Semisupervised Manifold Alignment of Multimodal Remote Sensing Images
This addresses the need for automated alignment of remote sensing images from various sensors and conditions, reducing user interaction and parameter tuning, though it appears incremental as it builds on existing manifold alignment concepts.
The authors tackled the problem of aligning multimodal remote sensing images with different resolutions and acquisition conditions by introducing a semisupervised manifold alignment method that pulls same-class samples together and pushes different-class samples apart while preserving manifold geometry. The method performed well in toy examples and real classification problems, leading to accurate classification for all domains.
We introduce a method for manifold alignment of different modalities (or domains) of remote sensing images. The problem is recurrent when a set of multitemporal, multisource, multisensor and multiangular images is available. In these situations, images should ideally be spatially coregistred, corrected and compensated for differences in the image domains. Such procedures require the interaction of the user, involve tuning of many parameters and heuristics, and are usually applied separately. Changes of sensors and acquisition conditions translate into shifts, twists, warps and foldings of the image distributions (or manifolds). The proposed semisupervised manifold alignment (SS-MA) method aligns the images working directly on their manifolds, and is thus not restricted to images of the same resolutions, either spectral or spatial. SS-MA pulls close together samples of the same class while pushing those of different classes apart. At the same time, it preserves the geometry of each manifold along the transformation. The method builds a linear invertible transformation to a latent space where all images are alike, and reduces to solving a generalized eigenproblem of moderate size. We study the performance of SS-MA in toy examples and in real multiangular, multitemporal, and multisource image classification problems. The method performs well for strong deformations and leads to accurate classification for all domains.