Noncontact detection of earthquake-induced landslides by an enhanced image binarization method incorporating with Monte-Carlo simulation

Detecting landslides using remote sensing images involves converting gray level images into binary images. Given the complex background and non-uniform illumination in the regional remote sensing image, the commonly-used global thresholding methods are limited to interpret some landslides those hidden in the shadow. In this paper, we report on an enhanced image thresholding method for the noncontact detection of earthquake-induced landslides. The proposed method incorporates Monte-Carlo simulation into the local thresholding method, and essential issues, regarding complex illumination condition and uncertainties of determining block size in local thresholding method, are addressed. To better separate landslide candidate objects from the background, we incorporate Digital Surface Model (DSM) into the binary image, such that the interferences by built-up areas, terraces, and rivers can be significantly reduced considering the indicator of slope gradient. The described method has been tested using two benchmark tests, showing that the proposed method performs well dealing with the complex background and illumination condition. As a case study, we use the proposed method to detect landslides in a remote sensing image near Beichuan area after the 2008 Ms8.0 Wenchuan earthquake. Results demonstrate that the presented method interprets landslides resembling those of manually visual delineation.