Image-based three-dimensional reconstruction processing method and device

Abstract

The invention particularly relates to an image-based three-dimensional reconstruction method and device, a computer readable medium and electronic equipment. The method comprises the following steps:acquiring an image sequence and acquiring positioning information; selecting a plurality of successive frames of subsequent images of the first image from the image sequence, performing feature pointmatching on the first image and each subsequent image to screen the subsequent images matched with the first image, generating a first image matching pair, and establishing a matching relationship between the first image and the subsequent images; screening a second image set matched with the first image in position in the image sequence by using the positioning information, performing feature point matching on the first image and each image in the second image set to screen a second image matched with the first image, generating a second image matching pair, and establishing a matching relationship between the first image and the second image; constructing a global matching relationship based on the image matching relationship between the first image matching pair and the second image matching pair corresponding to the first image; performing three-dimensional reconstruction on the image sequence based on the global matching relationship.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular to an image-based three-dimensional reconstruction method, an image-based three-dimensional reconstruction device, a computer-readable medium, and an electronic device. Background technique [0002] In the field of computer vision, 3D reconstruction is a research focus. Generally speaking, 3D reconstruction algorithms commonly used in the prior art include: SFM (Structure from motion, structure from motion) technology, Dynamic Fusion (dynamic fusion) algorithm, Bundle Fusion (bundle fusion) algorithm, and the like. In related technologies, most of them adopt matching and screening methods based on image features, which rely more on the robustness of image feature descriptors. However, for locally similar textures, image features cannot effectively solve this kind of scene reconstruction. For example, when the same signboard or logo appears in different places...

AI Technical Summary

Problems solved by technology

However, for locally similar textures, image features cannot effectively solve this kind of scene reconstruction.

For example, when the same signboard or logo appears in different places, there may be false matching; that is, pictures that do not belong to the same place are correlated with each other, which will seriously reduce the accuracy of 3D reconstruction, and even cause the failure of mapping

Images