A Multiple Soft Constrained Stereo Matching Method Based on Cost Matrix

Abstract

The invention discloses a multiple soft-constrained stereo matching method based on a cost matrix. First, a three-dimensional matching cost matrix is ​​calculated and multi-scale downsampling is performed on it to form a cost matrix pyramid; at the same time, corresponding multi-scale downsampling is performed on the image, Construct the image pyramid, and perform image segmentation on each layer of the image; then carry out the cost accumulation of adaptive weight and the cost accumulation under the "voting" segmentation constraint layer by layer, and pass the upper layer cost accumulation result to the lower layer cost matrix, Realize the cost accumulation under multi-scale constraints; finally, combine the reliable point cost diffusion method in the underlying cost matrix to achieve stereo matching. The invention enhances the stability and reliability of the matching result, greatly improves the matching problems of weak texture and repeated texture regions and parallax discontinuity, and can be used to improve image-based modeling and other engineering application problems involving stereo matching.

Description

technical field [0001] The invention belongs to the technical field of computational vision and photogrammetry, and relates to a stereo matching method based on a cost matrix, in particular to a stereo matching method based on a cost matrix with multiple soft constraints. Background technique [0002] Stereo matching is a fundamental and key problem in the fields of computational vision and photogrammetry. The concept of stereo matching was first proposed in the field of photogrammetry to solve the problem of automatic mapping of digital aerial photogrammetry. Stereo matching is also a key issue in the field of computer vision, affecting modeling of the human visual system, robot navigation and manipulation, 3D model building, and mixing real-world actions with computer-generated images. [0003] Stereo matching is a pathological problem, especially for the lack of texture and repeated texture regions, and the mismatching problems of discontinuous disparity have been diffic...

AI Technical Summary

Problems solved by technology

[0005] The present invention mainly solves the problem of excessive dependence on the priori condition constraints existing in the prior art; it provides a multiple soft constraint cost accumulation method based on the cost matrix that can simultaneously incorporate multiple priori constraints to complete stereo matching, It can effectively solve the problem of lack of texture and repeated texture areas and the mismatch of edges

Images