Deep Learning-based identification of human gait by radar micro-Doppler measurements
V. S. Papanastasiou (Student TU Delft)
R. P. Trommel (Thales Nederland B.V.)
R. I.A. Harmanny (Thales Nederland B.V.)
Alexander Yarovoy (TU Delft - Microwave Sensing, Signals & Systems)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
For the first time identification of human individuals using micro-Doppler (m-D) features measured at X-band has been demonstrated. Deep Convolutional Neural Networks (DCNNs) have been used to perform classification. Inspection and visualization of the classification results were performed using Uniform Manifold Approximation and Projection (UMAP). Classification accuracy of above 93.5% is obtained for a population of 22 subjects. The results show that human identification on a specific population based on X-band m-D measurements can be performed reliably using a DCNN.