Exploring the use of classification uncertainty to improve classification accuracy

Daniel Moraes, P. Benevides, F. D. Moreira, Hugo Costa, Mário Caetano

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

Abstract

Supervised classification of remotely sensed images has been widely used to map land cover and land use. Since the performance of supervised methods depends on the quality of the training data, it is essential to develop methods to generate an enhanced training dataset. Active learning represents an alternative for such purpose as it proposes to create a dataset of optimized samples, normally collected based on classification uncertainty. However, it is heavily dependent on human interaction, since the user has to label selected samples over a number of iterations. In this paper, we explore the use of uncertainty to improve classification accuracy through a single iteration. We conducted experiments in a region of Portugal (Trás-os-Montes), using multioral Sentinel-2 images. The proposed approach consisted in computing the classification uncertainty of a Random Forest to collect additional training data from areas of high uncertainty and perform a new classification. An accuracy assessment was performed to compare the overall accuracy of the initial and new classifications. The results exhibited an increase in accuracy, though considered not statistically significant. Obstacles related to labelling additional sampling units resulted in a lack of additional training data for various classes, which might have limited the accuracy improvement. Additionally, an uneven proportion of additional training sampling units per class and the collection of new sample data from a limited number of uncertainty regions might also have prevented a higher increase in accuracy. Nevertheless, visual inspection of the maps revealed that the new classification reduced the confusion between some classes.

Original languageEnglish
Title of host publicationThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLIII-B3-2021 XXIV ISPRS Congress (2021 edition)
Pages81-86
Number of pages6
DOIs
Publication statusPublished - 28 Jun 2021
Event2021 24th ISPRS Congress Commission III: Imaging Today, Foreseeing Tomorrow - Nice, France
Duration: 5 Jul 20219 Jul 2021

Publication series

NameInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
PublisherInternational Society for Photogrammetry and Remote Sensing
NumberB3-2021
Volume43
ISSN (Print)1682-1750

Conference

Conference2021 24th ISPRS Congress Commission III: Imaging Today, Foreseeing Tomorrow
CountryFrance
CityNice
Period5/07/219/07/21

Keywords

  • Accuracy Assessment
  • Classification Uncertainty
  • Land Cover
  • Remote Sensing
  • Supervised Classification

Fingerprint

Dive into the research topics of 'Exploring the use of classification uncertainty to improve classification accuracy'. Together they form a unique fingerprint.

Cite this