A novel protocol for accuracy assessment in classification of very high resolution images

Claudio Persello*, Lorenzo Bruzzone

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

90 Citations (Scopus)
6 Downloads (Pure)

Abstract

This paper presents a novel protocol for the accuracy assessment of the thematic maps obtained by the classification of very high resolution images. As the thematic accuracy alone is not sufficient to adequately characterize the geometrical properties of high-resolution classification maps, we propose a protocol that is based on the analysis of two families of indices: 1) the traditional thematic accuracy indices and 2) a set of novel geometric indices that model different geometric properties of the objects recognized in the map. In this context, we present a set of indices that characterize five different types of geometric errors in the classification map: 1) oversegmentation; 2) undersegmentation; 3) edge location; 4) shape distortion; and 5) fragmentation. Moreover, we propose a new approach for tuning the free parameters of supervised classifiers on the basis of a multiobjective criterion function that aims at selecting the parameter values that result in the classificationmap that jointly optimize thematic and geometric error indices. Experimental results obtained on QuickBird images show the effectiveness of the proposed protocol in selecting classification maps characterized by a better tradeoff between thematic and geometric accuracies than standard procedures based only on thematic accuracy measures. In addition, results obtained with support vector machine classifiers confirm the effectiveness of the proposed multiobjective technique for the selection of freeparameter values for the classification algorithm.

Original languageEnglish
Article number2029570
Pages (from-to)1232-1244
Number of pages13
JournalIEEE transactions on geoscience and remote sensing
Volume48
Issue number3 PART 1
DOIs
Publication statusPublished - 2010

Keywords

  • Accuracy assessment
  • Classification maps
  • Geometric accuracy
  • Image classification
  • Remote sensing
  • Thematic accuracy
  • Very high resolution (VHR) images
  • ADLIB-ART-4664
  • n/a OA procedure

Fingerprint

Dive into the research topics of 'A novel protocol for accuracy assessment in classification of very high resolution images'. Together they form a unique fingerprint.

Cite this