No 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.

Identification of human individuals within a group of 39 persons using micro-Doppler (μ-D) features has been investigated. Deep convolutional neural networks with two different training procedures have been used to perform classification. Visualization of the inner network layers revealed the sections of the input image most relevant when determining the class label of the target. A convolutional block attention module is added to provide a weighted feature vector in the channel and feature dimension, highlighting the relevant μ-D feature-filled areas in the image and improving classification performance.