Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mansourian, Amir M., Somers, Vladimir, De Vleeschouwer, Christophe, Kasaei, Shohreh
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913199511568384
author Mansourian, Amir M.
Somers, Vladimir
De Vleeschouwer, Christophe
Kasaei, Shohreh
author_facet Mansourian, Amir M.
Somers, Vladimir
De Vleeschouwer, Christophe
Kasaei, Shohreh
contents Effective tracking and re-identification of players is essential for analyzing soccer videos. But, it is a challenging task due to the non-linear motion of players, the similarity in appearance of players from the same team, and frequent occlusions. Therefore, the ability to extract meaningful embeddings to represent players is crucial in developing an effective tracking and re-identification system. In this paper, a multi-purpose part-based person representation method, called PRTreID, is proposed that performs three tasks of role classification, team affiliation, and re-identification, simultaneously. In contrast to available literature, a single network is trained with multi-task supervision to solve all three tasks, jointly. The proposed joint method is computationally efficient due to the shared backbone. Also, the multi-task learning leads to richer and more discriminative representations, as demonstrated by both quantitative and qualitative results. To demonstrate the effectiveness of PRTreID, it is integrated with a state-of-the-art tracking method, using a part-based post-processing module to handle long-term tracking. The proposed tracking method outperforms all existing tracking methods on the challenging SoccerNet tracking dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2401_09942
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking
Mansourian, Amir M.
Somers, Vladimir
De Vleeschouwer, Christophe
Kasaei, Shohreh
Computer Vision and Pattern Recognition
Artificial Intelligence
Effective tracking and re-identification of players is essential for analyzing soccer videos. But, it is a challenging task due to the non-linear motion of players, the similarity in appearance of players from the same team, and frequent occlusions. Therefore, the ability to extract meaningful embeddings to represent players is crucial in developing an effective tracking and re-identification system. In this paper, a multi-purpose part-based person representation method, called PRTreID, is proposed that performs three tasks of role classification, team affiliation, and re-identification, simultaneously. In contrast to available literature, a single network is trained with multi-task supervision to solve all three tasks, jointly. The proposed joint method is computationally efficient due to the shared backbone. Also, the multi-task learning leads to richer and more discriminative representations, as demonstrated by both quantitative and qualitative results. To demonstrate the effectiveness of PRTreID, it is integrated with a state-of-the-art tracking method, using a part-based post-processing module to handle long-term tracking. The proposed tracking method outperforms all existing tracking methods on the challenging SoccerNet tracking dataset.
title Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2401.09942