文章基本信息

标题：UWB-gestures, a public dataset of dynamic hand gestures acquired using impulse radar sensors
本地全文：下载
作者：Ahmed, Shahzad ; Wang, Dingyang ; Park, Junyoung 等
期刊名称：Scientific Data
电子版ISSN：2052-4463
出版年度：2021
卷号：8
期号：1
页码：1-9
DOI：10.1038/s41597-021-00876-0
语种：English
出版社：Nature Publishing Group
摘要：In the past few decades, deep learning algorithms have become more prevalent for signal detection and classification. To design machine learning algorithms, however, an adequate dataset is required. Motivated by the existence of several open-source camera-based hand gesture datasets, this descriptor presents UWB-Gestures, the first public dataset of twelve dynamic hand gestures acquired with ultra-wideband (UWB) impulse radars. The dataset contains a total of 9,600 samples gathered from eight different human volunteers. UWB-Gestures eliminates the need to employ UWB radar hardware to train and test the algorithm. Additionally, the dataset can provide a competitive environment for the research community to compare the accuracy of different hand gesture recognition (HGR) algorithms, enabling the provision of reproducible research results in the field of HGR through UWB radars. Three radars were placed at three different locations to acquire the data, and the respective data were saved independently for flexibility.