Har-SURF-RAN feature point matching method for stereoscopic visual three-dimensional reconstruction

Abstract

The invention, which belongs to the field of digital image processing, discloses a Har-SURF-RAN feature point matching method for stereoscopic visual three-dimensional reconstruction. The method comprises: step one, Gaussian difference preprocessing is carried out on pixel points in an image, candidate feature points are screened, and screening is carried out again by using a weight coefficient toobtain feature points; step two, a feature point data set is processed to obtain feature descriptors of the feature points; step three, the detected feature points are matched by using nearest neighbor feature matching; and step four, false determination points in feature matching point pairs are rejected preliminarily, a data set is sorted by using the idea of PROSAC, an RANSAC selection model and evaluation parts are improved, the RANSAC is improved by using the local optimization idea, and the local part of the model is optimized further by introducing an optimization parameter K. Therefore, the computing load is reduced; the speed is increased; redundant points generated by the improved algorithm are reduced; and the precision is improved.

Description

technical field [0001] The invention belongs to the field of digital image processing, in particular to a Har-SURF-RAN feature point matching method for three-dimensional reconstruction of stereo vision. Background technique [0002] In recent years, computer hardware and software have kept pace with each other, and great progress has been made in terms of operating efficiency and information processing capabilities. People have also raised higher expectations for the information presented and processed by computers. As a result, 3D reconstruction technology has been continuously developed and improved. [0003] 3D reconstruction is a common scientific problem and core technology in the fields of computer-aided geometric design, computer graphics, computer animation, computer vision, medical image processing, scientific computing and virtual reality, and digital media creation. recover the three-dimensional structure. At present, it has been widely used in various fields s...

AI Technical Summary

Problems solved by technology

[0007] (1) Although the existing feature point detection algorithms are becoming mature, there are still some shortcomings such as many redundant points and weak anti-interference ability, and the accuracy and efficiency still need to be further improved

Among the common centralized feature point detection methods, Harris feature point detection method has strong stability but slow speed, SURF feature detection speed is fast but poor stability, both have certain limitations

[0008] (2) The 3D reconstruction based on stereo vision does not have high requirements on the scale, but the pyramid structure proposed by the SURF algorithm to ensure the invariance of the scale makes the algorithm slow and computationally intensive

[0009] (3) The efficiency of the existing mismatch elimination algorithm is related to the size of the subset, the proportion of intra-class points and the size of the data set, and the efficiency is low in some scenarios; in terms of accuracy, considering the efficiency factor, the obtained parameters are often Whether it is the optimal parameter, it cannot be directly applied, and needs to be refined

Images