The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B1-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B1-2021, 45–50, 2021
https://doi.org/10.5194/isprs-archives-XLIII-B1-2021-45-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B1-2021, 45–50, 2021
https://doi.org/10.5194/isprs-archives-XLIII-B1-2021-45-2021

  28 Jun 2021

28 Jun 2021

ON THE CLASSIFIER PERFORMANCE FOR SIMULATION BASED DEBRIS DETECTION IN SAR IMAGERY

S. Kuny1,2, H. Hammer1, and K. Schulz1 S. Kuny et al.
  • 1Fraunhofer IOSB, Institute of Optronics, System Technologies and Image Exploitation, Ettlingen, Germany
  • 2Institute of Photogrammetry and Remote Sensing IPF, Karlsruhe Institute of Technology KIT, Germany

Keywords: SAR simulation, debris, damage detection, texture features, classifier performance

Abstract. Urban areas struck by disasters such as earthquakes are in need of a fast damage detection assessment. A post-event SAR image often is the first available image, most likely with no matching pre-event image to perform change detection. In previous work we have introduced a debris detection algorithm for this scenario that is trained exclusively with synthetically generated training data. A classification step is employed to separate debris from similar textures such as vegetation. In order to verify the use of a random forest classifier for this context, we conduct a performance comparison with two alternative popular classifiers, a support vector machine and a convolutional neural network. With the direct comparison revealing the random forest classifier to be best suited, the effective performance on the prospect of debris detection is investigated for the post-earthquake Christchurch scene. Results show a good separation of debris from vegetation and gravel, thus reducing the false alarm rate in the damage detection operation considerably.