Three-dimensional reconstruction method of large-scene object

Abstract

The invention discloses a three-dimensional reconstruction method of a large-scene object. The method comprises the following steps: 1, acquiring a plurality of sequence pictures of the scene object from different visual angles and positions by use of a camera; 2, dividing the sequence pictures into a plurality of units Ni; 3, performing feature detection and matching on three sequence pictures of each unit by use of an SIFT algorithm; 4, initializing a first sequence picture of a unit N1 (i=1), and calculating a basic matrix F and an intrinsic matrix E of the other two sequence pictures; 5, solving camera parameters Ri and Ti and three-dimensional point cloud coordinates Mj of each sequence picture in other units; 6, obtaining seed surface sheets of the scene object; 7, expanding the seed surface sheets; and 8, filtering the seed surface sheets. According to the invention, by use of three-view constraints, mismatch points are effectively removed, an accurate basic matrix is obtained, the reconstruction precision is high, the units do not need coordinate conversion, the calculation complexity is reduced, and through performing dense reconstruction on the basis of a motion recovery structure, obtained point clouds of a three-dimensional model are enabled to be denser.

Description

technical field [0001] The invention relates to the fields of computer vision and computer graphics, in particular to a method for three-dimensional reconstruction of large scene objects. Background technique [0002] The ultimate goal of 3D reconstruction is to restore the 3D structure of the target scene, and 3D reconstruction based on image sequences is one of the main means to obtain 3D structure. This method can be regarded as the inverse process of photography, its cost is relatively low, it only needs an ordinary camera, it is easy to operate and easy to carry, feature point matching and multi-view stereo reconstruction based on image sequences are researches in computer vision technology Basics and focus. [0003] The 3D reconstruction method for large scene objects is currently used more often than SFM (Structure FromMotion). Its disadvantage is that the epipolar geometric constraints are used for feature detection and matching, and it can only be determined that t...

AI Technical Summary

Problems solved by technology

[0003] The 3D reconstruction method for large scene objects is currently used more often than SFM (Structure FromMotion). Its disadvantage is that the epipolar geometric constraints are used for feature detection and matching, and it can only be determined that the matching point is on the corresponding epipolar line. The exact position of the matching point cannot be determined, and this constraint is relatively weak

Once the mismatching points cannot be deleted, it is wrong to solve the basic matrix, and the obtained 3D point cloud coordinates are also wrong, and the point cloud coordinates corresponding to other image matching points obtained from this are also wrong, and the problem of error accumulation will occur.

There is also a 3D reconstruction based on independent three views, which uses each of the three images as an independent unit for 3D reconstruction. After reconstruction, coordinate transformation and scale transformation are performed between each unit to transform all 3D point clouds into the same coordinates. The computational complexity of this method is relatively large

In addition, these two methods have a common problem that the reconstructed point cloud is relatively sparse, which cannot satisfy the visualization effect.

Images