Detection of Fragmented Rectangular Enclosures in Very-High-Resolution Remote Sensing Images

dc.contributor.authorZingman, Igor
dc.contributor.authorSaupe, Dietmar
dc.contributor.authorPenatti, Otavio
dc.contributor.authorLambers, Karsten
dc.date.accessioned2016-03-22T16:03:26Z
dc.date.available2016-03-22T16:03:26Z
dc.date.issued2016eng
dc.description.abstractWe develop an approach for detection of ruins of livestock enclosures in alpine areas captured by high-resolution remotely sensed images. These structures are usually of approximately rectangular shape and appear in images as faint fragmented contours in complex background. We address this problem by introducing a rectangularity feature that quantifies the degree of alignment of an optimal subset of extracted linear segments with a contour of rectangular shape. The rectangularity feature has high values not only for perfectly regular enclosures, but also for ruined ones with distorted angles, fragmented walls, or even a completely missing wall. Furthermore, it has zero value for spurious structures with less than three sides of a perceivable rectangle.
We show how the detection performance can be improved by learning a linear combination of the rectangularity and size features from just a few available representative examples and a large number of negatives. Our approach allowed detection of enclosures in the Silvretta Alps that were previously unknown.
A comparative performance analysis is provided. Among other features, our comparison includes the state-of-the-art features that were generated by pre-trained deep convolutional neural networks (CNN). The deep CNN features, though learned from a very different type of images, provided the basic ability to capture the visual concept of the livestock enclosures. However, our handcrafted rectangularity-size features showed considerably higher performance.
eng
dc.description.versionacceptedeng
dc.identifier.urihttps://kops.uni-konstanz.de/handle/123456789/32382
dc.language.isoengeng
dc.rightsterms-of-use
dc.rights.urihttps://rightsstatements.org/page/InC/1.0/
dc.subjectObject detection, incomplete rectangles, man-made structures, maximal cliques, rectangularity feature, deep CNN featureseng
dc.subject.ddc004
dc.titleDetection of Fragmented Rectangular Enclosures in Very-High-Resolution Remote Sensing Imageseng
dc.typeJOURNAL_ARTICLEeng
dspace.entity.typePublication
kops.description.openAccessopenaccessgreen
kops.flag.knbibliographytrue
kops.flag.quicksubmissiontrueeng
source.identifier.eissn1558-0644
source.identifier.issn0196-2892
source.periodicalTitleIEEE Transactions on Geoscience and Remote Sensing (T-GRS)eng
temp.submission.doi
temp.submission.source
Dateien
Originalbündel
Gerade angezeigt 1 - 1 von 1
Lade...
Vorschaubild
Name:
fragmentedRectangularStructuresIEEE_revised.pdf
Größe:
2.43 MB
Format:
Adobe Portable Document Format
Beschreibung:
Lizenzbündel
Gerade angezeigt 1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
license.txt
Größe:
3.88 KB
Format:
Item-specific license agreed upon to submission
Beschreibung:
license.txt
license.txtGröße: 3.88 KBDownloads: ?

Versionsgeschichte

Gerade angezeigt 1 - 3 von 3
VersionDatumZusammenfassung
2017-08-02 08:24:22
3*
2016-03-22 15:57:07
After a minor revision the article was accepted to IEEE Transactions on Geoscience and Remote Sensing
2015-12-11 10:41:51
* Ausgewählte Version