ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-2-2020
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2020, 573–582, 2020
https://doi.org/10.5194/isprs-annals-V-2-2020-573-2020
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2020, 573–582, 2020
https://doi.org/10.5194/isprs-annals-V-2-2020-573-2020

  03 Aug 2020

03 Aug 2020

INFRASTRUCTURE DEGRADATION AND POST-DISASTER DAMAGE DETECTION USING ANOMALY DETECTING GENERATIVE ADVERSARIAL NETWORKS

S. M. Tilon1, F. Nex1, D. Duarte2,3, N. Kerle1, and G. Vosselman1 S. M. Tilon et al.
  • 1Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, Enschede, The Netherlands
  • 2INESC-Coimbra, Institute for Systems Engineering and Computers at Coimbra, University of Coimbra, Coimbra, Portugal
  • 3Department of Mathematics, University of Coimbra, Coimbra, Portugal

Keywords: Generative Adversarial Networks, anomaly detection, degradation, damage, infrastructure monitoring, post-disaster

Abstract. Degradation and damage detection provides essential information to maintenance workers in routine monitoring and to first responders in post-disaster scenarios. Despite advance in Earth Observation (EO), image analysis and deep learning techniques, the quality and quantity of training data for deep learning is still limited. As a result, no robust method has been found yet that can transfer and generalize well over a variety of geographic locations and typologies of damages. Since damages can be seen as anomalies, occurring sparingly over time and space, we propose to use an anomaly detecting Generative Adversarial Network (GAN) to detect damages. The main advantages of using GANs are that only healthy unannotated images are needed, and that a variety of damages, including the never before seen damage, can be detected. In this study we aimed to investigate 1) the ability of anomaly detecting GANs to detect degradation (potholes and cracks) in asphalt road infrastructures using Mobile Mapper imagery and building damage (collapsed buildings, rubble piles) using post-disaster aerial imagery, and 2) the sensitivity of this method against various types of pre-processing. Our results show that we can detect damages in urban scenes at satisfying levels but not on asphalt roads. Future work will investigate how to further classify the found damages and how to improve damage detection for asphalt roads.