High-speed image-free target detection and classification in single-pixel imaging

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

4 Citations (Scopus)

Abstract

In this paper, an efficient image-free target detection and classification framework for single-pixel imaging (SPI) is presented. The proposed method captures target information by sampling it with very few patterns (at 1-10% sampling rate), and employs signal-processing based feature extraction coupled with radial basis function neural network (RBF-NN) for accurate target classification. The proposed method can replace existing deep learning (DL) based target detection and classification methods because of its high-speed, accuracy and simple shallow design.

Original languageEnglish
Title of host publicationSPIE Future Sensing Technologies
EditorsMasafumi Kimata, Joseph A. Shaw, Christopher R. Valenta
PublisherSPIE
ISBN (Electronic)9781510638617
DOIs
Publication statusPublished - 2020
EventSPIE Future Sensing Technologies 2020 - Virtual, Online, Japan
Duration: 9 Nov 202013 Nov 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11525
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceSPIE Future Sensing Technologies 2020
Country/TerritoryJapan
CityVirtual, Online
Period9/11/2013/11/20

Keywords

  • Deep learning
  • Radial basis function neural network
  • Single-pixel imaging
  • Target classification

Fingerprint

Dive into the research topics of 'High-speed image-free target detection and classification in single-pixel imaging'. Together they form a unique fingerprint.

Cite this