Automatic thresholding for land cover change detection in SAR images

Bhogendra Mishra, Junichi Susaki

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

1 Citation (Scopus)

Abstract

In this research, we propose an unsupervised change detection methodology for synthetic aperture radar (SAR) images. By analyzing the goodness of fit, it is found that pixels in no change area in the change image generated by normalized difference ratio (NDR) operator better fit with normal distribution. Based on this assumption, we identify the pixel range that fits the normal distribution better than any other range iteratively in the image and the range is defines as the threshold value. Finally, a region growing segmentation algorithm was modified to fit for the post processing in change detection. Experiments were carried out with all possible cases of changes: (i) double change, (ii) single change and (iii) no change to prove the effectiveness of the proposed methodology.

Original languageEnglish
Title of host publication2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages3347-3350
Number of pages4
ISBN (Electronic)978-1-4799-1114-1
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013: Building a Sustainable Earth through Remote Sensing - Melbourne, Australia
Duration: 21 Jul 201326 Jul 2013
Conference number: 33
http://www.igarss2013.org/

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
PublisherIEEE
Volume2013
ISSN (Print)2153-6996
ISSN (Electronic)2153-7003

Conference

Conference33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013
Abbreviated titleIGARSS
Country/TerritoryAustralia
CityMelbourne
Period21/07/1326/07/13
Internet address

Keywords

  • Change detection
  • Normalized difference ratio
  • Region growing
  • Thresholding
  • n/a OA procedure

Fingerprint

Dive into the research topics of 'Automatic thresholding for land cover change detection in SAR images'. Together they form a unique fingerprint.

Cite this