A Dense Matching Algorithm of Multi-view Image Based on the Integrated Multiple Matching Primitives
Wang Jing-xu · Acta Geodaetica et Cartographica Sinica · 2013
Aiming at the occlusion problem of multi-view image matching,a new dense matching algorithm was presented by integrating the feature points in image object and plane elements in the space object,which is based on the space plane divided in regular grids.Firstly,it realized the simultaneously matching of feature points and plane elements by the constrains of the projection ranges of feature points in multi-view image and the positions of plane elements,and provided a reliable initial DSM for the next dense matching.Then it carried on the dense matching of regular distribution plane elements by combining the vertical line locus method and the height-based occlusion detection method,and densitied the initial matching results.Finally,the validity of the algorithm proposed in this paper was verified by the experiments using four UltraCamX(UCX)digital aerial images.