Textural classification of very high-resolution satellite imagery: Empirical estimation of the interaction between window size and detection accuracy in urban environment

In the framework of the textural-based classification of very-high resolution satellite imagery for urban analysis applications, the paper presents an exploration of the interaction between textural window size and standard statistical classification output quality. In contrast to the common approach that assumes a generically decreasing accuracy function for increasing textural window size, a non-intuitive result of this work is the demonstration of the possibility of obtaining high classification performance with very wide-area textural windows. Another interesting result is the observation that small textural patches in the image can also be detected with relatively very large textural windows.