Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi Player Tracking in Ice Hockey with Homographic Projections

Harish Prakash, Jia Cheng Shang, Ken M. Nsiempba, Yuhao Chen, David A. Clausi, John S. Zelek

TL;DR

This work tackles robust multi-object tracking of ice hockey players from monocular broadcast feeds, where occlusions and rapid motion challenge identity continuity. It introduces a bipartite graph matching framework augmented by homography-based footpoint projection to an overhead rink template, coupled with a temporal graph neural network to propagate identity cues over time. The approach yields significant improvements in ID switches and IDF1 on two hockey datasets, including cross-dataset generalization to VIP-HTD, demonstrating strong practical potential for broadcast analytics. By providing reliable top-view positional cues and global feature reasoning, the method enhances tracking reliability in sports analytics and can extend to other sports with appropriate homography models.

Abstract

Multi Object Tracking (MOT) in ice hockey pursues the combined task of localizing and associating players across a given sequence to maintain their identities. Tracking players from monocular broadcast feeds is an important computer vision problem offering various downstream analytics and enhanced viewership experience. However, existing trackers encounter significant difficulties in dealing with occlusions, blurs, and agile player movements prevalent in telecast feeds. In this work, we propose a novel tracking approach by formulating MOT as a bipartite graph matching problem infused with homography. We disentangle the positional representations of occluded and overlapping players in broadcast view, by mapping their foot keypoints to an overhead rink template, and encode these projected positions into the graph network. This ensures reliable spatial context for consistent player tracking and unfragmented tracklet prediction. Our results show considerable improvements in both the IDsw and IDF1 metrics on the two available broadcast ice hockey datasets.

Multi Player Tracking in Ice Hockey with Homographic Projections

TL;DR

This work tackles robust multi-object tracking of ice hockey players from monocular broadcast feeds, where occlusions and rapid motion challenge identity continuity. It introduces a bipartite graph matching framework augmented by homography-based footpoint projection to an overhead rink template, coupled with a temporal graph neural network to propagate identity cues over time. The approach yields significant improvements in ID switches and IDF1 on two hockey datasets, including cross-dataset generalization to VIP-HTD, demonstrating strong practical potential for broadcast analytics. By providing reliable top-view positional cues and global feature reasoning, the method enhances tracking reliability in sports analytics and can extend to other sports with appropriate homography models.

Abstract

Multi Object Tracking (MOT) in ice hockey pursues the combined task of localizing and associating players across a given sequence to maintain their identities. Tracking players from monocular broadcast feeds is an important computer vision problem offering various downstream analytics and enhanced viewership experience. However, existing trackers encounter significant difficulties in dealing with occlusions, blurs, and agile player movements prevalent in telecast feeds. In this work, we propose a novel tracking approach by formulating MOT as a bipartite graph matching problem infused with homography. We disentangle the positional representations of occluded and overlapping players in broadcast view, by mapping their foot keypoints to an overhead rink template, and encode these projected positions into the graph network. This ensures reliable spatial context for consistent player tracking and unfragmented tracklet prediction. Our results show considerable improvements in both the IDsw and IDF1 metrics on the two available broadcast ice hockey datasets.
Paper Structure (17 sections, 18 equations, 4 figures, 6 tables, 2 algorithms)

This paper contains 17 sections, 18 equations, 4 figures, 6 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Works
  3. MOT for Pedestrians
  4. MOT for Sports
  5. Tracking with Graphs
  6. Proposed Method
  7. Problem Formulation
  8. Homographic Projection
  9. Temporal Graph Association
  10. Message Passing Network
  11. Post-Processing
  12. Implementation Details
  13. Datasets
  14. Training Details.
  15. Evaluation Metrics
  16. ...and 2 more sections

Figures (4)

  • Figure 1: Other trackers vs Our approach. a) During a significant occlusion scenario $(t+2)$, other trackers lead to an ID switch error; b) Our method consistently tracks players before and after occlusion; c) Overhead rink template used for homography projection; d) Player footpoint coordinates mapped to the overhead template. At $(t+2)$, there is a clear distinction between overlapping players from the top view. This information aids our tracker in maintaining player tracklets.
  • Figure 2: Proposed Approach. a) The general pipeline of our spatio-temporal graph. b) $G$ denotes the three stages of Graph Initialization, MPN, and Classification. c) $PP$ denotes the Post-Processing stage where we Prune, solve graph violations, and assign player IDs
  • Figure 3: No. of message passing steps, $L$ vs. No. of IDsw incurred
  • Figure 4: Qualitative results for the VIP-HTD vip-htd test-set. Our tracker generalizes well to this unseen dataset, incurring neglible ID switches