Non local stereopair dense matching method based on image gray scale guiding

Abstract

The invention relates to a non local stereopair dense matching method based on image gray scale guiding. The non local stereopair dense matching method based on image gray scale guiding includes the steps: performing cost computation: taking an improved HOG operator as a cost measure, computing the cost between homonymous pixels, taking the cost as the means of describing the similarity between the homonymous pixels, and establishing a cost matrix; performing cost accumulation based on image gray scale guiding, and obtaining a stable cost accumulation result; according to a WTA strategy, obtaining an initial disparity image, rejecting a mis-matching point and an occulsion point, and obtaining a refined disparity image; and finally according to the disparity image, generating a dense high-precision three dimensional point cloud. The non local stereopair dense matching method based on image gray scale guiding fully considers the edge gray scale characteristics, has relatively high matching precision on the disparity edge, uses an eight-direction iterative cost accumulation mode so as to increase the matching robustness of a texture lacking area, and can quickly obtain a dense high-precision three dimensional point cloud, thus having great application prospect in the field of aerospace photogrammetry, low altitude photogrammetry and close-range photogrammetry, automatic driving of unmanned vehicle.

Description

technical field [0001] The invention relates to an image matching method, in particular to a non-local stereo pair dense matching method based on image gray scale guidance. Background technique [0002] Stereo pair dense matching is one of the enduring research hotspots in the field of photogrammetry and computer vision. Its main task is to find the same-named points between two images pixel by pixel. Dense matching has broad application prospects in DEM\DSM production, 3D reconstruction of digital cities, image rendering, unmanned automatic driving, robot navigation, augmented reality, virtual reality, etc. So far, most dense stereo image pair matching algorithms can be summarized into four steps: 1. Cost calculation; 2. Cost accumulation; 3. Parallax calculation; 4. Parallax correction. [0003] Although dense matching has been developed for decades and the technology is becoming more and more mature, there is still a lot of research space in terms of cost calculation and...

AI Technical Summary

Problems solved by technology

[0004] The present invention mainly solves the problem that the traditional dense matching method has poor matching accuracy at the parallax edge and the overall matching result is not robust, and proposes a stereo pair dense matching method based on image grayscale guidance, which can use an improved HOG operator, Reasonably describe the similarity between pixels with the same name and construct a cost matrix; constrain the cost transfer according to the designed quadratic function, and use the eight-direction iterative method for non-local cost accumulation to obtain a stable cost accumulation result; finally correct the initial disparity map , and generate dense high-precision 3D point clouds

Images