Neural Network-Based Human Detection Using Raw UWB Radar Data

• Published in: 2024 IEEE Workshop on Microwave Theory and Technology in Wireless Communications (MTTW) pp. 37 - 42
• Main Authors: Dogan, Emine Berjin, Yousefi, Mohammad, Soyak, Ece Gelal, Karamzadeh, Saeid
• Format: Conference Proceeding
• Language: English
• Published: IEEE 02.10.2024
• Subjects: Conferences; convolutional neural network; Convolutional neural networks; deep neural network; human detection; Microwave communication; Neural networks; Position measurement; Radar tracking; Ultra wideband radar; UWB radar; Wireless communication
• DOI: 10.1109/MTTW64344.2024.10742175

Ultra-Wideband (UWB) radar technology is a widely used technology for human detection and tracking through walls, because of its effectiveness in low-visibility situations. This study demonstrates a neural network-based identification of human presence using raw data obtained directly from the UWB radar. First, measurements have been collected with different human subjects at different positions relative to the UWB radar. A convolutional neural network (CNN) model has been trained on this dataset, to detect the presence of a human. Next, the algorithm effectiveness is deeply investigated using the Gradient-weighted Class Activation Mapping (Grad-CAM) method, and the observations on detected presence are discussed.