Extracting the spatial features from satellite images using the multilayer level set method

Several sophisticated algorithms have been proposed to automatically extract spatial features from satellite images. They use gradient methods to compare the differences between pixels in order to extract edges and other characteristics from a given image. This is in contrast to manual extraction, which is currently the most popular method of converting geographic data from analog to digital. These algorithms are not entirely automated however, as they require some manual input to manage large differences between pixels. In an attempt to avoid this, we employ a multilayer level set method to isolate regional boundaries such that they are implicitly represented by several nested level lines according to pre-specified level values. This method provides numerical stability and quick convergence. After each iteration the initial curves automatically extend closer to the regional boundaries in order to minimize energy. This method is not only able to extract the regional boundaries from the given image but also generate an optimal piecewise continuous image such that each approximation sub-region is homogeneous. In this paper, a SPOT satellite image is used to evaluate the performance of the multilayer algorithms. The spatial features are extracted separately for each band in the multispectral image. They are then combined together to produce the full delineation of extracted features. Using these numerical results, the river and its surrounding areas in the given images can be extracted and shown with different layer values. With careful choice of parameters, the multilayer level set method demonstrates robustness in extracting spatial features from images.