Detecting Mid-Air Gestures for Digit Writing With Radio Sensors and a CNN
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Leem, Seong Kyu | - |
dc.contributor.author | Khan, Faheem | - |
dc.contributor.author | Cho, Sung Ho | - |
dc.date.accessioned | 2021-08-02T09:28:33Z | - |
dc.date.available | 2021-08-02T09:28:33Z | - |
dc.date.created | 2021-05-12 | - |
dc.date.issued | 2020-04 | - |
dc.identifier.issn | 0018-9456 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/9897 | - |
dc.description.abstract | In this paper, we classify digits written in mid-air using hand gestures. Impulse radio ultrawideband (IR-UWB) radar sensors are used for data acquisition, with three radar sensors placed in a triangular geometry. Conventional radar-based gesture recognition methods use whole raw data matrices or a group of features for gesture classification using convolutional neural networks (CNNs) or other machine learning algorithms. However, if the training and testing data differ in distance, orientation, hand shape, hand size, or even gesture speed or the radar setup environment, these methods become less accurate. To develop a more robust gesture recognition method, we propose not using raw data for the CNN classifier, but instead employing the hand & x2019;s mid-air trajectory for classification. The hand trajectory has a stereotypical shape for a given digit, regardless of the hand & x2019;s orientation or speed, making its classification easy and robust. Our proposed method consists of three stages: signal preprocessing, hand motion localization, and tracking and transforming the trajectory data into an image to classify it using a CNN. Our proposed method outperforms conventional approaches because it is robust to changes in orientation, distance, and hand shape and size. Moreover, this method does not require building a huge training database of digits drawn by different users in different orientations; rather, we can use training databases already available in the image processing field. Overall, the proposed mid-air handwritten digit recognition system provides a user-friendly and accurate mid-air handwriting modality that does not place restrictions on users. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Detecting Mid-Air Gestures for Digit Writing With Radio Sensors and a CNN | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Cho, Sung Ho | - |
dc.identifier.doi | 10.1109/TIM.2019.2909249 | - |
dc.identifier.scopusid | 2-s2.0-85082052445 | - |
dc.identifier.wosid | 000521163500012 | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, v.69, no.4, pp.1066 - 1081 | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT | - |
dc.citation.title | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT | - |
dc.citation.volume | 69 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 1066 | - |
dc.citation.endPage | 1081 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Instruments & Instrumentation | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Instruments & Instrumentation | - |
dc.subject.keywordPlus | Character recognition | - |
dc.subject.keywordPlus | Classification (of information) | - |
dc.subject.keywordPlus | Convolution | - |
dc.subject.keywordPlus | Convolutional neural networks | - |
dc.subject.keywordPlus | Data acquisition | - |
dc.subject.keywordPlus | Gesture recognition | - |
dc.subject.keywordPlus | Human computer interaction | - |
dc.subject.keywordPlus | Impulse noise | - |
dc.subject.keywordPlus | Learning algorithms | - |
dc.subject.keywordPlus | Machine learning | - |
dc.subject.keywordPlus | Metadata | - |
dc.subject.keywordPlus | Motion tracking | - |
dc.subject.keywordPlus | Radar | - |
dc.subject.keywordPlus | Radar equipment | - |
dc.subject.keywordPlus | Radio | - |
dc.subject.keywordPlus | Sensors | - |
dc.subject.keywordPlus | Trajectories | - |
dc.subject.keywordPlus | Ultra-wideband (UWB) | - |
dc.subject.keywordPlus | Conventional approach | - |
dc.subject.keywordPlus | Gesture classifications | - |
dc.subject.keywordPlus | Handwritten digit recognition | - |
dc.subject.keywordPlus | image | - |
dc.subject.keywordPlus | Impulse radio ultra wideband (IR-UWB) | - |
dc.subject.keywordPlus | localization | - |
dc.subject.keywordPlus | mid-air handwriting | - |
dc.subject.keywordPlus | Training and testing | - |
dc.subject.keywordPlus | Palmprint recognition | - |
dc.subject.keywordAuthor | Sensors | - |
dc.subject.keywordAuthor | Clutter | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Radar imaging | - |
dc.subject.keywordAuthor | Trajectory | - |
dc.subject.keywordAuthor | Gesture recognition | - |
dc.subject.keywordAuthor | Convolutional neural network (CNN) | - |
dc.subject.keywordAuthor | gesture recognition | - |
dc.subject.keywordAuthor | human-computer interaction | - |
dc.subject.keywordAuthor | image | - |
dc.subject.keywordAuthor | impulse radio ultrawideband (IR-UWB) radar | - |
dc.subject.keywordAuthor | localization | - |
dc.subject.keywordAuthor | mid-air handwriting | - |
dc.subject.keywordAuthor | sensor | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/8682073 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.