A Computer Vision-Based System for Stride Length Estimation using a Mobile Phone Camera

Conditions such as Parkinson's disease (PD), a chronic neurodegenerative disorder which severely affects the motor system, will be an increasingly common problem for our growing and aging population. Gait analysis is widely used as a noninvasive method for PD diagnosis and assessment. However, current clinical systems for gait analysis usually require highly specialized cameras and lab settings, which are expensive and not scalable. This paper presents a computer vision-based gait analysis system using a camera on a common mobile phone. A simple PVC mat was designed with markers printed on it, on which a subject can walk whilst being recorded by a mobile phone camera. A set of video analysis methods were developed to segment the walking video, detect the mat and feet locations, and calculate gait parameters such as stride length. Experiments showed that stride length measurement has a mean absolute error of 0.62 cm, which is comparable with the "gold standard" walking mat system GAITRite. We also tested our system on Parkinson's disease patients in a real clinical environment. Our system is affordable, portable, and scalable, indicating a potential clinical gait measurement tool for use in both hospitals and the homes of patients.

[1]  Z. Hocenski,et al.  Improved Canny Edge Detector in Ceramic Tiles Defect Detection , 2006, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics.

[2]  Camila Torriani-Pasin,et al.  Effect of Kinect games on postural control of patients with Parkinson's disease , 2015, REHAB.

[3]  Surachai Ongkittikul,et al.  Real-Time Bilateral Filtering Using GPGPU , 2015 .

[4]  Lu Yang,et al.  A B-spline curve extension algorithm , 2016 .

[5]  Maria Petrou,et al.  Image processing - the fundamentals , 1999 .

[6]  R. McDonald,et al.  CIE94‐a new colour‐difference formula* , 2008 .

[7]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[8]  Sos S. Agaian,et al.  An improved canny edge detection application for asphalt concrete , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[9]  Adrian Hilton,et al.  A survey of advances in vision-based human motion capture and analysis , 2006, Comput. Vis. Image Underst..

[10]  Christopher G. Goetz Chairperson,et al.  Movement Disorder Society Task Force report on the Hoehn and Yahr staging scale: Status and recommendations The Movement Disorder Society Task Force on rating scales for Parkinson's disease , 2004 .

[11]  Soumik Mondal,et al.  A study on human gait analysis , 2012, CCSEIT '12.

[12]  Aleksandar Milenkovic,et al.  Quantifying Timed-Up-and-Go test: A smartphone implementation , 2013, 2013 IEEE International Conference on Body Sensor Networks.

[13]  Honey Gupta,et al.  Implementation of Gaussian and Box Kernel Based Approximation of Bilateral Filter Using OpenCL , 2015, 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[14]  Jieqing Tan,et al.  Least square geometric iterative fitting method for generalized B-spline curves with two different kinds of weights , 2015, The Visual Computer.

[15]  Shanwen Zhang,et al.  Gait Image Segmentation Based Background Subtraction , 2015, ICIC.

[16]  Yu Wang,et al.  Medical image processing by denoising and contour extraction , 2008, 2008 International Conference on Information and Automation.

[17]  Hong Shan Neoh,et al.  Adaptive Edge Detection for Real-Time Video Processing using FPGAs , 2005 .

[18]  G. Farin.  Curves and Surfaces for Cagd: A Practical Guide , 2001 .

[19]  HiltonAdrian,et al.  A survey of advances in vision-based human motion capture and analysis , 2006 .

[20]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[21]  Narendra Ahuja,et al.  Constant Time Median and Bilateral Filtering , 2014, International Journal of Computer Vision.

[22]  Yongmin Kim,et al.  Integrating region growing and edge detection using regularization , 1995, Medical Imaging.

[23]  D. W. Chinchkhede,et al.  IMAGE SEGMENTATION IN VIDEO SEQUENCES USING MODIFIED BACKGROUND SUBTRACTION , 2012 .

[24]  Ye Wang,et al.  Validating an iOS-based Rhythmic Auditory Cueing Evaluation (iRACE) for Parkinson's Disease , 2014, ACM Multimedia.

[25]  Luigi Cinque,et al.  Run-Based Algorithms for Binary Image Analysis and Processing , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Javier Cudeiro,et al.  Temporal variability of gait in Parkinson disease: effects of a rehabilitation programme based on rhythmic sound cues. , 2005, Parkinsonism & related disorders.

[27]  Dmitry Korotkin,et al.  Inertial Measurement System for Human Gait Analysis , 2013, BODYNETS.

[28]  Jun-Hai Yong,et al.  A B-spline curve extension algorithm , 2015, Science China Information Sciences.

[29]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  François Charpillet,et al.  A gait analysis method based on a depth camera for fall prevention , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[31]  S. Hamid Nawab,et al.  Dynamic neural network detection of tremor and dyskinesia from wearable sensor data , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[32]  Guojin Wang,et al.  Constructing iterative non-uniform B-spline curve and surface to fit data points , 2004, Science in China Series : Information Sciences.

[33]  Mark Latt,et al.  Reliability of the GAITRite walkway system for the quantification of temporo-spatial parameters of gait in young and older people. , 2004, Gait & posture.

[34]  Chang Yuqing.  An Improved Canny Algorithm for Edge Detection , 2007 .

[35]  Yonina C. Eldar,et al.  Interpolation with nonuniform B-splines , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.