Name
Abstract | ||
|---|---|---|
Gestures recognition as the main technology of human-computer interaction draws a great amount attention of researchers. Comparing to existing methods, the RFID-based passive gesture recognition requires no specialized equipment which makes it much easier to be used. To achieve the goal, we build a priori gesture database according to signal features caused by perturbation of different gestures. Then, the modified dynamic time warping (DTW) algorithm has been used to match with the priori fingerprint database. Besides, we propose a wireless phase calibration algorithm by utilizing the theory that the noise subspace and the signal subspace is orthogonal in multiple signal classification (MUSIC) algorithm to estimate and remove phase errors that may caused by equipment differences so that we can ensure the accuracy of angle of arrival (AoA) estimation. To evaluate the effectiveness of our gesture recognition system, the experiments in a real scene were carried out. And the experimental results show that we can achieve about 92% accuracy. |
Year | Venue | Field |
|---|---|---|
2017 | MSN | Computer vision,Subspace topology,Dynamic time warping,Computer science,Gesture,A priori and a posteriori,Gesture recognition,Angle of arrival,Feature extraction,Artificial intelligence,Signal subspace,Distributed computing |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
17 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xuan Wang | 1 | 0 | 0.34 |
| Xin Kou | 2 | 0 | 0.34 |
| Zifan Wang | 3 | 0 | 0.34 |
| Lanqing Wang | 4 | 0 | 0.34 |
| Baoying Liu | 5 | 1 | 3.72 |
| Feng Chen | 6 | 17 | 5.44 |