Frequency Modulated Continuous Wave Radar-Based Human Sitting Posture Detection In Bathroom Environment
Authors:
- 22 September 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1230-1233
Abstract
In the bathroom environment, the sitting posture usually changes due to the occurrence of accidents, and by detecting the change of sitting posture, we can respond to the occurrence of accidents in time. However, the current sitting detection technology is not suitable for use in private places such as the bathroom environment. To facilitate the detection of sitting posture in the bathroom environment without violating privacy, this paper proposes a method for detecting human sitting posture in the bathroom environment using Frequency Modulated Continuous Wave (FMCW) radar. By using FMCW radar to obtain time-range and range-velocity feature information on human sitting posture in the bathroom environment, we combine a dual-channel convolutional neural network to detect sitting posture in the bathroom environment and verify the feasibility of the proposed method with experiments. The research results show that the FMCW radar bathroom sitting detection method can finally achieve 98.75% detection accuracy, which can effectively carry out the bathroom environment sitting detection.Keywords
This publication has 16 references indexed in Scilit:
- Human tracking and identification through a millimeter wave radarAd Hoc Networks, 2021
- High Precision Human Detection and Tracking Using Millimeter-Wave RadarsIEEE Aerospace and Electronic Systems Magazine, 2021
- Classification of Interference Signal for Automotive Radar Systems With Convolutional Neural NetworkIEEE Access, 2020
- Human Activity Classification With Radar: Optimization and Noise Robustness With Iterative Convolutional Neural Networks Followed With Random ForestsIEEE Sensors Journal, 2018
- Hand Gesture Recognition Using Micro-Doppler Signatures With Convolutional Neural NetworkIEEE Access, 2016
- Human Detection and Activity Classification Based on Micro-Doppler Signatures Using Deep Convolutional Neural NetworksIEEE Geoscience and Remote Sensing Letters, 2015
- The “Acceptance” of Ambient Assisted Living: Developing an Alternate Methodology to This Limited Research Lens2011
- Triggering of cardiovascular incidents by micturition and defecationInternational Journal of Cardiology, 2006
- Home accidents in elderly patients presenting to an emergency departmentAccident and Emergency Nursing, 1999
- The Center of Gravity of the Human Body in the Antero-Posterior Plane and Its Relation to Posture, Physical Fitness, and Athletic AbilityResearch Quarterly. American Physical Education Association, 1935