Single-Sensor Localization of Moving Sources Using Diffusion Kernels and Brownian Motion Model

Eran Zeitouni, Israel Cohen

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

Abstract

Recently, we introduced a single-sensor method for estimating the location and velocity of moving sources. The obtained state-of-the-art results are valid to slow sources whose velocities are gradually changing through time. In this paper, we challenge our algorithm's fundamental assumption. We apply the algorithm to sources that have rapid and random fluctuations in their velocity. The proposed algorithm is based on a supervised learning approach, using diffusion maps with a Euclidean distance-based diffusion kernel. Experimental results demonstrate the benefits of the proposed single-sensor localization method for sources with a Brownian motion model of randomly fluctuating movements.

Original languageEnglish
Title of host publication2022 IEEE 24th International Workshop on Multimedia Signal Processing, MMSP 2022
ISBN (Electronic)9781665471893
DOIs
StatePublished - 2022
Event24th IEEE International Workshop on Multimedia Signal Processing, MMSP 2022 - Shanghai, China
Duration: 26 Sep 202228 Sep 2022

Publication series

Name2022 IEEE 24th International Workshop on Multimedia Signal Processing, MMSP 2022

Conference

Conference24th IEEE International Workshop on Multimedia Signal Processing, MMSP 2022
Country/TerritoryChina
CityShanghai
Period26/09/2228/09/22

Keywords

  • Source localization
  • diffusion maps
  • direction finding
  • manifold learning
  • non-cooperative localization
  • passive sensing
  • position finding
  • single-sensor
  • single-site

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Media Technology

Fingerprint

Dive into the research topics of 'Single-Sensor Localization of Moving Sources Using Diffusion Kernels and Brownian Motion Model'. Together they form a unique fingerprint.

Cite this