Stereoscopic image dense matching method and system based on LiDAR point cloud assistance

Abstract

According to a stereoscopic image dense matching method and system based on LiDAR point cloud assistance, LiDAR point clouds in a projection acquired stereopair overlapping range are subjected to parallel filtering processing; the filtered point clouds are projected to an epipolar line stereopair and a parallax range of subsequent dense matching is determined; a pyramid is built, starting from a top layer of the pyramid, a cost matrix is transformed by adopting a triangulation network constraint, SGM dense matching is carried out, and left and right consistency detection is carried out so as to obtain a final parallax image of the top layer; a parallax image of a current layer of the pyramid is transferred to a next layer to be used as an initial parallax image, a parallax range of the next layer is correspondingly determined according to the parallax image of the current layer, and the next layer is used as a new current layer; and on the basis of the new current layer, processing is carried out as well to obtain a final parallax image of the current layer up to a bottom layer of the pyramid, a parallax image of an original image is output, and according to the parallax image of the original image, corresponding image points of the stereopair are obtained and the densely matched point clouds are generated.

Description

technical field [0001] The invention relates to the technical field of dense matching of stereo pairs, in particular to a technical scheme of dense matching of stereo pairs guided by control information. Background technique [0002] In the field of photogrammetry and computer vision, dense matching refers to the process of matching points with the same name pixel by pixel based on two or more optical images to generate a dense 3D point cloud. The dense matching technology can quickly obtain the 3D surveying and mapping information of the surveyed area surface, and has great potential in the fields of smart cities and geographical conditions monitoring such as road and water body extraction, 3D modeling of buildings, change detection, DEM / DSM and true orthophoto production, vehicle automatic driving, etc. Very broad application prospects. [0003] Laser scanning and stereo image dense matching technology are two mainstream means of acquiring 3D information of terrain and ob...

AI Technical Summary

Problems solved by technology

[0005] The present invention mainly solves the current situation that the LiDAR point cloud three-dimensional reconstruction technology and the dense matching three-dimensional reconstruction technology are isolated from each other, and the technical problems that the dense matching parallax range parameters need to manually set the threshold, etc.; provides a LiDAR point cloud-assisted three-dimensional image semi- Global dense matching technology can automatically determine the disparity range of dense matching, and guide dense matching through LiDAR point cloud, so as to obtain more accurate and reliable dense matching products

Images