Tracking
SoccerNet Tracking
We release 12 complete soccer games taken only from the main camera and annotate player tracklets. This task is particularly useful in soccer analytics as it allows to assess the performances of the players separately.
Our task.
Multi-object tracking (MOT) aims at recovering trajectories of multiple objects in time by estimating object bounding boxes and identities in videos sequences.
We consider two tasks: (1) a pure association task that considers ground-truth detections (task of the 2022 challenge), or (2) a complete tracking task that expects detecting the objects of interest from the raw video (task of the 2023 challenge).
Our classes.
The classes are not taken into account in the baseline or the evaluation, but the object to retrieve are among the following classes: {player team left, player team right, goalkeeper team left, goalkeeper team right, main referee, side referee, staff, ball}.
Our data.
The data consists of 100 videos clips of 30 seconds each from the main camera available at 1080p. The challenge set for 2022 is composed of 50 separate clips of 30 seconds. The challenge set for 2023 is composed of another set of 50 separate clips of 30 seconds.
Our Metric.
For our benchmark and challenge, we consider HOTA as the main metric. More specifically, this metric can be decomposed into two components: DetA and AssA, focusing on detection and association accuracy, respectively.
2023 challenge leaderboard
2022 challenge leaderboard
Our videos on Tracking
Soccer Player Tracking, Re-ID, Camera Calibration and Action Spotting - SoccerNet Challenges 2022
In this video, we present our new SoccerNet Challenges for CVPR 2022! We introduce the three tasks of Calibration, Re-identification and Tracking on soccer games, in partnership with EVS Broadcast Equipment, SportRadar and Baidu Research. We also reiterate our previous Action Spotting and Replay Grounding Challenges at the ActivityNet workshop.
How to cite this work ?
@InProceedings{cioppa2022soccernet,
title={SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos},
author={Cioppa, Anthony and Giancola, Silvio and Deliege, Adrien and Kang, Le and Zhou, Xin and Cheng, Zhiyu and Ghanem, Bernard and Van Droogenbroeck, Marc},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={3491--3502},
year={2022}
}