Miniature Crane Prototype: A Novel Approach for Recognizing Yoga Postures to Treat Autistic Children

Abstract

The paper presents a miniature crane prototype including a deep learning model especially designed for autistic children to assist them by teaching yoga. The objective of the paper is to propose a solution to help autistic kids overcome their difficulties faced in their local environment and adapt themselves to society for their well-being. Autistic kids find it hard to involve in social communications and feel insecure to talk with unknown people. Also, some of the kids have repetitive behaviors. To propose a solution, we introduce a miniature crane prototype to assist children in teaching yoga by which autistic kids can overcome their social difficulties. Play can create a positive impact on children during the learning phase and get rid of their difficulties. The play will take the input of the user and react accordingly. The miniature is mobile to get closer and playable with children by Responsive incorporation. The miniature can capture pictures depicting the behavior of the kid and respond to the kid through the LCD screen. The play enhances the activity of the kid and motivates them to learn yoga. The play is included with a yoga detection model which helps the play assist kids in learning yoga. The deep learning algorithm AlexNet is used which can detect and instruct while learning yoga. The model achieves higher accuracy of 98.61% which helps in assisting yoga postures the children with the proper instructions.