Scholarlink

This study presents the development of a real-time hand gesture classification system utilizing inertial measurement units (IMUs) and a lightweight 1-D convolutional neural network (CNN) implemented on an embedded system. The IMU sensors were positioned on the index and thumb of the participants’ hands to accurately capture data for four distinct gestures, each representing different geometric shapes: square, triangle, circle, and line. Experimental results indicated that the proposed system achieved a classification accuracy of 75%, with an inference time of 11.82 milliseconds and an energy consumption of 0.58 millijoules.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

On-Edge 1-D Convolutional Neural Network for Hand-Gesture Classification

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Daniella Shebly,
  • Haydar Al Haj Ali,
  • Mohamad Yaacoub,
  • Hussein Chibli,
  • Maurizio Valle,
  • christian Gianoglio

摘要

This study presents the development of a real-time hand gesture classification system utilizing inertial measurement units (IMUs) and a lightweight 1-D convolutional neural network (CNN) implemented on an embedded system. The IMU sensors were positioned on the index and thumb of the participants’ hands to accurately capture data for four distinct gestures, each representing different geometric shapes: square, triangle, circle, and line. Experimental results indicated that the proposed system achieved a classification accuracy of 75%, with an inference time of 11.82 milliseconds and an energy consumption of 0.58 millijoules.