Automatic multisensor image registration based on global and local geometric consistent edge segments

Edge based image registration is efficient for multisensor image registration. However, original similarity measures are sensitive to noise or geometric distortion. In order to solve the problems, a new similarity measure is proposed combining chord distance and local geometric modal. Meanwhile consistency between global and local geometric modal is used to enhance the robustness of registration. Only matched edge segments consistent with both global and local geometric modal are reserved as final matched results. Experiments show that the proposed method is applicable in registering multisensor images with strong edges.