Detection of Unmonitored Graveyards in VHR Satellite Data Using Fully Convolutional Networks

Henri Debray, Monika Kuffer, Christien Klaufus, Claudio Persello, Michael Wurm, Hannes Taubenböck, Karin Pfeffer

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

Abstract

Lima, Peru, is a highly dynamic urban region home to perpetually evolving informal areas. Earth observation (EO) studies on these areas focused almost solely on their inhabited parts, the informal housing. In this study, we propose to extend the focus to another component of the informal settlements: informal graveyards. Their emerging morphologies in Lima are similar to informal housing, making this particular distinction challenging. Furthermore, both graveyards and housing typically experience joint, intertwined spatial development. The adjacency of graveyards and informal housing causes social and public health risks. Therefore, detection of boundaries between graveyards and adjacent (in)formal housing is essential, e.g. as an information basis for preventing the spread of diseases and supporting public health and safety in general. However, housing invasions on burial grounds have not yet been systematically monitored. Therefore, this study aims to develop a method for the distinction of graveyards from (in)formal housing. We combined anthropological field observations with fully convolutional networks (FCNs) with dilated convolution of increasing spatial kernels to acquire features of deep level of abstraction on Pleiades optical satellite images. The trained neural network developed reaches good accuracies in mapping informal graveyards, (in)formal housing, and non-built areas with an average F1 score of 0.878.
Original languageEnglish
Title of host publicationUrban Inequalities from Space: Earth Observation Applications in the Majority World
EditorsMonika Kuffer, Stefanos Georganos
Pages167-188
Number of pages22
ISBN (Electronic)978-3-031-49183-2
DOIs
Publication statusPublished - 8 May 2024

Publication series

Name Remote Sensing and Digital Image Processing
Volume26

Keywords

  • 2024 OA procedure

Fingerprint

Dive into the research topics of 'Detection of Unmonitored Graveyards in VHR Satellite Data Using Fully Convolutional Networks'. Together they form a unique fingerprint.

Cite this