Skip to main navigation Skip to search Skip to main content

Fusang: Graph-inspired Robust and Accurate Object Recognition on Commodity mmWave Devices

  • Guorong He
  • , Shaojie Chen
  • , Dan Xu
  • , Xiaojiang Chen
  • , Yaxiong Xie
  • , Xinhuai Wang
  • , Dingyi Fang
  • Northwest University China
  • Xidian University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Scopus citations

Abstract

This paper presents the design and implementation of Fusang, a low-barrier system that brings accurate and robust 3D object recognition to Commercial-Off-The-Shelf mmWave devices. The basic idea of Fusang is leveraging the large bandwidth of mmWave Radars to capture a unique set of fine-grained reflected responses generated by object shapes. Moreover, Fusang constructs two novel graph-structured features to robustly represent the reflected responses of the signal in the frequency domain and IQ domain, and carefully designs a neural network to accurately recognize objects even in different multipath scenarios. We have implemented a prototype of Fusang on a commodity mmWave Radar device. Our experiments with 24 different objects show that Fusang achieves a mean accuracy of 97% in different multipath environments. The code, dataset, and trained models of Fusang can be obtained at https://github.com/OpenNISLab/Pro-Fusang.

Original languageEnglish
Title of host publicationMobiSys 2023 - Proceedings of the 21st ACM International Conference on Mobile Systems, Applications and Services
PublisherAssociation for Computing Machinery, Inc
Pages489-502
Number of pages14
ISBN (Electronic)9798400701108
DOIs
StatePublished - Jun 18 2023
Event21st ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2023 - Helsinki, Finland
Duration: Jun 18 2023Jun 22 2023

Publication series

NameMobiSys 2023 - Proceedings of the 21st Annual International Conference on Mobile Systems, Applications and Services

Conference

Conference21st ACM International Conference on Mobile Systems, Applications, and Services, MobiSys 2023
Country/TerritoryFinland
CityHelsinki
Period06/18/2306/22/23

Keywords

  • HRRP
  • graph-inspired feature
  • mmwave radar
  • object recognition

Fingerprint

Dive into the research topics of 'Fusang: Graph-inspired Robust and Accurate Object Recognition on Commodity mmWave Devices'. Together they form a unique fingerprint.

Cite this