piedpapers alpha

Paper Info

Learning Representations for Neural Networks Applied to Spectrum-Based Direction-of-Arrival Estimation for Automotive Radar
Add to binder
Log in

M Gall, M Gardill, J Fuchs, T Horn

2020 IEEE/MTT-S International Microwave Symposium (IMS), 1031-1034, 2020.


Reviews

From yassendobrev, rated 4/5. June 28, 2021.
A paper using machine learning to achieve DoA super-resolution. They don't say much about the network itself, but it sounds like it's pretty big. Multiplying the spectrum by the radiation pattern makes no sense to me and leads to problems as they show. The idea to represent the targets as wide peaks instead of Diracs during training sounds good.

Remove from your binders
Are you sure you want to remove this paper? Your reading progress, rating, and review will be lost.
© 2020-2025 Copyright: piedpapers