Multi-target reflection point model of cyclists for automotive radar

Stolz, Martin; Schubert, Eugen; Meinl, Frank; Kunert, Martin; Menzel, Wolfgang

doi:10.23919/eurad.2017.8249155

Cited by 19 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, electrical parameters like gain pattern, channel attenuation were kept default from the phased array toolbox. In order to have close similarity between real measurement and simulated pedestrian and cyclist Doppler spectrum, both physical and motion model are designed using bioinspired human [15] and cyclist [16]. A closer look on both VRUs is shown in Fig.…”

Section: Simulation Setupmentioning

confidence: 99%

Integrated Classification and Localization of Targets Using Bayesian Framework In Automotive Radars

Dubey

Santra

Fuchs

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Automatic radar based classification of automotive targets, such as pedestrians and cyclist, poses several challenges due to low inter-class variations among different classes and large intra-class variations. Further, different targets required to track in typical automotive scenario can have completely varying dynamics which gets challenging for tracker using conventional state vectors. Compared to state-of-the-art using independent classification and tracking, in this paper, we propose an integrated tracker and classifier leading to a novel Bayesian framework. The tracker's state vector in the proposed framework not only includes the localization parameters of the targets but is also augmented with the targets's feature embedding vector. In consequence, the tracker's performance is optimized due to a better separability of the targets. Furthermore, the classifier's performance is enhanced due to Bayesian formulation utilizing the temporal smoothing of classifier's embedding vector.

show abstract

Section: Simulation Setupmentioning

confidence: 99%

Integrated Classification and Localization of Targets Using Bayesian Framework In Automotive Radars

Dubey

Santra

Fuchs

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Human micro-Doppler has been investigated in [17]- [25]. The micro-Doppler response of cyclists was investigated in [14], [16], [26], [27]. In [28], [29], studies were conducted to measure the micro-Doppler response of drones and birds at 24 GHz and 94 GHz.…”

Section: Introductionmentioning

confidence: 99%

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

“…The recent 77-79 GHz band fast chirp frequency modulated continuous wave (FMCW) radar can ensure a high range and velocity resolution to classify the target by itself, depending on the waveform design. Research on classifying targets using radar sensor data usually focusses on the radar cross-section (RCS) characteristic of targets [7][8][9][10], the characteristic of the measured signal according to the size and shape of targets [11][12][13] or measured signal patterns over time [14][15][16][17][18]. Because it is difficult to classify targets consistently with an individual characteristic, machine learning techniques are used to classify targets by combining various characteristics [11,15,16,[19][20][21][22].…”

Section: Introductionmentioning

confidence: 99%

Radar target classification considering unknown classes using deep convolutional neural network ensemble

Lee

Kang

et al. 2021

IET Radar Sonar & Navi

View full text Add to dashboard Cite

The target classification of unknown classes using radar sensor data is discussed. The neural network-based classifier shows high classification accuracy for the learned class targets. However, there is a risk of false decision for the untrained class target owing to an overconfidence problem. The output confidence of the classifier is calibrated using the deep convolutional neural network ensemble structure to propose a method to set the proper threshold for output confidence to decide unknown class targets. When using the proposed method, the accuracy of the learned target is maintained similar to that of the existing single neural network-based classifier, whereas the unknown class target is better identified. Further analysis verifies the effectiveness of the proposed method using commercial automotive radar. The proposed method can classify learned targets with an accuracy of 95% and distinguish unknown class targets with an accuracy of at least 85%. Based on the interaction with other sensors, individual sensors need to make reserved decisions about uncertain information. It is expected that the proposed ensemble network will be efficient in designing the classifier to perform target classification including unknown class decision.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

show abstract

Multi-target reflection point model of cyclists for automotive radar

Cited by 19 publications

References 6 publications

Integrated Classification and Localization of Targets Using Bayesian Framework In Automotive Radars

Integrated Classification and Localization of Targets Using Bayesian Framework In Automotive Radars

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

Radar target classification considering unknown classes using deep convolutional neural network ensemble

Contact Info

Product

Resources

About