System for fully automatically reconstructing foot-type three-dimensional surface from a plurality of images captured by a plurality of cameras simultaneously

Abstract

The name of the invention is 'system for fully automatically reconstructing foot-type three-dimensional surface from a plurality of images captured by a plurality of cameras simultaneously'. The invention relates to a system for fully automatically reconstructing foot-type three-dimensional surface from a plurality of images, comprising the following main steps of: firstly carrying out statistical analysis on a shoe-tree sample set so as to obtain the statistical deformation model; arranging the imaging environment; obtaining the calibrated template and the image of the human foot by a plurality of cameras; deforming statistical model, and fitting the foot type image so as to obtain the initially estimated model and generate the sparse grid model; and iterating to finely divide the grid model, wherein the image characteristic points from each image are divided in each turn of iteration, the plane characteristic point is matched with the space point, and the grid model is subdivided by using the spatial characteristic point; and finally obtaining the foot type model consistent with the target object. In the invention, a mark point is unnecessary to be set on the foot, and a high-precision laser measurement device is unnecessary; the camera and the computer are only used, and the shutter imaging time and the calculation processing time are only required. The system has fast speed, and can be widely applied to the condition for the three-dimensional reconstruction of the biological skin with relatively low precision request.

Description

technical field [0001] The invention relates to a system for three-dimensional measurement and reconstruction of the foot shape, which can automatically reconstruct the three-dimensional surface of the foot shape by using multiple cameras to capture multiple images of the foot shape at the same time, and can be used for foot shape measurement, shoe and last customization, sports Analysis, foot medical and other fields, with the characteristics of simple use and low cost. Background technique [0002] With the continuous improvement of social modernization and material living standards, people's needs for the comfort and individuality of their shoes are increasing day by day. There are no two identical foot shapes in the world. Even if two people wear the same shoe size, their feet will be different in length, fat and thin, and the height of the arch will be different. The walking posture will also be different. The same pair of shoes can be worn On foot comfort will not be ...

AI Technical Summary

Problems solved by technology

[0004] 1. Manual measurement methods, such as the traditional old method, use calipers, soft rulers and other tools to measure key parts, the speed is slow, the accuracy is low, and the 3D model cannot be obtained directly

[0005] 2. Laser measurement methods, such as CANFIT-PLUS TM Yeti TM 3D Foot Scanner is currently a very popular way to acquire 3D data, with high precision and wide application range, but the equipment is expensive

Due to the scanning method, the speed is slow, generally more than a few minutes; and the accuracy of the beginning and end of the foot shape is very low, which is difficult to handle

However, the laser measurement method is easily affected by the optical properties of the surface of the object. Because the skin texture of the human body surface is rich and the optical properties are changeable, it is not applicable.

[0006] 3. Contact measurement, such as power hand, is cheap, but manual operation, slow speed and low precision

Pan Yunhe provided a series of methods for measuring foot shapes with cameras. "A method for measuring and modeling three-dimensional foot shapes based on specific grid patterns" (Chinese Application No. 200310108856.2) needs to wear socks with special grids printed on them. At the same time, the accuracy is relatively low; "Sparse grid-oriented 3D foot shape rapid acquisition method based on standard foot deformation" (application number 2005100612723) and "Sparse grid-oriented 3D foot shape data measurement method based on surface subdivision" (Application No. 200510061271.9), first establish a standard foot shape library, then manually align the sparse grid model and the target foot shape, and then select a foot length and foot width information from the standard foot shape library according to the foot length and width information to be close to it Then manually adjust the position and posture of the standard foot model, and finally manually find the corresponding points between the standard foot model and the sparse mesh foot model, and re-modify the control vertices of the sparse mesh foot model according to the corresponding points. Control vertices to reconstruct the sparse mesh foot model, and then subdivide the mesh to obtain 3D foot shape data. The whole method is basically done manually, and the standard foot shape library is difficult to establish

Images