Dynamic Gesture Design and Recognition for Human-Robot Collaboration with Convolutional Neural Networks
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.
H. Chen et al., "Dynamic Gesture Design and Recognition for Human-Robot Collaboration with Convolutional Neural Networks," Proceedings of the 2020 International Symposium on Flexible Automation, American Society of Mechanical Engineers (ASME), Jul 2020.
The definitive version is available at https://doi.org/10.1115/ISFA2020-9609
2020 International Symposium on Flexible Automation, ISFA 2020 (2020: Jul. 8-9, Virtual)
Mechanical and Aerospace Engineering
Keywords and Phrases
Convolutional Neural Networks; Dynamic gesture recognition; Human-robot collaboration; Motion History Image
International Standard Book Number (ISBN)
Article - Conference proceedings
© 2020 American Society of Mechanical Engineers (ASME), All rights reserved.
09 Jul 2020
National Science Foundation, Grant NRI-1830479