ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume IV-2/W5
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2/W5, 453–460, 2019
https://doi.org/10.5194/isprs-annals-IV-2-W5-453-2019
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2/W5, 453–460, 2019
https://doi.org/10.5194/isprs-annals-IV-2-W5-453-2019

  29 May 2019

29 May 2019

CHANGE DETECTION BETWEEN DIGITAL SURFACE MODELS FROM AIRBORNE LASER SCANNING AND DENSE IMAGE MATCHING USING CONVOLUTIONAL NEURAL NETWORKS

Z. Zhang1, G. Vosselman1, M. Gerke2, C. Persello1, D. Tuia3, and M. Y. Yang1 Z. Zhang et al.
  • 1Dept. of Earth Observation Science, Faculty ITC, University of Twente, The Netherlands
  • 2Institute of Geodesy and Photogrammetry, Technical University of Brunswick, Germany
  • 3Wageningen University and Research, The Netherlands

Keywords: Change Detection, Digital Surface Model (DSM), Airborne Laser Scanning, Dense Image Matching, Convolutional Neural Network (CNN)

Abstract. Airborne photogrammetry and airborne laser scanning are two commonly used technologies used for topographical data acquisition at the city level. Change detection between airborne laser scanning data and photogrammetric data is challenging since the two point clouds show different characteristics. After comparing the two types of point clouds, this paper proposes a feed-forward Convolutional Neural Network (CNN) to detect building changes between them. The motivation from an application point of view is that the multimodal point clouds might be available for different epochs. Our method contains three steps: First, the point clouds and orthoimages are converted to raster images. Second, square patches are cropped from raster images and then fed into CNN for change detection. Finally, the original change map is post-processed with a simple connected component analysis. Experimental results show that the patch-based recall rate reaches 0.8146 and the precision rate reaches 0.7632. Object-based evaluation shows that 74 out of 86 building changes are correctly detected.