Open Dataset Recorded by Single Cameras for Multi-Player Tracking in Soccer Scenarios
Source abstract
Abstract
Multi-player action recognition for automatic analysis in sports is the subject of increasing attention. Trajectory-tracking technology is key for accurate recognition, but little research has focused on this aspect, especially for non-professional matches. Here, we study multi-player tracking in the most popular and complex sport among non-professionals—soccer. In this non-professional soccer player tracking (NPSPT) challenge, single-view-based motion recording systems for continuous data collection were installed in several soccer fields, and a new benchmark dataset was collected. The dataset consists of 17 2-min long super-high-resolution videos with diverse game types consistently labeled across time, covering almost all possible situations for multi-player detection and tracking in real games. A comprehensive evaluation was conducted on the state-of-the-art multi-object-Tracking (MOT) systems, revealing insights into player tracking in real games. Our challenge introduces a new dimension for researchers in the player recognition field and will be beneficial to further studies.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Analysis and Summarization · Human Pose and Action Recognition · Advanced Optical Sensing Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
National Engineering Research Center for Optical Instruments, Centre for Optical and Electromagnetic Research, Zhejiang University, Hangzhou 310058, China
Hangzhou Zhuxing Information Technology Co., Ltd., Hangzhou 311100, China
Department of Sports Science, Zhejiang University, Hangzhou 310058, China
Department of Public Physical and Art Education, Zhejiang University, Hangzhou 310058, China
Funding
Key Projects of Major Humanities and Social Sciences of Zhejiang’s Universities · The National Natural Science Foundation of China
References (49)
Show source-provided references
1. Soccer analytics unravelling the complexity of “the beautiful game”10.1111/j.1740-9713.2018.01146.x ↗
2. Fernandez, J., and Bornn, L. (2018). Wide open spaces: A statistical technique for measuring space creation in professional soccer. Sloan Sport. Anal. Conf., 2018.
3. Space evaluation in football games via field weighting based on tracking data10.1038/s41598-021-84939-7 ↗
4. Forvizor: Visualizing spatio-temporal team formations in soccer10.1109/TVCG.2018.2865041 ↗
5. Wei, X., Sha, L., Lucey, P., Morgan, S., and Sridharan, S. (2013, January 26–28). Large-scale analysis of formations in soccer. Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Hobart, Australia.10.1109/DICTA.2013.6691503 ↗
6. FIFA (2022, June 15). Handbook of Test Methods for Wearable Epts Devices. Technical Report, Fédération Internationale de Football Association, 2020. Available online: https://digitalhub.fifa.com/m/194e24782f329d14/original/test-manual-epts-wearables-v20.pdf.
7. A public data set of spatio-temporal match events in soccer competitions10.1038/s41597-019-0247-7 ↗
8. Multiple object tracking: A literature review10.1016/j.artint.2020.103448 ↗
9. Dendorfer, P., Rezatofighi, H., Milan, A., Shi, J., Cremers, D., Reid, I., Roth, S., Schindler, K., and Leal-Taixé, L. (2020). Mot20: A benchmark for multi object tracking in crowded scenes. arXiv.
10. Milan, A., Leal-Taixé, L., Reid, I., Roth, S., and Schindler, K. (2016). Mot16: A benchmark for multi-object tracking. arXiv.
11. Ua-detrac: A new benchmark and protocol for multi-object detection and tracking10.1016/j.cviu.2020.102907 ↗
12. Vats, K., Walters, P., Fani, M., Clausi, D.A., and Zelek, J. (2021). Player tracking and identification in ice hockey. arXiv.
13. Deliege, A., Cioppa, A., Giancola, S., Seikavandi, M.J., Dueholm, J.V., Nasrollahi, K., Ghanem, B., Moeslund, T.B., and Droogenbroeck, M.V. (2021, January 20–25). Soccernet-v2: A dataset and benchmarks for holistic understanding of broadcast soccer videos. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPRW53098.2021.00508 ↗
14. Multi-camera multi-player tracking with deep player identification in sports video10.1016/j.patcog.2020.107260 ↗
15. Multiple player tracking in basketball court videos10.1007/s11554-020-00968-x ↗
16. Skill and chance in association football10.2307/2343726 ↗
17. Big data and tactical analysis in elite soccer: Future challenges and opportunities for sports science10.1186/s40064-016-3108-2 ↗
18. Global positioning system data analysis: Velocity ranges and a new definition of sprinting for field sport athletes10.1519/JSC.0b013e3182276555 ↗
19. Silva, V.D., Caine, M., Skinner, J., Dogan, S., Kondoz, A., Peter, T., Axtell, E., BiRnIe, M., and Smith, B. (2018). Player tracking data analytics as a tool for physical performance management in football: A case study from chelsea football club academy. Sports, 6.10.3390/sports6040130 ↗
20. Playerank: Data-driven performance evaluation and player ranking in soccer via a machine learning approach10.1145/3343172 ↗
21. FIFA (2022, June 15). Fifa Quality Programme for Electronic Performance Tracking Systems(epts). Technical Report, Fédération Internationale de Football Association. Available online: https://digitalhub.fifa.com/m/46ee2f5a70b330b3/original/how-to-obtain-epts-certification.pdf.
22. Tactical demands of small-sided games in football: Influence of tracking technology
23. A survey on player tracking in soccer videos10.1016/j.cviu.2017.02.002 ↗
24. Leal-Taixé, L., Milan, A., Reid, I., Roth, S., and Schindler, K. (2015). Motchallenge 2015: Towards a benchmark for multi-target tracking. arXiv.
25. Tezcan, O., Duan, Z., Cokbas, M., Ishwar, P., and Konrad, J. (2022, January 4–8). Wepdtof: A dataset and benchmark algorithms for in-the-wild people detection and tracking from overhead fisheye cameras. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.10.1109/WACV51458.2022.00145 ↗
26. Multi-target tracking using cnn-based features: Cnnmtt10.1007/s11042-018-6467-6 ↗
27. Wojke, N., Bewley, A., and Paulus, D. (2017, January 17–20). Simple online and realtime tracking with a deep association metric. Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China.10.1109/ICIP.2017.8296962 ↗
28. Yu, F., Li, W., Li, Q., Liu, Y., Shi, X., and Yan, J. (2016, January 11–14). Poi: Multiple object tracking with high performance detection and appearance feature. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-48881-3_3 ↗
29. Bochkovskiy, A., Wang, C.-H., and Liao, H.-M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv.
30. Lin, T.-S., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
31. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst., 28.
32. Welch, G., and Bishop, G. (2022, June 15). An Introduction to the Kalman Filter. Technical Report, 1995. Available online: https://perso.crans.org/club-krobot/doc/kalman.pdf.
33. The hungarian method for the assignment problem10.1002/nav.3800020109 ↗
34. Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition10.1109/TPAMI.2017.2781233 ↗
35. Multi-task learning as multi-objective optimization
36. Voigtlaender, P., Krause, M., Osep, A., Luiten, J., Sekar, B.B.G., Geiger, A., and Leibe, B. (2019, January 27–28). Mots: Multi-object tracking and segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seoul, Korea.10.1109/CVPR.2019.00813 ↗
37. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.322 ↗
38. Wang, Z., Zheng, L., Liu, Y., Li, Y., and Wang, S. (2020, January 23–28). Towards real-time multi-object tracking. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58621-8_7 ↗
39. Fairmot: On the fairness of detection and re-identification in multiple object tracking10.1007/s11263-021-01513-4 ↗
40. Zhang, Z., Cheng, D., Zhu, X., Lin, S., and Dai, J. (2018). Integrated object detection and tracking with tracklet-conditioned detection. arXiv.
41. Bergmann, P., Meinhardt, T., and Leal-Taixe, L. (2019, January 27–28). Tracking without bells and whistles. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea.10.1109/ICCV.2019.00103 ↗
42. Zhou, X., Koltun, V., and Krähenbühl, P. (2020, January 23–28). Tracking objects as points. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58548-8_28 ↗
43. Meinhardt, T., Kirillov, A., Leal-Taixe, L., and Feichtenhofer, C. (2022, January 19–23). Trackformer: Multi-object tracking with transformers. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00864 ↗
44. Zhu, X., Su, W., Lu, L., Li, B., Wang, X., and Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection. arXiv.
45. Sun, P., Cao, J., Jiang, Y., Zhang, R., Xie, E., Yuan, Z., Wang, C., and Luo, P. (2020). Transtrack: Multiple object tracking with transformer. arXiv.
46. Xu, Y., Ban, Y., Delorme, G., Gan, C., Rus, D., and Alameda-Pineda, X. (2021). Transcenter: Transformers with dense queries for multiple-object tracking. arXiv.
47. Breast tumor segmentation and shape classification in mammograms using generative adversarial and convolutional neural network10.1016/j.eswa.2019.112855 ↗
48. A flexible new technique for camera calibration10.1109/34.888718 ↗
49. Hota: A higher order metric for evaluating multi-object tracking10.1007/s11263-020-01375-2 ↗