Person Re-identification Using 3D Data Analysis Method and Kinect Sensor

Authors

  • Wisrut Kwankhoom Department of Electrical and Computer Engineering, Faculty of Engineering, Naresuan University, Phitsanulok 65000, Thailand.
  • Paisarn Muneesawang Department of Electrical and Computer Engineering, Faculty of Engineering, Naresuan University, Phitsanulok 65000, Thailand.

Keywords:

Personal Identification, Gesture Recognition, IDTW, Kinect Camera, Computer Visions.,

Abstract

Automated personal identification systems, such as personal facial recognition systems and automated motor vehicle registration number checking, are examples of public security protection systems. The area of personal identification for security purposes is of growing interest for security assessment in public places, and airports, as examples, now becoming an imperative matter for research in the Internet netscape. We propose a method of immediate recognition of a subject person, based on Incremental Dynamic Time Warping (IDTW) which identifies personal gait patterns recorded via a 3D depth sensing camera such as in Microsoft’s Kinect® version 2, by analyzing a dataset of gait gestures derived from a sample of 16 people. The experimental results show that the IDTW algorithm increases the efficiency of recognizing at 81%.

References

Fothergill, S., Mentis, H., Kohli, P. and Nowozin, S. Instructing people for training gestural interactive systems. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, (2012).

Maquet, Paul GJ. Biomechanics of the knee: with application to the pathogenesis and the surgical treatment of osteoarthritis. Springer Science & Business Media, (2012).

Dikovski, Bojan, Gjorgji Madjarov, and Dejan Gjorgjevikj. Evaluation of different feature sets for gait recognition using skeletal data from Kinect. Information and Communication Technology, Electronics and Microelectronics (MIPRO), 37th International Convention on. IEEE, (2014).

Iosifidis, Alexandros, Anastasios Tefas, Nikolaos Nikolaidis, and Ioannis Pitas. Multi-view human movement recognition based on fuzzy distances and linear discriminant analysis. Computer Vision and Image Understanding, 116.3 (2012): 347-360.

Munsell, B. C., Temlyakov, A., Qu, C., and Wang, S. Person identification using full-body motion and anthropometric biometrics from kinect videos. In Computer Vision–ECCV 2012. Workshops and Demonstrations. Springer Berlin Heidelberg, (2012) 91-100.

Naimul Mefraz Khan, Stephen Lin, Ling Guan, and Baining Guo. A Visual Evaluation Framework for In-Home Physical Rehabilitation. IEEE International Symposium on Multimedia, (2014).

M. Kyan, G. Sun, H. Li, L. Zhong, P. Muneesawang, N. Dong, B. Elder, and L. Guan, An Approach to Ballet Dance Training through MS Kinect and Visualization in a CAVE Virtual Reality Environment.Special Issue on Visual Understanding with RGB-D Sensors, ACM Transactions on Intelligent Systems and Technology (TIST), Vol. 6(2), Article ID 23 (2015).

W. Kwankhoom and P. Muneesawang. Recognition of Standard Thai Traditional Dance Through 3D Data Analysis. Naresuan University Engineering Journal, Vol.11, No.2 (2016) 75-84.

Microsoft Developer Network. JointType Enumeration. Available at https://msdn.microsoft.com/enus/library/microsoft.kinect.jointtype.aspx. Accessed Nov 11, (2016).

Miguel Reyes, Gabriel Dominguez, and Sergio Escalera. Feature Weighting in Dynamic Time Warping for Gesture Recognition in Depth Data. IEEE International Conference on Computer Vision,(2011).

Downloads

Published

2017-06-01

How to Cite

Kwankhoom, W., & Muneesawang, P. (2017). Person Re-identification Using 3D Data Analysis Method and Kinect Sensor. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 9(2-5), 151–154. Retrieved from https://jtec.utem.edu.my/jtec/article/view/2416