Key size automatic extraction method in three dimensional human body measurement

Abstract

The present invention discloses a key size automatic extraction method in three dimensional human body measurement. The method comprises the following steps of 1) scanning and obtaining the three dimensional point cloud data of the human body morphology via a high definition camera, segmenting the obtained human body right side and side images by the super-pixel segmentation, and further extracting and measuring the edge coordinate points of a cross-section in which the human body key size is located according to the curvature; 2) automatically transforming the three dimensional point cloud data into the two-dimensional image data, wherein the two-dimensional image data comprises a right side projection image, a side projection image and a backside projection image, and standardizing and adjusting the two-dimensional image data. The method of the present invention can better solve a human body contour accurate extraction problem, has the very good guidance and reference significance for the three dimensional measurement in the other application fields, and has a certain application value.

Description

technical field [0001] The invention relates to a dimension extraction method, in particular to an automatic extraction method for key dimensions in three-dimensional human body measurement. Background technique [0002] At present, in the field of human body shape measurement, 3D scanning technology is widely used, mainly in data collection and acquisition. Although there are many 3D systems or software that can open and process 3D data, most of them belong to the category of reverse engineering modeling, not specialized measurement systems or software. Some of these software can measure the distance between the most basic straight line and curve, or some can measure the local volume, but the accuracy of the measurement is relatively low, and there are few measured data items, such as body surface angle or local (chest) It is difficult to obtain detailed data, so the data measured by the existing three-dimensional system is far from enough to describe the shape of the huma...

AI Technical Summary

Problems solved by technology

Some of these software can measure the distance between the most basic straight line and curve, or some can measure the local volume, but the accuracy of the measurement is relatively low, and there are few measured data items, such as body surface angle or local (chest) It is difficult to obtain detailed data, so the existing three-dimensional system me