DOI QR코드

DOI QR Code

Development of Squat Posture Guidance System Using Kinect and Wii Balance Board

  • Oh, SeungJun (Department of Sports ICT Convergence, Sangmyung University Graduate School) ;
  • Kim, Dong Keun (Department of Intelligent Engineering Informatics for Human, Sangmyung University)
  • Received : 2018.07.24
  • Accepted : 2019.03.03
  • Published : 2019.03.31

Abstract

This study designs a squat posture recognition system that can provide correct squat posture guidelines. This system comprises two modules: a Kinect camera for monitoring users' body movements and a Wii Balance Board(WBB) for measuring balanced postures with legs. Squat posture recognition involves two states: "Stand" and "Squat." Further, each state is divided into two postures: correct and incorrect. The incorrect postures of the Stand and Squat states were classified into three and two different types of postures, respectively. The factors that determine whether a posture is incorrect or correct include the difference between shoulder width and ankle width, knee angle, and coordinate of center of pressure(CoP). An expert and 10 participants participated in experiments, and the three factors used to determine the posture were measured using both Kinect and WBB. The acquired data from each device show that the expert's posture is more stable than that of the subjects. This data was classified using a support vector machine (SVM) and $na{\ddot{i}}ve$ Bayes classifier. The classification results showed that the accuracy achieved using the SVM and $na{\ddot{i}}ve$ Bayes classifier was 95.61% and 81.82%, respectively. Therefore, the developed system that used Kinect and WBB could classify correct and incorrect postures with high accuracy. Unlike in other studies, we obtained the spatial coordinates using Kinect and measured the length of the body. The balance of the body was measured using CoP coordinates obtained from the WBB, and meaningful results were obtained from the measured values. Finally, the developed system can help people analyze the squat posture easily and conveniently anywhere and can help present correct squat posture guidelines. By using this system, users can easily analyze the squat posture in daily life and suggest safe and accurate postures.

Keywords

E1ICAW_2019_v17n1_74_f0001.png 이미지

Fig. 1. Overall procedure of posture recognition system.

E1ICAW_2019_v17n1_74_f0002.png 이미지

Fig. 2. Measuring difference between shoulder width and ankle width.

E1ICAW_2019_v17n1_74_f0003.png 이미지

Fig. 3. Determination of knee angle: measuring the knee angle (θ) using coordinates of the three points.

E1ICAW_2019_v17n1_74_f0004.png 이미지

Fig. 4. Coordinate axis and pressure sensor recognized by Wii Balance Board.

E1ICAW_2019_v17n1_74_f0005.png 이미지

Fig. 5. Stand posture, Normal Stand posture: (a) posture, Incorrect Posture: (b)~(d) posture. (a), (b), (c) and (d) from the left. The solid line indicates the position of the user's feet, and the dotted line indicates the center of the body.

E1ICAW_2019_v17n1_74_f0006.png 이미지

Fig. 6. Squat posture, Normal Squat Posture: (e) posture, Knee Protruding posture: (f) posture. (e) and (f) from the left. The solid line indicates the position of the user's knee, and the dotted line indicates the position of the knee in the correct posture.

E1ICAW_2019_v17n1_74_f0007.png 이미지

Fig. 7. Comparison of CoP trajectory between expert and experiment subject: (e) posture.

E1ICAW_2019_v17n1_74_f0008.png 이미지

Fig. 8. FFT results of CoP-Origin distance comparison between experts and subject.

Table 1. Items to be measured between experiments

E1ICAW_2019_v17n1_74_t0001.png 이미지

Table 2. The paired t-test result of the difference in the ${\parallel}\overrightarrow{SLSR}{\parallel}$ - ${\parallel}\overrightarrow{ALAR}{\parallel}$ values and θ(Knee) values for expert and subjects in (a)~(f) posture

E1ICAW_2019_v17n1_74_t0002.png 이미지

Table 3. Mean values of CoP-Origin distance comparison between experts and subject

E1ICAW_2019_v17n1_74_t0003.png 이미지

Table 4. Accuracy (%) of SVM and Naïve Bayes classification

E1ICAW_2019_v17n1_74_t0004.png 이미지

References

  1. W. R. Jr. Stevens, A. Y. Kokoszka, A. M. Anderson, and K. Tulchin-Francis, "Automated event detection algorithm for two squatting protocols," Gait & Posture, vol. 59, pp 253-257, 2018. DOI: 10.1016/j.gaitpost.2017.10.025.
  2. H. S. Joo, J. Woo, Y. Lee, D. Kim, S. Kim, and M. Woo, "The prediction of squat depth by using Kinanthropometric data: Neural network vs. multiple linear regression," Journal of Korean Association of Physical Education and Sport for Girls and Women, vol. 30, no. 4, pp. 373-386, 2016. [Online] Available: http://www.dbpia.co.kr/Journal/ArticleDetail/NODE07103572. https://doi.org/10.16915/jkapesgw.2016.12.30.4.373
  3. Y. Na, "Muscle activity analysis of erector spinae and rectus femoris depending on toe out angles in squat movement," M.S. dissertation, Chungnam National University, Daejeon, Korea, 2013.
  4. L. V. Slater and J. M. Hart, "The influence of knee alignment on lower extremity kinetics during squats," Journal of Electromyography and Kinesiology, vol. 31, pp. 96-103, 2016. DOI: 10.1016/j.jelekin.2016.10.004.
  5. J. Clement, N. Hagemeister, R. Aissaoui, and J. A. de Guise, "Comparison of quasi-static and dynamic squats: A three-dimensional kinematic, kinetic and electromyographic study of the lower limbs," Gait & Posture, vol. 40, Issue 1, pp. 94-100, 2014. DOI: 10.1016/j.gaitpost.2014.02.016.
  6. L. Stickler, M. Finley, and H. Gulgin, "Relationship between hip and core strength and frontal plane alignment during a single leg squat," Physical Therapy in Sport, vol. 16, Issue 1, pp. 66-71, 2015. DOI: 10.1016/j.ptsp.2014.05.002.
  7. Y. Kim, "An analysis of muscle activations by the increase of load in squats," M.S. dissertation, Pusan University of Foreign Studies, Busan, Korea, 2010.
  8. N. Choi, "The effects of doing smith machine squat exercise on unstable ground on lower extremity muscle and trunk muscle," M.S. dissertation, Dankook University, Cheonan, Korea, 2015.
  9. S. Choi, "The effects of 12-week squat training on body composition, maximal muscular strength and power in female boxers," M.S. dissertation, Sejong University, Seoul, Korea, 2014.
  10. H. S. Park, "Comparative analysis on muscle activities of lower limb depending on the types and load of squat exercise," M.S. dissertation, Hanyang University, Ansan, Korea, 2016.
  11. L. M. de Souza, D. B. da Fonseca, H. D. Cabral, L. F. de Oliveira, and T. M. Vieira, "Is myoelectric activity distributed equally within the rectus femoris muscle during loaded, squat exercises?," Journal of Electromyography and Kinesiology, vol. 33, pp. 10-19, 2017. DOI: 10.1016/j.jelekin.2017.01.003.
  12. S. Oh, "Study on the proposal of proper squat posture guidelines using Kinect and Wii Balance Board," M.S. dissertation, Sangmyung University, Seoul, Korea, 2017.
  13. E. Lee, "Balance evaluation using multiple motion gaming devices," M.S. dissertation, Soongsil University, Seoul, Korea, 2016.
  14. R. A. Clark, A. L. Bryant, Y. Pua, P. McCrory, K. Bennell, and M. Hunt, "Validity and reliability of the Nintendo Wii Balance Board for assessment of standing balance," Gait & posture, vol. 31, no. 3, pp. 307-310, 2010. DOI: 10.1016/j.gaitpost.2009.11.012.
  15. Y. Cho, and K. S. Park, "Design and development of the multiple Kinect sensor-based exercise pose estimation system," Journal of the Korea Institute of Information and Communication Engineering, vol. 21, no. 3, pp. 558-567, 2017. [Online] Available: http://www.dbpia.co.kr/Journal/ArticleDetail/NODE07129414. https://doi.org/10.6109/jkiice.2017.21.3.558
  16. W. Lee, B. Kang, Y. Kim, H. Kim, J. K. Park, and S. E Park, "A study on the lower body muscle strengthening system using Kinect sensor," Journal of the Korea Institute of Information and Communication Engineering, vol. 21, no. 11, pp. 2095-2102, 2017. [Online] Available: http://www.dbpia.co.kr/Journal/ArticleDetail/NODE07272370. https://doi.org/10.6109/JKIICE.2017.21.11.2095
  17. E. Dooley, J. Carr, E. Carson, and S. Russell, "The effects of knee support on the sagittal lower-body joint kinematics and kinetics of deep squats," Journal of Biomechanics, vol. 82, pp. 164-170, 2018. DOI: 10.1016/j.jbiomech.2018.10.024.
  18. D. H. Seo, K. S. Park, and D. K. Kim, "Design and development of virtual reality exergame using smart mat and camera sensor," Journal of the Korea Institute of Information and Communication Engineering, vol. 20, no. 12, pp. 2297-2304, 2016. [Online] Available: http://www.dbpia.co.kr/Journal/ArticleDetail/NODE07083107. https://doi.org/10.6109/jkiice.2016.20.12.2297
  19. B. Peek, Managed Library for Nintendo's Wiimote, 2015, [Online] available: http://wiimotelib.codeplex.com/.
  20. J. M. Leach, M. Mancini, R. J. Peterka, T. L. Hayes, and F. B. Horak, "Validating and calibrating the Nintendo Wii balance board to derive reliable center of pressure measures," Sensors, vol. 14, no. 10, pp. 18244-18267, 2014. DOI: 10.3390/s141018244.
  21. A. Almandeel, D. H. Myszka, A. Gonzalez, and P. Fraisse, "Rapidly locating and accurately tracking the center of mass using statically equivalent serial chains," in Proceeding of 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pp. 570-575, 2015. DOI: 10.1109/HUMANOIDS.2015.7363419.
  22. R. Kohen-Raz, "Application of tetra-ataxiametric posturography in clinical and developmental diagnosis," Perceptual and Motor Skills, vol. 73, no. 2, pp. 635-656, 1991. DOI: 10.2466/pms.1991.73.2.635.

Cited by

  1. Interactive Spatial Augmented Reality Book on Cultural Heritage of Myanmar vol.18, pp.2, 2019, https://doi.org/10.6109/jicce.2020.18.2.69