A wireless laser sensor web for human gait disorder recognition based on the Buffons needle model

This paper presents a wireless laser sensing system based on the Buffon's needle model for human gait recognition. This research aims to develop a minimalist sensing system for gait disorder recognition based on integral geometry theories. In this study, each gait is modeled as a pair of rotating sticks (i.e. arms and legs). The wireless laser sensing system includes laser modules, photo detectors, and wireless motes. The subject interrupting the laser beams can be detected by the photo detectors. The two-bit binary data stream generated by intersections between arms/legs and laser beams are utilized to identify human gait disorders. Three statistical parameters are chosen as signal features: (1) correlation between two binary streams, (2) temporal correlation of each binary stream, and (3) intersection probability of arms/legs and laser beams. These three parameters are orthogonal to each other and can constitute a well-conditioned feature space. Metrics of symmetry, coordination, and balance are defined to describe the degree of gait disorders. The initial experiments results have demonstrated the gait recognition capability by using such a laser sensor web with high data efficiency and energy efficiency.

[1]  Qi Hao,et al.  Buffon's needle model based walker recognition with distributed binary sensor networks , 2012, 2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[2]  L. Santaló.  Integral geometry and geometric probability , 1976 .

[3]  Kwang Suk Park,et al.  Gait analysis for freezing detection in patients with movement disorder using three dimensional acceleration system , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[4]  George A. Bekey,et al.  Toward a more comprehensive gait disorder analysis expert system , 1989, Conference Proceedings., IEEE International Conference on Systems, Man and Cybernetics.

[5]  Shun-ichi Amari,et al.  Information geometry on hierarchy of probability distributions , 2001, IEEE Trans. Inf. Theory.

[6]  Tieniu Tan,et al.  Human identification based on gait , 2005, The Kluwer international series on biometrics.

[7]  Sudeep Sarkar,et al.  Improved gait recognition by gait dynamics normalization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.