Details
| Original language | English |
|---|---|
| Pages (from-to) | 263-277 |
| Number of pages | 15 |
| Journal | Photogrammetric Engineering and Remote Sensing |
| Volume | 84 |
| Issue number | 5 |
| Publication status | Published - 1 May 2018 |
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. If the training labels are acquired from an outdated map, the classifier must cope with errors in the training labels. These errors (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 priori in regions which are likely to contain changes. Additionally we expand the model for multitemporal data, making it applicable for time series. Our experiments are based on four test areas, including a multitemporal example. Our results show that this method helps to distinguish between real changes over time and false detections caused by misclassification and thus improve the accuracy of the classification results.
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Photogrammetric Engineering and Remote Sensing, Vol. 84, No. 5, 01.05.2018, p. 263-277.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Multitemporal classification under label noise based on outdated maps
AU - Maas, Alina E.
AU - Rottensteiner, Franz
AU - Alobeid, Abdalla
AU - Heipke, Christian
N1 - Funding Information: dgpf/DKEP-Allg.html. This work was supported by the Ger- Funding Information: man Science Foundation (DFG) under grant HE 1822/35-1. Publisher Copyright: © 2018 American Society for Photogrammetry and Remote Sensing. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/5/1
Y1 - 2018/5/1
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. If the training labels are acquired from an outdated map, the classifier must cope with errors in the training labels. These errors (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 priori in regions which are likely to contain changes. Additionally we expand the model for multitemporal data, making it applicable for time series. Our experiments are based on four test areas, including a multitemporal example. Our results show that this method helps to distinguish between real changes over time and false detections caused by misclassification and thus improve 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. If the training labels are acquired from an outdated map, the classifier must cope with errors in the training labels. These errors (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 priori in regions which are likely to contain changes. Additionally we expand the model for multitemporal data, making it applicable for time series. Our experiments are based on four test areas, including a multitemporal example. Our results show that this method helps to distinguish between real changes over time and false detections caused by misclassification and thus improve the accuracy of the classification results.
UR - http://www.scopus.com/inward/record.url?scp=85047421029&partnerID=8YFLogxK
U2 - 10.14358/PERS.84.5.263
DO - 10.14358/PERS.84.5.263
M3 - Article
AN - SCOPUS:85047421029
VL - 84
SP - 263
EP - 277
JO - Photogrammetric Engineering and Remote Sensing
JF - Photogrammetric Engineering and Remote Sensing
SN - 0099-1112
IS - 5
ER -