Reconstruction method based on point-line feature rapid fusion

Abstract

The invention discloses a reconstruction method based on point-line feature rapid fusion. The method comprises the following steps of intercepting a video as an image, and performing preprocessing, such as focal length extraction, downsampling, etc., to reduce the reconstruction complexity; carrying out the point feature matching, carrying out the point feature extraction and matching by adoptingscale invariant feature transformation; matching the line features quickly from coarse to fine, using the line segment segmentation detector features for extracting and describing the line features, and obtaining an image line segment feature matching pair through the four steps of violent matching, motion estimation, Hamming distance threshold judgment and length screening on the line segment descriptors; carrying out the point-line feature fusion, converting a final line segment feature matching pair into the pixel points, analyzing the pixel points and the pixel coordinate positions of theexisting point features, deleting the repeated points, and then fusing the line segment pixel points and the point features; calculating a camera outer posture and a three-dimensional point cloud, calculating a substantive matrix by using a final image point-line feature matching pair, solving the camera outer posture, solving the three-dimensional point cloud in a triangularization manner, and optimizing a result by using a beam adjustment method.

Description

technical field [0001] The invention belongs to the field of three-dimensional reconstruction of computer vision, in particular to a reconstruction method based on fast fusion of point-line features. Background technique [0002] 3D reconstruction of images from sparse point clouds, also known as structure recovery from motion. The traditional reconstruction process mainly calculates the camera pose and sparse 3D point cloud through point features. At present, its research is mainly divided into two categories. [0003] One is incremental rebuilding. First, image point features are extracted, usually using scale-invariant feature transformation, and through the extraction and matching of point features between image pairs, the external pose of the camera and the 3D point cloud are solved, and the results are optimized by least squares. [0004] The other is a global rebuild. First of all, it also extracts image point features, extracts and matches image pair point featur...

AI Technical Summary

Problems solved by technology

Especially for 3D reconstruction in an image lacking texture information, a small number of point features will be obtained, and the number of 3D point clouds generated will be less, and the result will be less reliable.

Images