Hand gestures recorded with mm-Wave FMCW radar (AWR1642)

Citation Author(s):
Piotr
Grobelny
Wroclaw University of Science and Technology
Adam
Narbudowicz
Wroclaw University of Science and Technology
Submitted by:
Adam Narbudowicz
Last updated:
Thu, 06/03/2021 - 07:31
DOI:
10.21227/wh5w-c362
Data Format:
License:
3870 Views
Categories:
Keywords:
5
3 ratings - Please login to submit your rating.

Abstract 

The dataset contains 4600 samples of 12 different hand-movement gestures. Data were collected from four different people using the FMCW AWR1642 radar. Each sample is saved as a CSV file associated with its gesture type. Gesture description: (G1) arm to left – full swipe of an arm from right to left, (G2) arm to right – full swipe of an arm from left to right, (G3) hand away – taking a hand away from radar, (G4) hand closer – taking a hand closer to the radar, (G5) arm up – an arm movement from bottom to top, (G6) arm down – an arm movement from top to bottom, (G7) palm up – rotating a palm upwards, (G8) palm down – rotating a palm downwards, (G9) hand to the left – a hand movement to the left (without an arm movement), (G10) hand to the right – a hand movement to the right, (G11) closing a fist horizontally, (G12) closing a fist vertically.

Instructions: 

Dataset is divided into 12 separate folders associated to different gesture types. Each folder contains gesture samples saved as a CSV file. First line of the CSV file is a headline describing the columns of data: FrameNumber, ObjectNumber, Range, Velocity, PeakValue, x coordinate, y coordinate. In order to read the gestures into matrix representation copy all 12 folders into single folder called “data”. Copy the “read_gesture.py” script to the same folder as “data” and run it. Script will convert CSV files of given gesture type into the numpy matrix.