Radar Measurement of Human Polarimetric Micro-Doppler

Tahmoush, David; Silvious, Jerry

doi:10.1155/2013/804954

Cited by 11 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A multitude of works in the open literature have considered the use of multiple polarizations for a variety of applications, such as MIMO radar [7]- [11] , weather radar [12]- [14], or imaging radar [15]- [19], among others. More recently, the exploitation of such diversity has been considered for target classification based on the polarimetric micro-Doppler signature [20]- [23] as well as an effective way to improve the performance of passive radar systems [24]- [28].…”

Section: Introductionmentioning

confidence: 99%

Autoregressive Model Based Polarimetric Adaptive Detection Scheme Part I: Theoretical Derivation and Performance Analysis

Colone

Filippini

2020

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

This paper deals with the problem of target detection in coherent radar systems exploiting polarimetric diversity. We resort to a parametric approach and we model the disturbance affecting the data as a multi-channel autoregressive (AR) process. Following this model, a new polarimetric adaptive detector is derived, which aims at improving the target detection capability while relaxing the requirements on the training data size and the computational burden with respect to existing solutions. A complete theoretical characterization of the asymptotic performance of the derived detector is provided, using two different target fluctuation models. The effectiveness of the proposed approach is shown against simulated data, in comparison with alternative existing solutions.

show abstract

Section: Introductionmentioning

confidence: 99%

Autoregressive Model Based Polarimetric Adaptive Detection Scheme Part I: Theoretical Derivation and Performance Analysis

Colone

Filippini

2020

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

show abstract

“…Various campaigns have been undertaken to measure micro-Doppler characteristics via direct measurement [16], [17], [19], [21], [23], [25], [31], [32], [38]. A 94 GHz radar was used for measurements in [23] to obtain spectrograms for human motion detection.…”

Section: A Measurementmentioning

confidence: 99%

“…Velocity is determined by exploiting the Doppler-effect. Specifically, a target with a velocity v relative to a stationary transmitter will induce a frequency shift, f d in the reflected signal given by [19]…”

Section: A Micro-doppler Theorymentioning

confidence: 99%

“…For micro-Doppler based VRU classification, this means that a small training data sample, poorly labeled data or noisy data can lead to overfitting. Traditionally, spectrograms have been obtained using direct measurement [16], [17], [19], [21], [23], [25], [31], [32], [38] and primitive-based simulations [14], [16], [22], [24], [26], [27], [29], [32], [35], [37]. Measurements are valuable, however, CNNs typically require thousands of data samples for reliable training.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

High Fidelity Physics Simulation-Based Convolutional Neural Network for Automotive Radar Target Classification Using Micro-Doppler

et al. 2021

View full text Add to dashboard Cite

Detection and classification of vulnerable road users (VRUs) such as pedestrians and cyclists is a key requirement for the realization of fully autonomous vehicles. Radar-based classification of VRUs can be achieved by exploiting differences in the micro-Doppler signatures associated with VRUs. Specifically, machine learning (ML) algorithms can be trained to classify VRUs using the spectral content of radar signals. The performance of these models depends on the quality and quantity of the data used during the training process. Currently, data collection is typically done through measurements or low fidelity physics, primitive-based simulations. The feasibility of carrying out measurements to collect training data is typically limited by the vast amounts of data required and practicality issues when using VRUs like animals. In this paper, we present a computationally efficient, high fidelity physics-based simulation workflow that can be used to obtain a large quantity of spectrograms from the micro-Doppler signatures of VRUs. The simulations are conducted on full-scale VRU models with a 77 GHz, frequency-modulated continuouswave (FMCW) radar sensor model. Here, we collect the spectrograms of 4 targets; car, pedestrian, cyclist and dog at different speeds and angles-of-arrival. This data is then used to train a 5-layer convolutional neural network (CNN) that achieves nearly 100% classification accuracy after 5 epochs. Studies are conducted to investigate the impact of training data size, velocity and observation time window size on the accuracy of the CNN. Results from this study demonstrate how an accuracy of 95% can be realized using spectrograms obtained over a 0.2 s time window.

show abstract

“…Fully polarimetric radar data can potentially improve the separability of different parts of human motion. One of the techniques to determine whether people are carrying something in their arms is looking at their arm motion [84, 85]. The arm is often bent at the elbow, providing a surface similar to a dihedral, which creates a double bounce of the radar signal.…”

Section: Review Of Micro‐doppler Effect In Radarmentioning

confidence: 99%