Broadcast2pitch++: depth-aware game state reconstruction from unconstrained soccer videos
Machine Vision and Applications · 2026-11 · 37 (6)
DOI: 10.1007/s00138-026-01895-w ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Vision and Applications, online erschienen am 20.08.2026. Verfasst von Yewon Hwang und 7 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Gefördert von: The Korea Institute of Science and Technology (KIST) Institutional Program.
Abstract (Originalsprache)
Game State Reconstruction (GSR) aims to recover the spatial positions and semantic identities of all players from broadcast soccer videos, requiring robust localization, tracking, and identity association under unconstrained camera motion and severe visual ambiguity. In this work, we present Broadcast2Pitch++, an extended framework for robust game-state reconstruction from broadcast soccer footage. We introduce two major extensions to the original framework for enhanced temporal identity consistency. First, we propose a depth-aware tracking formulation that incorporates monocular depth cues into the DeepEIoU association process. Second, we propose an improved tracklet refinement strategy that combines appearance similarity, motion consistency, and vision-language-derived identity attributes within a unified soft merge formulation. Comprehensive experiments on the SoccerNet-Tracking and SoccerNet-GSR benchmarks demonstrate that the proposed extensions consistently improve temporal association consistency in challenging broadcast soccer scenarios.
Förderung
- The Korea Institute of Science and Technology (KIST) Institutional Program
Zitieren
APA
Hwang, Y., Oo, Y. M., Robbani, M. A., Chao, V., Jamsrandorj, A., Nguyen, H. Q., Mun, K., & Kim, J. (2026). Broadcast2pitch++: depth-aware game state reconstruction from unconstrained soccer videos. Machine Vision and Applications, 37(6). https://doi.org/10.1007/s00138-026-01895-w
Vancouver
Hwang Y, Oo YM, Robbani MA, Chao V, Jamsrandorj A, Nguyen HQ, et al. Broadcast2pitch++: depth-aware game state reconstruction from unconstrained soccer videos. Machine Vision and Applications. 2026;37(6). doi:10.1007/s00138-026-01895-w
BibTeX
@article{Hwang2026,
author = {Hwang, Yewon and Oo, Yin May and Robbani, Muhammad Amrulloh and Chao, Vanyi and Jamsrandorj, Ankhzaya and Nguyen, Hoang Quoc and Mun, Kyung-Ryoul and Kim, Jinwook},
title = {Broadcast2pitch++: depth-aware game state reconstruction from unconstrained soccer videos},
journal = {Machine Vision and Applications},
year = {2026},
volume = {37},
number = {6},
doi = {10.1007/s00138-026-01895-w}
}
EUVIMED