EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Table Tennis Track Detection Based on Temporal Feature Multiplexing Network

Wenjie Li, Xiangpeng Liu, Kang An, Chengjin Qin iD, Yuhua Cheng

Sensors · 03.02.2023 · 23 (3) · 1726

DOI: 10.3390/s23031726 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.02.2023. Verfasst von Wenjie Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, China. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Normal University, The Natural Science Foundation of Shanghai, The National Innovation and Entrepreneurship Training Program for College Students.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recording the trajectory of table tennis balls in real-time enables the analysis of the opponent’s attacking characteristics and weaknesses. The current analysis of the ball paths mainly relied on human viewing, which lacked certain theoretical data support. In order to solve the problem of the lack of objective data analysis in the research of table tennis competition, a target detection algorithm-based table tennis trajectory extraction network was proposed to record the trajectory of the table tennis movement in video. The network improved the feature reuse rate in order to achieve a lightweight network and enhance the detection accuracy. The core of the network was the “feature store & return” module, which could store the output of the current network layer and pass the features to the input of the network layer at the next moment to achieve efficient reuse of the features. In this module, the Transformer model was used to secondarily process the features, build the global association information, and enhance the feature richness of the feature map. According to the designed experiments, the detection accuracy of the network was 96.8% for table tennis and 89.1% for target localization. Moreover, the parameter size of the model was only 7.68 MB, and the detection frame rate could reach 634.19 FPS using the hardware for the tests. In summary, the network designed in this paper has the characteristics of both lightweight and high precision in table tennis detection, and the performance of the proposed model significantly outperforms that of the existing models.

Schlagwörter

Stichwörter der Autor:innen

Transformer modeldeep learningfeature reuselightweight networkmotion trajectoryobject detection

Autor:innen und Institutionen

  • College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, China.
  • School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
  • Shanghai Research Institute of Microelectronics, Peking University, Shanghai 201203, China.

ORCID-Profile: Chengjin Qin

Förderung

  • Shanghai Normal University
  • The Natural Science Foundation of Shanghai
  • The National Innovation and Entrepreneurship Training Program for College Students

Zitieren

APA

Li, W., Liu, X., An, K., Qin, C., & Cheng, Y. (2023). Table Tennis Track Detection Based on Temporal Feature Multiplexing Network. Sensors, 23(3), 1726. https://doi.org/10.3390/s23031726

Vancouver

Li W, Liu X, An K, Qin C, Cheng Y. Table Tennis Track Detection Based on Temporal Feature Multiplexing Network. Sensors. 2023;23(3):1726. doi:10.3390/s23031726

BibTeX
@article{Li2023,
  author = {Li, Wenjie and Liu, Xiangpeng and An, Kang and Qin, Chengjin and Cheng, Yuhua},
  title = {Table Tennis Track Detection Based on Temporal Feature Multiplexing Network},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {3},
  pages = {1726},
  doi = {10.3390/s23031726}
}
Kostenlos starten →