Non-contact Fall detection and Alerting system

based on the millimetre-wave radar and machine learning algorithms

Picture1

Research Background

  1. The pace of populating ageing is much faster than in the past, and there will be a increasing number of elder people who live alone.
  2. Falls are the second leading cause of unintentional injury deaths worldwide, and adults older than 60 years old suffer the greatest number of fatal falls. The fall accident can happen at any time and at any place. After a fall accident happens, timely rescue can save lives.

  3. Thus, it is significant to design and implement a fall detection and alerting system in the elder people’s homes

Solution

  1. Time-frequency analysis based-on the FMCW radar
  2. Feature extraction method based-on the Pattern Contour [1][2]
  3. Motion classification method based on CNN(e.g. Line Kernel CNN [3]) and the radar data
  4. Realization of the time-frequency analysis method, feature extraction method, and CNN on FPGA
  5. Motion detection method based on the video anormaly detection
Related publications

Didn't answer your question?

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Diam vel quam elementum pulvinar etiam non quam.

  1. B. Wang, H. Zhang, and Y.-X. Guo, “Radar-based Soft Fall Detection using Pattern Contour Vector,” accepted by IEEE Internet of Things Journal.
  2. B. Wang, Z. Zheng, and Y.-X. Guo, “Millimeter-Wave Frequency Modulated Continuous Wave Radar-Based Soft Fall Detection Using Pattern Contour-Confined,” IEEE Sens. J., vol. 22, no. 10, pp. 9824–9831, 2022.
  3. B. Wang, L. Guo, H. Zhang, and Y. X. Guo, “A Millimetre-Wave Radar-Based Fall Detection Method Using Line Kernel Convolutional Neural Network,” IEEE Sens. J., vol. 20, no. 22, pp. 13364–13370, 2020.
  4.  B. Wang, and Y. Guo, “Motion detection method and system”, Chinese patent, publication no.: CN 112630777 A.
  5. B. Wang, Z. Zheng, and Y. Guo, “Motion detection method, motion detection device, and terminal device and storage medium”, Chinese patent application no.: 202210339126.6.