Model Order Estimation using a Multi-Layer Perceptron for Direction-of-Arrival Estimation in Automotive Radar Sensors

Fuchs J, Weigel R, Gardill M (2019)


Publication Language: English

Publication Status: Published

Publication Type: Conference contribution, Conference Contribution

Future Publication Type: Conference contribution

Publication year: 2019

Pages Range: 1-3

Event location: Orlando, Florida US

DOI: 10.1109/WISNET.2019.8711806

Abstract

In this work, a machine-learning-based approach to decide whether one or two targets are present in the same range-velocity cell of a chirp-sequence FMCW radar system is evaluated. An experimental setup for generating sufficient large sets of training and testing data using real measurement data from automotive 77 GHz radar sensors is presented. Using this data a multi-layer perceptron is trained to directly estimate the number of present targets from the received signals in order to determine if resolution in the spatial domain is necessary. Evaluations of the trained model show that the network is able to inherently learn the underlying signal model and reach super-resolution performance.

Authors with CRIS profile

Related research project(s)

Involved external institutions

How to cite

APA:

Fuchs, J., Weigel, R., & Gardill, M. (2019). Model Order Estimation using a Multi-Layer Perceptron for Direction-of-Arrival Estimation in Automotive Radar Sensors. In Proceedings of the 2019 IEEE Topical Conference on Wireless Sensors and Sensor Networks (WiSNet) (pp. 1-3). Orlando, Florida, US.

MLA:

Fuchs, Jonas, Robert Weigel, and Markus Gardill. "Model Order Estimation using a Multi-Layer Perceptron for Direction-of-Arrival Estimation in Automotive Radar Sensors." Proceedings of the 2019 IEEE Topical Conference on Wireless Sensors and Sensor Networks (WiSNet), Orlando, Florida 2019. 1-3.

BibTeX: Download