Considering the uncertainty in image matching caused by repetitive textures and occlusions

this paper presents a multi-view image matching algorithm for feature point under the moving Z-Plane constraint. This algorithm projects the feature points extracted from multiple images onto different height planes

then uses the grid cells in the Z-Plane to constrain the corresponding matching candidate. It carries on the selective matching for multiple images depending on the projection rays in the grid cell

so as to avoid the problem caused by occlusions. Finally

the validity of the algorithm proposed in this paper is verified by the experiments using four UltraCamX （UCX） digital aerial images

the algorithm is shown to have reliable matching results.