A real-time algorithm for vision-based localization

Amir Averbuch, Alon Scholar

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

Abstract

We present a real-time algorithm for the localization of an agent in an area whose topography is given. The data is organized in a matrix whose cells correspond to square area units of the terrain. Our algorithm consists of two stages: pre-processing and localization. In the pre-process stage the a-priori data is processed to yield information which will be used during the localization stage. Specifically, the skyline of the panoramic view which is seen from each point in the terrain is extracted. A feature vector is constructed based upon the skyline data. In the localization stage, the feature vector of the panoramic skyline, which is seen from the agent, is matched against the pre-processed feature data in order to find the location of the agent.

Original languageEnglish
Title of host publicationProceedings Elmar-2004 - 46th International Symposium Electronics in Marine
EditorsT. Kos, M. Grgic
Pages125-130
Number of pages6
DOIs
StatePublished - 2004
EventProceedings Elmar-2004 - 46th International Symposium Electronics in Marine - Zadar, Croatia
Duration: 16 Jun 200418 Jun 2004

Publication series

NameProceedings Elmar - International Symposium Electronics in Marine
ISSN (Print)1334-2630

Conference

ConferenceProceedings Elmar-2004 - 46th International Symposium Electronics in Marine
Country/TerritoryCroatia
CityZadar
Period16/06/0418/06/04

Keywords

  • Localization
  • Real-time
  • Vision-based

Fingerprint

Dive into the research topics of 'A real-time algorithm for vision-based localization'. Together they form a unique fingerprint.

Cite this