Plant three-dimensional reconstruction method and system based on depth map repair

Abstract

The invention discloses a plant three-dimensional reconstruction method and system based on depth map repair. The method comprises the following steps: obtaining a plurality of views; obtaining a depth map corresponding to each view, and recording the depth map as a first depth map; repairing a cavity area in the first depth map, and dynamically adjusting the size of a filtering window in a repairing algorithm by using super-pixel block label information; performing filtering processing on the repaired first depth map to obtain a second depth map; carrying out fusion processing on the second depth map to obtain a plant dense point cloud model; and extracting a plant three-dimensional surface from the dense point cloud model by using a surface reconstruction algorithm to complete the reconstruction of the plant three-dimensional model. The method is simple to operate and low in cost. The size of the filtering window is dynamically adjusted by using the boundary information of the super-pixel block, so that pixels which do not belong to the same depth area do not participate in filtering calculation, the occurrence of errors is reduced, plant dense point clouds are more dense, and afinally reconstructed plant model is more accurate and complete.

Description

technical field [0001] The invention relates to the field of three-dimensional reconstruction, in particular to a method and system for three-dimensional reconstruction of plants based on depth map repair. Background technique [0002] Plant modeling is widely used in agricultural guidance, virtual landscape, protection of ancient and famous trees, etc. How to reconstruct plant models quickly and at low cost is an urgent problem in the field of computer vision. Multi-view based on depth map generation Figure three Dimensional reconstruction is a common means of plant modeling, but due to the complex growth environment of plants, repeated textures of trunks and leaves, thin plant branches, and the lack of robustness of current stereo matching algorithms, it is usually difficult to generate accurate and complete depth maps, resulting in The plant model obtained by depth map fusion has a lot of noise and holes. [0003] The plant reconstruction method based on multi-view is a...

AI Technical Summary

Problems solved by technology

Although traditional Gaussian filtering and median filtering methods can reduce image noise, they will lead to blurred depth boundary information

Bilateral filtering combines spatial information and gray similarity, making great progress in image inpainting technology, but it cannot preserve the information of object boundaries very well

The joint bilateral filtering algorithm, on the basis of the bilateral filtering algorithm, adds a color map as a guide map, which makes the acquisition of the gray value similarity factor and the spatial proximity factor more accurate. Although the joint bilateral filtering algorithm solves the problem of boundary blur, it is accurate sex is still bad

Images