calbta.blogg.se

The proposed framework has been tested against the video clips of children performing arm flapping behavior taken from public dataset. HAR involved in human body detection and the skeleton representation to show the arm asymmetrical in arm flapping movement which indicates the possibility of ASD signs by extracting the body pose into stickman model. We used human action recognition (HAR) algorithm. Thus, we aim to propose a computational framework to semi-automate the diagnosis process. Typically, a standard Repetitive Behavior Scale-Revised (RBSR) - set of questionnaire - used by clinicians for ASD diagnosis usually involved multiple and long sessions that apparently would delay and may have nonconformity. Arm flapping is a good example of a stereotypical behavior of ASD early sign. Unfortunately, the awareness of early sign of Autism Spectrum Disorder (ASD) is still insufficiently provided to the public. Presently, the number of children with autism appears to be growing at disturbing rate. This technique may be considered as a relatively unexplored application area, and the proposed system is an attempt to address the problem with reasonable accuracy and scopes for further research. The results showed that the proposed algorithm gave the overall matching rate of 99.21% with maximum mean success rate of dancers gave 99.68% and non-dancers gave the percentage of 98.76%. For this study, the traditional dance of Zapin was chosen because it consists of simple body movements and data were acquired using Microsoft Kinect.

This paper outlines a new approach to implement Normalize Dynamic Time Warping (NDTW) algorithm using skeleton tracking techniques to imitate the intricate movements of traditional dance and to assess the robustness of the algorithm. However, the use of gesture sensor for accurately mapping the dance movements of traditional dance is not yet explored, since only modern dances are normally available to the masses in the form of computer games.

Recent developments in technology and ever- growing online community, traditional dance are undergoing a revolution where these dance form can be studied and observed easily especially when there are dance software that can help guide users to learn by performing the dance steps in real-time. For example, Zapin, Kuda Kepang, Mak Yong, Joget, Ngajat and much more. Traditional dance in Malaysia is generating considerable amount of interest due to its unique elements of heritage which have contributed to its diverse music and dance forms.