Scipediacontent: Scipediacontent moved page Draft Content 641793975 to Belgiu Drǎgut 2014a

2021-02-03T17:34:58Z

Scipediacontent moved page Draft Content 641793975 to Belgiu Drǎgut 2014a

Scipediacontent: Created page with " == Abstract == hough multiresolution segmentation (MRS) is a powerful technique for dealing with very high resolution imagery, some of the image objects that it generates do..."

2021-02-03T17:34:54Z

Created page with " == Abstract == hough multiresolution segmentation (MRS) is a powerful technique for dealing with very high resolution imagery, some of the image objects that it generates do..."

New page

== Abstract ==

hough multiresolution segmentation (MRS) is a powerful technique for dealing with very high resolution imagery, some of the image objects that it generates do not match the geometries of the target objects, which reduces the classification accuracy. MRS can, however, be guided to produce results that approach the desired object geometry using either supervised or unsupervised approaches. Although some studies have suggested that a supervised approach is preferable, there has been no comparative evaluation of these two approaches. Therefore, in this study, we have compared supervised and unsupervised approaches to MRS. One supervised and two unsupervised segmentation methods were tested on three areas using QuickBird and WorldView-2 satellite imagery. The results were assessed using both segmentation evaluation methods and an accuracy assessment of the resulting building classifications. Thus, differences in the geometries of the image objects and in the potential to achieve satisfactory thematic accuracies were evaluated. The two approaches yielded remarkably similar classification results, with overall accuracies ranging from 82% to 86%. The performance of one of the unsupervised methods was unexpectedly similar to that of the supervised method; they identified almost identical scale parameters as being optimal for segmenting buildings, resulting in very similar geometries for the resulting image objects. The second unsupervised method produced very different image objects from the supervised method, but their classification accuracies were still very similar. The latter result was unexpected because, contrary to previously published findings, it suggests a high degree of independence between the segmentation results and classification accuracy. The results of this study have two important implications. The first is that object-based image analysis can be automated without sacrificing classification accuracy, and the second is that the previously accepted idea that classification is dependent on segmentation is challenged by our unexpected results, casting doubt on the value of pursuing ‘optimal segmentation’. Our results rather suggest that as long as under-segmentation remains at acceptable levels, imperfections in segmentation can be ruled out, so that a high level of classification accuracy can still be achieved.

== Original document ==

The different versions of the original document can be found in:

* [http://dx.doi.org/10.1016/j.isprsjprs.2014.07.002 http://dx.doi.org/10.1016/j.isprsjprs.2014.07.002] under the license http://creativecommons.org/licenses/by/4.0

* [http://dx.doi.org/10.1016/j.isprsjprs.2014.07.002 http://dx.doi.org/10.1016/j.isprsjprs.2014.07.002] under the license http://creativecommons.org/licenses/by/4.0/

* [http://europepmc.org/articles/PMC4183749 http://europepmc.org/articles/PMC4183749]

* [https://doi.org/10.1016/j.isprsjprs.2014.07.002 https://doi.org/10.1016/j.isprsjprs.2014.07.002] under the license cc-by

* [https://api.elsevier.com/content/article/PII:S0924271614001749?httpAccept=text/xml https://api.elsevier.com/content/article/PII:S0924271614001749?httpAccept=text/xml],
: [https://api.elsevier.com/content/article/PII:S0924271614001749?httpAccept=text/plain https://api.elsevier.com/content/article/PII:S0924271614001749?httpAccept=text/plain],
: [http://dx.doi.org/10.1016/j.isprsjprs.2014.07.002 http://dx.doi.org/10.1016/j.isprsjprs.2014.07.002] under the license https://www.elsevier.com/tdm/userlicense/1.0/

* [https://www.sciencedirect.com/science/article/pii/S0924271614001749 https://www.sciencedirect.com/science/article/pii/S0924271614001749],
: [https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4183749 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4183749],
: [http://europepmc.org/articles/PMC4183749 http://europepmc.org/articles/PMC4183749],
: [http://ui.adsabs.harvard.edu/abs/2014JPRS...96...67B/abstract http://ui.adsabs.harvard.edu/abs/2014JPRS...96...67B/abstract],
: [https://core.ac.uk/display/82454642 https://core.ac.uk/display/82454642],
: [https://research.utwente.nl/en/publications/comparing-supervised-and-unsupervised-multiresolution-segmentatio https://research.utwente.nl/en/publications/comparing-supervised-and-unsupervised-multiresolution-segmentatio],
: [https://www.epistemio.com/p/T60Sb4BY https://www.epistemio.com/p/T60Sb4BY],
: [https://pubag.nal.usda.gov/catalog/6006562 https://pubag.nal.usda.gov/catalog/6006562],
: [https://uni-salzburg.elsevierpure.com/de/publications/comparing-supervised-and-unsupervised-multiresolution-segmentatio https://uni-salzburg.elsevierpure.com/de/publications/comparing-supervised-and-unsupervised-multiresolution-segmentatio],
: [https://academic.microsoft.com/#/detail/2089716607 https://academic.microsoft.com/#/detail/2089716607]

* [ ]

← Older revision	Revision as of 17:34, 3 February 2021
(No difference)

Belgiu Drǎgut 2014a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 641793975 to Belgiu Drǎgut 2014a

Scipediacontent: Created page with " == Abstract == hough multiresolution segmentation (MRS) is a powerful technique for dealing with very high resolution imagery, some of the image objects that it generates do..."