High performance inventive system for gait automation and detection of physically disabled persons

Physically challenged persons may face many difficulties in the present modern environment as most of the commercial facilities and utilities for a day to day life is designed for normal people to lead a sophisticated life. Particularly, people with physically disabilities face struggles in escalators in malls and public transportation places. It is very difficult for the disabled individual to be identified as one among in a large crowd and they normally feel unconformable to step inside in a running escalator. This research work proposes a novel method to identify the physically challenged persons from a large crowd by their nature of legs, walking pattern and hand sticks and provide necessary preference for them to get inside the escalators. Gait automation and detection mechanism is used for person identification for all gait events and deep learning-based neural network (DNN) is used for learning the patterns and making the system to automatically identify the physically challenged. Experimental results show that the proposed system automatically measures all the angle of gait events with an accuracy level of 95.4% and thus offers a cost effective solution for gait kinematic analysis for disabled peoples.