Sports Field Registration via Keypoints-aware Label Condition

Chu, Yen-Jui; Su, Jheng-Wei; Hsiao, Kai-Wen; Lien, Chi-Yu; Fan, Shu-Ho; Hu, Min‐Chun; Lee, Ruen‐Rone; Yao, Chih‐Yuan; Chu, Hung‐Kuo

doi:10.1109/cvprw56347.2022.00396

Cited by 23 publications

(19 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… We demonstrate the performance of the proposed methods through extensive experiments on several datasets. Our homography estimation method is state-of-the-art and outperforms previous works on multiple metrics using the WorldCup [ 3 ] and the TS-WorldCup [ 11 ] public datasets. Our tracking algorithm also outperforms previous works on the SoccerNet-tracking [ 1 ] and SportsMOT [ 19 ] public datasets.…”

Section: Introductionmentioning

confidence: 85%

“…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%

“…The attention mechanisms of our vision transformer encoder [ 14 ] can capture characteristic pitch features globally in the frames. Instead of using a uniform distribution of the pitch keypoints in the pitch space [ 10 , 11 ], we applied a perspective-aware sampling of the keypoints. This produces a more uniform distribution in the frame space to improve the homography estimation using the RANSAC algorithm.…”

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: Introductionmentioning

confidence: 85%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

“…The model is trained with a pixel classification approach. Chu et al [5] recently improved the keypoint detection by using dynamic filters.…”

Section: Related Work 21 Sports-field Registration Methodsmentioning

confidence: 99%

“…Nevertheless, this small number of images can introduce biases in the training and evaluation of the appraoches. Chu et al [5] therefore recently publicly released their TS-WorldCup datasets composed of 3812 soccer images. For its second edition, the Soccer-Net challenge [9] also publicly released a soccer-field registration dataset with 20028 annotated frames.…”

Section: Public Datasetsmentioning

confidence: 99%