$k$-means on Positive Definite Matrices, and an Application to Clustering in Radar Image Sequences
This provides a method for radar image analysis, but appears incremental as it adapts existing clustering techniques to a specific data type.
The paper tackles the problem of clustering Symmetric Positive Definite matrices by extending $k$-means to a non-Euclidean space, and applies this to group pixels in Synthetic Aperture Radar image sequences based on their autocovariance matrices.
We state theoretical properties for $k$-means clustering of Symmetric Positive Definite (SPD) matrices, in a non-Euclidean space, that provides a natural and favourable representation of these data. We then provide a novel application for this method, to time-series clustering of pixels in a sequence of Synthetic Aperture Radar images, via their finite-lag autocovariance matrices.