- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 15th European Radar Conference (EuRAD) - Madrid, Spain (2018.9.26-2018.9.28)] 2018 15th European Radar Conference (EuRAD) - Deep Learning-Based Segmentation for the Extraction of Micro-Doppler Signatures
摘要： We present a method for extracting micro-Doppler signatures using a deep convolutional neural network that learns to identify and separate relevant micro-Doppler components from the background. A modified convolutional neural network (fully convolutional network) is trained end-to-end to perform dense predictions from the micro-Doppler signature at the input, generating a map with labels on a pixel level at the output. The network learns intermediate representations with the characteristic patterns of the micro-Doppler paths generated by individual scatterers and is capable of identifying and locating them in the time-frequency representation. The model trained on a simulated environment shows very good performance metrics even in noisy environments, and the experimental results with a continuous wave (CW) radar at 24 GHz indicates that the model can be applied to real scenarios. Moreover, the method scales properly to more complex signatures when several components are superimposed in the time-frequency representation, which indicates that this concept might represent a promising approach for interpreting complex micro-Doppler signatures.
关键词： segmentation,micro-Doppler signatures,deep learning
更新于2025-09-23 15:21:21
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Study of Room Temperature Photoluminescence For 1-stage Co-Evaporated Ultra-Thin Cu(In,Ga)Se <sub/>2</sub> Solar Cells
摘要： In this paper, we investigate the feasibility of recognizing human hand gestures using micro-Doppler signatures measured by Doppler radar with a deep convolutional neural network (DCNN). Hand gesture recognition using radar can be applied to control electronic appliances. Compared with an optical recognition system, radar can work regardless of light conditions and it can be embedded in a case. We classify ten different hand gestures, with only micro-Doppler signatures on spectrograms without range information. The ten gestures, which included swiping from left to right, swiping from right to left, rotating clockwise, rotating counterclockwise, pushing, double pushing, holding, and double holding, were measured using Doppler radar and their spectrograms investigated. A DCNN was employed to classify the spectrograms, with 90% of the data utilized for training and the remaining 10% for validation. After ?ve-fold validation, the classi?cation accuracy of the proposed method was found to be 85.6%. With seven gestures, the accuracy increased to 93.1%.
关键词： Doppler radar,micro-Doppler signatures,Hand gesture,deep convolutional neural networks
更新于2025-09-23 15:19:57
-
[IEEE 2018 11th UK-Europe-China Workshop on Millimeter Waves and Terahertz Technologies (UCMMT) - HangZhou, China (2018.9.5-2018.9.7)] 2018 11th UK-Europe-China Workshop on Millimeter Waves and Terahertz Technologies (UCMMT) - RCS Reduction of 2??2 Microstrip Antenna Array Using All Dielectric Metasurface
摘要： In this paper, we investigate the feasibility of recognizing human hand gestures using micro-Doppler signatures measured by Doppler radar with a deep convolutional neural network (DCNN). Hand gesture recognition using radar can be applied to control electronic appliances. Compared with an optical recognition system, radar can work regardless of light conditions and it can be embedded in a case. We classify ten different hand gestures, with only micro-Doppler signatures on spectrograms without range information. The ten gestures, which included swiping from left to right, swiping from right to left, rotating clockwise, rotating counterclockwise, pushing, double pushing, holding, and double holding, were measured using Doppler radar and their spectrograms investigated. A DCNN was employed to classify the spectrograms, with 90% of the data utilized for training and the remaining 10% for validation. After ?ve-fold validation, the classi?cation accuracy of the proposed method was found to be 85.6%. With seven gestures, the accuracy increased to 93.1%.
关键词： Doppler radar,micro-Doppler signatures,Hand gesture,deep convolutional neural networks
更新于2025-09-16 10:30:52
-
Coupled micro-Doppler signatures of closely located targets
摘要： The classical Doppler shift originates from the movement of a target’s center of mass, but it does not hold information about the internal dynamics of the scattering object. In contrast, micro-Doppler signatures contain data about the micromotions that arise from internal degrees of freedom within the target (such as rotation and vibration), which can be remotely detected by careful analysis of the scattered ?eld. Here we investigate, both theoretically and experimentally, how coupling between a pair of closely situated targets affects the resulting micro-Doppler signatures. The presented model considers a pair of near-?eld coupled resonators with dynamically recon?gurable scattering properties. Voltage controlled varactor diodes enable modulating the scattering cross section of each target independently, mimicking rotational degrees of freedom. As a result, coupled micro-Doppler combs are observed, containing frequency components that arise from the near ?eld interactions, making it possible to extract information about the internal geometry of the system from far-?eld measurements. From a practical point of view, micro-Doppler spectroscopy allows remote classi?cation of distant objects, while deep understanding of the coupling effects on such signatures in the low frequency regime can provide valuable insight for radar and sonar systems, as well as optical and stellar radio-interferometry, among many others.
关键词： sonar,coupled resonators,stellar radio-interferometry,micro-Doppler signatures,radar,optical interferometry
更新于2025-09-16 10:30:52
-
Extraction of micro-doppler characteristics of drones using high-resolution time-frequency transforms
摘要： The demand for detecting and tracking drones has increased for reasons of surveillance and security. Radar is one of the promising methods in this regard. The recognition and identification of drones using a radar system requires the extraction of their unique micro-Doppler signatures produced by their rotating blades. Because of the blades’ rapid rotation speed, difficulties are inherent in visualizing clear micro-Doppler signatures in a conventional joint time-frequency analysis such as the short-time Fourier transform. In this paper, we propose the use of high-resolution transform techniques to visualize the micro-Doppler signatures of drones in a spectrogram. The techniques used include Wigner-Ville distribution, smoothed pseudo-Wigner-Ville distribution, and short-time MUltiple SIgnal Classification (MUSIC) algorithm. In particular, the latter, which had never previously been applied to drones, is suggested to visualize the details of micro-Doppler signatures. We measured three drones using a continuous-wave radar, and performances of these algorithms were compared using data collected from the drones. We could observe that the short-time MUSIC method showed the clearest spectrogram for identifying micro-Doppler signatures. This study can potentially be useful in the field of drone classification.
关键词： micro-Doppler Signatures,Wigner Ville distribution,Time-frequency MUSIC,Joint time-frequency Analysis
更新于2025-09-09 09:28:46