Nils Pohl — accepted AI-conference papers

2021

A DNN Autoencoder for Automotive Radar Interference Mitigation

Shengyi Chen, Jalal Taghia, Tai Fei, Uwe Kühnau, Nils Pohl, Rainer Martin

ICASSP 2021accepted

In this paper, a novel interference mitigation approach using an autoencoder in combination with a traditional interference detection filter is introduced. It is shown that by employing the gated convolution, the encoder has the ability to learn the signal pattern from the remaining interference-fre…

Cited by 0 Source ↗Scholar ↗

2019

Automatic Radar-based Gesture Detection and Classification via a Region-based Deep Convolutional Neural Network

Yuliang Sun, Tai Fei, Shangyin Gao, Nils Pohl

ICASSP 2019accepted

In this paper, a region-based deep convolutional neural network (R-DCNN) is proposed to detect and classify gestures measured by a frequency-modulated continuous wave radar system. Micro-Doppler (µD) signatures of gestures are exploited, and the resulting spectrograms are fed into a neural network.…

Cited by 0 Source ↗Scholar ↗