Spectranet: A High Resolution Imaging Radar Deep Neural Network for Autonomous Vehicles

Ruxin Zheng, Shunqiao Sun, David Scharff, Teresa Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The potentials of automotive radar for autonomous driving have not been fully exploited due to the difficulty of extracting targets' information from the radar signals and the lack of radar datasets. In this paper, a novel signal processing pipeline is proposed to address the max ambiguous velocity reduction issue introduced by staggered time division multiplexing (TDM) scheme of high resolution imaging radar system with a large number of transmit antennas. A dataset of 1,410 synchronized frames (stereo cameras, LiDAR, radar) with three classes, i.e., bus, car, and people, is constructed from field experiments. Next, we implement a vanilla SpectraNet and show its promising performance on moving object detection and classification with a mean average precision (mAP) of 81.9% at an intersection over union (IoU) of 0.5.

Original languageEnglish (US)
Title of host publication2022 IEEE 12th Sensor Array and Multichannel Signal Processing Workshop, SAM 2022
PublisherIEEE Computer Society
Pages301-305
Number of pages5
ISBN (Electronic)9781665406338
DOIs
StatePublished - 2022
Event12th IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2022 - Trondheim, Norway
Duration: Jun 20 2022Jun 23 2022

Publication series

NameProceedings of the IEEE Sensor Array and Multichannel Signal Processing Workshop
Volume2022-June
ISSN (Electronic)2151-870X

Conference

Conference12th IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2022
Country/TerritoryNorway
CityTrondheim
Period6/20/226/23/22

Keywords

  • Automotive radar
  • autonomous vehicles
  • deep neural network
  • machine learning

ASJC Scopus subject areas

  • Signal Processing
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Spectranet: A High Resolution Imaging Radar Deep Neural Network for Autonomous Vehicles'. Together they form a unique fingerprint.

Cite this