Joint-angle-based yoga posture
recognition for prevention of falls
among older people
Department of MCA, Kalasalingam University,
Srivilliputhur, India, and
School of Computing, Kalasalingam University, Srivilliputhur, India
Purpose –United Nations’World Population Ageing Report states that falls are one of the most common
problems in the elderl y around the world. Falls are a leading cause of mo rbidity and mortality among
mature adults, and the second leading cause of accidental or unintentional injury/death after road traffic
injuries. The rates are h igher in hospitalized p atients and nursing hom e residents. Major cont ributing
reasons for falling a re loss of footing or tra ction, balance proble m in carpets and rugs, r educed muscle
strength, poor vision, mobility/gait, cogn itive impairment: in ot her words lack of balance . Balance
can be improved by the practice of yog a which helps to balance both body and mind t hrough a series of
physical postures call ed asanas, breathing co ntrol and meditation. El ders, especially wome n, are often
unable to practice yoga r egularly, largely brought on by a feeling of disc omfort at having to do so in full
public view, preferring instead to have private sessions at home, and at leisure. A computer-assisted
self-learning syste m can be developed to help suc h elders, though imprope r training and the postur es
associated with it may harm th e body’s muscles and ligaments. To havea flawless system it is essential to
classify asanas, and id entify the one the practitioner is currently practici ng, following which the system ca n
offer the guidance necessary. The purpose of this paper is to propose a posture recognition system,
especially of sitting a nd standing postures . Asanas are chiefly cla ssified into two: sittin g and standing
postures. This study h elps to decide the values of the parameters for classifica tion, which involve the hip
and joint angles.
Design/methodology/approach –To model human bodies, skeleton parts such as head, neck (which are
responsible for head movements), arms, hands (to decide on hand postures), and legs and feet (for standing
posture identification) have been modeled and stored as a vector. Each feature is defined as a set of movable
joints. Every interaction among the skeleton joints defines an action. Human skeletal information may be
represented as a hierarchy of joints, in a parent–child relationship. So that whenever there is a change in joint
its corresponding parent joint may also be altered.
Findings –The findings have to do with analyzi ng the reasons for falls in the elderly and their need for
yoga as a precautiona ry measure. As yoga is ideally suited to self-assis ted learning, it is feasible t o design a
system that assists pe ople who do not wish to pra ctice yoga in public. H owever, asanas are to be
classified prior to doi ng so. In this paper, the aut hors have designed a po sture identificatio n framework
comprising the sitting and s tanding postures that are fun damental to all yoga asanas, us ing joint angle
measurements. Havin g fixed joint angle values is not possibl e, given the variations in angle values amo ng
the participants. Co nsequently, such paramete rs as the hip joint and knee angle s are to be specified in range
for a classification of asanas.
Research limitations/implications –This work identifies the angle limits of standing and sitting
postures so as to design a self-assisting system for yoga. Yoga asanas are classified and tested to enable their
accurate identification. Extensive testing with older people is needed to assess the system.
Practical implications –The increase in the population of the elderly, coupled with their need for medical
care, is a major concern worldwide. As older people are reluctant to practice yoga in public, it is anticipated
that the proposed system will motivate them to do so at their convenience, and in the seclusion of their homes.
Social implications –As older people are reluctant to adapt as well as practice yoga in public view, the
proposal motivates and helps them to carry out yoga practices at their convenience.
Originality/value –This paper fulfills the initial study on the need and feasibility of creating a self-assisted
yoga learning system. To identify postures and classify them joint angles are used; their range of motion has
been calculated in order to set them as parameters of classification.
Keywords Falls, Yoga, Cognitive impairment, Assisted learning, Joint angle, Posture recognition
Paper type Research paper
Data Technologies and
Vol. 53 No. 4, 2019
© Emerald PublishingLimited
Received 19 March 2019
Revised 5 August 2019
Accepted 3 September 2019
The current issue and full text archive of this journal is available on Emerald Insight at: