An expectation-maximization-based approach to the relative grid-locking problem

Stefano Fortunati, Fulvio Gini, Maria S. Greco, Alfonso Farina, Antonio Graziano, Sofia Giompapa

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

Abstract

An important prerequisite for successful multisensory integration is that the data from the reporting sensors are transformed to a common reference frame free of systematic or registration bias errors. If not properly corrected, the registration errors can seriously degrade the global surveillance system performance. The relative sensor registration (or grid-locking) process aligns remote data to local data under the assumption that the local data are bias free and that all biases reside with the remote sensor. In this paper, we take into account all registration errors involved in the grid-locking problem. An EM-based estimator of these bias terms is derived and its statistical performance compared to the hybrid Cramér-Rao lower bound (HCRLB).

Original languageEnglish
Title of host publicationIEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011
Pages508-513
Number of pages6
DOIs
Publication statusPublished - 1 Dec 2011
Externally publishedYes
Event11th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011 - Bilbao, Spain
Duration: 14 Dec 201117 Dec 2011

Publication series

NameIEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011

Conference

Conference11th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011
Country/TerritorySpain
CityBilbao
Period14/12/1117/12/11

Keywords

  • Expectation-Maximization algorithm
  • HCRLB
  • Multi-sensor system
  • bias errors
  • sensor registration

Fingerprint

Dive into the research topics of 'An expectation-maximization-based approach to the relative grid-locking problem'. Together they form a unique fingerprint.

Cite this