Efficient One-Shot Sports Field Image Registration with Arbitrary Keypoint Segmentation

Jacquelin, Nicolas; Vuillemot, Romain; Duffner, Stefan

doi:10.1109/icip46576.2022.9897170

Cited by 2 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method has been recently improved by Chu et al [ 11 ] by the integration of dynamic filters in the encoder–decoder network. Jacquelin et al [ 12 ] also build upon this framework for swimming pool registration.…”

Section: Previous Workmentioning

confidence: 99%

“…These views are highly distorted, rendering it unfeasible to generate a homography between the field and frame space. Jaquelin et al [ 12 ] released a swimming pool registration dataset with their method. The DeepSportRadar dataset [ 36 ] has also been released for basketball camera calibration.…”

Section: Previous Workmentioning

confidence: 99%

“…Our encoder–decoder model is based on a vision transformer and generates heatmaps to locate the pitch keypoints. Previous sports field registration methods use models based on convolutions [ 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 ], which are limited by their receptive fields. The attention mechanisms of our vision transformer encoder [ 14 ] can capture characteristic pitch features globally in the frames.…”

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

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: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%