Compact SFM three-dimensional reconstruction method without feature extraction

Abstract

The invention discloses a compact SFM three-dimensional reconstruction method without feature extraction. The method comprises the steps that n images related to a certain scene are input, where n is larger than or equal to two; a world coordinate system identical to a certain camera coordinate system is established; the depth of the three-dimensional scene and a camera projection matrix serve as variables, an objective function similar to that of light stream estimation is established, a method of a pyramid becoming thinner is adopted, an iterative algorithm is designed, the objective function is optimized, and the depth representing three-dimensional information of the scene and the camera projection matrix representing relative pose information of a camera are output; according to the depth representing the three-dimensional information of the scene, compact projection and similarity or Euclid reconstruction are achieved. According to the method, compact SFM three-dimensional reconstruction can be completed through one step. Due to the fact that the compact three-dimensional information is estimated through one-step optimization, a objective function value serves as an index, an optimal solution can be obtained, the optimal solution is at least a locally optimal solution, and the method is greatly improved compared with an existing method and is preliminarily verified through experiments.

Description

technical field [0001] The invention relates to the field of image three-dimensional reconstruction, and more specifically, relates to a compact SFM three-dimensional reconstruction method without feature extraction. Background technique [0002] 3D reconstruction based on computer vision refers to the use of digital cameras or video cameras to obtain images, construct algorithms to estimate the 3D information of the captured scene or target, and achieve the purpose of expressing the 3D objective world. Its applications include robot navigation, automotive automation or assisted driving, Virtual reality, digital media creation, computer animation, image-based rendering and preservation of cultural heritage, etc. [0003] Motion-based modeling (Structure from Motion, SFM) is a commonly used 3D reconstruction method, which estimates the 3D information of a scene or object from two or more images or videos. The existing technical means for realizing SFM three-dimensional recon...

AI Technical Summary

Problems solved by technology

[0004] The existing SFM 3D reconstruction algorithm is divided into two steps, which cannot really achieve the optimal effect

Due to the error in the two-dimensional coordinates of the feature points detected from the image, even if the optimization algorithm is used to reconstruct the three-dimensional information on the basis of it, the optimization result in the global sense cannot be obtained.

Since the matching accuracy of feature points is usually relatively low, it inevitably results in low-precision 3D reconstruction

[0005] The 3D reconstruction effect is sparse; since only the 3D information of the extracted feature points is estimated, compact (dense) 3D reconstruction cannot be achieved, that is, the 3D information of all pixels cannot be estimated

Although it is possible to further estimate the 3D information of other points on the basis of the feature points by using the estimated epipolar constraint and other technical means to achieve compact or semi-compact (quasi dense) reconstruction, but due to the estimated There is a certain error in the 3D information of the point and the camera pose, which affects the 3D estimation effect of other points in the follow-up

Images