Riemannian geometry for Compound Gaussian distributions: application to recursive change detection
This work addresses change detection in image time series, offering a computationally efficient method, though it appears incremental as it builds on existing Riemannian geometry concepts.
The authors tackled the problem of change detection in multivariate image time series by proposing a new Riemannian geometry for Compound Gaussian distributions, which enabled a recursive approach that achieved optimal performance with improved computational efficiency.
A new Riemannian geometry for the Compound Gaussian distribution is proposed. In particular, the Fisher information metric is obtained, along with corresponding geodesics and distance function. This new geometry is applied on a change detection problem on Multivariate Image Times Series: a recursive approach based on Riemannian optimization is developed. As shown on simulated data, it allows to reach optimal performance while being computationally more efficient.