Enhanced Basketball Target Tracking in Panoramic Vision Systems via Advanced YOLO and Camshift Algorithm Integration

Jiaojiao Lu

Abstract


The panoramic vision basketball robot can not only provide a 360° panoramic view, but also obtain real-time position and distance information of the basketball. To improve the target tracking performance of panoramic vision basketball robots, a target detection algorithm is first designed as the basis for subsequent robot target tracking. In object detection, the You Only Look Once version 8 is adopted. A bidirectional feature pyramid network and an improved cross stage partial 2-fusion are introduced for optimization. Based on the improved MeanShift algorithm, namely the continuous adaptive mean shift algorithm, target tracking is achieved. Subsequently, the research introduces Kalman filtering algorithm, target template update judgment, and fused features to optimize the target tracking algorithm. In terms of evaluation indicators, the study selects precision, recall, time consumption, central error, missed detection rate, and false detection rate, and conducted practical application tests. The precision, recall, and time consumption were 98.67%, 97.65%, and 54.21ms, respectively. Under obstructions, lighting changes, and background interference, the precision of the tracking algorithm was 95.67%, 96.47%, and 95.26%, respectively. The maximum central errors were 24 pixels, 21 pixels, and 22 pixels, respectively. The designed object detection and tracking algorithm has good performance and can provide solid technical support for the application of panoramic vision basketball robots in actual competitions.


Full Text:

PDF

References


M. G. Majeed, W. Hameed, N. H. Haroon, S. R. Abdul Kadeem, H. M. Salman, and S. Kadry. “Optimizing Resource Management in Physical Education through Intelligent 5G-Enabled Robotic Systems,” Fusion: Pract. Appl., vol. 13, no. 1, pp. 162-174, May, 2023, DOI: 10.54216/FPA.130113.

L. Xu. “Application analysis of sports robots based on pose recognition and action feature analysis,” Int. J. Syst. Assurance Eng. Manag., vol. 14, no. 2, pp. 519-528, April, 2023, DOI: 10.1007/s13198-021-01245-1.

M. M. Sadr, T. Saheb, and A. Farahani. “A Mapping and Visualization of the Role of Artificial Intelligence in Sport Industry,” Res. Sport Manag. Mark., vol. 5, no. 1, pp. 44-56, January, 2023, DOI: 10.22098/rsmm.2023.13064.1241.

W. Chen and X. Huang. “RETRACTED ARTICLE: Research on reliability of sports intelligent training system based on hybrid wolf pack algorithm and IoT,” Soft Comput., vol. 27, no. 14, pp. 10189-10197, April, 2023, DOI: 10.1007/s00500-023-08247-0.

M. A. Arif, A. Zhu, H. Mao, and Y. Tu. “Panoramic visual system for spherical mobile robots,” Robotica, vol. 42, no. 7, pp. 2089-2107, February, 2024, DOI: 10.1017/S0263574724000043.

C. Zha, S. Luo, and X. Xu. “Infrared multi-target detection and tracking in dense urban traffic scenes,” IET Image Process., vol. 18, no. 6, pp. 1613-1628, February, 2024, DOI: 10.1049/ipr2.13053.

M. Zhai, H. Zhang, L. Wang, D. Xiao, Z. Gu, and Z. Li. “Special Vehicle Target Detection and Tracking Based on Virtual Simulation Environment and YOLOv5-Block+ DeepSort Algorithm,” Comput. Mater. Continua, vol. 81, no. 2, pp. 3241-3260, April, 2024, DOI: 10.32604/cmc.2024.056241.

Y. Wu, H. Deng, H. Liu, X. Zhao, and Y. Fang. “NKhex: A New Miniature Hexapod Crawling Robot with Visual Perception and Target Tracking,” IEEE Trans. Ind. Electron., vol. 72, no. 1, pp. 693-702, January, 2025, DOI: 10.1109/TIE.2024.3409901.

M. Alymani, M. E. Karar, and H. I. Shehata. “A Practical Study of Intelligent Image-Based Mobile Robot for Tracking Colored Objects,” Comput. Mater. Continua, vol. 80, no. 8, pp. 2181-2197, August, 2024, DOI: 10.32604/cmc.2024.052406.

S. Kong, J. Sun, A. Luo, W. Chi, C. Zhang, S. Zhang, and J.Yu. “A Collision-Free Target Tracking Controller with Uncertain Disturbance Rejection for Quadruped Robots,” IEEE Trans. Intell. Vehicles, vol. 9, no. 1, pp. 670-680, January, 2024, DOI: 10.1109/TIV.2023.3296669.

S. L. Dai, J. Liang, K. Lu, and X. Jin. “Adaptive image-based moving-target tracking control of wheeled mobile robots with visibility maintenance and obstacle avoidance,” IEEE Trans. Control Syst. Technol., vol. 32, no. 2, pp. 488-501, March, 2024, DOI: 10.1109/TCST.2023.3331553.

J. Yan, J. Lin, X. Yang, C. Chen, and X. Guan. “Cooperation detection and tracking of underwater target via Aerial-Surface-Underwater vehicles,” IEEE Trans. Autom. Control, vol. 70, no. 2, pp. 1068-1083, February, 2025, DOI: 10.1109/TAC.2024.3447976.

Y. Liu, B. An, S. Chen, and D. Zhao. “Multi-target detection and tracking of shallow marine organisms based on improved YOLO v5 and DeepSORT,” IET Image Process., vol. 18, no. 9, pp. 2273-2290, April, 2024, DOI: 10.1049/ipr2.13090.

S. Pal, A. Roy, P. Shivakumara, and U. Pal. “Adapting a Swin Transformer for License Plate Number and Text Detection in Drone Images,” Artif. Intell. Appl., vol. 1, no. 3, pp. 145-154, April, 2023, DOI: 10.47852/bonviewAIA3202549.

S. Li, M. Wang, Y. Zhou, Q. Su, L. Liu, and T. Wu. “IG-YOLOv8: Insulator Guardian Based on YOLO for Insulator Fault Detection,” IEEJ Trans. Electr. Electron. Eng., vol. 20, no. 4, pp. 537-547, November, 2025, DOI: 10.1002/tee.24221.

H. Zhang, G. Li, D. Wan, Z. Wang, J. Dong, S. Lin, and H. Liu. “DS-YOLO: A dense small object detection algorithm based on inverted bottleneck and multi-scale fusion network,” Biomimetic Intelligence and Robotics, vol. 4, no. 4, pp. 64-75, December, 2024, DOI: 10.1016/j.birob.2024.100190.

Q. Zhang, C. Wang, H. Li, S. Shen, W. Cao, X. Li, and D. Wang. “Improved YOLOv8-CR Network for Detecting Defects of the Automotive MEMS Pressure Sensors,” IEEE Sens. J., vol. 24, no. 16, pp. 26935-26945, August, 2024, DOI: 10.1109/JSEN.2024.3419806.

P. I. Jun, N. Hou, and G. Zhi. “Lightweight human pose estimation algorithm by integrating CA and BiFPN,” J. Graphics, vol. 44, no. 5, pp. 868-878, December, 2023, DOI: 10.11996/JG.j.2095-302X.2023050868.

S. Liu, Y. Yang, T. Cao, and Y. Zhu. “A BiFPN-SECA detection network for foreign objects on top of railway freight vehicles,” Signal, Image and Video Processing, vol. 18, no. 12, pp. 9027-9035, September, 2024, DOI: 10.1007/s11760-024-03527-0.

P. Yu, Y. Lin, Y. Lai, S. Cheng, and P. Lin. “Dense log end face detection method using the hybrid of BiFPN and YOLOv5s,” J. Forestry Eng., vol. 8, no. 1, pp. 126-134, November, 2023, DOI: 10.13360/j.issn.2096-1359.202204006.

D. Y. Bernanda, D. N. A. Jawawi, S. Abd Halim, and F. Adikara. “Natural Language Processing for Requirement Elicitation in University Using Kmeans and Meanshift Algorithm,” Baghdad Science Journal, vol. 21, no. 2, pp. 561-567, May, 2024, DOI: 10.21123/bsj.2024.9675.

Y. Zhang and Y. C. Chen. “Linear convergence of the subspace constrained mean shift algorithm: from Euclidean to directional data,” Inf. Inference: A Journal of the IMA, vol. 12, no. 1, pp. 210-311, June, 2023, DOI: 10.1093/imaiai/iaac005.

S. Devaraj and B. Sridharan. “Deep Perona-Malik Diffusive Mean Shift Image Classification for Early Glaucoma and Stargardt Disease Detection,” Malaysian J. Comput. Sci., vol. 36, no. 1, pp. 14-39, January, 2023, DOI: 10.22452/mjcs.vol36no1.2.

D. Xiong, and F. Xu. “A robust diagnostic approach in mean shifts for multivariate statistical process control,” J. Stat. Comput. Simulation, vol. 95, no. 3, pp. 507-524, November, 2025, DOI: 10.1080/00949655.2024.2431856.

J. Wang, Z. Jia, H. Lai, and F. Shi. “A real time target face tracking algorithm based on saliency detection and Camshift,” MULTIMED TOOLS APPL., vol. 82, no. 28, pp. 43599-43624, April, 2023, DOI: 10.1007/s11042-023-14889-x.

L. S. K. Vatsavai, and K. S. V. Mantena. “Camshift Algorithm with GOA-Neural Network for Drone Object Tracking,” ISI., vol. 28, no. 2, pp. 491-498, April, 2023, DOI: 10.18280/isi.280226.

P. D. Barua, T. Keles, M. Kuluozturk, M. A. Kobat, S. Dogan, M. Baygin, and U. R. Acharya. “Automated asthma detection in a 1326-subject cohort using a one-dimensional attractive-and-repulsive center-symmetric local binary pattern technique with cough sounds,” Neural Comput. Appl., vol. 36, no. 27, pp. 16857-16871, June, 2024, DOI: 10.1007/s00521-024-09895-5.

J. C. Sekhar, P. J. Josephson, A. Chinnasamy, M. Maheswari, S. Sankar, and R. R. Kalangi. “Automated face recognition using deep learning technique and center symmetric multivariant local binary pattern,” Neural Comput. Appl., vol. 37, no. 1, pp. 263-281, November, 2025, DOI: 10.1007/s00521-024-10447-0.

C. Zhiyuan, Z. Zhichao, and S. U. I. Qingyang. “Online identification of key parameters of secondary edges in underwater WPT system based on unscented Kalman filtering algorithm,” Proc. CSEE, vol. 44, no. 11, pp. 4470-4479, May, 2024, DOI: 10.13334/j.0258-8013.pcsee.230708.

C. Zhu, S. Wang, C. Yu, H. Zhou, and C. Fernandez. “An improved proportional control forgetting factor recursive least square-Monte Carlo adaptive extended Kalman filtering algorithm for high-precision state-of-charge estimation of lithium-ion batteries,” J. Solid State Electrochem., vol. 27, no. 9, pp. 2277-2287, May, 2023, DOI: 10.1007/s10008-023-05514-w.

Z. Li, S. Fu, L. Xu, M. Bo, Z. Xin, and J. Qing. “Research on gangue target detection algorithm based on MBI-YOLOv8,” J. Graphics., vol. 45, no. 6, pp. 1301-1312, May, 2024, DOI: 10.11996/JG.j.2095-302X.2024061301.

H. M. N. Fiyad, H. M. B. Metwally, M. A. El-Hameed, and M. A. H. Abozied. “Improved Real Time Target Tracking System Based on Cam-Shift and Kalman Filtering Techniques,” J. Appl. Res. Technol., vol. 21, no. 2, pp. 297-308, June, 2023, DOI: 10.22201/icat.24486736E.2023.21.2.1565.




DOI: https://doi.org/10.31449/inf.v49i23.9880

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.