Skip to main content
SpringerLink
Log in

Application of intelligent real-time image processing in fitness motion detection under internet of things

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

The purpose is to study the applicability of digital and intelligent real-time Image Processing (IP) in fitness motion detection under the environment of the Internet of Things (IoT). Given the absence of real-time training standards and possible workout injury problems during fitness activities, an intelligent fitness real-time IP system based on Deep Learning (DL) is implemented. Specifically, the keyframes of the real-time images are collected from the fitness monitoring video, and the DL algorithm is introduced to analyze the fitness motions. Afterward, the performance of the proposed system is evaluated through simulation. Subsequently, the Noise Reduction (NR) performance of the proposed algorithm is evaluated from the Peak Signal-to-Noise Ratio (PSNR), which remains above 20 dB for seriously noisy images (with a noise density reaching up to 90%). By comparison, the PSNR of the Standard Median Filter (SMF) and Ranked-order Based Adaptive Median Filter (RAMF) algorithms are not higher than 10 dB. Meanwhile, the proposed algorithm outperforms other DL algorithms by over 2.24% with a detection accuracy of 97.80%; the proposed system can adaptively detect the fitness motion, with a transmission delay no larger than 1 s given a maximum of 750 keyframes. Therefore, the proposed DL-based intelligent fitness real-time IP algorithm has strong robustness, high detection accuracy, and excellent real-time image diagnosis and processing effect, thus providing an experimental reference for sports digitalization and intellectualization.

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

Access this article

Log in via an institution

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
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Ba H (2020) Medical sports rehabilitation deep learning system of sports injury based on MRI image analysis[J]. J Med Imag Health Inform 10(5):1091–1097

    Article  Google Scholar 

  2. Yong B, Xu Z, Wang X et al (2018) IoT-based intelligent fitness system[J]. J Parallel Distrib Comp 118:14–21

    Article  Google Scholar 

  3. Lee J, Joo H, Lee J et al (2020) Automatic classification of squat posture using inertial sensors: deep learning approach[J]. Sensors 20(2):361–361

    Article  MathSciNet  Google Scholar 

  4. Liu N, Liu P (2021) Goaling recognition based on intelligent analysis of real-time basketball image of internet of things[J]. J Supercomp. https://doi.org/10.1007/s11227-021-03877-3

    Article  Google Scholar 

  5. Hashemi H, Abdelghany K (2018) End-to-end deep learning methodology for real-time traffic network management[J]. Comput-Aided Civil Infrastruct Engineer 33(10):849–863

    Article  Google Scholar 

  6. Zou Y, Wang D, Hong S et al (2020) A low-cost smart glove system for real-time fitness coaching[J]. IEEE Internet Things J 7(8):7377–7391

    Article  Google Scholar 

  7. Nadeem A, Jalal A, Kim K (2020) Accurate physical activity recognition using multidimensional features and Markov model for smart health fitness[J]. Symmetry 12(11):1766–1766

    Article  Google Scholar 

  8. Chen L, Papandreou G, Kokkinos I et al (2018) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Trans Pattern Anal Mach Intell 40(4):834–848

    Article  Google Scholar 

  9. Nasir YS, Guo D (2019) Multi-agent deep reinforcement learning for dynamic power allocation in wireless networks[J]. IEEE J Sel Areas Commun 37(10):2239–2250

    Article  Google Scholar 

  10. Sultana N, Chilamkurti N, Peng W et al (2019) Survey on SDN-based network intrusion detection system using machine learning approaches[J]. Peer-to-peer Netw Appl 12(2):493–501

    Article  Google Scholar 

  11. Wang Y, Yang J, Liu M et al (2020) LightAMC: Lightweight automatic modulation classification via deep learning and compressive sensing[J]. IEEE Trans Veh Technol 69(3):3491–3495

    Article  Google Scholar 

  12. He D, Li L (2021) A novel deep learning method based on modified recurrent neural network for sports posture recognition[J]. J Appl Sci Eng 24(1):43–48

    Google Scholar 

  13. Cust EE, Sweeting AJ, Ball K et al (2019) Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance[J]. J Sports Sci 37(5):568–600

    Article  Google Scholar 

  14. Khan MA, Javed K, Khan SA et al (2020) Human action recognition using the fusion of multiview and deep features: an application to video surveillance[J]. Multimed Tools Appl. https://doi.org/10.1007/s11042-020-08806-9

    Article  Google Scholar 

  15. Hu X, Zong B, Pang B (2021) Simulation of sports action monitoring based on feature similarity model[J]. J Ambient Intell Human Comp. https://doi.org/10.1007/s12652-021-03046-7

    Article  Google Scholar 

  16. Argyris YA, Wang Z, Kim Y et al (2020) The effects of visual congruence on increasing consumers’ brand engagement: an empirical investigation of influencer marketing on Instagram using deep-learning algorithms for automatic image classification[J]. Comput Human Behav 112:106443

    Article  Google Scholar 

  17. Chinnappa G, Rajagopal MK (2021) Residual attention network for deep face recognition using micro-expression image analysis[J]. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-021-03003-4

    Article  Google Scholar 

  18. Qureshi MA, Qureshi KN, Jeon G et al (2021) Deep learning-based ambient assisted living for self-management of cardiovascular conditions[J]. Neural Comput Appl. https://doi.org/10.1007/s00521-020-05678-w

    Article  Google Scholar 

  19. Mohammadi M, Al-Fuqaha A, Sorour S et al (2018) Deep learning for IoT big data and streaming analytics: a survey[J]. IEEE Commun Surv Tutorials 20(4):2923–2960

    Article  Google Scholar 

  20. Janarthanan R, Doss S, Baskar S (2020) Optimized unsupervised deep learning assisted reconstructed coder in the on-nodule wearable sensor for human activity recognition[J]. Measurement 164:108050–108050

    Article  Google Scholar 

  21. Bormann CL, Kanakasabapathy MK, Thirumalaraju P et al (2020) Performance of deep learning-based neural network in the selection of human blastocysts for implantation[J]. Elife 9:e55301

    Article  Google Scholar 

  22. Wang T, Gan Y, Arena SD et al (2021) Advances for indoor fitness tracking, coaching, and motivation: a review of existing technological advances[J]. IEEE Systems, Man, Cybern Mag 7(1):4–14

    Article  Google Scholar 

  23. Johnson WR, Mian A, Robinson MA et al (2020) Multidimensional ground reaction forces and moments from wearable sensor accelerations via deep learning[J]. IEEE Trans Biomed Eng 68(1):289–297

    Article  Google Scholar 

  24. Gochoo M, Tahir SBUD, Jalal A et al (2021) Monitoring real-time personal locomotion behaviors over smart indoor-outdoor environments via body-worn sensors[J]. IEEE Access 9:70556–70570

    Article  Google Scholar 

  25. Zhang Z, Han D, Dezert J et al (2018) A new adaptive switching median filter for impulse noise reduction with pre-detection based on evidential reasoning[J]. Signal Process 147:173–189

    Article  Google Scholar 

  26. Tang R, Zhou X, Wang D (2017) Improved adaptive median filter algorithm for removing impulse noise from grayscale images[J]. Int J Eng 30(10):1503–1509

    Google Scholar 

  27. Tang D (2020) Hybridized hierarchical deep convolutional neural network for sports rehabilitation exercises[J]. IEEE Access 8:118969–118977

    Article  Google Scholar 

  28. Zhu ZA, Lu YC, You CH et al (2019) Deep learning for sensor-based rehabilitation exercise recognition and evaluation[J]. Sensors 19(4):887–887

    Article  Google Scholar 

  29. Waldner F, Diakogiannis FI (2020) Deep learning on edge: extracting field boundaries from satellite images with a convolutional neural network[J]. Remote Sens Environ 245:111741

    Article  Google Scholar 

  30. Yu J, Park S, Kwon SH et al (2020) AI-based stroke disease prediction system using real-time electromyography signals[J]. Appl Sci 10(19):6791–6791

    Article  Google Scholar 

  31. Spears BK, Brase J, Bremer PT et al (2018) Deep learning: a guide for practitioners in the physical sciences[J]. Phys Plasmas 25(8):080901–080901

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Sports Science and Physical Education, Nanjing Normal University, JIangsu, Nanjing 210000, China

    Hang Cai

Authors
  1. Hang Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hang Cai.

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

Cai, H. Application of intelligent real-time image processing in fitness motion detection under internet of things. J Supercomput 78, 7788–7804 (2022). https://doi.org/10.1007/s11227-021-04145-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-021-04145-0

Keywords

Search

Navigation