The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 1189–1193, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-1189-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 1189–1193, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-1189-2020

  14 Aug 2020

14 Aug 2020

DEEP LEARNING APPLIED TO WATER SEGMENTATION

T. S. Akiyama1, J. Marcato Junior1, W. N. Gonçalves1,2, P. O. Bressan2, A. Eltner3, F. Binder3, and T. Singer4 T. S. Akiyama et al.
  • 1Faculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande, Brazil
  • 2Faculty of Computer Science, Federal University of Mato Grosso do Sul, Campo Grande, Brazil
  • 3Institute of Photogrammetry and Remote Sensing, Technische Universität Dresden, 01062 Dresden, Germany
  • 4Institute of Hydrology, Technische Universität Dresden, Dresden, Germany

Keywords: Convolutional Neural Network, Semantic Segmentation, Hydrology, Remote Sensing, Urban Floods

Abstract. The use of deep learning (DL) with convolutional neural networks (CNN) to monitor surface water can be a valuable supplement to costly and labour-intense standard gauging stations. This paper presents the application of a recent CNN semantic segmentation method (SegNet) to automatically segment river water in imagery acquired by RGB sensors. This approach can be used as a new supporting tool because there are only a few studies using DL techniques to monitor water resources. The study area is a medium-scale river (Wesenitz) located in the East of Germany. The captured images reflect different periods of the day over a period of approximately 50 days, allowing for the analysis of the river in different environmental conditions and situations. In the experiments, we evaluated the input image resolutions of 256 × 256 and 512 × 512 pixels to assess their influence on the performance of river segmentation. The performance of the CNN was measured with the pixel accuracy and IoU metrics revealing an accuracy of 98% and 97%, respectively, for both resolutions, indicating that our approach is efficient to segment water in RGB imagery.