Foot-shaped three-dimensional surface reconstruction method based on image segmentation and grid subdivision

Abstract

The invention relates to a foot-shaped three-dimensional surface reconstruction method based on image segmentation and grid subdivision, comprising the steps of: carrying out statistics and analysis on a shoe last sample set to obtain a statistic deformation model, using a plurality of cameras to obtain images of a foot, then using the statistic model to fit the foot-shaped images, obtaining a sparse grid model, then segmenting image characteristic points from all the images, reducing the planar characteristic points into spatial points, finally using the spatial characteristic points subdivide the grid model and carrying out the subdivision iteratively, thus obtaining a foot-shaped model consistent to a target object. In the foot-shaped three-dimensional surface reconstruction method, marking points do not need to be arranged on the foot, high-accuracy laser measurement equipment is also not needed, artificial participation is not needed, only the cameras and a computer and other devices are used, and the reconstruction risk is finished by software in a full-automatic manner. A reconstruction network can be consistent to a target foot shape automatically, can capture the detail characteristics in the images automatically and can adapt to information provided by the images automatically.

Description

technical field [0001] The invention relates to a three-dimensional surface reconstruction method, in particular a foot shape three-dimensional surface reconstruction method based on image segmentation and grid subdivision, which can be used in multiple fields such as foot shape measurement, shoe and last customization, and foot medical treatment. Background technique [0002] The method of 3D reconstruction of the surface of the foot is currently more popular three-coordinate measurement equipment such as laser measurement, but these three-coordinate measurement equipment often output discrete points, and subsequent reverse engineering processing is required to obtain the three-dimensional surface of the target object, and it is not suitable for The measurement of objects such as human skin; and other methods for reconstructing targets from images often have a single idea, poor adaptability to different shapes of feet, and cannot automatically achieve the highest reconstruct...

AI Technical Summary

Problems solved by technology

[0002] The method of 3D reconstruction of the surface of the foot is currently more popular three-coordinate measurement equipment such as laser measurement, but these three-coordinate measurement equipment often output discrete points, and subsequent reverse engineering processing is required to obtain the three-dimensional surface of the target object, and it is not suitable for Measurement of objects such as human skin; while other methods for reconstructing targets from images often have a single idea, poor adaptability to different shapes of feet, and cannot automatically achieve the highest reconstruction accuracy of the amount of information provided by the image

Chinese patent 200510061271.9 is a sparse grid-oriented 3D foot shape data measurement method based on surface subdivision. Using the grid subdivision method, after the initial estimation of the foot shape by the statistical deformation model, the details of the target object are reconstructed to capture different foot shapes. It can automatically restore the three-dimensional surface of the original real foot shape according to multiple photos, but many links need to be manually operated, not fully automated, and the practical effect is limited

Images