 80% accuracy for 22 of 29 keypoints

Demonstrates the effectiveness of joint pose estimation in complex sports scenarios

Abstract

In the field of computer vision-driven ice hockey analytics, one of the most challenging and least studied tasks is goalie pose estimation. Unlike general human pose estimation, goalie pose estimation is much more complex as it involves not only the detection of keypoints corresponding to the joints of the goalie concealed under thick padding and mask, but also a large number of non-human keypoints corresponding to the large leg pads and gloves worn, the stick, as well as the hockey net. To tackle this challenge, we introduce GoalieNet, a multi-stage deep neural network for jointly estimating the pose of the goalie, their equipment, and the net. Experimental results using NHL benchmark data demonstrate that the proposed GoalieNet can achieve an average of 84\% accuracy across all keypoints, where 22 out of 29 keypoints are detected with more than 80\% accuracy. This indicates that such a joint pose estimation approach can be a promising research direction.