JISE


  [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] [14]


Journal of Information Science and Engineering, Vol. 35 No. 6, pp. 1193-1208


Motion Detection with Local Linear Embedding and its Application to Indoor Device- Free Human Trajectory Tracking

HONGLI YU1, GWO-JONG YU2,*, BIN YANG1 AND JINJUN LIU1
1College of Computer and Information Engineering
Chuzhou University
Chuzhou, 239000 P.R. China
2Department of Computer Science and Information Engineering
Aletheia University
New Taipei City, 25103 Taiwan
E-mail: hly@chzu.edu.cn; yugj@mail.au.edu.tw;
ybcup@126.com; jinjunl@chzu.edu.cn

Device-free indoor human trajectory tracking is critical to support health care applications for elderly people. Many device-free localization algorithms depend on expensive hardware to achieve tracking accuracy. In contrast to such algorithms, this paper proposes a new device-free human trajectory tracking algorithm for indoor environments based on channel state information that is extracted from a Wi-Fi network interface card, which is a low-cost component. The proposed algorithm first uses the characteristics of locally linear embedding to detect whether a person is moving and applies quadratic discriminant analysis to determine the new location of the person. The determined locations of the person are connected to form a trajectory. Experimental results revealed that the proposed algorithm provides an effective solution for passive human trajectory tracking.

Keywords: device-free localization, trajectory tracking, channel state information, Wi-Fi, local linear embedding algorithm

  Retrieve PDF document (JISE_201906_02.pdf)