• Corpus ID: 239016492

A MIMO Radar-based Few-Shot Learning Approach for Human-ID

  title={A MIMO Radar-based Few-Shot Learning Approach for Human-ID},
  author={Pascal Weller and Fady Aziz and Sherif Abdulatif and Urs Schneider and Marco F. Huber},
Radar for deep learning-based human identification has become a research area of increasing interest. It has been shown that micro-Doppler (μ-D) can reflect the walking behavior through capturing the periodic limbs’ micro-motions. One of the main aspects is maximizing the number of included classes while considering the real-time and training dataset size constraints. In this paper, a multiple-inputmultiple-output (MIMO) radar is used to formulate micromotion spectrograms of the elevation… 
1 Citations

Figures and Tables from this paper

A MIMO Radar-Based Metric Learning Approach for Activity Recognition
A MIMO radar is used to formulate a novel micro-motion spectrogram for the angular velocity (μ-ω) in non-tangential scenarios, which has shown better performance than previous models based on the captured microDoppler signatures.


Person Identification and Body Mass Index: A Deep Learning-Based Study on Micro-Dopplers
The study shows that the body mass index (BMI) has a correlation with the µ-D signature of the walking subject and an accuracy of 98% on the test set with high signal-to-noise-ratio (SNR) and 84% in case of different SNR levels.
Human identification based on natural gait micro‐Doppler signatures using deep transfer learning
This study investigates the use of micro-Doppler (m-D) signatures retrieved from a frequency-modulated continuous-wave radar sensor to identify individuals based on their natural gait characteristics using a simple and cost-efficient radar device.
Open-Set Human Identification Based on Gait Radar Micro-Doppler Signatures
Human identification based on gait radar micro-Doppler signatures has received significant attention in recent years. In real world applications, a recognition system should have the ability to
Radar Signal Processing for Human Identification by Means of Reservoir Computing Networks
This work explores the application of Reservoir Computing Networks to the problem of identifying a limited number of people in an indoor environment, leveraging gait information captured by micro-wave radar measurements, showing that RCNs have a great potential in processing the noisy features provided by a low-power radar.
Deep Learning-based identification of human gait by radar micro-Doppler measurements
The results show that human identification on a specific population based on X-band m-D measurements can be performed reliably using a DCNN.
Radar-Based Human-Motion Recognition With Deep Learning: Promising applications for indoor monitoring
This article puts DL in the context of data-driven approaches for motion classification and compares its performance with other approaches employing handcrafted features and discusses recent proposed enhancements of DL classification performance.
Indoor Person Identification Using a Low-Power FMCW Radar
This paper investigates the use of micro-Doppler signatures retrieved from a low-power radar device to identify a set of persons based on their gait characteristics and proposes a robust feature learning approach based on deep convolutional neural networks.
Human identification based on radar micro‐Doppler signatures separation
A method for personnel recognition using deep convolutional neural networks (DCNNs) based on human micro-Doppler (m-D) signal separation, which shows that an average recognition accuracy of about 90% can be achieved for different human group sizes.
Gait Recognition using FMCW Radar and Temporal Convolutional Deep Neural Networks
An efficient classifier based on deep learning is used for the purpose of identifying individuals features by resorting to the micro-Doppler data extracted from low-power frequency-modulated continuous-wave radar measurements, confirming the applicability of deep learning to the problem at hand.
MU-ID: Multi-user Identification Through Gaits Using Millimeter Wave Radios
MU-ID, a gait-based multi-user identification system leveraging a single commercial off-the-shelf (COTS) millimeter-wave (mmWave) radar, achieves up to 97% single-person identification accuracy, and over 92% identification accuracy for up to four people, while maintaining a low false positive rate.