Multi-vision image dense coupling fusion method and system based on multiple characteristics and multiple constraints

Abstract

The invention provides a multi-vision image dense coupling fusion method and system based on multiple characteristics and multiple constraints. The method comprises the following steps: according to the multiple constraints, respectively selecting a plurality of images to be coupled for each reference image, obtaining to-be-coupled image sets, and the reference images and corresponding coupling image sets form coupling models; for each coupling model, by use of multi-vision constraint conditions, carrying out half global dense coupling to directly generate a dense coupling result of a single coupling model, and obtaining a corresponding elevation graph; according to elevation smooth constraints between grid points, under the condition of a minimum global energy function, carrying out fusion on the dense coupling results of the multiple coupling models; and through combination with surface characteristics and line characteristics, carrying out point cloud optimization to generate final point clouds. According to the technical scheme provided by the invention, a reasonable stereo image pair can be automatically selected, coupling results are enabled to be more accurate and reliable by use of multi-vision information, optimal multi-vision fusion results with global significance can be obtained, and the point clouds generated through the optimization are finer.

Description

technical field [0001] The present invention relates to the technical field of dense multi-view image matching, in particular to a method and system for dense matching and fusion of multi-view images based on multi-features and multi-constraints. Background technique [0002] The 21st century is an era of informationization. Informatization and digitalization have had a profound impact on social development. As the world is developing from a digital earth to a smart earth, my country is also promoting the rapid development of "digital China" and "smart cities", providing public management, breakthrough services for government departments, enterprises and the public, etc. It is of great significance in service aspects such as emergency response and scientific decision-making. Image intensive matching technology is one of the mainstream methods for obtaining 3D information of ground objects. Cameras are mounted on remote sensing platforms at different heights, such as satellit...

AI Technical Summary

Problems solved by technology

[0004] The present invention mainly solves the problems of insufficient density of point clouds generated by traditional dense matching technology, poor texture, serious mismatching phenomenon in texture repeating areas, and serious "burr" phenomenon on the edge of linear features; it provides a multi-feature and multi-constraint based The image dense matching and point cloud fusion optimization technology can automatically select the optimal matching model, make full use of multi-view constraints in the dense matching process, obtain the optimal fusion result in the global sense, and combine surface features and line features to Optimize point cloud to get more accurate and reliable dense matching products

Images