Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Improving active queries with a local segmentation step and application to land cover classification

: Wuttke, Sebastian; Middelmann, Wolfgang; Stilla, Uwe

Fulltext urn:nbn:de:0011-n-4534557 (3.3 MByte PDF)
MD5 Fingerprint: 9c458d86d2bf438969190678be70fd7c
(CC) by
Created on: 6.7.2017

Heipke, C. ; International Society for Photogrammetry and Remote Sensing -ISPRS-:
ISPRS Hannover Workshop 2017 : HRIGI 17 - CMRT 17 - ISA 17 - EuroCOW 17, 6-9 June 2017, Hannover, Germany
Istanbul: ISPRS, 2017 (ISPRS Annals IV-1/W1)
Hannover Workshop "High-Resolution Earth Imaging for Geospatial Information" (HRIGI) <2017, Hannover>
European Calibration and Orientation Workshop (EuroCOW) <2017, Hannover>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()
Active Learning; Remote Sensing; Land Cover Classification; Segmentation; Hierarchical Clustering; Active Queries; Nat

Active queries is an active learning method used for classification of remote sensing images. It consists of three steps: hierarchical clustering, dendrogram division, and active label selection. The goal of active learning is to reduce the needed amount of labeled data while preserving classification accuracy. We propose to apply local segmentation as a new step preceding the hierarchical clustering. We are using the SLIC (simple linear iterative clustering) algorithm for dedicated image segmentation. This incorporates spatial knowledge which leads to an increased learning rate and reduces classification error. The proposed method is applied to six different areas of the Vaihingen dataset.