Estimation of Gait Parameters from 3D Pose for Elderly Care

For elderly people, walking, standing up from a chair, turning and leaning are necessary for independent mobility. These mobilities such as gait depends on a complex interplay of major parts of the nervous, musculoskeletal and cardiorespiratory systems. Every individuals gait pattern is influenced by age, personality, mood, sociocultural factors and predominantly the persons health condition. In order to understand the health condition of an elderly person, analysis of gait patterns became an important aspect. Gait parameters such as cadence, step length, step duration etc. analyzed out of gait patterns proved as an important factor in estimation of the healthy daily living. For this purpose, gait data of several elderly individuals is collected many times over a period of time using Kinect sensor. The acquired data consist of RGB image sequences and depth data. From this data, 3D pose of the individual is identified. These 3D poses are used to extract the necessary gait parameters of the individual. The extracted gait parameters will be used in future to assess the health condition of the individual.

[1]  Ioannis A. Kakadiaris,et al.  3D Human pose estimation: A review of the literature and analysis of covariates , 2016, Comput. Vis. Image Underst..

[2]  Joseph T. Gwin,et al.  Motor control and aging: Links to age-related brain structural, functional, and biochemical effects , 2010, Neuroscience & Biobehavioral Reviews.

[3]  P. Rabins,et al.  Dementia , 2008, Annals of Internal Medicine.

[4]  David Picard,et al.  2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  D. Maron,et al.  The Role of Dual Tasking in the Assessment of Gait, Cognition and Community Reintegration of Veterans with Mild Traumatic Brain Injury , 2017, Materia socio-medica.

[6]  Deva Ramanan,et al.  3D Human Pose Estimation = 2D Pose Estimation + Matching , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Yaser Sheikh,et al.  OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Pascal Fua,et al.  Learning Monocular 3D Human Pose Estimation from Multi-view Images , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Cédric Annweiler,et al.  Poor Gait Performance and Prediction of Dementia: Results From a Meta-Analysis. , 2016, Journal of the American Medical Directors Association.

[10]  S. Fritz,et al.  Walking speed: the functional vital sign. , 2015, Journal of aging and physical activity.

[11]  Stephen J. McKenna,et al.  Human Pose Estimation Using Learnt Probabilistic Region Similarities and Partial Configurations , 2004, ECCV.

[12]  Richard Bowden,et al.  Detection and Tracking of Humans by Probabilistic Body Part Assembly , 2005, BMVC.

[13]  W. M. van der Flier,et al.  Epidemiology and risk factors of dementia , 2005, Journal of Neurology, Neurosurgery & Psychiatry.

[14]  Hans-Hellmut Nagel,et al.  Tracking Persons in Monocular Image Sequences , 1999, Comput. Vis. Image Underst..

[15]  Xiaowei Zhou,et al.  Learning to Estimate 3D Human Pose and Shape from a Single Color Image , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Hui Gao,et al.  Gender Recognition from Walking Movements using Adaptive Three-Mode PCA , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[17]  Yichen Wei,et al.  Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[18]  Fei Wang,et al.  Study of gait symmetry quantification and its application to intelligent prosthetic leg development , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[19]  C. Prathap,et al.  Human identification using gait recognition , 2017, 2017 International Conference on Communication and Signal Processing (ICCSP).

[20]  Sidharth Bhatia,et al.  Tracking loose-limbed people , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[21]  Ramakant Nevatia,et al.  Human Pose Tracking in Monocular Sequence Using Multilevel Structured Models , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Xiaowei Zhou,et al.  Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Cordelia Schmid,et al.  Learning to Parse Pictures of People , 2002, ECCV.

[24]  C. Dolea,et al.  World Health Organization , 1949, International Organization.

[25]  R. Gallagher,et al.  The 6MWT: Will Different Methods of Instruction and Measurement Affect Performance of Healthy Aging and Older Adults? , 2013, Journal of geriatric physical therapy.

[26]  Tieniu Tan,et al.  Silhouette Analysis-Based Gait Recognition for Human Identification , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Xiaowei Zhou,et al.  Harvesting Multiple Views for Marker-Less 3D Human Pose Annotations , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Karl Rohr,et al.  Incremental recognition of pedestrians from image sequences , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Pascal Fua,et al.  Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation , 2018, ECCV.

[30]  Olivier Beauchet,et al.  Gait analysis in demented subjects: Interests and perspectives , 2008, Neuropsychiatric disease and treatment.

[31]  Herman Buschke,et al.  Abnormality of gait as a predictor of non-Alzheimer's dementia. , 2002, The New England journal of medicine.

[32]  David C. Hogg.  Model-based vision: a program to see a walking person , 1983, Image Vis. Comput..

[33]  David A. Forsyth,et al.  Strike a pose: tracking people by finding stylized poses , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[34]  C. Billington,et al.  Orexin activation counteracts decreases in nonexercise activity thermogenesis (NEAT) caused by high-fat diet , 2017, Physiology & Behavior.

[35]  Hans-Peter Seidel,et al.  VNect , 2017, ACM Trans. Graph..

[36]  ChewYean Yam,et al.  On the relationship of human walking and running: automatic person identification by gait , 2002, Object recognition supported by user interaction for service robots.

[37]  H. Nagel,et al.  Tracking of persons in monocular image sequences , 1997, Proceedings IEEE Nonrigid and Articulated Motion Workshop.