Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Universal Protocol to Benchmark Camera Calibration for Sports (2404.09807v1)

Published 15 Apr 2024 in cs.CV

Abstract: Camera calibration is a crucial component in the realm of sports analytics, as it serves as the foundation to extract 3D information out of the broadcast images. Despite the significance of camera calibration research in sports analytics, progress is impeded by outdated benchmarking criteria. Indeed, the annotation data and evaluation metrics provided by most currently available benchmarks strongly favor and incite the development of sports field registration methods, i.e. methods estimating homographies that map the sports field plane to the image plane. However, such homography-based methods are doomed to overlook the broader capabilities of camera calibration in bridging the 3D world to the image. In particular, real-world non-planar sports field elements (such as goals, corner flags, baskets, ...) and image distortion caused by broadcast camera lenses are out of the scope of sports field registration methods. To overcome these limitations, we designed a new benchmarking protocol, named ProCC, based on two principles: (1) the protocol should be agnostic to the camera model chosen for a camera calibration method, and (2) the protocol should fairly evaluate camera calibration methods using the reprojection of arbitrary yet accurately known 3D objects. Indirectly, we also provide insights into the metric used in SoccerNet-calibration, which solely relies on image annotation data of viewed 3D objects as ground truth, thus implementing our protocol. With experiments on the World Cup 2014, CARWC, and SoccerNet datasets, we show that our benchmarking protocol provides fairer evaluations of camera calibration methods. By defining our requirements for proper benchmarking, we hope to pave the way for a new stage in camera calibration for sports applications with high accuracy standards.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. Monocular 3D human pose estimation for sports broadcasts using partial sports field registration. In IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), pages 5109–5118, Vancouver, Can., Jun. 2023. Inst. Electr. Electron. Eng. (IEEE).
  2. Beyond the Premier: Assessing action spotting transfer capability across diverse domains. In IEEE Int. Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), CVsports, Seattle, WA, USA, Jun. 2024.
  3. 3D ball trajectory reconstruction of a ballistic shot from a monocular basketball video. In Annu. Conf. IEEE Ind. Electron. Soc. (IECON), pages 1–6, Singapore, Singapore, Oct. 2023. Inst. Electr. Electron. Eng. (IEEE).
  4. Sports camera calibration via synthetic data. In IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), pages 2497–2504, Long Beach, CA, USA, Jun. 2019. Inst. Electr. Electron. Eng. (IEEE).
  5. Sports field registration via keypoints-aware label condition. In IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), pages 3522–3529, New Orleans, LA, USA, Jun. 2022. Inst. Electr. Electron. Eng. (IEEE).
  6. Scaling up SoccerNet with multi-view spatial localization and re-identification. Sci. Data, 9(1):1–9, Jun. 2022.
  7. Camera calibration and player localization in SoccerNet-v2 and investigation of their representations for action spotting. In IEEE Int. Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), CVsports, pages 4532–4541, Nashville, TN, USA, Jun. 2021.
  8. SoccerNet-tracking: Multiple object tracking dataset and benchmark in soccer videos. In IEEE Int. Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), CVsports, pages 3490–3501, New Orleans, LA, USA, Jun. 2022. Inst. Electr. Electron. Eng. (IEEE).
  9. SoccerNet 2023 challenges results. CoRR, abs/2309.06006, 2023.
  10. Real-time camera pose estimation for sports fields. Mach. Vis. Appl., 31(3), Mar. 2020.
  11. Paul J. Claasen and Jill P. de Villiers. Video-based sequential Bayesian homography estimation for soccer field registration. CoRR, abs/2311.10361, 2023.
  12. SoccerNet-v2: A dataset and benchmarks for holistic understanding of broadcast soccer videos. In IEEE Int. Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), CVsports, pages 4508–4519, Nashville, TN, USA, Jun. 2021.
  13. EVS Broadcast Equipment. Multi-camera review system - Xeebra. https://evs.com/products/video-assistance/xeebra, Jun. 2022.
  14. FIBA. 2022 official basketball rules: Basketball rules & basketball equipment. Technical report, Fédération Internationale de Basketball, Mies, Switzerland, 2022.
  15. FIFA. Handbook of test methods for virtual offside line assessment. Technical report, Fédération Internationale de Football Association, Zurich, Switzerland, Jun. 2019.
  16. FIVB. Official volleyball rules. Technical report, Fédération Internationale de Volleyball, Lausanne, Switzerland, 2021.
  17. SoccerNet: A scalable dataset for action spotting in soccer videos. In IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), pages 1792–179210, Salt Lake City, UT, USA, Jun. 2018. Inst. Electr. Electron. Eng. (IEEE).
  18. SoccerNet 2022 challenges results. In Int. ACM Work. Multimedia Content Anal. Sports (MMSports), pages 75–86, Lisbon, Port., Oct. 2022. ACM.
  19. VARS: Video assistant referee system for automated soccer decision making from multiple views. In IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), pages 5086–5097, Vancouver, Can., Jun. 2023. Inst. Electr. Electron. Eng. (IEEE).
  20. X-vars: Introducing explainability in football refereeing with multi-modal large language models. In IEEE Int. Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), CVsports, Seattle, WA, USA, Jun. 2024.
  21. Sports field localization via deep structured models. In IEEE Int. Conf. Comput. Vis. Pattern Recognit. (CVPR), pages 4012–4020, Honolulu, HI, USA, Jul. 2017. Inst. Electr. Electron. Eng. (IEEE).
  22. Pose2UV: Single-shot multiperson mesh recovery with deep UV prior. IEEE Trans. Image Process., 31:4679–4692, 2022.
  23. IFAB. Laws of the game. Technical report, The International Football Association Board, Zurich, Switzerland, 2022.
  24. IIHF. IIHF Official rule book 2022/23. Technical report, International Ice Hockey Federation, Zurich, Switzerland, Jul. 2022.
  25. DeepSportradar-v2: A multi-sport computer vision dataset for sport understandings. In Int. ACM Work. Multimedia Content Anal. Sports (MMSports), pages 23–29, Ottawa, Ontario, Can., Oct. 2023. ACM.
  26. Optimizing through learned errors for accurate sports field registration. In IEEE Winter Conf. Appl. Comput. Vis. (WACV), pages 201–210, Snowmass, CO, USA, Mar. 2020. Inst. Electr. Electron. Eng. (IEEE).
  27. GolfPose: Golf swing analyses with a monocular camera based human pose estimation. In IEEE Int. Conf. Multimedia Expo Work. (ICMEW), pages 1–6, Taipei City, Taiwan, Jul. 2022. Inst. Electr. Electron. Eng. (IEEE).
  28. Accurate and practical calibration of multiple pan-tilt-zoom cameras for live broadcasts. IEEE Access, 8:153993–154006, 2020.
  29. Accuracy evaluation and prediction of single-image camera calibration. IEEE Access, 11:19312–19323, 2023.
  30. Accurate ball tracking in volleyball actions to support referees. Opto-Electronics Review, 26(4):296–306, Dec. 2018.
  31. SoccerNet-Depth: a scalable dataset for monocular depth estimation in sports videos. In IEEE Int. Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), CVsports, Seattle, WA, USA, Jun. 2024.
  32. Soccer field registration based on geometric constraint and deep learning method. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV), volume 13020 of Lect. Notes Comput. Sci., pages 287–298, Beijing, China, 2021. Springer Int. Publ.
  33. Single view camera calibration for augmented virtual environments. In IEEE Virtual Reality Conference, pages 255–258, Charlotte, NC, 2007. Inst. Electr. Electron. Eng. (IEEE).
  34. A combined physical and mathematical calibration method for low-cost cameras in the air and underwater environment. Sensors, 23(4):1–18, Feb. 2023.
  35. Individual locating of soccer players from a single moving view. Sensors, 23(18):1–28, Sept. 2023.
  36. A robust and efficient framework for sports-field registration. In IEEE Winter Conf. Appl. Comput. Vis. (WACV), pages 1935–1943, Waikoloa, HI, USA, Jan. 2021. Inst. Electr. Electron. Eng. (IEEE).
  37. I see you: A vehicle-pedestrian interaction dataset from traffic surveillance cameras. CoRR, abs/2211.09342, 2022.
  38. Soccer on your tabletop. In IEEE Int. Conf. Comput. Vis. Pattern Recognit. (CVPR), pages 4738–4747, Salt Lake City, UT, USA, Jun. 2018.
  39. Dynamic camera calibration of roadside traffic management cameras for vehicle speed estimation. IEEE Trans. Intell. Transp. Syst., 4(2):90–98, Jun. 2003.
  40. End-to-end camera calibration for broadcast videos. In IEEE Int. Conf. Comput. Vis. Pattern Recognit. (CVPR), pages 13627–13636, Seattle, WA, USA, Jun. 2020. Inst. Electr. Electron. Eng. (IEEE).
  41. Automated top view registration of broadcast football videos. In IEEE Winter Conf. Appl. Comput. Vis. (WACV), pages 305–313, Lake Tahoe, NV, USA, Mar. 2018. Inst. Electr. Electron. Eng. (IEEE).
  42. Self-supervised shape alignment for sports field registration. In IEEE Winter Conf. Appl. Comput. Vis. (WACV), pages 3768–3777, Waikoloa, HI, USA, Jan. 2022. Inst. Electr. Electron. Eng. (IEEE).
  43. Mark Shortis. Camera calibration techniques for accurate measurement underwater. In 3D Recording and Interpretation for Maritime Archaeology, volume 31 of Coast. Res. Libr., pages 11–27. Springer Int. Publ., London, Engl., 2019.
  44. A camera calibration method based on scene and human semantics. In Youth Acad. Annu. Conf. Chin. Assoc. Autom. (YAC), pages 216–221, Beijing, China, Nov. 2022. Inst. Electr. Electron. Eng. (IEEE).
  45. SoccerNet game state reconstruction: End-to-end athlete tracking and identification on a minimap. In IEEE Int. Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), CVsports, Seattle, WA, USA, Jun. 2024.
  46. Richard Szeliski. Computer Vision: Algorithms and Applications. Springer, second edition, 2022.
  47. Novel optimization approach for camera calibration in traffic scenes. Transp. Res. Rec.: J. Transp. Res. Board, 2677(3):1048–1066, Sept. 2022.
  48. TVCalib: Camera calibration for sports field registration in soccer. In IEEE/CVF Winter Conf. Appl. Comput. Vis. (WACV), pages 1166–1175, Waikoloa, HI, USA, Jan. 2023. Inst. Electr. Electron. Eng. (IEEE).
  49. Sports camera calibration using flexible intersection selection and refinement. ITE Trans. Media Technol. Appl., 9(1):95–104, 2021.
  50. 3D ball localization from a single calibrated image. In IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Work. (CVPRW), pages 3471–3479, New Orleans, LA, USA, Jun. 2022. Inst. Electr. Electron. Eng. (IEEE).
  51. DeepSportradar-v1: Computer vision dataset for sports understanding with high quality annotations. In Int. ACM Work. Multimedia Content Anal. Sports (MMSports), pages 1–8, Lisbon, Port., Oct. 2022. ACM.
  52. Puck localization and multi-task event recognition in broadcast hockey videos. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4567–4575, 2021.
  53. Multi-camera 3D ball tracking framework for sports video. IET Image Process., 14(15):3751–3761, Dec. 2020.
  54. Wide-baseline multi-camera calibration using person re-identification. CoRR, abs/2104.08568, 2021.
  55. A fast and effective framework for camera calibration in sport videos. In IEEE Int. Conf. Vis. Commun. Image Process. (VCIP), pages 1–5, Suzhou, China, Dec. 2022. Inst. Electr. Electron. Eng. (IEEE).
  56. Vehicle localisation and deep model for automatic calibration of monocular camera in expressway scenes. IET Intell. Transp. Syst., 16(4):459–473, Dec. 2021.
Citations (9)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now