Hand Gesture Recognition Using an IR-UWB Radar with an Inception Module-Based Classifier

Handgestenerkennung unter Verwendung eines IR-UWB-Radars mit einem Inception-Modul-basierten Klassifikator

Clicks: 287
ID: 266389
2020
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #928 of 1,694 articles by views in sensors

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 1,694 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
The emerging integration of technology in daily lives has increased the need for more convenient methods for human–computer interaction (HCI). Given that the existing HCI approaches exhibit various limitations, hand gesture recognition-based HCI may serve as a more natural mode of man–machine interaction in many situations. Inspired by an inception module-based deep-learning network (GoogLeNet), this paper presents a novel hand gesture recognition technique for impulse-radio ultra-wideband (IR-UWB) radars which demonstrates a higher gesture recognition accuracy. First, methodology to demonstrate radar signals as three-dimensional image patterns is presented and then, the inception module-based variant of GoogLeNet is used to analyze the pattern within the images for the recognition of different hand gestures. The proposed framework is exploited for eight different hand gestures with a promising classification accuracy of 95%. To verify the robustness of the proposed algorithm, multiple human subjects were involved in data acquisition.
Die zunehmende Integration von Technologie in den Alltag hat den Bedarf an komfortableren Methoden der Mensch–Computer-Interaktion (HCI) erhöht. Da bestehende HCI-Ansätze diverse Einschränkungen aufweisen, kann eine auf Handgestenerkennung basierende HCI in vielen Situationen als natürlichere Form der Mensch–Maschine-Interaktion dienen. Inspiriert von einem auf Inception-Modulen basierenden Deep-Learning-Netzwerk (GoogLeNet) stellt diese Arbeit ein neuartiges Verfahren zur Handgestenerkennung für Impuls-Radio-Ultrabreitband-Radare (IR-UWB) vor, das eine höhere Genauigkeit bei der Gestenerkennung erzielt. Zunächst wird eine Methodik vorgestellt, um Radarsignale als dreidimensionale Bildmuster darzustellen; anschließend wird die auf Inception-Modulen basierende Variante von GoogLeNet eingesetzt, um die Muster innerhalb der Bilder zur Erkennung verschiedener Handgesten zu analysieren. Das vorgeschlagene Framework wird für acht verschiedene Handgesten angewendet und erreicht eine vielversprechende Klassifikationsgenauigkeit von 95 %. Um die Robustheit des vorgeschlagenen Algorithmus zu überprüfen, wurden mehrere Probanden in die Datenerfassung einbezogen.
Reference Key
ahmed2020sensorshand Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Shahzad Ahmed;Sung Ho Cho;Ahmed, Shahzad;Cho, Sung Ho;
Journal sensors
Year 2020
DOI
10.3390/s20020564
URL
https://www.mdpi.com/1424-8220/20/2/564#citedby
Keywords
Deep learning human–computer interaction ir-uwb radar hand gesture recognition inception module

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.