Semantic information extraction from multispectral geospatial imagery via a flexible framework

Shaun Gleason, Regina Ferrell, Anil Cheriyadat, Raju Vatsavai, Soumya De

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

15 Scopus citations

Abstract

Identification and automatic labeling of facilities in high-resolution satellite images is a challenging task as the current thematic classification schemes and the low-level image features are not good enough to capture complex objects and their spatial relationships. In this paper we present a novel algorithm framework for automated semantic labeling of large image collections. The framework consists of various segmentation, feature extraction, vector quantization, and Latent Dirichlet Allocation modules. Initial experimental results show promise as well as the challenges in semantic classification technology development for nuclear proliferation monitoring.

Original languageEnglish
Title of host publication2010 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages166-169
Number of pages4
ISBN (Print)9781424495658, 9781424495665
DOIs
StatePublished - 2010
Event2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010 - Honolulu, United States
Duration: Jul 25 2010Jul 30 2010

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)

Conference

Conference2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010
Country/TerritoryUnited States
CityHonolulu
Period07/25/1007/30/10

Keywords

  • Invariant features
  • Latent Dirichlet Allocation
  • Satellite image analysis
  • Semantic classification

Fingerprint

Dive into the research topics of 'Semantic information extraction from multispectral geospatial imagery via a flexible framework'. Together they form a unique fingerprint.

Cite this