Using Texture to Annotate Remote Sensed Datasets

Texture remains largely underutilized in the analysis of remote sensed datasets compared to descriptors based on the orthogonal spectral dimension. This paper describes our recent efforts towards using texture to automate the annotation of remote sensed imagery Two applications are described that use the homogeneous texture descriptor recently standardized by MPEG-7. In the Jirst, higher-level access to remote sensed imagery is enabled by using the texture descriptor to model geospatial objects. In particular, the common textures, or texture motifs, are characterized as Gaussian mixtures in the high-dimensional feature space. In the second application, the texture descriptor is used to label regions in a large collection of aerial videography in a perceptually meaningfid way. Gaussian mhtures are used to model the distribution af feature vectors for a variety of semantic classes. Frame level similarif?i retrieval based an semantic layout and semantic histogram is enabled by modeling the spatial arrangement af the labeled regions as a Markov random$eld.