ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-1-2020
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-1-2020, 25–32, 2020
https://doi.org/10.5194/isprs-annals-V-1-2020-25-2020
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-1-2020, 25–32, 2020
https://doi.org/10.5194/isprs-annals-V-1-2020-25-2020

  03 Aug 2020

03 Aug 2020

URBAN MATERIAL CLASSIFICATION USING SPECTRAL AND TEXTURAL FEATURES RETRIEVED FROM AUTOENCODERS

R. Ilehag, J. Leitloff, M. Weinmann, and A. Schenk R. Ilehag et al.
  • Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology, Germany

Keywords: Material classification, Spectral features, Textural features, Autoencoder, Compressed representation, Spectral library

Abstract. Classification of urban materials using remote sensing data, in particular hyperspectral data, is common practice. Spectral libraries can be utilized to train a classifier since they provide spectral features about selected urban materials. However, urban materials can have similar spectral characteristic features due to high inter-class correlation which can lead to misclassification. Spectral libraries rarely provide imagery of their samples, which disables the possibility of classifying urban materials with additional textural information. Thus, this paper conducts material classification comparing the benefits of using close-range acquired spectral and textural features. The spectral features consist of either the original spectra, a PCA-based encoding or the compressed spectral representation of the original spectra retrieved using a deep autoencoder. The textural features are generated using a deep denoising convolutional autoencoder. The spectral and textural features are gathered from the recently published spectral library KLUM. Three classifiers are used, the two well-established Random Forest and Support Vector Machine classifiers in addition to a Histogram-based Gradient Boosting Classification Tree. The achieved overall accuracy was within the range of 70–80% with a standard deviation between 2–10% across all classification approaches. This indicates that the amount of samples still is insufficient for some of the material classes for this classification task. Nonetheless, the classification results indicate that the spectral features are more important for assigning material labels than the textural features.