Skip to main content

Advertisement

Springer Nature Link
Log in

Sports video athlete detection based on deep learning

  • S.I.: Artificial Intelligence Technologies in Sports and Art Data Applications
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The deep fusion of sports and machine vision has become a research hot spot in sports video target detection, athlete state recovery and sports promotion. On the basis of in-depth study, it can detect a large number of sports videos, complete the drawing and analysis of human body detection model, and detect and evaluate the posture of corresponding athletes in the video, which can save a lot of costs and maximize the more professional training of athletes. In order to solve the above problems, this paper innovatively completes the automatic language description of sports video based on time-sharing memory algorithm. Its principle is to realize the accurate decomposition of athletes' sports data through the mapping relationship between the corresponding letter sequence and video sequence in time-sharing memory. In order to capture the key posture of athletes' sports video, this paper innovatively proposes an object extraction algorithm based on athletes' skeleton motion enhancement. In practical application, based on the key pose capture, it is necessary to train the depth selection network in time to extract the key pose of the skeleton. Based on this network, it can enhance the key posture of bone information and accurately express its related features. After extracting the actual athlete's bone information, we need to fine-tune the training network to realize the accurate recognition of key features. Based on the above key algorithms, this paper designs a sports video athlete detection system based on deep learning and makes an experimental research on the related sports video. The experimental results show that the detection accuracy of athletes' sports video is improved by nearly 10% compared with the traditional convolution network recognition algorithm, so the algorithm has obvious advantages in recognition accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Liu Y, Ji Y (2021) Target recognition of sport athletes based on deep learning and convolutional neural network. J Intell Fuzzy Syst 40(2):2253–2263

    Article  Google Scholar 

  2. Thanjavur K, Babul A, Foran B et al (2021) Recurrent neural network-based acute concussion classifier using raw resting state EEG data. Sci Rep 11(1):12353

    Article  Google Scholar 

  3. Wang P, Chi X, Yu Y (2021) The application of deep learning in college students’ sports cognition and health concept. J Intell Fuzzy Syst 11(24):1–13

    Google Scholar 

  4. Chen Y (2021) Sports sequence images based on convolutional neural network. Math Probl Eng 2021(4):1–14

    Google Scholar 

  5. Yamins D, Dicarlo JJ (2016) Using goal-driven deep learning models to understand sensory cortex. Nat Neurosci 19(3):356

    Article  Google Scholar 

  6. Sirinukunwattana K, Shan E, Tsang YW et al (2016) Locality Sensitive Deep Learning for detection and classification of nuclei in routine colon cancer histology images. IEEE Trans Med Imaging 35(5):1196–1206

    Article  Google Scholar 

  7. Thesen S, Heid O, Mueller E et al (2015) Prospective acquisition correction for head motion with image-based tracking for real-time fMRI. Magn Resonan Med 44(3):457–465

    Article  Google Scholar 

  8. Zhu Y, Drangova M, Pelc NJ (2015) Fourier tracking of myocardial motion using cine-PC data. Magn Resonan Med 35(4):471–480

    Article  Google Scholar 

  9. Hungr N, Baumann M, Long JA et al (2012) A 3D ultrasound robotic prostate brachytherapy system with prostate motion tracking. IEEE Trans Rob 28(6):1382–1397

    Article  Google Scholar 

  10. Xióngbiāo Luó a, B M F A , A D D , et al. Development and comparison of new hybrid motion tracking for bronchoscopic navigation. Med Image Anal, 2012, 16( 3):577–596.

  11. Inoue Y, Sakaguchi Y (2014) Periodic change in phase relationship between target and hand motion during visuo-manual tracking task: Behavioral evidence for intermittent control. Hum Mov Sci 33(2):211–226

    Article  Google Scholar 

  12. Stancic I, Ante et al. Design, development and evaluation of optical motion-tracking system based on active white light markers. IET Sci Meas Technol, 2013, 7(4):206–214.

  13. Olesen OV, Paulsen RR, Hojgaard L et al (2012) Motion tracking for medical imaging: a nonvisible structured light tracking approach. Med Imag IEEE Trans 31(1):79–87

    Article  Google Scholar 

  14. Fu J, Chai T, Su CY et al (2013) Motion/force tracking control of nonholonomic mechanical systems via combining cascaded design and backstepping. Automatica 49(12):3682–3686

    Article  MATH  Google Scholar 

  15. Ji S, Fan X, Roberts DW et al (2014) Cortical surface shift estimation using stereovision and optical flow motion tracking via projection image registration. Med Image Anal 18(7):1169–1183

    Article  Google Scholar 

  16. Wu J, Wang J, Liu L (2007) Feature extraction via KPCA for classification of gait patterns. Hum Mov Sci 26(3):393–411

    Article  Google Scholar 

  17. Liu Y, Lai S, Wang B et al (2012) Feature-driven motion model-based particle-filter tracking method with abrupt motion handling. Opt Eng 51(4):7203

    Article  Google Scholar 

  18. Wang N, Mo D, Song Z et al (2019) Feature extraction of precession target based on Doppler profile sequences by maximum likelihood estimation. Electr Lett 55(9):554–556

    Article  Google Scholar 

  19. Torheim G, Godtliebsen F, Axelson D et al (2001) Feature extraction and classification of dynamic contrast-enhanced T2*-weighted breast image data. IEEE Trans Med Imag 20(12):1293

    Article  Google Scholar 

  20. Pham D, Arandjelovic O, Venkatesh S (2014) Detection of dynamic background due to swaying movements from motion features. IEEE Trans Image Process 24(1):332–344

    Article  MATH  Google Scholar 

  21. Couceiro R, Carvalho P, Paiva RP et al (2014) Detection of motion artifact patterns in photoplethysmographic signals based ontime and period domain analysis. Physiol Meas 35(12):2369–2388

    Article  Google Scholar 

  22. Koh YJ, Lee C, Kim CS (2015) Video stabilization based on feature trajectory augmentation and selection and robust mesh grid warping. IEEE Trans Image Process 24(12):5260–5273

    Article  MATH  Google Scholar 

  23. Goldman GH (2013) Doppler-based motion compensation algorithm for focusing the signature of a rotorcraft. J Acoust Soc Am 133(2):688–696

    Article  Google Scholar 

  24. Kim SK, Kang SJ, Wang TS et al (2013) Feature point classification based global motion estimation for video stabilization. IEEE Trans Consum Electron 59(1):267–272

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Sports, Xinxiang Medical University, Xinxiang, 453003, Henan, China

    Hao Ren

Authors
  1. Hao Ren
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Hao Ren.

Ethics declarations

Conflict of interest

We declare that there is no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ren, H. Sports video athlete detection based on deep learning. Neural Comput & Applic 35, 4201–4210 (2023). https://doi.org/10.1007/s00521-022-07077-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07077-9

Keywords