What is it about?
We investigate which radar features are most useful for detecting people behind walls using machine-learning models. Twenty-six features describing different characteristics of the radar signal were evaluated, including signal values, temporal changes, and frequency-related information.
Featured Image
Photo by Lucas Law on Unsplash
Why is it important?
Detecting people behind walls is relevant to security and search and rescue. This study offers initial findings on how feature selection can affect detection performance. It was done on an existing dataset and does not represent a real-time or deployable system.
Perspectives
This work may be of interest to researchers working on radar sensing, machine learning, through-wall detection, and disaster response. The results also highlight the need to evaluate the selected features with larger datasets and more diverse wall materials, environments, and human movement conditions.
Zainab Malik
Read the Original
This page is a summary of: Feature Engineering to Detect People Behind Walls Using UWB Sensor, May 2024, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/siu61531.2024.10601158.
You can read the full text:
Contributors
The following have contributed to this page
