Landslide Mapping From PlanetScope Images Using Improved Region-Based Level Set Evolution
Ping Lü, Wenyang Shi, Zhongbin Li
Abstract
A timely and reliable inventory is essential for landslide hazard assessment and risk management. In this study, we use images from PlanetScope, which provides global 3 m daily Earth observations, for rapid mapping of landslide inventory. We propose a semiautomated method that combines change detection and region-based level set evolution (RLSE) to improve landslide mapping efficiency. Our approach uses change detection methods of independent component analysis (ICA), principal component analysis (PCA), and change vector analysis (CVA) for automated generation of landslide zero-level curves (ZLCs), and then incorporates the RLSE method to refine landslide mapping results. To corroborate the applicability of the proposed method, we test the landslide mapping performance on the Kodagu event (India, 2018) using ICA-, PCA- and CVA-based RLSE. The results show that ICA-based RLSE can achieve better landslide mapping accuracy in terms of completeness, correctness, and the Kappa coefficient. This study demonstrates the suitability and potential of low-orbit miniature satellites such as PlanetScope for landslide mapping. To the best of our knowledge, it is the first attempt to incorporate PlanetScope images and the change detection-based RLSE method for landslide mapping.