Please use this identifier to cite or link to this item:
Title: Spatial estimation of classification accuracy using indicator kriging with an image-derived ambiguity index
Authors: Park, No-Wook 
Kyriakidis, Phaedon 
Hong, Suk-Young 
Major Field of Science: Engineering and Technology
Field Category: Electrical Engineering - Electronic Engineering - Information Engineering
Keywords: Classification;Accuracy;Indicator kriging;Posteriori probability
Issue Date: 11-Apr-2016
Source: Remote Sensing, 2016, vol. 8, no. 4, pp. 320
Volume: 8
Issue: 4
Start page: 320
DOI: 10.3390/rs8040320
Journal: Remote Sensing 
Abstract: Traditional classification accuracy assessments based on summary statistics from a confusion matrix furnish a global (location invariant) view of classification accuracy. To estimate the spatial distribution of classification accuracy, a geostatistical integration approach is presented in this paper. Indicator kriging with local means is combined with logistic regression to integrate an image-derived ambiguity index with classification accuracy values at reference data locations. As for the ambiguity measure, a novel discrimination capability index (DCI) is defined from per class posteriori probabilities and then calibrated via logistic regression to derive soft probabilities. Integration of indicator-coded reference data with soft probabilities is finally carried out for mapping classification accuracy. It is demonstrated via a case study involving classification of multi-temporal and multi-sensor SAR datasets, that the proposed approach can provide a map of locally-varying accuracy values, while respecting the overall accuracy derived from the confusion matrix. It can also highlight areas where the benefit of data fusion was significant. It is expected that the indicator approach presented in this paper could be a useful methodology for assessing the spatial quality of classification results in a probabilistic way.
ISSN: 2072-4292
DOI: 10.3390/rs8040320
Rights: © Multidisciplinary Digital Publishing Institute
Type: Article
Affiliation : Inha Univeristy 
Cyprus University of Technology 
National Institute of Agricultural Sciences 
Appears in Collections:Άρθρα/Articles

Files in This Item:
File Description SizeFormat
remotesensing-08-00320-v2.pdfArticle7.67 MBAdobe PDFView/Open
CORE Recommender
Show full item record


checked on Jun 23, 2021


Last Week
Last month
checked on Apr 22, 2021

Page view(s)

Last Week
Last month
checked on Jun 24, 2021

Download(s) 10

checked on Jun 24, 2021

Google ScholarTM



Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.