Hand Gesture Recognition Using a Radar Echo I–Q Plot and a Convolutional Neural Network

• Sakamoto, Takuya

• Gao, Xiaomeng

• Yavari, Ehsan

• Rahman, Ashikur

• Boric-Lubecke, Olga

• Lubecke, Victor M.

Abstract

We propose a hand gesture recognition technique using a convolutional neural network applied to radar echo inphase/quadrature (I/Q) plot trajectories. The proposed technique is demonstrated to accurately recognize six types of hand gestures for ten participants. The system consists of a low-cost 2.4-GHz continuous-wave monostatic radar with a single antenna. The radar echo trajectories are converted to low-resolution images and are used for the training and evaluation of the proposed technique. Results indicate that the proposed technique can recognize hand gestures with average accuracy exceeding 90%.

Journal

• IEEE Sensors Letters

  IEEE Sensors Letters 2 (3), 1-4, 2018-09

  IEEE

Keywords

• Sensor signals processing
• gesture recognition
• machine learning
• neural network
• radar

Details

• CRID: 1050004953545197824
• NII Article ID: 120006898149
• ISSN: 24751472
• DOI: 10.1109/lsens.2018.2866371
• HANDLE: 2433/259194
• Web Site: http://xplorestaging.ieee.org/ielx7/7782634/8396241/08443083.pdf?arnumber=8443083
• Text Lang: en
• Article Type: journal article
• Data Source:
  • IRDB
  • Crossref
  • CiNii Articles
  • KAKEN