Study of millimeter wave radar based gesture sensing

• Main Author: Li, Ruirui
• Other Authors: Lu Yilong
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering
• Online Access: http://hdl.handle.net/10356/74738
• Institution: Nanyang Technological University

This project conducted a preliminary study of gesture sensing by exploring two different types of microwave sensors to understand their advantages and limitations. This report focus on the study of gesture sensing and classification using both millimeter wave radar and antennas with vector network analyzer (VNA). Starting from basic knowledge learning on radar signal processing, image processing and machine learning techniques, we build up the understanding on FMCW radar working principle and analysis methodology. The overall system combines hardware in collecting raw gesture data and software in further signal processing and machine intelligence for classification. In our experiment, we tested two common gestures using millimeter wave radar and vector network analyzer separately. Using MATLAB figure out these data get from radar and VNA into time-frequency and range-Doppler images to verify whether data and processing are correct. Features are extracted from those images and build up a trained model for auto-classification. Testing on accuracy on both equipment were carried out and some comparison has done.