Vision-based gait impairment analysis for aided diagnosis

  • Javier Ortells
  • María Trinidad Herrero-Ezquerro
  • Ramón A. Mollineda
Original Article


Gait is a firsthand reflection of health condition. This belief has inspired recent research efforts to automate the analysis of pathological gait, in order to assist physicians in decision-making. However, most of these efforts rely on gait descriptions which are difficult to understand by humans, or on sensing technologies hardly available in ambulatory services. This paper proposes a number of semantic and normalized gait features computed from a single video acquired by a low-cost sensor. Far from being conventional spatio-temporal descriptors, features are aimed at quantifying gait impairment, such as gait asymmetry from several perspectives or falling risk. They were designed to be invariant to frame rate and image size, allowing cross-platform comparisons. Experiments were formulated in terms of two databases. A well-known general-purpose gait dataset is used to establish normal references for features, while a new database, introduced in this work, provides samples under eight different walking styles: one normal and seven impaired patterns. A number of statistical studies were carried out to prove the sensitivity of features at measuring the expected pathologies, providing enough evidence about their accuracy.

Graphical Abstract

Graphical abstract reflecting main contributions of the manuscript: at the top, a robust, semantic and easy-to-interpret feature set to describe impaired gait patterns; at the bottom, a new dataset consisting of video-recordings of a number of volunteers simulating different patterns of pathological gait, where features were statistically assessed.


Gait impairment Video-based gait analysis Gait database Computer-aided diagnosis 



The authors would like to thank the staff at Communication Sciences Laboratory (LABCOM) of Univ. Jaume I for their help in using these facilities.

Funding information

This work has been supported by grants P1-1B2015-74 and PREDOC/2012/05 from Univ. Jaume I, and TIN2013-46522-P from Spanish Ministry of Economy and Competitiveness.


  1. 1.
    Altilio R, Paoloni M, Panella M (2017) Selection of clinical features for pattern recognition applied to gait analysis. Med Biol Eng Comput 55(4):685–695CrossRefPubMedGoogle Scholar
  2. 2.
    Chen WL, O’Connor JJ, Radin EL (2003) A comparison of the gaits of chinese and caucasian women with particular reference to their heelstrike transients. Clinic Biomech 18(3):207–213CrossRefGoogle Scholar
  3. 3.
    Eltoukhy M, Kuenze C, Oh J, Wooten S, Signorile J (2017) Kinect-based assessment of lower limb kinematics and dynamic postural control during the star excursion balance test. Gait Post 58:421–427CrossRefGoogle Scholar
  4. 4.
    Eltoukhy M, Oh J, Kuenze C, Signorile J (2017) Improved kinect-based spatiotemporal and kinematic treadmill gait assessment. Gait Post 51:77–83CrossRefGoogle Scholar
  5. 5.
    Goetz CG, Tilley BC, Shaftman SR et al (2008) Movement disorder society-sponsored revision of the unified Parkinson’s disease rating scale (MDS-UPDRS): Scale presentation and clinimetric testing results. Mov Disord 23(15):2129–2170CrossRefPubMedGoogle Scholar
  6. 6.
    González I, López-Nava IH, Fontecha J et al (2016) Comparison between passive vision-based system and a wearable inertial-based system for estimating temporal gait parameters related to the GAITRite electronic walkway. J Biomed Inform 62(C):210–223CrossRefPubMedGoogle Scholar
  7. 7.
    González I, Nieto-Hidalgo M, Mora J et al (2015) A dual approach for quantitative gait analysis based on vision and wearable pressure systems. LNCS 9455:206–218Google Scholar
  8. 8.
    Han J, Bhanu B (2006) Individual recognition using gait energy image. IEEE Trans Pattern Anal Mach Intell 28(2):316–322CrossRefPubMedGoogle Scholar
  9. 9.
    Hase K (2008) A computer simulation study on the causal relationship between walking and physical malfunctions in older adults. Anthropol Sci J Anthropol Soc Nippon 116(2):95–104Google Scholar
  10. 10.
    Kim A, Kim J, Rietdyk S, Ziaie B (2015) A wearable smartphone-enabled camera-based system for gait assessment. Gait Post 42(2):138–144CrossRefGoogle Scholar
  11. 11.
    Lau HY, Tong KY, Zhu H (2008) Support vector machine for classification of walking conditions using miniature kinematic sensors. Med Biol Eng Comput 46(6):563–573CrossRefPubMedGoogle Scholar
  12. 12.
    Lin SH, Chen SW, Lo YC et al (2016) Quantitative measurement of parkinsonian gait from walking in monocular image sequences using a centroid tracking algorithm. Med Biol Eng Comput 54(2):485–496CrossRefPubMedGoogle Scholar
  13. 13.
    López-Nava IH, Muñoz-Meléndez A, Pérez-SanPablo AI et al (2015) Estimation of temporal gait parameters using bayesian models on acceleration signals. Comput Methods Biomech Biomed Engin 19(4):396–403CrossRefPubMedGoogle Scholar
  14. 14.
    Ma HI, Hwang WJ, Lin KC (2009) The effects of two different auditory stimuli on functional arm movement in persons with Parkinson’s disease: a dual-task paradigm. Clin Rehabil 23(3):229–237CrossRefPubMedGoogle Scholar
  15. 15.
    Makihara Y, Mannami H, Tsuji A et al (2012) The OU-ISIR gait database comprising the treadmill dataset. IPSJ Trans Comput Vis Appl 4:53–62CrossRefGoogle Scholar
  16. 16.
    Martin CL, Phillips BA, Kilpatrick TJ et al (2006) Gait and balance impairment in early multiple sclerosis in the absence of clinical disability. Multiple sclerosis 12(5):620–628CrossRefPubMedGoogle Scholar
  17. 17.
    Martínez-Martín P, García-Urra D, del Ser-Quijano T et al (1997) A new clinical tool for gait evaluation in Parkinson’s disease. Clin Neuropharmacol 20(3):183–194CrossRefPubMedGoogle Scholar
  18. 18.
    Mun KR, Lim SB, Guo Z et al (2017) Biomechanical effects of body weight support with a novel robotic walker for over-ground gait rehabilitation. Med Biol Eng Comput 55(2):315–326CrossRefPubMedGoogle Scholar
  19. 19.
    Nieto-Hidalgo M, Ferrández-Pastor FJ, Valdivieso-Sarabia RJ et al (2016) A vision based proposal for classification of normal and abnormal gait using RGB camera. J Biomed Inform 63:82–89CrossRefPubMedGoogle Scholar
  20. 20.
    Ortells J, Mollineda RA, Mederos B et al (2017) Gait recognition from corrupted silhouettes: a robust statistical approach. Mach Vis Appl 28(1):15–33CrossRefGoogle Scholar
  21. 21.
    Plotnik M, Giladi N, Balash Y et al (2005) Is freezing of gait in Parkinson’s disease related to asymmetric motor function? Ann Neurol 57(5):656–663CrossRefPubMedGoogle Scholar
  22. 22.
    Raheja JL, Chaudhary A, Nandhini K et al (2015) Pre-consultation help necessity detection based on gait recognition. SIViP 9(6):1357–1363CrossRefGoogle Scholar
  23. 23.
    Rocha AP, Choupina H, Fernandes JM et al (2015) Kinect v2 based system for Parkinson’s disease assessment. In: 37th Annual international conference of the IEEE engineering in medicine and biology society (EMBC’15), pp 1279–1282Google Scholar
  24. 24.
    Saner RJ, Washabaugh EP, Krishnan C (2017) Reliable sagittal plane kinematic gait assessments are feasible using low-cost webcam technology. Gait Post 56:19–23CrossRefGoogle Scholar
  25. 25.
    Spasojević S, Santos-Victor J, Ilić T et al (2015) A vision-based system for movement analysis in medical applications: the example of Parkinson disease. LNCS 9163:424–434Google Scholar
  26. 26.
    Stolze H, Kuhtz-Buschbeck J, Mondwurf C et al (1997) Gait analysis during treadmill and overground locomotion in children and adults. Electroencephalography and Clinical Neurophysiology/Electromyography and Motor Control 105(6):490–497CrossRefPubMedGoogle Scholar
  27. 27.
    Sun B, Zhang Z, Liu X, Hu B, Zhu T (2017) Self-esteem recognition based on gait pattern using kinect. Gait Post 58:428–432CrossRefGoogle Scholar
  28. 28.
    Ṫupa O, Procházka A, Vyṡata O et al (2015) Motion tracking and gait feature estimation for recognising Parkinson’s disease using MS Kinect. Biomed Eng Online 14(1):1–20CrossRefGoogle Scholar
  29. 29.
    Vaughan CL, Davis BL, O’connor JC (1992) Dynamics of human gait. Human Kinetics Publishers, ChampaignGoogle Scholar
  30. 30.
    Wall JC, Turnbull GI (1986) Gait asymmetries in residual hemiplegia. Arch Phys Med Rehab 67(8):550–553Google Scholar
  31. 31.
    Wang J, She M, Nahavandi S et al (2010) A review of vision-based gait recognition methods for human identification. In: International conference on digital image computing: techniques and applications (DICTA’10), pp 320–327Google Scholar
  32. 32.
    Wang L (2006) Abnormal walking gait analysis using silhouette-masked flow histograms. In: 18th International conference on pattern recognition (ICPR’06), vol 3, pp 473–476Google Scholar
  33. 33.
    Yogev G, Plotnik M, Peretz C et al (2007) Gait asymmetry in patients with Parkinson’s disease and elderly fallers: when does the bilateral coordination of gait require attention? Exper Brain Res 177(3):336–346CrossRefGoogle Scholar
  34. 34.
    Zhou C, Mitsugami I, Yagi Y (2015) Detection of gait impairment in the elderly using patch-GEI. IEEJ Trans Electr Electron Eng 10(S1):S69–S76CrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2018

Authors and Affiliations

  1. 1.Institute of New Imaging TechnologiesUniversitat Jaume ICastellón de la PlanaSpain
  2. 2.School of Medicine, Department of Human Anatomy & PsychobiologyUniversidad de MurciaMurciaSpain

Personalised recommendations