Basketball Player Target Trackingbased on Improved YOLOv5 and Multi Feature Fusion

• Autorzy: Sun Jinjun , Liu Ronghua

Identyfikatory

DOI

10.22630/MGV.2025.34.1.1

• Języki publikacji: EN

Abstrakty

EN

Multi-target tracking has important applications in many fields including logistics and transportation, security systems and assisted driving. With the development of science and technology, multi-target tracking has also become a research hotspot in the field of sports. In this study, a multi-attention module is added to compute the target feature information of different dimensions for the leakage problem of the traditional fifth-generation single-view detection algorithm. The study adopts two-stage target detection method to speed up the detection rate, and at the same time, recursive filtering is utilized to predict the position of the athlete in the next frame of the video. The results indicated that the improved fifth generation monovision detection algorithm possessed better results for target tracking of basketball players. The running time was reduced by 21.26% compared with the traditional fifth-generation monovision detection algorithm, and the average number of images that could be processed per second was 49. The accuracy rate was as high as 98.65%, and the average homing rate was 97.21%.During the tracking process of 60 frames of basketball sports video, the computational delay was always maintained within 40 ms. It can be demonstrated that by deeply optimizing the detection algorithm, the ability to identify and locate basketball players can be significantly improved, which provides a solid data support for the analysis of players’ behaviors and tactical layout in basketball games.

Słowa kluczowe

EN

YOLOv5; object detection; action characteristics; recursive filtering; Mahalanobis distance; Hungarian algorithm

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2025
• Tom: Vol. 34, No. 1
• Strony: 3--24
• Opis fizyczny: Bibliogr. 34 poz., il., rys., tab., wykr.

Twórcy

autor

Sun Jinjun

• Department of Safety and Security, Zhejiang Posts and Telecom College, Shaoxing, China

• https://orcid.org/0009-0008-2622-7517

autor

Liu Ronghua

• Department of Fundamental Discipline, Department of Physical Education, Shanghai University of Finance and Economics, Zhejiang College, Jinhua, China

• https://orcid.org/0009-0002-8044-0067

Bibliografia

• [1] G. Bharathi and G. Anandharaj. A conceptual real-time deep learning approach for object detection, tracking and monitoring social distance using Yolov5. Indian Journal of Science and Technology, 15(47):2628-2638, 2022. doi:10.17485/IJST/v15i47.1880.
• [2] Y. Cui, C. Zeng, X. Zhao, Y. Yang, G. Wu, et al. SportsMOT: A large multi-object tracking dataset in multiple sports scenes. In: 2023 IEEE/CVF International Conference on Computer Vision(ICCV), pp. 9887-9897. IEEE Computer Society, 2023. doi:10.1109/ICCV51070.2023.00910.
• [3] Y. Cui, C. Zeng, X. Zhao, Y. Yang, G. Wu, et al. Sportsmot. GitHub, 2024. https://github.com/MCG-NJU/SportsMOT.
• [4] P. T. Esteves, J. Arede, B. Travassos, and M. Dicks. Gaze and shoot: Examining the effects of player height and attacker-defender interpersonal distances on gaze behavior and shooting accuracy of elite basketball players. Revista de Psicología del Deporte, 30(3):1-8, 2021. https://rpd-online.com/article-view/?id=466.
• [5] T. Facchinetti, R. Metulini, and P. Zuccolotto. Filtering active moments in basketball gamesusing data from players tracking systems. Annals of Operations Research, 325:521-538, 2023.doi:10.1007/s10479-021-04391-8.
• [6] R. Girshick, I. Radosavovic, G. Gkioxari, P. Dollár, and K. He. Detectron. GitHub, 2018. https://github.com/facebookresearch/detectron.
• [7] C. Guo, M. Cai, N. Ying, H. Chen, J. Zhang, et al. ANMS: Attention-based non-maximum suppression. Multimedia Tools and Applications, 81(8):11205-11219, 2022. doi:10.1007/s11042-022-12142-5.
• [8] M.-H. Guo, T.-X. Xu, J.-J. Liu, Z.-N. Liu, P.-T. Jiang, et al. Attention mechanisms in computervision: A survey. Computational Visual Media, 8(3):331-368, 2022. doi:10.1007/s41095-022-0271-y.
• [9] Z. Hao, X. Wang, and S. Zheng. Recognition of basketball players’ action detection based on visual image and Harris corner extraction algorithm. Journal of Intelligent and Fuzzy Systems,40(4):7589-7599, 2021. doi:10.3233/JIFS-189579.
• [10] M. Hasanvand, M. Nooshyar, Moharamkhani, and A. Selyari. Machine learning methodology for identifying vehicles using image processing. Artificial Intel ligence and Applications, 1(3):170-178,2023. doi:10.47852/bonviewAIA3202833.
• [11] L. He, J. C. W. Chan, and Z. Wang. Automatic depression recognition using CNN with attention mechanism from videos. Neurocomputing, 422(1):165-175, 2021. doi:10.1016/j.neucom.2020.10.015.
• [12] Y. Ji, Z. Kang, and C. Zhang. Two-stage gradient-based recursive estimation for nonlinear models by using the data filtering. International Journal of Control, Automation, and Systems, 19(8):2706-2715, 2021. doi:10.1007/s12555-019-1060-y.
• [13] M. Jin, H. Li, and Z. Xia. Hybrid attention network and center-guided non-maximum suppression for occluded face detection. Multimedia Tools and Applications, 82(10):15143-15170, 2023. doi:10.1007/s11042-022-13999-2.
• [14] Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou. A survey of convolutional neural networks: Analysis, applications, and prospects. IEEE Transactions on Neural Networks and Learning Systems,33(12):6999-7019, 2021. doi:10.1109/TNNLS.2021.3084827.
• [15] Y. Liu, L. Geng, W. Zhang, and Y. Gong. Survey of video-based small target detection. Journal of Image and Graphics, 9(4):122-134, 2021. doi:10.18178/joig.9.4.122-134.
• [16] Y. Ma, N. Li, Zhang, S. Wang, and H. Ma. Image encryption scheme based on alternate quantum walks and discrete cosine transform. Optics Express, 29(18):28338-28351, 2021.doi:10.1364/OE.431945.
• [17] J. Mao, Y. Sun, X. Yi, H. Liu, and D. Ding. Recursive filtering of networked nonlinear systems: a survey. International Journal of Systems Science, 52(6):1110-1128, 2021. doi:10.1080/00207721.2020.1868615.
• [18] Z. Niu, G. Zhong, and H. Yu. A review on the attention mechanism of deep learning. Neurocomputing, 452(1):48-62, 2021. doi:10.1016/j.neucom.2021.03.091.
• [19] J. Ren and Y. Wang. Overview of object detection algorithms using convolutional neural networks. Journal of Computer Communications, 10(1):115-132, 2022. doi:10.4236/jcc.2022.101006. https://www.scirp.org/journal/paperinformation?paperid=115011.
• [20] A. Rizaldy, P. Ghamisi, and R. Gloaguen. Channel attention module for segmentation of 3d hyperspectral point clouds in geological applications. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 48:103-109, 2024. doi:10.5194/isprs-archives-XLVIII-2-W11-2024-103-2024.
• [21] H. Song, X. Zhang, J. Song, and J. Zhao. Detection and tracking of safety helmet based on DeepSortand YOLOv5. Multimedia Tools and Applications, 82(7):10781-10794, 2023. doi:10.1007/s11042-022-13305-0.
• [22] R. Sun, J. Kuang, Y. Ding, J. Long, Y. Hu, et al. High-efficiency differential single-pixel imaging based on discrete cosine transform. IEEE Photonics Technology Letters, 35(17):955-958, 2023. doi:10.1109/LPT.2023.3286105.
• [23] H. Tan, B. Shen, and H. Shu. Robust recursive filtering for stochastic systems with time-correlated fading channels. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52(5):3102-3112,2021. doi:10.1109/TSMC.2021.3062848.
• [24] Z. Terner and A. Franks. Modeling player and team performance in basketball. Annual Review of Statistics and Its Applications, 8(1):1-23, 2021. doi:10.1146/annurev-statistics-040720-015536.
• [25] T. Wang and C. Shi. Basketball motion video target tracking algorithm based on improved gray neural network. Neural Computing and Applications, 35(6):4267-4282, 2023. doi:10.1007/s00521-022-07026-6.
• [26] W. Wang, S. Wang, Y. Li, and Y. Jin. Adaptive multi-scale dual attention network for semantic segmentation. Neurocomputing, 460(1):39-49, 2021. doi:10.1016/j.neucom.2021.06.068.
• [27] Y. Wu, D. Deng, X. Xie, M. He, J. Xu, et al. Obtracker: Visual analytics of off-ball movement in basketball. IEEE Transactions on Visualization and Computer Graphics, 29(1):929-939, 2022. doi:10.1109/TVCG.2022.3209373.
• [28] Y. Wu, A. Kirillov, F. Massa, W.-Y. Lo, and R. Girshick. Detectron2. GitHub, 2019. https://github.com/facebookresearch/detectron2.
• [29] J. Xu, B. Ai, W. Chen, A. Yang, P. Sun, et al. Wireless image transmission using deep source channel coding with attention modules. IEEE Transactions on Circuits and Systems for Video Technology, 32(4):2315-2328, 2021. doi:10.1109/TCSVT.2021.3082521.
• [30] X. Yang, Y. Luo, M. Li, Z. Yang, C. Sun, et al. Recognizing pests in field-based images by combining spatial and channel attention mechanism. IEEE Access, 9(1):162448-162458, 2021. doi:10.1109/ACCESS.2021.3132486.
• [31] M. C. Yesilli, J. Chen, F. A. Khasawneh, and Y. Guo. Automated surface texture analysis via discrete cosine transform and discrete wavelet transform. Precision Engineering, 77(1):141-152,2022. doi:10.1016/j.precisioneng.2022.05.006.
• [32] W. Zhan, C. Sun, M. Wang, J. She, Y. Zhang, et al. An improved Yolov5 real-time detection method for small objects captured by UAV. Soft Computing, 26(1):361-373, 2022. doi:10.1007/s00500-021-06407-8.
• [33] G. Zhaoxin, L. Han, Z. Zhijiang, and P. Libo. Design a robot system for tomato picking based on yolo v5. IFAC-PapersOnLine, 55(3):166-171, 2022. doi:10.1016/j.ifacol.2022.05.029.
• [34] X. Zhu, K. Guo, S. Ren, B. Hu, M. Hu, et al. Lightweight image super-resolution with expectation-maximization attention mechanism. IEEE Transactions on Circuits and Systems for Video Technology, 32(3):1273-1284, 2022. doi:10.1109/TCSVT.2021.3078436.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).