Quasi-Dense Matching Algorithm for Close-Range Image Combined With Feature Line Constraint

Abstract

Point-based sparse or dense matching can typically obtain satisfactory 3D point clouds of general contour features, but the deformation problem at the edges of artificial objects is prominent. Thus, a quasi-dense matching algorithm for close-range images combined with feature line constraint is proposed in this study. The method utilizes reliable matched points to construct the initial Delaunay triangulation and then optimizes the triangulation using the matched feature line. On this basis, iterative quasi-dense matching based on triangulation constraint is implemented. The process achieves matching with the center of the inscribed circle of each triangle as the seed point and growing matching. Two sets of stereo image pairs acquired using smartphones and four sets of sequence images provided by public datasets are selected for quasi-dense matching experiments. The comparison of results of constraint matching of the two triangulations before and after optimization as well as the matching results obtained via VisualSFM software demonstrated that the 3D point cloud obtained via quasi-dense matching with feature line constraint presents better results at the edges of buildings, thereby confirming the effectiveness of the proposed algorithm.INDEX TERMS Quasi-dense matching, Delaunay triangulation, close-range image, image matching, feature line constraint.

Marker points 3D matching based on Delaunay triangfulation structure and error dispersion

“…The distinctive characteristics of Delaunay triangles have led to their frequent utilisation in the field of 2D image matching in recent years. In the studies referenced in [28][29][30], the similarity of the Delaunay triangle structure and the constraint relationship between the triangle structures is exploited to enhance the accuracy of the matching results and achieve a balance between robustness and matching efficiency. Meanwhile, in the studies referenced in [31,32], the process of Delaunay triangulation is exploited as a greedy algorithm that searches as much as possible and retains them.…”

“…In light of the exemplary performance of Delaunay triangular profiling in 2D images matching as evidenced in the literatures [28][29][30][31][32][33][34], and the high compatibility of the nature of 3D Delaunay triangulation and the necessity for matching structural units, it is evident that this approach is highly suitable for marker points 3D matching. Consequently, the establishment of matching units with structural relationships in the matching marker points process by Delaunay triangulation.…”