Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 11-16 |
| Seitenumfang | 6 |
| Fachzeitschrift | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
| Jahrgang | 42 |
| Ausgabenummer | 1/W1 |
| Publikationsstatus | Veröffentlicht - 30 Mai 2017 |
| Veranstaltung | ISPRS Hannover Workshop 2017: HRIGI - High-Resolution Earth Imaging for Geospatial Information, CMRT - City Models, Roads and Traffic, ISA - Image Sequence Analysis, EuroCOW - European Calibration and Orientation Workshop - Hannover, Hannover, Deutschland Dauer: 6 Juni 2017 → 9 Juni 2017 |
Abstract
Updating topographic geospatial databases is often performed based on current remotely sensed images. To automatically extract the object information (labels) from the images, supervised classifiers are being employed. Decisions to be taken in this process concern the definition of the classes which should be recognised, the features to describe each class and the training data necessary in the learning part of classification. With a view to large scale topographic databases for fast developing urban areas in the Kingdom of Saudi Arabia we conducted a case study, which investigated the following two questions: (a) which set of features is best suitable for the classification?; (b) what is the added value of height information, e.g. derived from stereo imagery? Using stereoscopic GeoEye and Ikonos satellite data we investigate these two questions based on our research on label tolerant classification using logistic regression and partly incorrect training data. We show that in between five and ten features can be recommended to obtain a stable solution, that height information consistently yields an improved overall classification accuracy of about 5%, and that label noise can be successfully modelled and thus only marginally influences the classification results.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Information systems
- Sozialwissenschaften (insg.)
- Geografie, Planung und Entwicklung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Jahrgang 42, Nr. 1/W1, 30.05.2017, S. 11-16.
Publikation: Beitrag in Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review
}
TY - JOUR
T1 - AUTOMATIC CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGERY
T2 - ISPRS Hannover Workshop 2017 on High-Resolution Earth Imaging for Geospatial Information, HRIGI 2017, City Models, Roads and Traffic , CMRT 2017, Image Sequence Analysis, ISA 2017, European Calibration and Orientation Workshop, EuroCOW 2017
AU - Maas, A.
AU - Alrajhi, M.
AU - Alobeid, A.
AU - Heipke, C.
N1 - Copyright: Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2017/5/30
Y1 - 2017/5/30
N2 - Updating topographic geospatial databases is often performed based on current remotely sensed images. To automatically extract the object information (labels) from the images, supervised classifiers are being employed. Decisions to be taken in this process concern the definition of the classes which should be recognised, the features to describe each class and the training data necessary in the learning part of classification. With a view to large scale topographic databases for fast developing urban areas in the Kingdom of Saudi Arabia we conducted a case study, which investigated the following two questions: (a) which set of features is best suitable for the classification?; (b) what is the added value of height information, e.g. derived from stereo imagery? Using stereoscopic GeoEye and Ikonos satellite data we investigate these two questions based on our research on label tolerant classification using logistic regression and partly incorrect training data. We show that in between five and ten features can be recommended to obtain a stable solution, that height information consistently yields an improved overall classification accuracy of about 5%, and that label noise can be successfully modelled and thus only marginally influences the classification results.
AB - Updating topographic geospatial databases is often performed based on current remotely sensed images. To automatically extract the object information (labels) from the images, supervised classifiers are being employed. Decisions to be taken in this process concern the definition of the classes which should be recognised, the features to describe each class and the training data necessary in the learning part of classification. With a view to large scale topographic databases for fast developing urban areas in the Kingdom of Saudi Arabia we conducted a case study, which investigated the following two questions: (a) which set of features is best suitable for the classification?; (b) what is the added value of height information, e.g. derived from stereo imagery? Using stereoscopic GeoEye and Ikonos satellite data we investigate these two questions based on our research on label tolerant classification using logistic regression and partly incorrect training data. We show that in between five and ten features can be recommended to obtain a stable solution, that height information consistently yields an improved overall classification accuracy of about 5%, and that label noise can be successfully modelled and thus only marginally influences the classification results.
UR - http://www.scopus.com/inward/record.url?scp=85021095746&partnerID=8YFLogxK
U2 - 10.5194/isprs-archives-XLII-1-W1-11-2017
DO - 10.5194/isprs-archives-XLII-1-W1-11-2017
M3 - Conference article
AN - SCOPUS:85021095746
VL - 42
SP - 11
EP - 16
JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
SN - 1682-1750
IS - 1/W1
Y2 - 6 June 2017 through 9 June 2017
ER -