Performance analysis of curvature scale space for automatic spatial registration of multisensor shorelines

Registration is a fundamental task in image processing used to match two or more images taken at different times, from different sensors or from different viewpoints. Problems that can occur are change over time, occlusion, image noise and differences in image geometry. The authors concentrate on the automatic registation of shorelines extracted from multisensor imagery. The authors examine the use of curvature scale space (CSS) to represent the shape of shorelines. In CSS, curve evolution is studied by smoothing a shape with a Gaussian kernel and computing the curvature at varying levels of detail. A representation can be constructed that is robust to image noise and is scale invariant, allowing the extraction of control points which characterise a shoreline regardless of its original scale. To map a (sub)set of control points unto another set, the authors use relaxation labeling built on constraints of CSS features and sensor geometry