Human body BWH measuring method based on depth images

Abstract

The invention discloses a human body BWH measuring method based on depth images. The method includes obtaining a preset number of human body BWH data samples, and utilizing a linear regression method to fit linear regression equations of chest circumference, chest breadth and chest depth, waist circumference, waist breadth and waist depth and hip circumference, hp breadth and hip depth according to the preset number of human body BWH data samples; obtaining a human body front side depth image, a human body side face depth image and human body skeleton information of a user to be measured; processing the human body front side depth image to obtain a human body front side foreground picture; processing the human body side face depth information to obtain a human body side face foreground picture; and based on the human body side face foreground picture and the human body skeleton information, finally calculating and obtaining the chest breadth and chest depth, waist breadth and waist depth and hip breadth and hip depth of a human body, and substituting to the corresponding linear regression equations respectively, thereby obtaining BWH data of the human body. The human body BWH measuring method can calculate human body BWH data on line accurately, and is simple in structure and convenient to operate.

Description

technical field [0001] The invention relates to the technical field of measurement of body measurements, in particular to a method for measuring body measurements based on depth images. Background technique [0002] Generally, with the development of computer technology and Internet technology, more and more computer applications use 3D graphic image technology. In some application fields, such as online fitting, somatosensory games, 3D human body reconstruction, clothing design, game character animation, etc., there is an increasing demand for online acquisition of human body measurement data. However, due to various reasons such as differences in human bodies and the complexity of application scenarios, it has become a very difficult task to accurately calculate the data of human body measurements online. [0003] Chinese patent application CN105222738A discloses "a method for measuring the size of human body 3D model data". This method is a measurement method based on th...

AI Technical Summary

Problems solved by technology

This method has the following disadvantages: on the one hand, it is necessary to scan the human body with a 3D scanner to obtain the 3D model data file of the human body before measuring the measurement data, and at the same time, the data file must be placed on the server side, which cannot be used in conventional application scenarios, and it is also It cannot be measured online in real time; on the other hand, this method requires the operator to interact with the front desk of the system to perform measurement, which increases the complexity of the operation and also brings potential errors to the calculation results

This method has the following deficiencies: on the one hand, the method needs to preprocess the digital pictures after obtaining the digital pictures of the human body, and perform scaling, angle adjustment and flipping on multiple pictures, so that the proportions and angles of multiple pictures are consistent, which is undoubtedly This increases the complexity of the method, and at the same time causes calculation errors, making it difficult to implement the method. On the other hand, because the method uses digital images, it will inevitably be affected by light and the environment, so it will have certain requirements for the application scene. This also limits the wide application of this method

This method has the following disadvantages: on the one hand, the steps of this method are complicated, it is difficult to implement, and online real-time measurement cannot be carried out; on the other hand, this method requires the support of digital cameras and three-dimensional scanner hardware devices, and also requires vector software Data processing with 3D software, the accumulation of deviations in the processing process will eventually lead to large deviations in the obtained body measurement data; in addition, this method also uses digital images, which are also affected by the environment and light, and cannot be widely used

Images