Single-Snapshot Direction-of-Arrival Estimation of Multiple Targets using a Multi-Layer Perceptron

Fuchs J, Weigel R, Gardill M (2019)


Publication Language: English

Publication Status: Accepted

Publication Type: Conference contribution, Conference Contribution

Future Publication Type: Conference contribution

Publication year: 2019

Pages Range: 1-4

Event location: Detroit, MI US

DOI: 10.1109/ICMIM.2019.8726554

Abstract

An alternative approach to high-resolution direction-of-arrival estimation in the context of automotive FMCW signal processing is shown by training a neural network with simulation as well as experimental data to estimate the mean and distance of the azimuth angles from two targets. Testing results are post-processed to obtain the estimated azimuth angles which can be validated afterwards. The performance of the proposed neural network is then compared with a reference implementation of a maximum likelihood estimator. Final evaluations show super-resolution like performance with significantly reduced computation time, which is expected to have an impact on future multi-dimensional high-resolution DoA estimation.

Authors with CRIS profile

Related research project(s)

Involved external institutions

How to cite

APA:

Fuchs, J., Weigel, R., & Gardill, M. (2019). Single-Snapshot Direction-of-Arrival Estimation of Multiple Targets using a Multi-Layer Perceptron. In Proceedings of the 2019 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM) (pp. 1-4). Detroit, MI, US.

MLA:

Fuchs, Jonas, Robert Weigel, and Markus Gardill. "Single-Snapshot Direction-of-Arrival Estimation of Multiple Targets using a Multi-Layer Perceptron." Proceedings of the 2019 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM), Detroit, MI 2019. 1-4.

BibTeX: Download