Details
| Original language | English |
|---|---|
| Pages (from-to) | 215-222 |
| Number of pages | 8 |
| Journal | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Volume | 4 |
| Issue number | 1/W1 |
| Publication status | Published - 30 May 2017 |
| Event | 38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017 - New Delhi, India Duration: 23 Oct 2017 → 27 Oct 2017 |
Abstract
Supervised classification of remotely sensed images is a classical method for change detection. The task requires training data in the form of image data with known class labels, whose manually generation is time-consuming. If the labels are acquired from the outdated map, the classifier must cope with errors in the training data. These errors, referred to as label noise, typically occur in clusters in object space, because they are caused by land cover changes over time. In this paper we adapt a label noise tolerant training technique for classification, so that the fact that changes affect larger clusters of pixels is considered. We also integrate the existing map into an iterative classification procedure to act as a prior in regions which are likely to contain changes. Our experiments are based on three test areas, using real images with simulated existing databases. Our results show that this method helps to distinguish between real changes over time and false detections caused by misclassification and thus improves the accuracy of the classification results.
Keywords
- Label noise, Logistic regression, Map updating, Supervised classification, Supervised Classification, Label Noise, Logistic Regression, Map Updating
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
- Environmental Science(all)
- Environmental Science (miscellaneous)
- Physics and Astronomy(all)
- Instrumentation
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 4, No. 1/W1, 30.05.2017, p. 215-222.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - Classification under label noise based on outdated MAPS
AU - Maas, A.
AU - Rottensteiner, F.
AU - Heipke, C.
N1 - Funding Information: This research was funded by the German Science Foundation (DFG) under grant HE-1822/35-1. The Vaihingen data set was provided by the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) (Cramer, 2010): http://www.ifp.uni-stuttgart.de/dgpf/DKEP-Allg.html. Publisher Copyright: Copyright © 2017 ISRS, All Rights Reserved. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2017/5/30
Y1 - 2017/5/30
N2 - Supervised classification of remotely sensed images is a classical method for change detection. The task requires training data in the form of image data with known class labels, whose manually generation is time-consuming. If the labels are acquired from the outdated map, the classifier must cope with errors in the training data. These errors, referred to as label noise, typically occur in clusters in object space, because they are caused by land cover changes over time. In this paper we adapt a label noise tolerant training technique for classification, so that the fact that changes affect larger clusters of pixels is considered. We also integrate the existing map into an iterative classification procedure to act as a prior in regions which are likely to contain changes. Our experiments are based on three test areas, using real images with simulated existing databases. Our results show that this method helps to distinguish between real changes over time and false detections caused by misclassification and thus improves the accuracy of the classification results.
AB - Supervised classification of remotely sensed images is a classical method for change detection. The task requires training data in the form of image data with known class labels, whose manually generation is time-consuming. If the labels are acquired from the outdated map, the classifier must cope with errors in the training data. These errors, referred to as label noise, typically occur in clusters in object space, because they are caused by land cover changes over time. In this paper we adapt a label noise tolerant training technique for classification, so that the fact that changes affect larger clusters of pixels is considered. We also integrate the existing map into an iterative classification procedure to act as a prior in regions which are likely to contain changes. Our experiments are based on three test areas, using real images with simulated existing databases. Our results show that this method helps to distinguish between real changes over time and false detections caused by misclassification and thus improves the accuracy of the classification results.
KW - Label noise
KW - Logistic regression
KW - Map updating
KW - Supervised classification
KW - Supervised Classification
KW - Label Noise
KW - Logistic Regression
KW - Map Updating
UR - http://www.scopus.com/inward/record.url?scp=85044516146&partnerID=8YFLogxK
U2 - 10.5194/isprs-annals-IV-1-W1-215-2017
DO - 10.5194/isprs-annals-IV-1-W1-215-2017
M3 - Conference article
VL - 4
SP - 215
EP - 222
JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
SN - 2194-9042
IS - 1/W1
T2 - 38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017
Y2 - 23 October 2017 through 27 October 2017
ER -