Automatic registration fusion method of point cloud data and optical image based on line feature

Abstract

The invention discloses an automatic registration fusion method of point cloud data and an optical image based on a line feature. The method comprises the steps of filtering point cloud data by means of a mathematical morphology method; determining a depth map of the optical image and the point cloud data by means of an adaptive supporting weight dense three-dimensional algorithm and a Delaunay triangulation algorithm; extracting the line feature of the depth map through a Hough algorithm, and performing coarse matching in a manner that a ratio between an included angle of two lines and a line length of the line feature is used as a similarity measure; eliminating error matching point pairs through a two-step RANSAC algorithm, and obtaining camera position parameter estimation; and performing color texture mapping between the point cloud data and the optical image, thereby obtaining a fused three-dimensional image. The automatic registration fusion method has advantages of no dependence to prior techniques such as GPS and INS, high robustness and high automatic registration degree.

Description

technical field [0001] The invention belongs to an improved heterogeneous image registration algorithm, in particular to an automatic registration and fusion method of point cloud data and optical images based on line features. Background technique [0002] The registration of LiDAR point cloud data and optical images can be divided into grayscale-based registration methods and feature-based registration methods according to the registration primitives used. The feature registration is further divided into point feature, line feature and surface feature registration. Point features are the most commonly used in feature-based image registration methods, but point feature registration has limitations and cannot be applied universally. Line feature is a higher-level ground object feature than point. As far as feature extraction is concerned, it is easier to extract meaningful line features than to extract meaningful point features. Moreover, there are abundant features in both...

AI Technical Summary

Problems solved by technology

This method uses line features relatively completely and comprehensively, but the complexity is high and the calculation time is long. Moreover, for buildings with similar regular edges extracted from aerial remote sensing images, the matching features are reduced, and the false matching rate will decrease. Becomes high

The above algorithms generally need to rely on initial position priors such as GPS / INS. For three-dimensional registration, the algorithm complexity is very high, and it depends on the accuracy of three-dimensional reconstruction

Images