ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Optimal Dual Cameras Setup for Motion Recognition in Salat Activity

Journal: The International Arab Journal of Information Technology (Vol.16, No. 6)

Publication Date:

Authors : ; ; ; ;

Page : 1082-1089

Keywords : Motion recognition; Salat activity; Multisensor; Hidden Markov model; Human-Computer Interaction.;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Motion recognition has received significant attention in recent years in the area of computer vision since it has a wide range of potential application that can be developed. A wide variety of algorithms and techniques were proposed in the context of developing human motion recognition systems. This paper investigated optimal dual sensors setup in motion recognition for salat activity by using multisensor which has remained unexplored. Existing works in the related field are able to recognise few salat movements, but not from the multisensor perspective which is important for better recognition and analytic results. This research proposed a solution that is relevant to the current scenario where we deal with one of the fundamental activities required for every Muslim which is salat. Not only carrying out salat with the right actions will help strengthen our relationship with Allah Subhanahu Wa Taʿala (SWT), but also enable the formation of a positive personality, mental well-being, and physical health. Firstly, this research identified the best position setup of a dual sensor. Then, Hidden Markov Model was used to classify all movements in salat activity and the data were trained before the testing phase. This study led to a new way of learning for salat activity which can be further explored and developed. This research contributed a new way of learning by incorporating new interaction in human computer interaction. The outcome of this research will be very useful in validating the salat movements of every Muslim.

Last modified: 2019-11-11 21:53:02