Context image classification with proportion estimation of mixed pixels under the assumption of continuously situated boundary pixels with almost same proportion

Abstract

A contextual image classifcation method with a proportion estimation of the pixels composed of several classes, Mixed pixels (MIXELs), is proposed. The method allows us to check the conectivity of separated road segments, which are observed frequently as discontinuity of roads in satellite remote sensing imagery.
Under the assumption of almost same proportions for the MIXELs in the discontinuous portion of road segments, a proportion estimation method utilizing Inverse Problem Solving is proposed.
The experimental results with the simulation data including observation noise show 73.5-98.8(%) of improvements in terms of proportion estimation accuracy (RMS error), compared to the results from the previously proposed method with generalized inverse matrix. Also usefulness of contextual classification based on the proposed proportion estimation was confirmed for the investigation of connectivity of roads in remotely sensed images from space.