Hugo Costa
Using mixed objects in the training of object-based image classifications
Costa, Hugo; Foody, Giles M.; Boyd, Doreen S.
Authors
GILES FOODY giles.foody@nottingham.ac.uk
Professor of Geographical Information
DOREEN BOYD doreen.boyd@nottingham.ac.uk
Professor of Earth Observation
Abstract
Image classification for thematic mapping is a very common application in remote sensing, which is sometimes realized through object-based image analysis. In these analyses, it is common for some of the objects to be mixed in their class composition and thus violate the commonly made assumption of object purity that is implicit in a conventional object-based image analysis. Mixed objects can be a problem throughout a classification analysis, but are particularly challenging in the training stage as they can result in degraded training statistics and act to reduce mapping accuracy. In this paper the potential of using mixed objects in training object-based image classifications is evaluated. Remotely sensed data were submitted to a series of segmentation analyses from which a range of under- to over-segmented outputs were intentionally produced. Training objects were then selected from the segmentation outputs, resulting in training data sets that varied in terms of size (i.e. number of objects) and proportion of mixed objects. These training data sets were then used with an artificial neural network and a generalized linear model, which can accommodate objects of mixed composition, to produce a series of land cover maps. The use of training statistics estimated based on both pure and mixed objects often increased classification accuracy by around 25% when compared with accuracies obtained from the use of only pure objects in training. So rather than the mixed objects being a problem, they can be an asset in classification and facilitate land cover mapping from remote sensing. It is, therefore, desirable to recognize the nature of the objects and possibly accommodate mixed objects directly in training. The results obtained here may also have implications for the common practice of seeking an optimal segmentation output, and also act to challenge the widespread view that object-based classification is superior to pixel-based classification.
Citation
Costa, H., Foody, G. M., & Boyd, D. S. (2017). Using mixed objects in the training of object-based image classifications. Remote Sensing of Environment, 190, https://doi.org/10.1016/j.rse.2016.12.017
Journal Article Type | Article |
---|---|
Acceptance Date | Dec 29, 2016 |
Online Publication Date | Jan 4, 2017 |
Publication Date | Mar 1, 2017 |
Deposit Date | Jan 11, 2017 |
Publicly Available Date | Jan 11, 2017 |
Journal | Remote Sensing of Environment |
Print ISSN | 0034-4257 |
Electronic ISSN | 1879-0704 |
Publisher | Elsevier |
Peer Reviewed | Peer Reviewed |
Volume | 190 |
DOI | https://doi.org/10.1016/j.rse.2016.12.017 |
Keywords | OBIA; Mixed pixels; Under-segmentation; Over-segmentation; Scale parameter |
Public URL | https://nottingham-repository.worktribe.com/output/842685 |
Publisher URL | http://www.sciencedirect.com/science/article/pii/S0034425716304965 |
Contract Date | Jan 11, 2017 |
Files
Mixed_training_revised_cleanIII.pdf
(1.8 Mb)
PDF
Copyright Statement
Copyright information regarding this work can be found at the following address: http://creativecommons.org/licenses/by-nc-nd/4.0
You might also like
Good practices for estimating area and assessing accuracy of land change
(2014)
Journal Article
Usability of VGI for validation of land cover maps
(2015)
Journal Article
Downloadable Citations
About Repository@Nottingham
Administrator e-mail: discovery-access-systems@nottingham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search