Extended SLIC superpixels algorithm for applications to non-imagery geospatial rasters

Abstract

Converting an image to a set of superpixels is a useful preprocessing step in many computer vision applications; it reduces the dimensionality of the data and removes noise. The most popular superpixels algorithm is the Simple Linear Iterative Clustering (SLIC). To use original SLIC with non-imagery data (for example, rasters of discrete probability distributions, time-series, or matrices describing local texture or pattern), the data needs to be converted to the false-color RGB image constructed from the first three principal components. Here we propose to extend the SLIC algorithm so it can work with non-imagery data structures without data reduction and conversion to the false-color image. The modification allows for using a data distance measure most appropriate to a particular data structure and for using a custom function for averaging values of clusters centers. Comparisons between the extended and original SLIC algorithms in three different mapping tasks are presented and discussed. The results show that the extended SLIC improves the accuracy of the final products in reverse proportion to the percentage of variability explained by the three-dimensional (RGB) approximation to multidimensional non-imagery data. Thus, the largest advantage of using the modified SLIC can be expected in applications to data that cannot be compressed to three dimensions without a significant departure from its original variability. • Superpixels algorithm SLIC is extended to work with non-imagery geospatial data. • Case studies show that the extended SLIC outperforms the original on such data. • The improvement is inversely proportional to the compressibility of the data. • Extended SLIC expedites automated regionalization of large geospatial data.