Human activity recognition from skeleton poses

Human Action Recognition is an important task of Human Robot Interaction as cooperation between robots and humans requires that artificial agents recognise complex cues from the environment. A promising approach is using trained classifiers to recognise human actions through sequences of skeleton poses extracted from images or RGB-D data from a sensor. However, with many different data-sets focused on slightly different sets of actions and different algorithms it is not clear which strategy produces highest accuracy for indoor activities performed in a home environment. This work discussed, tested and compared classic algorithms, namely, support vector machines and k-nearest neighbours, to 2 similar hierarchical neural gas approaches, the growing when required neural gas and the growing neural gas.

[1]  T. Ingall,et al.  Stroke telemedicine. , 2009, Mayo Clinic proceedings.

[2]  Alexei A. Efros,et al.  Unbiased look at dataset bias , 2011, CVPR 2011.

[3]  Daniela Berg,et al.  Early diagnosis of Parkinson's disease. , 2010, International review of neurobiology.

[4]  A. Farmer,et al.  Interactive telemedicine: effects on professional practice and health care outcomes. , 2015, The Cochrane database of systematic reviews.

[5]  T. Masud,et al.  Epidemiology of falls. , 2001, Age and ageing.

[6]  Gian Franco Gensini,et al.  The future of telemedicine for the management of heart failure patients: a Consensus Document of the Italian Association of Hospital Cardiologists (A.N.M.C.O), the Italian Society of Cardiology (S.I.C.) and the Italian Society for Telemedicine and eHealth (Digital S.I.T.) , 2017, European heart journal supplements : journal of the European Society of Cardiology.

[7]  J. Winkler,et al.  Unbiased and Mobile Gait Analysis Detects Motor Impairment in Parkinson's Disease , 2013, PloS one.

[8]  Stefan Wermter,et al.  Human Action Recognition with Hierarchical Growing Neural Gas Learning , 2014, ICANN.

[9]  Cristiano Premebida,et al.  A probabilistic approach for human everyday activities recognition using body motion from RGB-D images , 2014, The 23rd IEEE International Symposium on Robot and Human Interactive Communication.

[10]  S. Berry,et al.  Falls: Epidemiology, pathophysiology, and relationship to fracture , 2008, Current osteoporosis reports.

[11]  Stefan Wermter,et al.  Self-organizing neural integration of pose-motion features for human action recognition , 2015, Front. Neurorobot..

[12]  C. B. Cooper,et al.  Respiratory applications of telemedicine , 2009, Thorax.

[13]  Paolo Dario,et al.  A Human Activity Recognition System Based on Dynamic Clustering of Skeleton Data , 2017, Sensors.

[14]  Jing Zhang,et al.  RGB-D-based action recognition datasets: A survey , 2016, Pattern Recognit..

[15]  Bart Selman,et al.  Unstructured human activity detection from RGBD images , 2011, 2012 IEEE International Conference on Robotics and Automation.

[16]  Ennio Gambi,et al.  A Human Activity Recognition System Using Skeleton Data from RGBD Sensors , 2016, Comput. Intell. Neurosci..

[17]  Stephen R. Marsland,et al.  A self-organising network that grows when required , 2002, Neural Networks.

[18]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[19]  Cesar H. Comin,et al.  A Systematic Comparison of Supervised Classifiers , 2013, PloS one.

[20]  Angelo Cangelosi,et al.  Implementation of a Modular Growing When Required Neural Gas Architecture for Recognition of Falls , 2016, ICONIP.

[21]  Deepu Rajan,et al.  Human activities recognition using depth images , 2013, MM '13.

[22]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[23]  Srinivas Akella,et al.  3D human action segmentation and recognition using pose kinetic energy , 2014, 2014 IEEE International Workshop on Advanced Robotics and its Social Impacts.

[24]  Antonio Fernández-Caballero,et al.  A survey of video datasets for human action and activity recognition , 2013, Comput. Vis. Image Underst..

[25]  B. Bogin,et al.  Leg Length, Body Proportion, and Health: A Review with a Note on Beauty , 2010, International journal of environmental research and public health.

[26]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[27]  Yoram Singer,et al.  Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers , 2000, J. Mach. Learn. Res..