DATA AND SAMPLING ISSUES ASSOCIATED WITH ACCURACY ASSESSMENT OF LANDCOVER CHANGE MAPS PRODUCED FROM MULTI-TEMPORAL IMAGE CLASSIFICATION

Kim Lowell*, Shanti Reddy, Elizabeth Farmer

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Problems associated with adequately populating a temporal confusion matrix that indicates the accuracy of a landcover change map are examined. The nature and availability of verification data such as high resolution imagery for t(1) and t(2) are discussed including inherent difficulties associated with pre-2000 time periods and seasonal mismatches. The scarcity of change pixels for obtaining robust estimates of the true commission and omission error rates are demonstrated numerically. Commission errors can potentially be estimated well since candidate error pixels are identified on the change maps - i.e., any pixel for which change was identified. Accurately estimating rates of omission errors, however, is particularly problematic unless one has ancillary knowledge about where landcover change was most likely to have occurred. The ability to adequately sample omission change errors decreases as overall classification accuracy increases, but is unaffected by the amount of landcover change in a region, and the correspondence between misclassified pixels at t(1) and t(2).

Original languageEnglish
Title of host publication2014 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS)
Place of PublicationNEW YORK
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages4
Publication statusPublished - 2014
EventIEEE International Geoscience and Remote Sensing Symposium (IGARSS) - Quebec, Canada
Duration: 13 Jul 201418 Jul 2014

Publication series

NameIEEE International Symposium on Geoscience and Remote Sensing IGARSS
PublisherIEEE
ISSN (Print)2153-6996

Conference

ConferenceIEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Country/TerritoryCanada
Period13/07/1418/07/14

Keywords / Materials (for Non-textual outputs)

  • temporal confusion matrix
  • commission errors
  • omission errors
  • landcover change accuracy

Fingerprint

Dive into the research topics of 'DATA AND SAMPLING ISSUES ASSOCIATED WITH ACCURACY ASSESSMENT OF LANDCOVER CHANGE MAPS PRODUCED FROM MULTI-TEMPORAL IMAGE CLASSIFICATION'. Together they form a unique fingerprint.

Cite this