On Land Slide Detection using TerraSAR-X over Earthen Levees
Mahrooghy, M., Aanstoos, J.V., Prasad, S., & Younan, N. H. (2012). On Land Slide Detection using TerraSAR-X over Earthen Levees. XXII International Society for Photogrammetry & Remote Sensing Congress. Melbourne, Australia: ISPRS.
Earthen levees have an important role to protect large areas of inhabited and cultivated land in the US from flooding. The failure of the levees can threaten the loss of life and property. There are more than 150,000 kilometers of levee structure with different designs and conditions over the entire US. Therefore, monitoring the levee system in order to detect and classify the levee vulnerabilities can help the levee boards and federal agencies to repair them rapidly. One of the problems which can lead to a complete failure during a high water event is a slough slide. Slough slides are slope failures along a levee. The roughness and corresponding textural characteristics of the soil in a slide can change the amount and pattern of radar backscatter. In this research, we are trying to detect the slides using x band SAR data. Our methodology consists of the following four steps: 1) segmentation of the levee area from background and exclusion of tree-covered areas; 2) extracting features including backscatter features (the magnitudes of the backscatter coefficients in each channel HH, VV) and texture features such as statistical features (variance, mean), features based on GLCM (Grey-Level Co-occurrence Matrix), and wavelet features (the mean and standard deviation of the approximation and detail (vertical, horizontal, and diagonal ) coefficients of a two-level decomposition using a sliding window size 7; 3) training a back propagation neural network classifier (one hidden layer) using ground-truth data (training data is based on healthy and slide pixels); and 4) testing the area of interest and validation of the results using ground truth data. A dual-polarimetric X-band image is acquired from the German TerraSAR-X satellite. Ground-truth data include the slides and healthy area. The study area is a 3 km stretch of levee along the lower Mississippi River in the United States. The output classification shows the two classes of healthy and slide areas. Preliminary results show classification accuracies of approximately 60% for detecting the slide pixels.