Open AccessThis article is
- freely available
Machine Learning Comparison between WorldView-2 and QuickBird-2-Simulated Imagery Regarding Object-Based Urban Land Cover Classification
German Remote Sensing Data Center (DFD), DLR, Oberpfaffenhofen, D-82234 Weßling, Germany
Remote Sensing Division (DSR), National Institute for Space Research (INPE), Sao Jose dos Campos, SP-12227-010, Brazil
Department of Photogrammetry and Remote Sensing, Technische Universitaet Muenchen (TUM), D-80333 Munich, Germany
* Author to whom correspondence should be addressed.
Received: 19 August 2011; in revised form: 14 October 2011 / Accepted: 14 October 2011 / Published: 21 October 2011
Abstract: The objective of this study is to compare WorldView-2 (WV-2) and QuickBird-2-simulated (QB-2) imagery regarding their potential for object-based urban land cover classification. Optimal segmentation parameters were automatically found for each data set and the obtained results were quantitatively compared and discussed. Four different feature selection algorithms were used in order to verify to which data set the most relevant object-based features belong to. Object-based classifications were performed with four different supervised algorithms applied to each data set and the obtained accuracies and model performances indexes were compared. Segmentation experiments carried out involving bands exclusively available in the WV-2 sensor generated segments slightly more similar to our reference segments (only about 0.23 discrepancy). Fifty seven percent of the different selected features and 53% of all the 80 selections refer to features that can only be calculated with the additional bands of the WV-2 sensor. On the other hand, 57% of the most relevant features and 63% of the second most relevant features can also be calculated considering only the QB-2 bands. In 10 out of 16 classifications, higher Kappa values were achieved when features related to the additional bands of the WV-2 sensor were also considered. In most cases, classifications carried out with the 8-band-related features generated less complex and more efficient models than those generated only with QB-2 band-related features. Our results lead to the conclusion that spectrally similar classes like ceramic tile roofs and bare soil, as well as asphalt and dark asbestos roofs can be better distinguished when the additional bands of the WV-2 sensor are used throughout the object-based classification process.
Keywords: urban remote sensing; high spatial resolution; feature selection; image segmentation; image classification
Citations to this Article
Cite This Article
MDPI and ACS Style
Novack, T.; Esch, T.; Kux, H.; Stilla, U. Machine Learning Comparison between WorldView-2 and QuickBird-2-Simulated Imagery Regarding Object-Based Urban Land Cover Classification
. Remote Sens. 2011, 3, 2263-2282.
Novack T, Esch T, Kux H, Stilla U. Machine Learning Comparison between WorldView-2 and QuickBird-2-Simulated Imagery Regarding Object-Based Urban Land Cover Classification
. Remote Sensing. 2011; 3(10):2263-2282.
Novack, Tessio; Esch, Thomas; Kux, Hermann; Stilla, Uwe. 2011. "Machine Learning Comparison between WorldView-2 and QuickBird-2-Simulated Imagery Regarding Object-Based Urban Land Cover Classification
." Remote Sens. 3, no. 10: 2263-2282.