Gesture recognition algorithm combining ResNet and ShuffleNet

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Gesture is a form of non-verbal communication and has many applications, such as sign language communication between deaf and dumb people, robot control, human-computer interaction and medical applications. The commonly used acquisition equipment in gesture recognition is the visible light camera, but illumination has a great impact on the accuracy of the collected data classification processing. The whole project designed a complete end-to-end edge computing system design and deployment, the system can achieve from gesture image acquisition to gesture recognition. A dataset of 3600 thermal images was created, and each gesture had 1200 thermal images with only 4∗4 resolution. These images were upsampled by bilinear interpolation and fed into a new lightweight deep learning model combining deep residual learning with ShuffleNet V2 for gesture classification. The system achieved 98.63% accuracy on the test data set. Another advantage is that it is based on thermal imaging, so the accuracy is not affected by background lighting conditions.

Original languageEnglish
Title of host publicationInternational Conference on Internet of Things and Machine Learning, IoTML 2021
EditorsPushpendu Kar, Steven Guan
PublisherSPIE
ISBN (Electronic)9781510653252
DOIs
StatePublished - 2022
Externally publishedYes
Event2021 International Conference on Internet of Things and Machine Learning, IoTML 2021 - Dalian, China
Duration: 17 Dec 202119 Dec 2021

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume12174
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2021 International Conference on Internet of Things and Machine Learning, IoTML 2021
Country/TerritoryChina
CityDalian
Period17/12/2119/12/21

Keywords

  • Deep learning
  • Gesture recognition
  • The neural network
  • Thermal imaging

Fingerprint

Dive into the research topics of 'Gesture recognition algorithm combining ResNet and ShuffleNet'. Together they form a unique fingerprint.

Cite this