300 GHz Radar Object Recognition based on Deep Neural Networks and Transfer Learning

TL;DR

This paper presents a deep learning approach for recognizing objects in 300GHz radar images, emphasizing robustness to environmental variations and leveraging transfer learning due to limited training data, as a step towards autonomous vehicle applications.

Contribution

It introduces a novel deep neural network methodology for radar-based object recognition at 300GHz, incorporating transfer learning to address limited data and testing in multi-object scenes.

Findings

Deep neural networks can effectively recognize objects in 300GHz radar images.

Transfer learning improves recognition robustness with limited training data.

The approach demonstrates potential for future autonomous vehicle radar systems.

Abstract

For high resolution scene mapping and object recognition, optical technologies such as cameras and LiDAR are the sensors of choice. However, for robust future vehicle autonomy and driver assistance in adverse weather conditions, improvements in automotive radar technology, and the development of algorithms and machine learning for robust mapping and recognition are essential. In this paper, we describe a methodology based on deep neural networks to recognise objects in 300GHz radar images, investigating robustness to changes in range, orientation and different receivers in a laboratory environment. As the training data is limited, we have also investigated the effects of transfer learning. As a necessary first step before road trials, we have also considered detection and classification in multiple object scenes.