TITLE:
Algorithm for Gesture Recognition Using an IR-UWB Radar Sensor
AUTHORS:
Nan Ren, Xuanjun Quan, Sung Ho Cho
KEYWORDS:
Impulse Radio Ultra-Wideband (IR-UWB) Radar, Ultra-Wide Band (UWB), Gesture Recognition
JOURNAL NAME:
Journal of Computer and Communications,
Vol.4 No.3,
March
2,
2016
ABSTRACT: This paper introduces a human gesture
recognition algorithm using an impulse radio ultra-wide- band (IR-UWB) radar
sensor. Human gesture recognition has been one of the hottest research topics
for quite a long time. Many gesture recognition algorithms or systems using
other sensors have been proposed such as using cameras, RFID tags and so on.
Among which gesture recognition systems using cameras have been extensively
studied in past years and widely used in practical. While it might show some
deficiencies in some cases. For example, the users might not like to be filmed
by cameras considering their privacies. Besides, it might not work well in very
dark environments. While RFID tags could be inconvenient to many people and are
likely to be lost. Our gesture recognition algorithm uses IR-UWB radar sensor
which has pretty high resolution in ranging and adjustable gesture recognition
range, meanwhile, does not have problems in privacy issues or darkness. In this
paper, the gesture recognition algorithm is based on the moving direction and
distance change of the human hand and the change of the frontal surface area of
hand towards radar sensor. By combining these changes while doing gestures, the
algorithm may recognize basically 6 kinds of hand gestures. The experimental
results show that these gestures are of quite good performance. The performance
analysis from experiments is also given.