Abstract

Video Repetition Counting is one of the important research areas in computer vision. It focuses on estimating the number of repeating actions. In this paper, we propose a method for video-based rope skipping repetition counting that combines the ResNet Model and a counting algorithm. Each frame in the given video is first classified into two categories: upward and downward, describing its current motion status. Then the classification sequence of the video is processed by a statistical counting algorithm to obtain the final repetition number. The experiments on real-world videos show the efficiency of our model.

References

  1. R. Cutler and L. S. Davis, “Robust real-time periodic motion detection, analysis, and applications,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 781–796, 2000, doi: 10.1109/34.868681.
  2. D. Dwibedi, Y. Aytar, J. Tompson, P. Sermanet, and A. Zisserman, “Counting out time: Class agnostic video repetition counting in the wild,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), Jun. 2020, pp. 10387–10396.
  3. O. Levy and L. Wolf, “Live repetition counting,” in Proceedings of the IEEE international conference on computer vision (ICCV), Dec. 2015, pp. 3020–3028.
  4. A. Thangali and S. Sclaroff, “Periodic motion detection and estimation via space-time sampling,” in 2005 seventh IEEE workshops on applications of computer vision (WACV/MOTION’05) - volume 1, 2005, vol. 2, pp. 176–182. doi: 10.1109/ACVMOT.2005.91.
  5. E. Pogalin, A. W. M. Smeulders, and A. H. C. Thean, “Visual quasi-periodicity,” in 2008 IEEE conference on computer vision and pattern recognition, 2008, pp. 1–8. doi: 10.1109/CVPR.2008.4587509.
  6. O. Azy and N. Ahuja, “Segmentation of periodically moving objects,” United States, 2008. doi: 10.1109/icpr.2008.4760949.
  7. T. F. H. Runia, C. G. M. Snoek, and A. W. M. Smeulders, “Real-world repetition estimation by div, grad and curl,” in 2018 IEEE/CVF conference on computer vision and pattern recognition, 2018, pp. 9009–9017. doi: 10.1109/CVPR.2018.00939.
  8. C. Panagiotakis, G. Karvounas, and A. Argyros, “Unsupervised detection of periodic segments in videos,” in 2018 25th IEEE international conference on image processing (ICIP), 2018, pp. 923–927. doi: 10.1109/ICIP.2018.8451336.
  9. S. L. Pintea, J. Zheng, X. Li, P. J. M. Bank, J. J. van Hilten, and J. C. van Gemert, “Hand-tremor frequency estimation in videos,” Sep. 2018.
  10. H. Zhang, X. Xu, G. Han, and S. He, “Context-aware and scale-insensitive temporal repetition counting,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), Jun. 2020, pp. 670–678.
  11. T. Alatiah and C. Chen, “Recognizing exercises and counting repetitions in real time.” 2020.
  12. R. Khurana, K. Ahuja, Z. Yu, J. Mankoff, C. Harrison, and M. Goel, “GymCam: Detecting, recognizing and tracking simultaneous exercises in unconstrained scenes,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 2, no. 4, pp. 1–17, Dec. 2018, doi: 10.1145/3287063.
  13. Q. Yu, H. Wang, F. Laamarti, and A. El Saddik, “Deep learning-enabled multitask system for exercise recognition and counting,” Multimodal Technologies and Interaction, vol. 5, no. 9, 2021, doi: 10.3390/mti5090055.
  14. B. Ferreira et al., “Deep learning approaches for workout repetition counting and validation,” Pattern Recognition Letters, vol. 151, pp. 259–266, 2021, doi: https://doi.org/10.1016/j.patrec.2021.09.006.
  15. K. Skawinski, F. Montraveta Roca, R. D. Findling, and S. Sigg, “Workout type recognition and repetition counting with CNNs from 3D acceleration sensed on the chest,” in Advances in computational intelligence, Cham, 2019, pp. 347–359.
  16. A. Soro, G. Brunner, S. Tanner, and R. Wattenhofer, “Recognition and repetition counting for complex physical exercises with deep learning,” Sensors, vol. 19, no. 3, 2019, doi: 10.3390/s19030714.
  17. [A. Ranjan and M. J. Black, “Optical flow estimation using a spatial pyramid network,” in 2017 IEEE conference on computer vision and pattern recognition (CVPR), 2017, pp. 2720–2729. doi: 10.1109/CVPR.2017.291.
  18. G. Farnebäck, “Two-frame motion estimation based on polynomial expansion,” in Image analysis, Berlin, Heidelberg, 2003, pp. 363–370.
  19. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), Jun. 2016, pp. 770–778.
  20. R. K. Srivastava, K. Greff, and J. Schmidhuber, “Training Very Deep Networks,” in Advances in Neural Information Processing Systems 28, C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, Eds. Curran Associates, Inc., 2015, pp. 2377–2385.