Segmentation of Micro-Doppler Signatures of Human Sequential Activities using Rényi Entropy
Nicolas C. Kruse (TU Delft - Microwave Sensing, Signals & Systems)
Ronny G. Guendel (TU Delft - Microwave Sensing, Signals & Systems)
F. Fioranelli (TU Delft - Microwave Sensing, Signals & Systems)
A.G. Yarovyi (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
Classifying continuous sequences of human activities is a current research challenge due to the unconstrained duration of the constituent activities. Segmentation of these sequences into single-activity segments is under investigation as a potential solution to this challenge and has been studied in this work. A segmentation method has been proposed based on the extracted Rényi entropy of micro-Doppler spectrogram representations of human motion. The proposed method has been compared to a state of the art method for three different experimental data sets, for various sequence types, and in varying signal-to-noise regimes. It has been shown that the performance of the proposed method is up to 55 ± 22% higher than the reference method when applied to different data sets with unchanged parameters. Additionally, improved performance under degraded signal-to-noise ratio (SNR) conditions has been demonstrated for the proposed method. Finally, two methods for sensor fusion have been formulated for enhanced segmentation performance when multiple radar nodes are available, and have been demonstrated to increase performance by up to 10 ± 2%. The improved segmentation performance is expected to lead to improvements in continuous activity classification.