CN112446325A - 2D-3D non-contact human body measurement method for old people - Google Patents
2D-3D non-contact human body measurement method for old people Download PDFInfo
- Publication number
- CN112446325A CN112446325A CN202011344683.4A CN202011344683A CN112446325A CN 112446325 A CN112446325 A CN 112446325A CN 202011344683 A CN202011344683 A CN 202011344683A CN 112446325 A CN112446325 A CN 112446325A
- Authority
- CN
- China
- Prior art keywords
- human body
- curve
- contact
- size
- elderly
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000691 measurement method Methods 0.000 title abstract description 9
- 238000005259 measurement Methods 0.000 claims abstract description 48
- 238000006243 chemical reaction Methods 0.000 claims abstract description 12
- 238000002474 experimental method Methods 0.000 claims abstract description 12
- 238000000513 principal component analysis Methods 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims description 44
- 238000000034 method Methods 0.000 claims description 41
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000000611 regression analysis Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 230000003068 static effect Effects 0.000 claims description 4
- 238000003064 k means clustering Methods 0.000 claims description 2
- 238000011430 maximum method Methods 0.000 claims description 2
- 238000009776 industrial production Methods 0.000 abstract description 4
- 210000000038 chest Anatomy 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000011160 research Methods 0.000 description 7
- 230000037237 body shape Effects 0.000 description 5
- 230000010354 integration Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 210000001015 abdomen Anatomy 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 210000000481 breast Anatomy 0.000 description 2
- 210000003127 knee Anatomy 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000000115 thoracic cavity Anatomy 0.000 description 2
- 230000003187 abdominal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 210000004872 soft tissue Anatomy 0.000 description 1
- 230000003238 somatosensory effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B5/00—Measuring arrangements characterised by the use of mechanical techniques
- G01B5/02—Measuring arrangements characterised by the use of mechanical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B5/00—Measuring arrangements characterised by the use of mechanical techniques
- G01B5/02—Measuring arrangements characterised by the use of mechanical techniques for measuring length, width or thickness
- G01B5/025—Measuring of circumference; Measuring length of ring-shaped articles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B5/00—Measuring arrangements characterised by the use of mechanical techniques
- G01B5/20—Measuring arrangements characterised by the use of mechanical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a 2D-3D non-contact type human body measurement method for the elderly, which comprises the steps of selecting three-dimensional non-contact type and contact type human body measurement experiment samples to obtain sufficient and comprehensive measurement data; acquiring the size of a characteristic part based on the experimental sample; performing principal component analysis on the sizes of the characteristic parts to determine body type classification standards of the old; measuring the length and the circumference of the main part of the human body based on the body type classification standard to obtain a contour curve function and a section curve function; and deducing and establishing a 2D-3D size conversion formula based on the obtained profile curve function and the section curve function, and calculating to obtain the size data of all parts of the human body of the old. The 2D-3D non-contact human body measurement method for the old people has the advantages of low cost, simplicity and convenience in operation, capability of meeting related industrial production requirements in precision, and suitability for market popularization and internet propagation.
Description
Technical Field
The invention relates to the field of human body measurement, in particular to a 2D-3D non-contact human body measurement method for the aged.
Background
The human body measuring system comprises a method, a technology, an instrument and the like, and is divided into a contact type and a non-contact type. The traditional contact method is gradually replaced by the non-contact method which is developed at the forefront because of the defects of low efficiency, discomfort of a tested person and the like. The non-contact human body measurement mainly comprises a three-dimensional human body scanning method and a two-dimensional direct photography method.
The basic principle of the three-dimensional body scanning method is based on optical measurement, using a vision device to capture the shape of an object, and then extracting the scanning data through system software. The working process comprises the following four steps: firstly, irradiating a scanned object by a light source with mechanical motion; the CCD camera detects a reflected image from a scanned object; calculating the distance from a specific point on the surface of the human body to the camera through the reflected image; and fourthly, converting the distance data through a software system to generate a three-dimensional image. The main methods include stereo photography, laser scanning, white light phase method, moire fringe method and far infrared ray method.
Representative studies in this area are: according to a projected grating phase method, a three-dimensional human body measuring system adopting structured light with certain characteristics; a three-dimensional imaging system of craniofacial soft tissue based on stereography and triangular laser scanning; a laser displacement meter for non-contact measurement of abdominal cross-section and waist circumference; a landmark detection method suitable for non-contact human body measurement based on the visual landmark idea; an optical scanner and electromagnetic field stylus based measurement system to capture specific body segment shapes for prosthetic and orthotic component fabrication in medical repair and orthotic; a three-dimensional human body measuring system scheme combined with a Kinect3D somatosensory camera; a computer network of a client-server is used for controlling a plurality of depth perception cameras and a three-dimensional human body scanner with a turntable as hardware.
The working principle of the two-dimensional direct photography method is that a digital image of a human body is shot by a camera device, and the human body size data is finally obtained through the processes of system parameter calibration, image processing, 2D-3D conversion and the like. Such as a human body dimension measuring system developed by the general military need equipment institute and the Beijing clothing college, a photoelectric human body dimension measuring system developed by the institute of laser and infrared application of the Sigan university, a non-contact human body measuring system developed by the Changhept university and the Taiwan Qinghua university in China, and a 2D-3D non-contact type measuring system developed by the clothing college of the Tianjin industry university.
Representative studies in this area are: a calculation method of hip circumference size in a two-dimensional non-contact human body measurement system; a method for acquiring human body size data of young women by using 2D-3D conversion calculation under a natural dressing state; researching an image processing and size obtaining method based on a 2D-3D human body scanning device; a three-dimensional body measurement method using a single camera; the non-contact two-dimensional measurement system is suitable for the body types of young females based on digital images; under a VB programming language, automatically extracting the human body size in the two-dimensional image by setting an environment variable; an automatic image cutting algorithm of a two-dimensional non-contact measurement system based on MATLAB.
Objective disadvantages of the prior art: in the aspect of a measuring system, the three-dimensional scanning body measuring system has higher precision, but the manufacturing cost and the requirement on the measuring environment are also higher, so the market popularity is weaker, and the research is developed in the directions of 'using more advanced scanning devices and further improving the measuring precision' and 'applicability research in different fields of scientific research and industrial production'. The two-dimensional body measurement system has the advantages of low cost, simplicity and convenience in operation, capability of meeting related industrial production requirements due to precision, suitability for market popularization, internet propagation and the like, and gradually becomes a main development direction of large-scale human body measurement and database construction research. And aiming at different crowds, the modularized function sharing and the combined application of the measuring system are realized, and the method has practical scientific and technological significance and wide application prospect.
In the aspect of measuring objects, the existing measurement research for the old people mostly uses contact measurement which is time-consuming and labor-consuming, or only stays in the utilization of the existing measurement system for regional old people size data acquisition and body type analysis, so that the existing measurement research is less involved in hunting and takes the physiological and psychological characteristics of the old people, which is a special group into consideration, and therefore, the universality is poor. For example, in the physiological aspect, the body type characteristics and postures of the elderly are changed due to body aging, long-term working and the like, the traditional adult body type classification method and the standard are not applicable any more, particularly, the sizes of the control parts of the body characteristics of the elderly, such as the abdomen, the back, the knees, the shoulders and the like, need to be carefully concerned, if the size is neglected, the measurement experiment is only grouped by age and gender and randomly expanded, the universality of the generated human body measurement and the ergonomic database thereof is greatly reduced, and the reference and the application are poor. In psychological aspects, the elderly are mostly reluctant to be scanned and measured in a closed environment in a naked body, underwear or tight-fitting state, the exposure of aging characteristics causes discomfort to the testee, and the manual contact measurement in a natural dressing state which can be accepted by the elderly is poor in precision.
Disclosure of Invention
The invention aims to provide a 2D-3D non-contact human body measuring method for the old people to solve the existing problems.
In order to achieve the above object, an embodiment of the present invention provides a 2D-3D non-contact anthropometric method for elderly people, which includes
Selecting three-dimensional non-contact and contact human body measurement experiment samples to obtain sufficient and comprehensive measurement data;
acquiring the size of a characteristic part based on the experimental sample;
performing principal component analysis on the sizes of the characteristic parts to determine body type classification standards of the old;
measuring the length and the circumference of the main part of the human body based on the body type classification standard to obtain a contour curve function and a section curve function;
and deducing and establishing a 2D-3D size conversion formula based on the obtained profile curve function and the section curve function, and calculating to obtain the size data of all parts of the human body of the old.
Further, the main component analysis is performed on the sizes of the characteristic parts to determine the body type classification standard of the elderly, and the method specifically comprises the following steps:
performing principal component analysis on the sizes of the characteristic parts to obtain contribution rates of all characteristic indexes;
determining a control variable by utilizing a correlation coefficient maximum method according to the contribution rate of each characteristic index;
and carrying out body type clustering according to the control variable, and classifying the body types by combining the girth difference.
Further, the body type clustering is carried out according to the control variables, and clustering is carried out through two algorithms of k-means clustering and fuzzy c-means clustering of machine learning.
Further, the profile curve function includes front, rear, and side profile curve functions, and is specifically obtained by performing regression analysis and curve fitting on the profile curve.
Further, the method deduces and establishes a 2D-3D size conversion formula based on the obtained profile curve function and the section curve function, and calculates to obtain size data of each part of the human body of the old, specifically:
selecting a typical representative section curve;
obtaining effective measurement point and line information of a human body, thereby obtaining a 2D size;
and based on the obtained 2D size, combining the integral of a typical representative section curve and obtaining the size data of all parts of the aged human body.
Further, the selecting of the typical representative section curve specifically includes:
dividing the surveying and mapping experiment samples into different types according to different vector ratios;
carrying out smooth symmetrical processing on the original curves in the same radius ratio range, and overlapping to determine a mean value;
a moderate proportion curve is selected as a typical representative cross-sectional curve based on the mean.
Further, the integral of the typical representative cross-sectional curve is specifically:
performing a preliminary analysis on the representative cross-sectional curve;
based on the preliminary analysis, performing regression analysis on a certain parameter of the human body represented by the typical representative curve and performing curve fitting to determine a fitting function;
and performing integral calculation on the fitting function.
Further, the obtaining of the effective measurement point and line information to obtain the 2D size includes obtaining the 2D size by fitting the effective measurement point and line information of the human body obtained by static shooting with a profile curve function and obtaining the 2D size by dynamically capturing the effective measurement point and line information of the human body.
Further, the statically photographed human body is in an underwear, tights state or a natural wearing state, and the dynamically captured human body is in a natural wearing state.
The invention has the beneficial technical effects that:
the invention provides a 2D-3D non-contact type human body measurement method for the elderly, which comprises the steps of selecting three-dimensional non-contact type and contact type human body measurement experiment samples to obtain sufficient and comprehensive measurement data; acquiring the size of a characteristic part based on the experimental sample; performing principal component analysis on the sizes of the characteristic parts to determine body type classification standards of the old; measuring the length and the circumference of the main part of the human body based on the body type classification standard to obtain a contour curve function and a section curve function; and deducing and establishing a 2D-3D size conversion formula based on the obtained profile curve function and the section curve function, and calculating to obtain the size data of all parts of the human body of the old. The invention analyzes, summarizes and classifies the body type characteristics of the old people, expands the body type classification standard suitable for the old people, analyzes and determines the measurement parts of the applied old people, and determines the body contour curve associated with the sizes of all the parts, and has the advantages of low cost, simple and convenient operation, high precision, capability of meeting the requirements of related industrial production, and suitability for market popularization and internet propagation.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of a 2D-3D non-contact anthropometric method for elderly people according to an embodiment of the present invention.
Fig. 2 is a comparison graph of a fit of a front profile curve provided by an embodiment of the present invention.
FIG. 3 is a comparison graph of a fit of a back profile curve provided by an embodiment of the present invention.
FIG. 4 is a comparison graph of a fit of a side profile curve provided by an embodiment of the present invention.
Fig. 5 is a schematic diagram of a typical cross-sectional thoracic curve provided by an embodiment of the present invention.
Fig. 6 is a schematic diagram of a typical waist cross-sectional curve provided by an embodiment of the invention.
FIG. 7 is a schematic view of a typical hip cross-sectional curve provided by an embodiment of the present invention.
Fig. 8 is a schematic diagram of a typical thoracic cross-sectional curve with a coordinate system according to an embodiment of the present invention.
Fig. 9 is a schematic diagram of a typical waist cross-sectional curve with a coordinate system according to an embodiment of the present invention.
FIG. 10 is a schematic view of a typical hip cross-section curve with a coordinate system provided by an embodiment of the present invention.
Figure 11 is a simplified schematic diagram of a front waist curve provided in accordance with an embodiment of the present invention.
Fig. 12 is a flowchart of calculating the intercept B according to the embodiment of the present invention.
Fig. 13 is a scatter diagram of the front and rear waist intercepts provided by the embodiment of the present invention.
Fig. 14 is a plan view of a scatter diagram of the front and back waist intercepts according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention.
The embodiment of the invention provides a 2D-3D non-contact human body measurement method for old people, which is shown in a figure 1 and comprises the following steps:
s11, selecting three-dimensional non-contact and contact human body measurement experiment samples to obtain sufficient and comprehensive measurement data;
in this embodiment, the experimental sample for three-dimensional non-contact body measurement may be obtained by a curve mapping table, a martin measuring instrument, a soft tape, or the like, and the experimental sample for three-dimensional contact body measurement may be obtained by a three-dimensional scanner, such as a laser scanning method, where the experimental sample for three-dimensional contact body measurement is obtained by measurement in an underwear state, so that the sample data is more accurate.
S12, acquiring the size of the characteristic part based on the experimental sample;
s13, performing principal component analysis on the sizes of the characteristic parts to determine the body type classification standard of the old;
in this embodiment, SPSS and MATLAB are used to preprocess measurement data of an experimental sample, and then principal component analysis is performed, and a control variable is determined by using a correlation coefficient maximization method according to each feature index contribution rate. Two algorithms of k-mean clustering and fuzzy c-mean clustering of machine learning are introduced, body types are clustered by means of control variables, and body types are subdivided by combining the circumference difference. The body shape characteristic analysis and classification method theory can comprehensively reflect different body shape characteristics of the old, rebuild body shape characteristic expression from a data source, change a method of simply classifying body shapes by chest-waist differences, and adapt to body shape judgment of the old.
S14, measuring the length and circumference of the main part of the human body based on the body type classification standard to obtain a contour curve function and a section curve function;
in this embodiment, the contour curve function includes front, back, and side contour curve functions, for example, a human body contour curve-chest side, back side, and waist side curve related to size data of a chest circumference (C), a waist circumference (W), and a hip circumference (H) of a young female, the contour curve function is obtained by performing regression analysis and curve fitting on the contour curve, and specifically, by curve segmentation, feature point extraction, and fitting tests, it is determined that the front, back, and side contour curves are cscvn, spline Interplant, and cscvn, respectively, and fig. 2 to 4 are fitting comparison diagrams.
And S15, deducing and establishing a 2D-3D size conversion formula based on the obtained contour curve function and the section curve function, and calculating to obtain size data of all parts of the human body of the old.
In the present embodiment, taking the young female human body CWH as an example, the curves related to the measurement and calculation thereof include a CWH cross-sectional curve and front, rear, and side contour curves. Selecting a representative typical curve, wherein the specific selection method is as follows, taking a chest circumference cross section curve as an example: firstly, dividing large sample mapping experiment samples into three types of 0.69-0.77, 0.78-0.83 and 0.84-0.95 according to different vector ratio such as breast thickness/breast width; secondly, performing smooth symmetrical processing on the original curves in the same radius ratio range, and overlapping to determine an average value; finally, a moderate-ratio curve is selected as a typical representative curve of the circumference cross section.
In the embodiment, effective measurement point and line information are obtained by statically shooting a human body in an underwear, a tights or a daily wearing state, and a 2D size is obtained by fitting the statically obtained effective measurement point and line information with a contour curve function; the 2D size is obtained by dynamically capturing the daily dressing state of the human body to obtain the effective measurement point and line information of the human body. The dynamic and static acquisition mode can realize the conversion between static and dynamic images and three-dimensional human body data of the old, and the feasibility of the 2D-3D non-contact human body measurement method oriented to different groups of people is improved.
In this embodiment, first, a preliminary analysis is performed on a typical representative section curve-CWH cross-section curve, as shown in fig. 5-7, as follows: a plane coordinate system XOY is established, as shown in fig. 8-10, taking the curve of the chest circumference cross section as an example, the curve above the x-axis is the anterior chest curve, the curve below the x-axis is the posterior chest curve, the line W1W2 is the chest width, T1T2 is the chest thickness, OT1 is the anterior chest thickness, and OT2 is the posterior chest thickness. According to the symmetry of human body, OW 1-OW 2-1/2 chest circumference. And (3) observing the trend rule of curves of all line segments: taking a line segment in (-W1,0) as an example, a and b are boundary points, the tangent slope of the arc segment W1a is larger, and the curvature is smaller; the arc ab, the tangent slope decreases and the curvature increases; and the arc bT1 has the smallest tangent slope and smaller curvature.
Based on the preliminary analysis, performing regression analysis and curve fitting on a certain parameter of the human body represented by the typical representative section curve to determine a fitting function, and performing regression analysis on the thickness of the human body CWH represented by the CWH cross section curve:
measuring the CWH curves obtained by a large sample experiment one by one to obtain a regression formula,
wherein, F-anterior, B-posterior, T-thickness, C-chest, W-waist.
The method for performing curve fitting on the CWH cross section curve and calculating the perimeter through 2D-3D conversion comprises hyperelliptic curve fitting, EE parameter spline curve fitting, binary primary linear regression, binary secondary regression and the like, the former two methods need a large amount of statistical data and measuring points, and the latter two methods have large errors and cannot meet the precision requirement of the research. According to the principles of few measuring points, high calculation speed, high precision and the like, a logarithmic curve, a trinomial curve, a power curve and a binomial curve are selected as test fitting curves. Through the fitting test, the following results are found: for the front and rear sections of the CWH cross-section curve, the confidence coefficient of the logarithmic curve fitting is best, and the shape of the logarithmic curve fitting is similar to the trend of the original curve, so that the logarithmic curve is finally determined as a fitting function.
Taking the front waist curve of 1/2 as an example, as shown in FIG. 11, the equation is given as follows.
Y＝A*Ln(x)+B (2)
Wherein, A-coefficient and B-intercept.
For intercept B values: the CWH arc length obtained by measuring a large sample changes the intercept B value by adopting a successive approximation method, the arc length of the curve is calculated by integration to be equal to the known arc length, so that the intercept B is determined and regarded as the accurate intercept B, and the calculation process is shown in figure 12. And deducing the corresponding relation between the intercept B and the width and the thickness. According to the expression (formula 3) of the correlation coefficient, the correlation coefficient between the intercept B and the width and the thickness is calculated. And fitting the intercept by adopting multivariate linear regression according to the correlation relation. In order to make the data more accurate, the distances C-W, the distances W-H and the heights are also subjected to correlation test and are subjected to integral calculation by using different regression formulas. After comparing the error of the integration result, the equation 4 is written into the integration program as the experimental result,
wherein Cov (X, Y) -the covariance of X and Y, D (X), D (Y) -the variances of X and Y, respectively,
wherein, H-hip.
Front and rear waist intercepts are examples, as shown in fig. 13-14.
Finally, the length of the fitting function is integrated.
According to equation 2, the length of the fitting function is expressed as equation 5, the effective integration range is (1,1/2 width), and k is 1/2 width, that is, equation 6. The curvature of the curve in the range of (0,1) is very small and sufficient point information cannot be extracted in MATLAB for fitting, so the approximate length is obtained by the calculation method of the hypotenuse (equation 7). Through a large number of experiments, the error of the algorithm is small.
And obtaining 2D size by combining the integral of the typical representative section curve, thereby obtaining the size data of each part of the aged human body. Since the elderly have various body types, different body types correspond to various different girth curves, the characteristic parts are not limited to the CWH, and other characteristic parts such as the shoulder, the neck, the back, the abdomen, the knee and the like belong to the protection scope of the invention.
In this embodiment, taking CWH of an old person as an example, three-dimensional non-contact and contact human body measurement experiment samples are selected, the size of a feature part is obtained, principal component analysis is performed on the size of the feature part to determine a body type classification standard of the old person, and length and circumference are measured on a main part of a human body based on the body type classification standard to obtain a contour curve function and a section curve function; and deducing and establishing a 2D-3D size conversion formula based on the obtained profile curve function and the section curve function, and calculating to obtain the size data of all parts of the human body of the old. The body type characteristic analysis, induction and classification of the old people are carried out, the body type classification standard suitable for the old people is expanded, the measurement positions of the application type old people are analyzed and determined, and the body contour curve associated with the sizes of all the positions is determined.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A2D-3D non-contact human body measuring method for the old people is characterized in that,
comprises that
Selecting three-dimensional non-contact and contact human body measurement experiment samples to obtain sufficient and comprehensive measurement data;
acquiring the size of a characteristic part based on the experimental sample;
performing principal component analysis on the sizes of the characteristic parts to determine body type classification standards of the old;
measuring the length and the circumference of the main part of the human body based on the body type classification standard to obtain a contour curve function and a section curve function;
and deducing and establishing a 2D-3D size conversion formula based on the obtained profile curve function and the section curve function, and calculating to obtain the size data of all parts of the human body of the old.
2. The elderly-oriented 2D-3D non-contact anthropometric method of claim 1, wherein the principal component analysis is performed on the size of the feature portion to determine the elderly body type classification standard, specifically:
performing principal component analysis on the sizes of the characteristic parts to obtain contribution rates of all characteristic indexes;
determining a control variable by utilizing a correlation coefficient maximum method according to the contribution rate of each characteristic index;
and carrying out body type clustering according to the control variable, and classifying the body types by combining the girth difference.
3. The elderly-oriented 2D-3D non-contact anthropometric method of claim 2, wherein the clustering of body types according to the control variables is performed by two algorithms of machine-learned k-means clustering and fuzzy c-means clustering.
4. The elderly-oriented 2D-3D non-contact anthropometric method of claim 1, wherein the profile curve function comprises front, back and side profile curve functions, specifically, the profile curve function is obtained by performing regression analysis and curve fitting on the profile curve.
5. The elderly-oriented 2D-3D non-contact anthropometric method according to claim 1, wherein the 2D-3D size conversion formula is derived and established based on the obtained profile curve function and cross-section curve function, and the data of the sizes of the parts of the elderly human body are obtained through calculation, specifically:
selecting a typical representative section curve;
obtaining effective measurement point and line information of a human body, thereby obtaining a 2D size;
and based on the obtained 2D size, combining the integral of a typical representative section curve and obtaining the size data of all parts of the aged human body.
6. The elderly-oriented 2D-3D non-contact anthropometric method of claim 5, wherein the selecting of the typical representative section curve is specifically:
dividing the surveying and mapping experiment samples into different types according to different vector ratios;
carrying out smooth symmetrical processing on the original curves in the same radius ratio range, and overlapping to determine a mean value;
a moderate proportion curve is selected as a typical representative cross-sectional curve based on the mean.
7. The elderly-oriented 2D-3D non-contact anthropometric method of claim 6, wherein the integral of the typical representative cross-sectional curve is:
performing a preliminary analysis on the representative cross-sectional curve;
based on the preliminary analysis, performing regression analysis on a certain parameter of the human body represented by the typical representative curve and performing curve fitting to determine a fitting function;
and performing integral calculation on the fitting function.
8. The elderly-oriented 2D-3D non-contact anthropometric method of claim 5, wherein the obtaining of the effective measurement point and line information to obtain the 2D size comprises obtaining the 2D size by fitting the effective measurement point and line information of the human body obtained by static shooting to a contour curve function and obtaining the 2D size by dynamically capturing the effective measurement point and line information of the human body.
9. The geriatric-oriented 2D-3D non-contact anthropometric method of claim 8, wherein the statically-photographed human body is in an underwear, tight-fitting state, or a natural wearing state, and the dynamically-captured human body is in a natural wearing state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011344683.4A CN112446325A (en) | 2020-11-26 | 2020-11-26 | 2D-3D non-contact human body measurement method for old people |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011344683.4A CN112446325A (en) | 2020-11-26 | 2020-11-26 | 2D-3D non-contact human body measurement method for old people |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112446325A true CN112446325A (en) | 2021-03-05 |
Family
ID=74737647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011344683.4A Pending CN112446325A (en) | 2020-11-26 | 2020-11-26 | 2D-3D non-contact human body measurement method for old people |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446325A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114140414A (en) * | 2021-11-25 | 2022-03-04 | 杭州贝嘟科技有限公司 | Non-contact human body measuring method and device and electronic equipment |
| CN115546543A (en) * | 2022-09-29 | 2022-12-30 | 北京鹰之眼智能健康科技有限公司 | Human body infrared image sample processing method and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013508A (en) * | 2007-02-12 | 2007-08-08 | 西安工程大学 | Method for constructing divisional composite three-dimensional parameterized digital mannequin |
| CN108741342A (en) * | 2018-04-13 | 2018-11-06 | 东华大学 | A kind of human somatotype clustering method based on factorial analysis and probabilistic neural network |
| CN110909593A (en) * | 2019-10-12 | 2020-03-24 | 浙江理工大学 | Body type classification method based on contour features and rotary shooting device matched with same |
-
2020
- 2020-11-26 CN CN202011344683.4A patent/CN112446325A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013508A (en) * | 2007-02-12 | 2007-08-08 | 西安工程大学 | Method for constructing divisional composite three-dimensional parameterized digital mannequin |
| CN108741342A (en) * | 2018-04-13 | 2018-11-06 | 东华大学 | A kind of human somatotype clustering method based on factorial analysis and probabilistic neural network |
| CN110909593A (en) * | 2019-10-12 | 2020-03-24 | 浙江理工大学 | Body type classification method based on contour features and rotary shooting device matched with same |
Non-Patent Citations (1)
| Title |
|---|
| 孙可可: "自然着装状态下非接触式人体测量技术的研究" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114140414A (en) * | 2021-11-25 | 2022-03-04 | 杭州贝嘟科技有限公司 | Non-contact human body measuring method and device and electronic equipment |
| CN115546543A (en) * | 2022-09-29 | 2022-12-30 | 北京鹰之眼智能健康科技有限公司 | Human body infrared image sample processing method and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018196371A1 (en) | Three-dimensional finger vein recognition method and system | |
| CN105066915B (en) | Mould camber processing error and surface roughness On-machine Test device and detection method | |
| CN112446325A (en) | 2D-3D non-contact human body measurement method for old people | |
| Wang et al. | 3-D particle surface reconstruction from multiview 2-D images with structure from motion and shape from shading (January 2020) | |
| CN107292948A (en) | A kind of human body modeling method, device and electronic equipment | |
| Podsiadlo et al. | Characterization of surface topography of wear particles by SEM stereoscopy | |
| CN103759676A (en) | Non-contact type workpiece surface roughness detecting method | |
| CN105740829A (en) | Scanning line processing based automatic reading method for pointer instrument | |
| CN104574432A (en) | Three-dimensional face reconstruction method and three-dimensional face reconstruction system for automatic multi-view-angle face auto-shooting image | |
| CN112116702A (en) | Human body measurement three-dimensional modeling method and system based on front and side profiles | |
| Manakov et al. | Visual shape and position sensing algorithm for a continuum robot | |
| CN105488798B (en) | SAR image method for measuring similarity based on point set contrast | |
| Jian et al. | Photometric stereo-based 3D reconstruction method for the objective evaluation of fabric pilling | |
| Nagano et al. | Development of a skin texture evaluation system using a convolutional neural network | |
| Liu et al. | A novel scratch detection and measurement method for automotive stamping parts | |
| Luximon et al. | Merging the point clouds of the head and ear by using the iterative closest point method | |
| Liu et al. | Study on Volumetric tool wear measurement using image processing | |
| Belhaoua et al. | Estimation of 3D reconstruction errors in a stereo-vision system | |
| Sun et al. | A 2D-3D non-contact anthropometric method for daily dressing state-takes young Asian women as example | |
| Awajan et al. | Quick method of measuring the furrows distribution on skin surface replicas | |
| Firdaus et al. | RGB-D Camera-Based Scanner for Hand Measurement | |
| Wang | A Body Measurement Method Based on the Ultrasonic Sensor | |
| Nagata et al. | Development of facial aging simulation system combined with three-dimensional shape prediction from facial photographs | |
| Liu et al. | Image-based 2-D non-contact human data measurement and its application to automotive seats | |
| Nakamura et al. | Analysis and classification of three-dimensional trunk shape of women by using the human body shape model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210305 |