Home > Research > Publications & Outputs > Semi-automated landslide inventory mapping from...


Text available via DOI:

View graph of relations

Semi-automated landslide inventory mapping from bitemporal aerial photographs using change detection and level set method

Research output: Contribution to journalJournal articlepeer-review

<mark>Journal publication date</mark>15/03/2016
<mark>Journal</mark>Remote Sensing of Environment
Number of pages16
Pages (from-to)215-230
Publication StatusPublished
Early online date15/01/16
<mark>Original language</mark>English


Landslide inventory mapping (LIM) is an increasingly important research topic in remote sensing and natural hazards. Past studies achieve LIM mainly using on-screen interpretation of aerial photos, and little attention has been paid to developing more automated methods. In recent years, the use of multitemporal remote sensing images makes it possible to map landslides semi-automatically. Although numerous methods have been proposed, only a few methods are competent for some specific situations and there is large room for improvement in their degree of automation. For these reasons, a semi-automated approach is proposed for reliable and accurate LIM from bitemporal aerial orthophotos. Specifically, it consists of two principal steps: 1) change detection-based thresholding (CDT) and 2) level set evolution (LSE). CDT is mainly used to generate the initial zero-level curve (ZLC) for LSE, thus automating the proposed method considerably. It includes three substeps: 1) generating difference image (DI) using change vector analysis (CVA), 2) detecting landslide candidates using a thresholding method, and 3) removing errors using morphology operations. Then, landslide boundaries are detected using two types of LSE, i.e., edge-based LSE (ELSE) and region-based LSE (RLSE). Finally, the effectiveness and advantages of the proposed methods are corroborated by a series of experiments. Given its efficiency and accuracy, it can be applied to rapid responses of natural hazards. This study is the first attempt to apply LSE to LIM from bitemporal remote sensing images.