SportsTrack: An Innovative Method for Tracking Athletes in Sports Scenes

Wang, Jie; Peng, Yuzhou; Yang, Xiaodong; Wang, Ting; Zhang, Yanming

doi:10.48550/arxiv.2211.07173

Cited by 3 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We train a YOLOX model [ 84 ] to detect the players on the field. It has, indeed, demonstrated in previous work its ability to well detect persons for team sport tracking applications [ 17 , 18 , 85 ]. It also achieves a good trade-off between speed and accuracy.…”

Section: Methodsmentioning

confidence: 97%

“…Hurault et al [ 16 ], Vats et al [ 81 ], and Maglo et al [ 82 ] use a Faster R-CNN model [ 83 ] to detect soccer, hockey, and rugby players. The YOLOX detector [ 84 ] has also been used in many recent frameworks [ 17 , 18 , 85 ] since it offers a state-of-the-art trade-off between detection speed and accuracy.…”

Section: Previous Workmentioning

confidence: 99%

“…Huang et al [ 17 ] combined the OC-SORT algorithm [ 45 ] with the OSNet re-identification network [ 88 ] and sport-specific tracklet-matching strategies. Wang et al [ 18 ] use three Hungarian matching algorithms that mix IoU and re-identification criteria. They restore the tracks of players that exit and re-enter with a re-identification criteria.…”

Section: Previous Workmentioning

confidence: 99%

“…This quick method generates good quality tracklets between the instances when players occlude each other. For the re-identification (re-ID) of the players, previous methods use a frozen convolutional neural network during the tracking [ 15 , 16 , 17 , 18 ]. These approaches have difficulties in recognizing the fine identification details of the players visible in the video clips.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Individual Locating of Soccer Players from a Single Moving View

Maglo,

Orcesi,

Denize

et al. 2023

Sensors

View full text Add to dashboard Cite

Positional data in team sports is key in evaluating the players’ individual and collective performances. When the sole source of data is a broadcast-like video of the game, an efficient video tracking method is required to generate this data. This article describes a framework that extracts individual soccer player positions on the field. It is based on two main components. As in broadcast-like videos of team sport games, the camera view moves to follow the action and a sport field registration method estimates the homography between the pitch and the frame space. Our method estimates the positions of key points sampled on the pitch thanks to an encoder–decoder architecture. The attention mechanisms of the encoder, based on a vision transformer, captures characteristic pitch features globally in the frames. A multiple person tracker generates tracklets in the frame space by associating, with bipartite matching, the player detections between the current and the previous frames thanks to Intersection-Over-Union and distance criteria. Tracklets are then iteratively merged with appearance criteria thanks to a re-identification model. This model is fine-tuned in a self-supervised way on the player thumbnails of the video sample to specifically recognize the fine identification details of each player. The player positions in the frames projected by the homographies allow the obtaining of the real position of the players on the pitch at every moment of the video. We experimentally evaluate our sport field registration method and our 2D player tracker on public datasets. We demonstrate that they both outperform previous works for most metrics. Our 2D player tracker was also awarded first place at the SoccerNet tracking challenge in 2022 and 2023.

show abstract

Section: Methodsmentioning

confidence: 97%

Section: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Individual Locating of Soccer Players from a Single Moving View

Maglo,

Orcesi,

Denize

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…For instance, ByteTrack effectively utilizes low-scoring detection results through secondstage correlation, improving correlation performance. SportsTrack [28] adopts a three-stage correlation approach, allowing all detection results to be correlated with trajectories in the first stage, providing more opportunities for low-scoring detections to be matched.…”

Section: Association Methodsmentioning

confidence: 99%

UniTracker:Transformer Based CrossUnihead for Multi-object Tracking

Wu,

Zhang

2024

Preprint

View full text Add to dashboard Cite

In recent years, tracking-by-detection (TBD) has emerged as the predominant approach for Multi-object Tracking (MOT). Most TBD algorithms typically employ separate branch heads to handle the coarse feature representations extracted from the backbone network. However, this approach often leads to suboptimal model performance. This is due to the presence of feature conflicts among multiple tasks on one hand, and the lack of information interaction among these tasks on the other. Inspired by CSTrack and Unihead, we have combined the feature decoupling module REN with the transformer-based task interaction module CIT to form CrossUnihead which is a plug and play module. This module not only effectively achieves task-based feature decoupling, but also facilitates information interaction among different tasks. The MOT algorithm based on CrossUnihead, named UniTracker, demonstrates impressive performance on the MOT dataset when compared to other advanced methods and is capable of achieving real-time tracking.

show abstract

SKT-MOT and DyTracker: A Multiobject Tracking Dataset and a Dynamic Tracker for Speed Skating Video

Wang,

Li,

et al. 2023

Scientific Programming

View full text Add to dashboard Cite

Speed skating serves as a significant application domain for multiobject tracking (MOT), presenting unique challenges such as frequent occlusion, highly similar appearances, and motion blur. To address these challenges, this paper constructs an MOT dataset called SKT-MOT for speed skating and analyzes the shortcomings of existing datasets and methods. Accordingly, we propose a dynamic MOT method called DyTracker. The method builds upon the DeepSORT baseline and enhances three key modules. At the global level, we design the track dynamic management (TDM) algorithm. In the motion branch, a novel metric is proposed to evaluate occlusion and Kalman filter dynamic update (KFDU) is implemented. In the appearance branch, we account for the difference in human posture and propose the feature dynamic selection and updating (FDSU) strategy. This makes our DyTracker flexible and efficient to achieve a multiobject tracking accuracy (MOTA) of 93.70% and identification F1 (IDF1) score of 92.39% on SKT-MOT, which is a significant advantage over existing SOTA methods. To validate the generalization of our proposed module, two dynamic update modules are inserted into other methods and validated on the public dataset MOT17, and the accuracy is generally improved by 0.2%–0.6%.

show abstract

SportsTrack: An Innovative Method for Tracking Athletes in Sports Scenes

Cited by 3 publications

References 0 publications

Individual Locating of Soccer Players from a Single Moving View

Individual Locating of Soccer Players from a Single Moving View

UniTracker:Transformer Based CrossUnihead for Multi-object Tracking

SKT-MOT and DyTracker: A Multiobject Tracking Dataset and a Dynamic Tracker for Speed Skating Video

Contact Info

Product

Resources

About