Skip to main navigation Skip to search Skip to main content

Dynamic gesture design and recognition for human-robot collaboration with convolutional neural networks

  • Missouri University of Science and Technology

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

13 Scopus citations

Abstract

Human-robot collaboration (HRC) is a challenging task in modern industry and gesture communication in HRC has attracted much interest. This paper proposes and demonstrates a dynamic gesture recognition system based on Motion History Image (MHI) and Convolutional Neural Networks (CNN). Firstly, ten dynamic gestures are designed for a human worker to communicate with an industrial robot. Secondly, the MHI method is adopted to extract the gesture features from video clips and generate static images of dynamic gestures as inputs to CNN. Finally, a CNN model is constructed for gesture recognition. The experimental results show very promising classification accuracy using this method.

Original languageEnglish
Title of host publication2020 International Symposium on Flexible Automation, ISFA 2020
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791883617
DOIs
StatePublished - 2020
Event2020 International Symposium on Flexible Automation, ISFA 2020 - Virtual, Online
Duration: Jul 8 2020Jul 9 2020

Publication series

Name2020 International Symposium on Flexible Automation, ISFA 2020

Conference

Conference2020 International Symposium on Flexible Automation, ISFA 2020
CityVirtual, Online
Period07/8/2007/9/20

Keywords

  • Convolutional Neural Networks
  • Dynamic gesture recognition
  • Human-robot collaboration
  • Motion History Image

Fingerprint

Dive into the research topics of 'Dynamic gesture design and recognition for human-robot collaboration with convolutional neural networks'. Together they form a unique fingerprint.

Cite this