Abstract
Reliable image matching is the basis of image-based three-dimensional (3D) reconstruction. This study presents a quasi-dense matching method based on triangulation constraint and propagation as applied to different types of close-range image matching, such as illumination change, large viewpoint, and scale change. The method begins from a set of sparse matched points that are used to construct an initial Delaunay triangulation. Edge-to-edge matching propagation is then conducted for the point matching. Two types of matching primitives from the edges of triangles with areas larger than a given threshold in the reference image, that is, the midpoints of edges and the intersections between the edges and extracted line segments, are used for the matching. A hierarchical matching strategy is adopted for the above-mentioned primitive matching. The points that cannot be matched in the first stage, specifically those that failed in a gradient orientation descriptor similarity constraint, are further matched in the second stage. The second stage combines the descriptor and the Mahalanobis distance constraints, and the optimal matching subpixel is determined according to an overall similarity score defined for the multiple constraints with different weights. Subsequently, the triangulation is updated using the newly matched points, and the aforementioned matching is repeated iteratively until no new matching points are generated. Twelve sets of close-range images are considered for the experiment. Results reveal that the proposed method has high robustness for different images and can obtain reliable matching results.
Highlights
Image matching is a process of identifying corresponding features on different images and is an essential step in image processing, such as three-dimensional (3D) reconstruction, image fusion, and target tracking [1,2,3]
This study mainly aims to obtain matching results as dense as possible for different types of images on the basis of initial sparse matching and matching propagation, and this study belongs to the quasi-dense matching domain
A large search space may exist, and this space is generally combined with other various geometric constraints, such as parallax constraints [11], Voronoi diagram [12,13,14], and Delaunay triangulation [15,16]
Summary
Image matching is a process of identifying corresponding features on different images and is an essential step in image processing, such as three-dimensional (3D) reconstruction, image fusion, and target tracking [1,2,3]. Jia et al [29] proved the mathematical property of equal proportion of triangulation affine transformation as a means of obtaining much denser matching results and proposed a dense matching method for wide baseline images based on the theory. In their method, the equal proportion points on the corresponding edges of triangles in two views that satisfy the similarity constraints are regarded as corresponding points. If at least one candidate point satisfies the condition in which the distance− value is smaller than the threshold T2, the optimal matching with subpixel accuracy should be determined further by utilizing multiple constraints. As for all the remaining potential matching subpixels, we calculate Θs and find the highest overall similarity score if the highest value is larger than the given threshold T5, which corresponds to the subpixel selected as the final matching point
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
