Sorry, you need to enable JavaScript to visit this website.

AUTOMATIC RADAR-BASED GESTURE DETECTION VIA REGION-BASED DCNN

Citation Author(s):
Yuliang Sun, Tai Fei, Shangyin Gao, Nils Pohl
Submitted by:
Yuliang Sun
Last updated:
9 May 2019 - 7:54am
Document Type:
Poster
Document Year:
2019
Event:
Presenters:
Yuliang Sun
 

In this paper, a region-based deep convolutional neural network
(R-DCNN) is proposed to detect and classify gestures
measured by a frequency-modulated continuous wave radar
system. Micro-Doppler (μD) signatures of gestures are exploited,
and the resulting spectrograms are fed into a neural
network. We are the first to use the R-DCNN for radar-based
gesture recognition, such that multiple gestures could be automatically
detected and classified without manually clipping
the data streams according to each hand movement in advance.
Further, along with the μD signatures, we incorporate
phase-difference information of received signals from an Lshaped
antenna array to enhance the classification accuracy.
Finally, the classification results show that the proposed network
trained with spectrogram and phase-difference information
can guarantee a promising performance for nine gestures.

up
0 users have voted: