Skip to main content
Springer Nature Link
Log in

Fall detection using features extracted from skeletal joints and SVM: Preliminary results

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In this work we are interested in detecting fall from a non-fall event by means of visual information. A non-fall event can be an activity of daily living (ADL) such as when a person is sitting, walking, lying on the floor, picking up an object. We propose a fall detection system based on a set of visual features, which captures the following information: whether the person is in balance, is close to the ground, the dispersion of joint heights and their change in a time window. The feature set is computed from the joint data provided by the Kinect. The sequences performed by the odd subjects from the TST Fall detection v2 dataset are used to generate the classifier, which is a support vector machine (SVM). This database provides the position of the skeletal joints for actions such as ADL and 4 types of falls. Subsequently, the proposed system is validated with the sequences executed by the even subjects from the TST v2 fall detection dataset and the other two publicly available 3D action datasets. The obtained recognition accuracy is respectively 89.5%, 97.2% and 96%. The experimental results show that the captured features are useful to detect the fall in datasets that are first seen by the classifier.

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
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

Similar content being viewed by others

References

  1. Agahian S, Negin F, Köse C (2019) Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition. Vis Comput 35 (4):591–607

    Article  Google Scholar 

  2. Baskoro AS, Priyono MG (2016) Design of humanoid robot stable walking using inverse kinematics and zero moment point. In: 2016 International electronics symposium (IES). IEEE, pp 335–339

  3. Cameron R, Zuo Z, Sexton G, Yang L (2017) A fall detection/recognition system and an empirical study of gradient-based feature extraction approaches. In: UK Workshop on computational intelligence. Springer, pp 276–289

  4. Chatzaki C, Pediaditis M, Vavoulas G, Tsiknakis M (2016) Human daily activity and fall recognition using a smartphone’s acceleration sensor. In: International conference on information and communication technologies for ageing well and e-health. Springer, pp 100–118

  5. Chen C, Jafari R, Kehtarnavaz N (2015) Utd-mhad: a multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor. In: 2015 IEEE International conference on image processing (ICIP). IEEE, pp 168–172

  6. Chen C, Jafari R, Kehtarnavaz N (2017) A survey of depth and inertial sensor fusion for human action recognition. Multimed Tools Appl 76(3):4405–4425

    Article  Google Scholar 

  7. Chen L, Wei H, Ferryman J (2013) A survey of human motion analysis using depth imagery. Pattern Recogn Lett 34(15):1995–2006

    Article  Google Scholar 

  8. Cippitelli E, Gasparrini S, Gambi E, Spinsante S (2016) A human activity recognition system using skeleton data from rgbd sensors. Computational Intelligence and Neuroscience, 2016. https://doi.org/10.1155/2016/4351435

  9. Dekker M (2009) Zero-moment point method for stable biped walking. Eindhoven University of Technology

  10. Gasparrini S, Cippitelli E, Gambi E, Spinsante S, Wåhslén J, Orhan I, Lindh T (2016) Proposal and experimental evaluation of fall detection solution based on wearable and depth data fusion. In: ICT Innovations 2015. Springer, pp 99–108

  11. Goldberg DE, et al. (2002) The Design of Innovation: Lessons from and for Competent Genetic Algorithmsby David E. goldberg, vol 7. Springer Science & Business Media, Berlin

    Book  Google Scholar 

  12. Gutiérrez J, Rodríguez V, Martin S (2021) Comprehensive review of vision-based fall detection systems. Sensors 21(3). https://doi.org/10.3390/s21030947. https://www.mdpi.com/1424-8220/21/3/947

  13. Hadjadji B, Saumard M, Aron M (2022) Multi-oriented run length based static and dynamic features fused with choquet fuzzy integral for human fall detection in videos. J Visual Commun Image Represent 82:103,375. https://doi.org/10.1016/j.jvcir.2021.103375

    Article  Google Scholar 

  14. Hernandez-Mendez S, Maldonado-Mendez C, Marin-Hernandez A, Rios-Figueroa HV (2017) Detecting falling people by autonomous service robots: a ros module integration approach. In: Electronics, communications and computers (CONIELECOMP), 2017 international conference on. IEEE, pp 1–7

  15. Htoo CK, Sein MM (2019) Geometric kinect joints computing for human fall recognition. Seventeenth International Conference on Computer Applications (ICCA), 2019

  16. Kepski M, Kwolek B (2017) Event-driven system for fall detection using body-worn accelerometer and depth sensor. IET Comput Vis 12(1):48–58

    Article  Google Scholar 

  17. Keskes O, Noumeir R (2021) Vision-based fall detection using st-gcn. IEEE Access 9:28,224–28,236. https://doi.org/10.1109/ACCESS.2021.3058219

    Article  Google Scholar 

  18. Maldonado-Mendez C, Hernandez-Mendez S, Hernandez-Ventura JD (2019) Fall recognition system: a review. In: 2019 IEEE International conference on engineering veracruz (ICEV), vol 1. IEEE, pp 1–6

  19. Maldonado-Mendez C, Solis AL, Rios-Figueroa HV, Marin-Hernandez A (2017) Human fallen pose detection by using feature selection and a generative model. In: Power, electronics and computing (ROPEC), 2017 IEEE international autumn meeting on. IEEE, pp 1–6

  20. Merrouche F, Baha N (2016) Depth camera based fall detection using human shape and movement. In: Signal and image processing (ICSIP), IEEE international conference on. IEEE, pp 586–590

  21. Min W, Yao L, Lin Z, Liu L (2018) Support vector machine approach to fall recognition based on simplified expression of human skeleton action and fast detection of start key frame using torso angle. IET Comput Vis 12(8):1133–1140

    Article  Google Scholar 

  22. Organization WH, Ageing WHO, Unit LC (2008) WHO global report on falls prevention in older age. World Health Organization

  23. Qin Y, Mo L, Li C, Luo J (2020) Skeleton-based action recognition by part-aware graph convolutional networks. The Visual Computer 36 (3):621–631

    Article  Google Scholar 

  24. Ren L, Peng Y (2019) Research of fall detection and fall prevention technologies: a systematic review. IEEE Access 7:77,702–77,722. https://doi.org/10.1109/ACCESS.2019.2922708

    Article  Google Scholar 

  25. Sardain P, Bessonnet G (2004) Forces acting on a biped robot. center of pressure-zero moment point. IEEE Transactions on Systems Man, and Cybernetics-Part A: Systems and Humans 34(5):630–637

    Article  Google Scholar 

  26. Seredin O, Kopylov A, Huang SC, Rodionov D (2019) A skeleton features-based fall detection using microsoft kinect v2 with one class-classifier outlier removal. ISPRS - International Archives of the Photogrammetry. Remote Sensing and Spatial Information Sciences XLII-2/W12, 189–195. https://doi.org/10.5194/isprs-archives-XLII-2-W12-189-2019

  27. Simon J (2012) Prince: Computer vision, Models, learning, and inference

  28. Sucerquia A, López J. D, Vargas-Bonilla JF (2017) Sisfall: A fall and movement dataset. Sensors 17(1):198

    Article  Google Scholar 

  29. Sun X, Zhao K, Jiang W, Jin X (2021) Method of analyzing and managing volleyball action by using action sensor of mobile device. J Sens, 2021. https://doi.org/10.1155/2021/6232968

  30. Valcourt L, De La Hoz Y, Labrador M (2016) Smartphone-based human fall detection system. IEEE Lat Am Trans 14(2):1011–1017

    Article  Google Scholar 

  31. Wilmart R, Rocha-Cózatl E, Narváez-Aroche O (2014) Computation of the safety zmp zone for a biped robot based on error factors

  32. Xia L, Chen C, Aggarwal J (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

  33. Xu Y, Chen J, Yang Q, Guo Q (2019) Human posture recognition and fall detection using kinect v2 camera. In: 2019 Chinese control conference (CCC). IEEE, pp 8488–8493

  34. Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 32

  35. Yao L, Yang W, Huang W (2019) An improved feature-based method for fall detection. Tehnički vjesnik 26(5):1363–1368

    Google Scholar 

  36. Yu X (2008) Approaches and principles of fall detection for elderly and patient. In: E-health networking, applications and services, 2008. Healthcom 2008. 10th international conference on. IEEE, pp 42–47

  37. Zhang J, Tang ZH, Gui W.hH., Chen Q, Liu J (2017) Interactive image segmentation with a regression based ensemble learning paradigm. Frontiers of Information Technology & Electronic Engineering 18(7):1002–1020. https://doi.org/10.1631/FITEE.1601401

    Article  Google Scholar 

  38. Zhang J, Ye G, Tu Z, Qin Y, Qin Q, Zhang J, Liu J (2020) A spatial attentive and temporal dilated (satd) gcn for skeleton-based action recognition. CAAI Transactions on Intelligence Technology. https://doi.org/10.1049/cit2.12012

Download references

Author information

Authors and Affiliations

  1. Universidad de Xalapa, Escuela de Ingenierías, Xalapa, Ver, Mexico

    Carolina Maldonado-Mendez

  2. Universidad Veracruzana, Artificial Intelligence Research Institute, Xalapa, Ver, Mexico

    Sergio Hernandez-Mendez

  3. Tecnológico Superior de San Martín Texmelucan, Puebla, Mexico

    Delia Torres-Muñoz

  4. Instituto Tecnológico Superior de Misantla, Doctorado en Ciencias de la Ingeniería, Misantla, Ver, Mexico

    Carlos Hernandez-Mejia

Authors
  1. Carolina Maldonado-Mendez
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sergio Hernandez-Mendez
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Delia Torres-Muñoz
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Carlos Hernandez-Mejia
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Carolina Maldonado-Mendez.

Ethics declarations

Conflict of Interests

The authors, Carolina Maldonado-Mendez, Sergio Hernandez-Mendez, Delia Torres-Muñoz and Carlos Hernandez-Mejia, declare that they have 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

Maldonado-Mendez, C., Hernandez-Mendez, S., Torres-Muñoz, D. et al. Fall detection using features extracted from skeletal joints and SVM: Preliminary results. Multimed Tools Appl 81, 27657–27681 (2022). https://doi.org/10.1007/s11042-022-12405-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12405-1

Keywords