Target recognition based on rough set and data fusion in remote sensing image

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

3 Scopus citations

Abstract

Focused on uncertainty of recognition of sensitive / interesting targets in the remote sensing image, a new scheme based on Rough set theory is employed. Firstly, a summary of data resource, the features of recognition, and the process of the traditional target recognition Is given. Then, we Introduce the theory of Rough Set briefly. Thirdly, the original features selection, features reduction and weighted set of the features calculating based on RS, and the strategy of recognition based on the decision-making are proposed in detail. Finally, the steps of the scheme and some examples are presented respectively. As a result, 14 features can be reduced to 10, and the recognition rate nearly reaches 100%, which is wonderful. It is shown that the scheme not only ensures the high recognition rate, reduces the dimension of feature vector, decreases the storage space of data and improves the efficiency of calculation, but also is be propitious to build ATR knowledge base and update the data of the database as well.

Original languageEnglish
Title of host publicationProceedings of the World Congress on Intelligent Control and Automation (WCICA)
Pages10420-10424
Number of pages5
DOIs
StatePublished - 2006
Event6th World Congress on Intelligent Control and Automation, WCICA 2006 - Dalian, China
Duration: 21 Jun 200623 Jun 2006

Publication series

NameProceedings of the World Congress on Intelligent Control and Automation (WCICA)
Volume2

Conference

Conference6th World Congress on Intelligent Control and Automation, WCICA 2006
Country/TerritoryChina
CityDalian
Period21/06/0623/06/06

Keywords

  • Automatic/ aided target recognition (ATR)
  • Image understanding (IU)
  • Information fusion
  • Remote sensing
  • Rough set

Fingerprint

Dive into the research topics of 'Target recognition based on rough set and data fusion in remote sensing image'. Together they form a unique fingerprint.

Cite this