Advertisement

Skeleton-based comparison of throwing motion for handball players

  • 109 Accesses

Abstract

The main goal of this work is to design an automated solution based on RGB-D data for quantitative analysis, perceptible evaluation and comparison of handball player’s performance. To that end, we introduced a new RGB-D dataset that can be used for an objective comparison and evaluation of handball player’s performance during throws. We filmed 62 handball players (44 beginners and 18 experts), who performed the same type of action, using a Kinect V2 sensor that provides RGB data, depth data and skeletons. Moreover, using skeleton data simulating 3D joint connections, we examined the main angles responsible for throwing performance in order to analyze individual skills of handball players (beginners against model and experts) relatively to throw actions. The comparison was performed statically (using only one frame) as well as dynamically during the entire throwing action. In particular, given the temporal sequence of 25 joints of each handball player, we adopted the dynamic time warping technique to compare the throwing motion between two athletes. The obtained results were found to be promising. Thus, the suggested markless solution would help handball coaches to optimize beginners’ movements during throwing actions.

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

Access options

Buy single article

Instant unlimited access to the full article PDF.

US$ 39.95

Price includes VAT for USA

Subscribe to journal

Immediate online access to all issues from 2019. Subscription will auto renew annually.

US$ 99

This is the net price. Taxes to be calculated in checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

References

  1. Abrams GD, Harris AH, Andriacchi TP, Safran MR (2014) Biomechanical analysis of three tennis serve types using a markerless system. Br J Sports Med 48(4):339–342

  2. Aguilar WG, Morales SG (2016) 3D environment mapping using the Kinect V2 and path planning based on RRT algorithms. Electronics 5(4):70

  3. Alderson J (2015) A markerless motion capture technique for sport performance analysis and injury prevention: toward a ‘big data’, machine learning future. J Sci Med Sport 19:e79

  4. Barhoumi W (2015) Detection of highly articulated moving objects by using co-segmentation with application to athletic video sequences. Signal Image Video Process 9(7):1705–1715

  5. Bernardina GR, Cerveri P, Barros RM, Marins JC, Silvatti AP (2016) Action sport cameras as an instrument to perform a 3D underwater motion analysis. PLoS One 11(8):e0160,490

  6. Berndt DJ, Clifford J (1994) Using dynamic time warping to find patterns in time series. In: KDD workshop, Seattle, WA, pp 359–370

  7. Bhorge SB, Manthalkar RR (2019) Recognition of vision-based activities of daily living using linear predictive coding of histogram of directional derivative. J Ambient Intell Human Comput 10(1):199–214

  8. Cai X, Zhou W, Wu L, Luo J, Li H (2016) Effective active skeleton representation for low latency human action recognition. IEEE Trans Multimedia 18(2):141–154

  9. Camomilla V, Bergamini E, Fantozzi S, Vannozzi G (2018) Trends supporting the in-field use of wearable inertial sensors for sport performance evaluation: a systematic review. Sensors 18(3):873

  10. Carey P, Bennett S, Lasenby J, Purnell T (2017) Aerodynamic analysis via foreground segmentation. Electron Imaging Comput Vis Appl Sports Soc Imaging Sci Technol 16:10–14

  11. Chen HT, Liu TL, Fuh CS (2006) Segmenting highly articulated video objects with weak-prior random forests. In: European conference on computer vision, Springer, Berlin, pp 373–385

  12. Chikhaoui B, Ye B, Mihailidis A (2017) Feature-level combination of skeleton joints and body parts for accurate aggressive and agitated behavior recognition. J Ambient Intell Human Comput 8(6):957–976

  13. Choi J, Jeon WJ, Lee SC (2008) Spatio-temporal pyramid matching for sports videos. In: Proceedings of the 1st ACM international conference on Multimedia information retrieval, ACM, pp 291–297

  14. Clark RA, Pua YH, Fortin K, Ritchie C, Webster KE, Denehy L, Bryant AL (2012) Validity of the microsoft Kinect for assessment of postural control. Gait Posture 36(3):372–377

  15. Clark RA, Pua YH, Oliveira CC, Bower KJ, Thilarajah S, McGaw R, Hasanki K, Mentiplay BF (2015) Reliability and concurrent validity of the Microsoft Xbox One Kinect for assessment of standing balance and postural control. Gait Posture 42(2):210–213

  16. Cockcroft J, Van Den Heever D (2016) A descriptive study of step alignment and foot positioning relative to the tee by professional rugby union goal-kickers. J Sports Sci 34(4):321–329

  17. Da Cunha Neto JS, Rebouças Filho PP, da Silva GPF, da Cunha Olegario NB, Duarte JBF, de Albuquerque VHC (2018) Dynamic evaluation and treatment of the movement amplitude using Kinect sensor. IEEE Access 6:17292–17305

  18. Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1110–1118

  19. Eltoukhy M, Kelly A, Kim CY, Jun HP, Campbell R, Kuenze C (2016) Validation of the microsoft Kinect® camera system for measurement of lower extremity jump landing and squatting kinematics. Sports Biomech 15(1):89–102

  20. Fernàndez-Baena A, Susín A, Lligadas X (2012) Biomechanical validation of upper-body and lower-body joint movements of kinect motion capture data for rehabilitation treatments. In: Intelligent networking and collaborative systems (INCoS), 2012 4th international conference on, IEEE, pp 656–661

  21. Ganapathi V, Plagemann C, Koller D, Thrun S (2012) Real-time human pose tracking from range data. In: European conference on computer vision, Springer, Berlin, pp 738–751

  22. Grigg J, Haakonssen E, Rathbone E, Orr R, Keogh JW (2018) The validity and intra-tester reliability of markerless motion capture to analyse kinematics of the bmx supercross gate start. Sports Biomech 17(3):383–401

  23. Han J, Shao L, Xu D, Shotton J (2013) Enhanced computer vision with microsoft kinect sensor: a review. IEEE Trans Cybern 43(5):1318–1334

  24. Imran J, Raman B (2019) Evaluating fusion of RGB-D and inertial sensors for multimodal human action recognition. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-019-01239-9

  25. Jiao J, Yuan L, Tang W, Deng Z, Wu Q (2017) A post-rectification approach of depth images of Kinect V2 for 3D reconstruction of indoor scenes. ISPRS Int J Geo Inf 6(11):349

  26. Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1725–1732

  27. Kim Y, Kim D (2018) Real-time dance evaluation by markerless human pose estimation. Multimedia Tools Appl 77(23):31199–31220

  28. Kitani KM, Okabe T, Sato Y, Sugimoto A (2011) Fast unsupervised ego-action learning for first-person sports videos. In: Computer vision and pattern recognition (CVPR), IEEE conference on, IEEE, pp 3241–3248

  29. Kong Y, Wei Z, Huang S (2017) Automatic analysis of complex athlete techniques in broadcast taekwondo video. Multimedia Tools Appl 77(11):13643–13660

  30. Li W, Zhang Z, Liu Z (2010) Action recognition based on a bag of 3d points. In: Computer vision and pattern recognition workshops (CVPRW), 2010 IEEE computer society conference on, IEEE, pp 9–14

  31. Marshall R, Elliott B (2000) Long-axis rotation: the missing link in proximal-to-distal segmental sequencing. J Sports Sci 18(4):247–254

  32. Maxwell SE, Delaney HD (1993) Bivariate median splits and spurious statistical significance. Psychol Bull 113(1):181

  33. Munaro M, Basso A, Fossati A, Van Gool L, Menegatti E (2014) 3D reconstruction of freely moving persons for re-identification with a depth sensor. In: Robotics and automation (ICRA), IEEE international conference on, IEEE, pp 4512–4519

  34. Nagano Y, Ida H, Akai M, Fukubayashi T (2011) Relationship between three-dimensional kinematics of knee and trunk motion during shuttle run cutting. J Sports Sci 29(14):1525–1534

  35. Tejero-de Pablos A, Nakashima Y, Sato T, Yokoya N, Linna M, Rahtu E (2018) Summarization of user-generated sports video by using deep action recognition features. IEEE Trans Multimedia 20(8):2000–2011

  36. Pansiot J (2009) Markerless visual tracking and motion analysis for sports monitoring. PhD thesis, Imperial College London

  37. Papadopoulos GT, Axenopoulos A, Daras P (2014) Real-time skeleton-tracking-based human action recognition using kinect data. In: International conference on multimedia modeling, Springer, Berlin, pp 473–483

  38. Pazhoumand-Dar H (2018) Fuzzy association rule mining for recognising daily activities using kinect sensors and a single power meter. J Ambient Intell Human Comput 9(5):1497–1515

  39. Pers J, Bon M, Vuckovic G (2006) Cvbase 06 dataset. In: Proceedings of workshop on computer vision based analysis in sport environment (ECCV)

  40. Presti LL, La Cascia M (2016) 3d skeleton-based human action classification: a survey. Pattern Recognit 53:130–147

  41. Rodriguez MD, Ahmed J, Shah M (2008) Action mach a spatio-temporal maximum average correlation height filter for action recognition. In: Computer vision and pattern recognition, CVPR, IEEE conference on, IEEE, pp 1–8

  42. Sabale AS, Vaidya YM (2016) Accuracy measurement of depth using kinect sensor. In: Advances in signal processing (CASP), conference on, IEEE, pp 155–159

  43. Sharaf A, Torki M, Hussein ME, El-Saban M (2015) Real-time multi-scale action detection from 3D skeleton data. In: IEEE winter conference on applications of computer vision (WACV), IEEE, pp 998–1005

  44. Singh S, Arora C, Jawahar C (2017) Trajectory aligned features for first person action recognition. Pattern Recognit 62:45–55

  45. Van den Tillaar R, Ettema G (2009) Is there a proximal-to-distal sequence in overarm throwing in team handball? J Sports Sci 27(9):949–955

  46. Van der Kruk E, Reijne MM (2018) Accuracy of human motion capture systems for sport applications; state-of-the-art review. Eur J Sport Sci 18(6):806–819

  47. Vemulapalli R, Arrate F, Chellappa R (2014) Human action recognition by representing 3D skeletons as points in a lie group. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 588–595

  48. Wagner H, Pfusterschmied J, Von Duvillard SP, Müller E (2012) Skill-dependent proximal-to-distal sequence in team-handball throwing. J Sports Sci 30(1):21–29

  49. Wolf C, Lombardi E, Mille J, Celiktutan O, Jiu M, Dogan E, Eren G, Baccouche M, Dellandréa E, Bichot CE et al (2014) Evaluation of video activity localizations integrating quality and quantity measurements. Comput Vis Image Understand 127:14–30

  50. Xia L, Chen CC, Aggarwal JK (2012) View invariant human action recognition using histograms of 3D joints. In: Computer vision and pattern recognition workshops (CVPRW), 2012 IEEE computer society conference on, IEEE, pp 20–27

  51. Yang X, Tian Y (2014) Effective 3D action recognition using eigenjoints. J Vis Commun Image Represent 25(1):2–11

  52. Zennaro S, Munaro M, Milani S, Zanuttigh P, Bernardi A, Ghidoni S, Menegatti E (2015) Performance evaluation of the 1st and 2nd generation kinect for multimedia applications. In: Multimedia and expo (ICME), IEEE international conference on, IEEE, pp 1–6

  53. Zhang M, Zhang Z, Chang Y, Aziz ES, Esche S, Chassapis C (2018) Recent developments in game-based virtual reality educational laboratories using the microsoft kinect. Int J Emerg Technol Learn (IJET) 13(1):138–159

Download references

Acknowledgements

We would like to thank our handball coaches and analysts collaborators: Prof. Hafsi Bedhioufi (Head of the Directorate General of Physical Education, Training and Research, Tunisia), Dr. Mourad Fadhloun (Assistant Professor of Applied Biological Sciences at Higher Institute of Sport and Physical Education, Tunisia) and Abdessalem Louizi (Handball coach and physical trainer at the Ministry of Youth and Sport Affairs, Tunisia).

Author information

Correspondence to Amani Elaoud.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Elaoud, A., Barhoumi, W., Zagrouba, E. et al. Skeleton-based comparison of throwing motion for handball players. J Ambient Intell Human Comput 11, 419–431 (2020). https://doi.org/10.1007/s12652-019-01301-6

Download citation

Keywords

  • Performance evaluation
  • Kinect V2
  • Skeleton
  • Dynamic time warping
  • Handball