BACKGROUND: Analysis of gait features provides important information during the treatment of neurological disorders, including Parkinson's disease. It is also used to observe the effects of medication and rehabilitation. The methodology presented in this paper enables the detection of selected gait attributes by Microsoft (MS) Kinect image and depth sensors to track movements in three-dimensional space. METHODS: The experimental part of the paper is devoted to the study of three sets of individuals: 18 patients with Parkinson's disease, 18 healthy aged-matched individuals, and 15 students. The methodological part of the paper includes the use of digital signal-processing methods for rejecting gross data-acquisition errors, segmenting video frames, and extracting gait features. The proposed algorithm describes methods for estimating the leg length, normalised average stride length (SL), and gait velocity (GV) of the individuals in the given sets using MS Kinect data. RESULTS: The main objective of this work involves the recognition of selected gait disorders in both the clinical and everyday settings. The results obtained include an evaluation of leg lengths, with a mean difference of 0.004 m in the complete set of 51 individuals studied, and of the gait features of patients with Parkinson's disease (SL: 0.38 m, GV: 0.61 m/s) and an age-matched reference set (SL: 0.54 m, GV: 0.81 m/s). Combining both features allowed for the use of neural networks to classify and evaluate the selectivity, specificity, and accuracy. The achieved accuracy was 97.2 %, which suggests the potential use of MS Kinect image and depth sensors for these applications. CONCLUSIONS: Discussion points include the possibility of using the MS Kinect sensors as inexpensive replacements for complex multi-camera systems and treadmill walking in gait-feature detection for the recognition of selected gait disorders.

Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Zikova 1903 4 166 36 Prague 6 Czech Republic

Department of Computing and Control Engineering University of Chemistry and Technology Prague Technická 5 166 28 Prague 6 Czech Republic

Department of Neurology Charles University Sokolská 581 500 05 Hradec Kralove Czech Republic

See more in PubMed

Karray F, Alemzadeh M, Saleh JA, Arab MN. Human–computer interaction: overview on state of the art. Int J Smart Sens Intell Sens. 2008;1(1):137–159.

Galna B, Jackson D, Schofield G, McNaney R, Webster M, Barry G, Mhiripiri D, Balaam M, Olivier P, Rochester L. Retraining function in people with Parkinson’s disease using the Microsoft Kinect: game design and pilot testing. J Neuroeng Rehabil. 2014;11(1):1–12. doi: 10.1186/1743-0003-11-1. PubMed DOI PMC

Brscic D, Kanda T, Ikeda T, Miyashita T. Person tracking in large public spaces using 3-D range sensors. IEEE Trans Hum Mach Syst. 2013;43(6):522–534. doi: 10.1109/THMS.2013.2283945. DOI

Han J, Shao L, Xu D, Shotton J. Enhanced computer vision with Microsoft Kinect sensor: a review. IEEE Trans Cybern. 2013;43(5):1318–1344. doi: 10.1109/TCYB.2013.2265378. PubMed DOI

Fortino G, Giannantonio R, Gravina R, Kuryloski P, Jafari R. Enabling effective programming and flexible management of efficient body sensor network applications. IEEE Trans Hum Mach Syst. 2013;43(1):115–133. doi: 10.1109/TSMCC.2012.2215852. DOI

Elgendi M, Picon F, Magnenat-Thalmann N, Abbott D. Arm movement speed assessment via a Kinect camera: a preliminary study in healthy subjects. BioMed Eng OnLine. 2014;13(88):1–14. PubMed PMC

Camplani M, Mantecon T, Salgado L. Depth-color fusion strategy for 3-D scene modeling with Kinect. IEEE Trans Cybern. 2013;43(6):1560–1571. doi: 10.1109/TCYB.2013.2271112. PubMed DOI

Schmitz A, Ye M, Shapiro R, Yang R, Noehren B. Accuracy and repeatability of joint angles measure during a single camera markerless motion capture system. J Biomech. 2014;47:587–591. doi: 10.1016/j.jbiomech.2013.11.031. PubMed DOI

Shum HPH, Ho ESL, Jiang Y, Takagi S. Real-time posture reconstruction for Microsoft Kinect. IEEE Trans Cybern. 2013;43(5):1357–1369. doi: 10.1109/TCYB.2013.2275945. PubMed DOI

Choudry MU, Beach TAC, Callaghan JP, Kulic D. A stochastic framework for movement strategy identification and analysis. IEEE Trans Hum Mach Syst. 2013;43(3):314–327. doi: 10.1109/TSMC.2013.2251629. DOI

Caby B, Kieffer S, Hubert M, Cremer G, Macq B. Feature extraction and selection for objective gait analysis and fall risk assessment by accelerometry. BioMed Eng OnLine. 2011;10(1):1–19. doi: 10.1186/1475-925X-10-1. PubMed DOI PMC

Clark RA, Pua YH, Fortin K, Ritchie C, Webster KE, Denehy L, Bryant AL. Validity of the Microsoft Kinect for assessment of postural control. Gait Posture. 2012;36:372–377. doi: 10.1016/j.gaitpost.2012.03.033. PubMed DOI

Cuaya G, Muñoz-Meléndez A, Carrera LN, Morales EF, Quiñones I, Pérez AI, Alessi A. A dynamic Bayesian network for estimating the risk of falls from real gait data. Med Biol Eng Comput. 2013;51(1–2):29–37. doi: 10.1007/s11517-012-0960-2. PubMed DOI

Clark RA, Bower KJ, Mentiplay BF, Peterson K, Pua YH, Bryant AL. Concurrent validity of the Microsoft Kinect for assessment of spatiotemporal gait variables. J Biomech. 2013;46(15):2772–2775. doi: 10.1016/j.jbiomech.2013.08.011. PubMed DOI

Galna B, Barry G, Jackson D, Mhiripiri D, Olivier P, Rochester L. Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson’s disease. Gait Posture. 2014;39(4):1062–1068. doi: 10.1016/j.gaitpost.2014.01.008. PubMed DOI

Venkat I, De Wilde P. robust gait recognition by learning and exploiting sub-gait characteristics. Int J Comput Vis. 2011;91(1):7–23. doi: 10.1007/s11263-010-0362-6. DOI

Chen YY, Cho CW, Lin SH, Lai HY, Lo YC, Chen SY, Chang YJ, Huang WT, Chen CH, Jaw FS, Tsang S, Tsai ST. A vision-based regression model to evaluate Parkinsonian gait from monocular image sequences. Expert Syst Appl. 2012;39(1):520–526. doi: 10.1016/j.eswa.2011.07.042. DOI

Yogev G, Giladi N, Peretz C, Springer S, Simon ES, Hausdorff JM. Dual tasking, gait rhythmicity, and Parkinson’s disease: which aspects of gait are attention demanding? Eur J Neurosci. 2005;22(5):1248–1256. doi: 10.1111/j.1460-9568.2005.04298.x. PubMed DOI

Xu X, McGorry RW, Lin J, Chang C. Accuracy of the Microsoft KinectTM for measuring gait parameters during treadmill walking. Gait Posture. 2015;42(2):145–151. doi: 10.1016/j.gaitpost.2015.05.002. PubMed DOI

Muro-de-la-Herran A, Zapirain GB, Zorrilla MA. Gait analysis methods: an overview of wearable and non-wearable systems. Highlighting clinical applications. Sensors. 2014;14(2):3362–3394. doi: 10.3390/s140203362. PubMed DOI PMC

Aggarwal CC, editor. Data classification: algorithms and applications. CRC Press, Taylor & Francis Group, Boca Raton; 2015. p. 33487.

Witten IH, Frank E, Hall MA. Data mining: practical machine learning tools and techniques. Burlington: Morgan Kaufmann Publishers; 2011.

Prochazka A, Vysata O, Tupa O, Yadollahi M, Valis M. Discrimination of axonal neuropathy using sensitivity and specificity statistical measures. Neural Comput Appl. 2014;25:1349–1358. doi: 10.1007/s00521-014-1622-0. DOI

Krzeszowski T, Switonski A, Kwolek B, Josinski H, Wojciechowski K. DTW-based gait recognition from recovered 3-D joint angles and inter-ankle distance. Sensors. 2014;8671:356–363.

Jarchi D, Wong C, Kwasnicki RM, Heller B, Tew GA, Yang GZ. Gait parameter estimation from a miniaturized ear-worn sensor using singular spectrum analysis and longest common subsequence. IEEE Trans Biomed Eng. 2014;61(4):1261–1273. doi: 10.1109/TBME.2014.2299772. PubMed DOI

Klempous R. Surface area under the motion curve as a new tool for gait recognition. Comput Aided Syst Theory EUROCAST. 2013;8112:199–208 (Springer, Berlin, Heidelberg).

Zhang Z. Accuracy and resolution of kinect depth data for indoor mapping applications. IEEE Multimed. 2012;19(2):4–10. doi: 10.1109/MMUL.2012.24. PubMed DOI PMC

Qin S, Zhu X, Yang Y. Real-time hand gesture recognition from depth images using convex shape decomposition method. J Signal Proces Syst. 2014;74:47–58. doi: 10.1007/s11265-013-0778-7. DOI

Dutta T. Evaluation of the Kinect sensor for 3-D kinematic measurement in the workplace. Appl Ergon. 2012;43:645–649. doi: 10.1016/j.apergo.2011.09.011. PubMed DOI

Tang J, Luo J, Tjahjadi T, Gao Y. 2.5D multi-view gait recognition based on point cloud registration. Sensors. 2014;14(4):6124–6143. doi: 10.3390/s140406124. PubMed DOI PMC

Lue J, Ying K, Bai J. Savitzky–Golay smoothing and differentiation filter for even 428 number data. Signal Process. 2005;85(7):1429–1434. doi: 10.1016/j.sigpro.2005.02.002. DOI

Schafer RW. What Is a Savitzky–Golay filter? IEEE Signal Process Mag. 2011;28(4):111–117. doi: 10.1109/MSP.2011.941097. DOI

Ruanaidh JJK, Fitzgerald W. Numerical Bayesian methods applied to signal processing. New York: Springer; 1996.

Zweig MH, Campbell G. Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin Chem. 1993;39:561–577. PubMed

Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett. 2006;27:861–874. doi: 10.1016/j.patrec.2005.10.010. DOI

Haykin S. Neural networks and learning machines. New York: Pearson International; 2009.

Mary MS, Raj VJ. Data classification with neural classifier using radial basis function with data reduction using hierarchical clustering. ICTACT J Soft Comput. 2012;2(3):348–352.

Schwenker F, Kestler HA, Palm G. Three learning phases for radial-basis-function networks. Neural Netw. 2002;14:439–458. doi: 10.1016/S0893-6080(01)00027-2. PubMed DOI

Tupa O. Multi-dimensional data modelling and analysis using MS KINECT. PhD thesis, Institute of Chemical Technology in Prague, Master thesis, 2014.

Moore ST, Dilda V, Hakim B, MacDougall HG. Validation of 24-hour ambulatory gait assessment in Parkinson’s disease with simultaneous video observation. BioMed Eng OnLine. 2011;10(82):1–8. PubMed PMC

Sleep Apnea Detection with Polysomnography and Depth Sensors

Microsoft Kinect Visual and Depth Sensors for Breathing and Heart Rate Analysis