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.

References

[1] Ahmed N., “A System for 360 Acquisition and 3D Animation Reconstruction using Multiple RGB-D Cameras,” in Proceedings of the 25th International Conference on Computer Animation and Social Agents, pp. 1-4, 2012.

[2] Albinali F., Goodwin M., and Intille S., “Recognizing Stereotypical Motor Movements in the Laboratory and Classroom: A Case Study with Children on the Autism Spectrum,” in Proceedings of the 11th International Conference on Ubiquitous Computing, Florida, pp. 71-80, 2009.

[3] Berger K., “A State of the Art Report onMultiple RGB-D Sensor Research and on Publicly Available RGB-D Datasets,” Computer Vision and Machine Learning with RGB-D Sensors, Cham, pp. 27-44, 2014.

[4] Berger K., Meister S., Nair R., and Kondermann D., “A State of The Art Report on Kinect Sensor Setups In Computer Vision,” in Proceedings of Time-of-Flight and Depth Imaging, Berlin, pp. 257-272, 2013

[5] Dubois A., Dib A., and Charpillet F., “Using HMMs for Discriminating Mobile From Static Objects in A 3D Occupancy Grid,” in Proceedings of IEEE 23rd International Conference on Tools with Artificial Intelligence, Boca Raton, pp. 170-176, 2011.

[6] El-Hoseiny M. and Shaban E., “Muslim Prayer Actions Recognition,” in Proceedings of 2nd International Conference on Computer and Electrical Engineering, Dubai, pp. 460-465, 2009.

[7] Hossny M., Filippidis D., Abdelrahman W., Mullins J., Creighton D., and Nahavandi S., “Low Cost Multimodal Facial Recognition Via Kinect Sensors,” in Proceedings of the Land Warfare Conference Potent Land Force for A Joint Maritime Strategy, Melbourne, pp. 77-86, 2012.

[8] Ibrahim F. and Ahmad S., “Assessment of Upper Body Muscle Activity During Salat and Stretching Exercise: A Pilot Study,” in Proceedings of IEEE-EMBS International Conference on Biomedical and Health Informatics, Hong Kong, pp. 412-415, 2012.

[9] Jaafar N., Ismail N., and Yusoff Y., “An Investigation of Motion Tracking For Solat Movement With Dual Sensor Approach,” Journal of Engineering and Applied Sciences, vol. 10, no. 23, pp. 17981-17985, 2015.

[10] Kim J., Choi J., and Koo B., “Calibration of Multi-Kinect and Multi-Camera Setup for Full 3D Reconstruction,” IEEE ISR, Seoul, pp. 2-6, 2013.

[11] Krishnan C., Washabaugh E., and Seetharaman Y., “A Low Cost Real-Time Motion Tracking Approach Using Webcam Technology,” Journal Biomech, vol. 48, no. 3, pp. 544-548, 2015.

[12] Martínez-Contreras F., Orrite-Uruñuela C., Herrero-Jaraba E., Ragheb H., and Velastin S., “Recognizing Human Actions Using Silhouette- Based HMM,” in Proceedings of 6th IEEE International Conference on Advanced Video and Signal Based Surveillance, Genova, pp. 43-48, 2009.

[13] Mendoza M. and De La Blanca N., “HMM- Based Action Recognition Using Contour Optimal Dual Cameras Setup for Motion Recognition in Salat Activity 1089 Histograms,” in Proceedings of Iberian Conference on Pattern Recognition and Image Analysis, Berlin, pp. 394-401, 2007.

[14] Patsadu O., Watanapa B., Dajpratham P., and Nukoolkit C., “Fall Motion Detection with Fall Severity Level Estimation by Mining Kinect 3D Data Stream,” The International Arab Journal of Information Technology, vol. 15, no. 3, pp. 378- 388, 2018.

[15] Piyathilaka L. and Kodagoda S., “Gaussian Mixture Based HMM for Human Daily Activity Recognition Using 3D Skeleton Features,” in Proceedings of IEEE 8th Conference on Industrial Electronics and Applications, Melbourne, pp. 567-572, 2013.

[16] Reza M., Urakami Y., and Mano Y., “Evaluation Of A New Physical Exercise Taken From Salat (Prayer) As A Short-Duration and Frequent Physical Activity in the Rehabilitation of Geriatric and Disabled Patients,” Annals of Saudi Medicine, vol. 22, no. 3-4, pp. 177-180, 2002.

[17] Saputra M., Widyawan., Putra G., and Santosa I., “Indoor Human Tracking Application Using Multiple Depth-Cameras,” in Proceedings of International Conference on Advanced Computer Science and Information Systems, Depok, pp. 3- 8, 2012.

[18] Satta R., Pala F., Fumera G., and Roli F., “Real- Time Appearance-Based Person Re- Identification Over Multiple Kinecttm Cameras,” in Proceedings of 8th International Conference on Computer Vision Theory and Applications VISAPP, Barcelona, pp. 407-410. 2013.

[19] Varkey J., Pompili D., and Walls T., “Human Motion Recognition Using A Wireless Sensor- Based Wearable System,” Personal and Ubiquitous Computing, vol. 16, no. 7, pp. 897- 910, 2011.

[20] Xu W. and Lee E., “Continuous Gesture Recognition System Using Improved HMM Algorithm Based on 2D and 3D Space,” International Journal of Multimedia and Ubiquitous Engineering, vol. 7, no. 2, pp. 335- 340, 2012.

[21] Yeung K., Kwok T., and Wang C., “Improved Skeleton Tracking by Duplex Kinects : A Practical Approach for Real-Time Applications,” Journal of Computing and Information Science in Engineering, vol. 13, no. 4, pp. 1-10, 2013.

[22] Yin Y. and Davis R., “Gesture Spotting and Recognition Using Salience Detection and Concatenated Hidden Markov Models,” in Proceedings of the 15th ACM on International Conference on Multimodal Interaction, Sydney, pp. 489-494, 2013.

[23] Zhang L., Sturm J., Cremers D., and Lee D., “Real-Time Human Motion Tracking Using Multiple Depth Cameras,” in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Vilamoura, pp. 2389-2395, 2012. Nor Azrini Jaafar received her bachelor’s Degree in computer science from Universiti Teknologi Malaysia in 2012. Currently, she is doing PhD in Human Computer Interaction (HCI). Her research interests include Human Computer Interaction, motion recognition and machine learning. Nor Azman Ismail received his BSc from Universiti Teknologi Malaysia, Master of Information Technology from Universiti Kebangsaan Malaysia, and PhD in the field of Human Computer Interaction (HCI) from Loughborough University. He has been a lecturer at the Faculty of Computing, Universiti Teknologi Malaysia for more than twenty years. He has made various contributions to the field of Human Computer Interaction (HCI) including research, practice, and education. Kamarul Azmi Jasmi receive his first degree in Islamic Education and Master of Art (Civilization Studies) from Universiti Malaya, and PhD (Islamic Education) from Universiti Kebangsaan Malaysia. He has been a lecturer at Faculty of Islamic Civilization for about nineteen years. Currently, he has made various contributions to field of the Islamic Education in Malaysia as an author, researcher and editor members. Yusman Azimi Yusoff received his bachelor’s Degree in computer science from Universiti Teknologi Malaysia in 2013. Currently, he is doing PhD in scientific visualization. His research interests include machine learning, data visualization and Internet-of-Things.