CN109288176B - Body measuring and tailoring method based on millimeter waves - Google Patents
Body measuring and tailoring method based on millimeter waves Download PDFInfo
- Publication number
- CN109288176B CN109288176B CN201811303427.3A CN201811303427A CN109288176B CN 109288176 B CN109288176 B CN 109288176B CN 201811303427 A CN201811303427 A CN 201811303427A CN 109288176 B CN109288176 B CN 109288176B
- Authority
- CN
- China
- Prior art keywords
- data
- human body
- circumference
- taking
- waist
- 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.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A41—WEARING APPAREL
- A41H—APPLIANCES OR METHODS FOR MAKING CLOTHES, e.g. FOR DRESS-MAKING OR FOR TAILORING, NOT OTHERWISE PROVIDED FOR
- A41H1/00—Measuring aids or methods
- A41H1/02—Devices for taking measurements on the human body
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Engineering & Computer Science (AREA)
- Textile Engineering (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for measuring and tailoring clothes based on millimeter waves, which comprises the following steps: the testee stands according to a certain standing posture rule to obtain three-dimensional data and a data matrix of the human bodyScale of (N)z,Nx,Ny) And carrying out normalization processing on the data; step two: the forward projection is used for acquiring data of a human body in X and Y directions, wherein the data comprises height, arm length, shoulder width and head circumference data; step three: the lateral projection acquires human body circumferential data, including hip circumference, waist height, chest circumference and abdominal circumference data. The invention fully utilizes the excellent characteristics of millimeter waves, adopts the microwave imaging technology, realizes the non-contact human body three-dimensional data acquisition, quickly analyzes to obtain the relevant sizes of the human body, realizes the body measurement and tailoring, has high integral speed of the original image data acquisition and calculation, and finishes the whole body measurement process within 5 s.
Description
Technical Field
The invention relates to a body measuring and tailoring method based on millimeter waves, which realizes rapid non-contact human body three-dimensional data acquisition by a millimeter wave imaging technology.
Background
The traditional method for measuring the body and cutting out the clothes adopts a tape measure to measure the body characteristics of the human body such as the height, the arm length, the chest circumference, the waist circumference, the hip circumference and the like. The method is low in measurement speed and suitable for measuring small-batch crowds; meanwhile, the method inevitably generates human body contact and lacks mutual respect. The other method is to adopt an optical imaging technology to carry out optical three-dimensional imaging on the human body and analyze the sizes of all parts, and although the method is non-contact, the calculation result has larger error because light cannot penetrate through clothes.
Disclosure of Invention
The technical problem solved by the invention is as follows: in order to overcome the defects of the prior art, the millimeter wave-based body measuring and tailoring method is provided, and the non-contact human body three-dimensional data acquisition is realized by adopting a microwave imaging technology.
The technical solution of the invention is as follows:
a method for measuring body and tailoring clothes based on millimeter waves comprises the following specific steps:
the method comprises the following steps: the testee stands according to a certain standing posture rule to obtain three-dimensional data of the human body, and the data matrix scale is (N)z,Nx,Ny) And carrying out normalization processing on the data;
step two: the forward projection is used for acquiring data of a human body in X and Y directions, wherein the data comprises height, arm length, shoulder width and head circumference data;
step three: the lateral projection acquires human body circumferential data, including hip circumference, waist height, chest circumference and abdominal circumference data.
The standing posture of the tested person is regulated as follows: standing upright at the center of the test point, keeping the arms at an angle of 30-45 degrees with the two sides of the body, with the thumb facing outward and the thumb separated from the palm.
And acquiring original discrete data of the human body echo by using a millimeter wave imaging technology, and processing the original discrete data of the human body echo by adopting a BP imaging algorithm to acquire three-dimensional data of the human body.
The method for acquiring the data of the human body in the X and Y directions by forward projection in the second step comprises the following steps:
(1) image data processing: firstly, carrying out Z-direction cumulative summation on the human body three-dimensional data obtained in the step one to obtain a matrix (N)x,Ny) Performing Gaussian filtering on the summed image, and finally performing contour extraction to obtain a forward projection contour of the human body;
(2) taking the highest point of the human body outline as the height;
(3) dividing the human body forward projection profile data into a left part and a right part, respectively normalizing and carrying out differential processing, and taking the maximum differential positive value as an initial value to obtain two shoulder control lines; below the shoulder control line, taking the highest point of the protrusion of the thumb and the included angle between the thumb and the arm as initial values to obtain two wrist control lines; obtaining the arm length by performing least square fitting on the data of the shoulder control lines and the wrist control lines, and obtaining the shoulder width by performing difference on the intersection points of the two shoulder control lines and the outline;
(4) and taking the lower sharp point of the highest point of the human body contour as an initial value to obtain head circumference position information, and obtaining the head circumference through elliptic Fourier fitting.
The method for acquiring the human body circumferential data by lateral projection in the third step comprises the following steps:
(1) image data processing: firstly, the human body three-dimensional data obtained in the step one is taken as the maximum value in the X direction to obtain a matrix (N)z,Ny) Then carrying out median filtering and finally carrying out contour extraction to obtain a human body lateral projection contour;
(2) dividing the human body lateral projection contour data into a left part and a right part;
(3) obtaining hip and waist position data extreme values by taking the hip and waist standard values as reference points, calculating a Z-direction difference value of left and right side data in the same Y-direction downwards by taking the extreme values as initial values, taking the Z-direction difference value extreme values as Y-direction position information of the hip and the waist, and obtaining hip circumference, waist circumference and waist height through elliptic Fourier fitting;
(4) and taking Y-direction position information of the shoulder and the waist as reference points, adjusting the offset through an offset coefficient related to the height, calculating a Z-direction difference value of data on the left side and the right side in the same Y-direction, taking a Z-direction difference value extreme value as Y-direction position information of the chest and the abdomen, and obtaining the chest circumference and the abdomen circumference through elliptic Fourier fitting.
In the third step, the method for obtaining the arm length by performing least square fitting on the shoulder control line and the wrist control line data comprises the following steps: if the difference value of the two groups of arm lengths is not more than 5% of the larger arm length, the average value of the two groups of arm lengths is the real arm length; and if the difference value of the two groups of arm lengths is more than 5% of the larger arm length, comparing the arm lengths with the standard arm length, and taking the value close to the standard arm length as the real arm length.
The deviation coefficient in the third step is the ratio of the difference value of the two standard parts to the height.
Can also include the step four according to the clothing volume: and D, adding corresponding offset to the ellipse Fourier fitting results of the hip circumference, the waist circumference, the chest circumference and the abdomen circumference obtained in the step three.
The method for calculating the fitting of the ellipse Fourier in the fourth step comprises the following steps: the points on the closed contour line of the perimeter of the human body section are described as P (t) ═ xt,yt) Expanding the points on the contour by the following elliptical Fourier series,
wherein A is0、C0X and y coordinates of the center point of the profile; n is the expansion stage number; t is the cumulative displacement of the point along the profile; t is the original contour perimeter.
Defining: x is the human width direction, Y is the human height direction, and Z is the human thickness direction; n is a radical ofxIs the size of the human body in the width direction, NyIs the size of the human body in the height direction, NzThe size in the thickness direction of the human body.
Compared with the prior art, the invention has the beneficial effects that:
(1) according to the invention, the excellent characteristics of millimeter waves are fully utilized, a microwave imaging technology is adopted, the non-contact human body three-dimensional data acquisition is realized, the relevant size of a human body is obtained through rapid analysis, the body measurement and tailoring are realized, the overall speed of the original image data acquisition and calculation is rapid, and the whole body measurement process is completed within 5 s;
(2) the invention has the advantages that the clothes are tailored without contact, the human body is respected, the clothes are penetrated, and the measurement precision is high;
(3) according to the invention, corresponding offset can be added to the acquired ellipse Fourier fitting results of hip circumference, waist circumference, chest circumference and abdomen circumference according to the clothing amount, and the measurement result is flexible.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a schematic view of the forward projection height and arm length control line of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, the millimeter wave has certain penetrability and no harm to human body, and can be used for human body detection. The invention fully utilizes the excellent characteristics of millimeter waves, adopts the microwave imaging technology, realizes the non-contact human body three-dimensional data acquisition, quickly analyzes to obtain the relevant size of the human body, realizes the body measurement and tailoring, and finishes the whole body measurement process within 5 s.
The specific working process is shown in fig. 1:
the method comprises the following steps: raw image data acquisition:
the standing posture of the testee is specified as follows: standing at the center of the test point; the arms and the two sides of the body keep an included angle of 30-45 degrees; the thumb faces outwards and is separated from the palm;
defining: x is the human width direction, Y is the human height direction, and Z is the human thickness direction; n is a radical ofxIs the size of the human body in the width direction, NyIs the size of the human body in the height direction, NzThe size of the human body in the thickness direction;
obtaining original discrete data of human body echo by millimeter wave imaging technology, processing the original discrete data of human body echo by BP imaging algorithm to obtain three-dimensional data of human body, wherein the data matrix has a scale of (N)z,Nx,Ny) And carrying out normalization processing on the data;
step two: forward projection calculation:
the purpose of forward projection is to obtain data of human body in X and Y directions, including but not limited to height, arm length, waist height, and shoulder width, as shown in FIG. 2. The initial value of each part can be determined by GB10000-88 Chinese adult human body size, and the specific operation process is as follows:
(1) image data processing: firstly, carrying out Z-direction cumulative summation on the human body three-dimensional data obtained in the step one to obtain a matrix (N)x,Ny) Performing Gaussian filtering on the summed image, and finally performing contour extraction to obtain a forward projection contour of the human body;
(2) taking the highest point of the human body outline as the height;
(3) dividing the human body forward projection profile data into a left part and a right part, respectively normalizing and carrying out differential processing, and taking the maximum differential positive value as an initial value to obtain two shoulder control lines; below the shoulder control line, taking the highest point of the protrusion of the thumb and the included angle between the thumb and the arm as initial values to obtain two wrist control lines; obtaining the arm length by performing least square fitting on the data of the shoulder control lines and the wrist control lines, and obtaining the shoulder width by performing difference on the intersection points of the two shoulder control lines and the outline;
(4) taking the lower sharp point of the highest point of the human body contour as an initial value to obtain head circumference position information, and obtaining the head circumference through elliptic Fourier fitting;
step three: calculating the lateral projection:
the purpose of the side projection is to acquire circumferential data of the human body, including but not limited to abdominal circumference, hip circumference, waist circumference, chest circumference and the like. The initialization value of each part can be determined by GB10000-88 human body size of Chinese adults, and the specific operation flow is as follows:
(1) image data processing: firstly, the human body three-dimensional data obtained in the step one is taken as the maximum value in the X direction to obtain a matrix (N)z,Ny) Then carrying out median filtering and finally carrying out contour extraction to obtain a human body lateral projection contour;
(2) the human body lateral projection contour data is divided into a left part and a right part,
(3) obtaining hip and waist position data extreme values by taking the hip and waist standard values as reference points, calculating a Z-direction difference value of left and right side data in the same Y-direction downwards by taking the extreme values as initial values, taking the Z-direction difference value extreme values as Y-direction position information of the hip and the waist, and obtaining hip circumference, waist circumference and waist height through elliptic Fourier fitting;
(4) and taking Y-direction position information of the shoulder and the waist as reference points, adjusting the offset through an offset coefficient related to the height, calculating a Z-direction difference value of data on the left side and the right side in the same Y-direction, taking a Z-direction difference value extreme value as Y-direction position information of the chest and the abdomen, and obtaining the chest circumference and the abdomen circumference through elliptic Fourier fitting.
The obtained data can be transmitted back and displayed, and clothes matched with the real size of the human body can be cut according to the data.
Can also include the step four according to the clothing volume: and D, adding corresponding offset to the ellipse Fourier fitting results of the hip circumference, the waist circumference, the chest circumference and the abdomen circumference obtained in the step three.
The method for obtaining the arm length by performing least square fitting on the shoulder control line and the wrist control line data comprises the following steps: if the difference value of the two groups of arm lengths is not more than 5% of the larger arm length, the average value of the two groups of arm lengths is the real arm length; and if the difference value of the two groups of arm lengths is more than 5% of the larger arm length, comparing the arm lengths with the standard arm length, and taking the value close to the standard arm length as the real arm length.
The offset coefficient is the ratio of the difference value of the two standard parts to the height.
The ellipse Fourier fitting calculation method comprises the following steps: the points on the closed contour line of the perimeter of the human body section are described as P (t) ═ xt,yt) Expanding the points on the contour by the following elliptical Fourier series,
wherein A is0、C0X and y coordinates of the center point of the profile; n is the expansion series, namely the number of the ellipses which are approximately approximated; t is the cumulative displacement of the point along the profile; t is the original contour perimeter.
By means of the method of the present invention,
(1) the whole speed of acquiring and calculating the original image data is high, the whole volume measuring process is finished within 5s,
(2) the non-contact type body-measuring tailoring is respectful to human body, penetrates through clothes, has high measuring precision,
(3) the millimeter wave has certain penetrability and is harmless to human bodies.
The millimeter wave-based method for tailoring the body according to the present invention is only used for helping to illustrate the present invention, and is not used as a specific embodiment for limiting the present invention, and many modifications and variations can be made according to the actual needs, so that the principle and the practical application of the present invention are included in the protection scope of the present invention, and the non-disclosure of the present invention is the common knowledge of those skilled in the art.
Claims (6)
1. A body measuring and tailoring method based on millimeter waves is characterized by comprising the following specific steps:
the method comprises the following steps: the testee stands according to a certain standing posture rule to obtain three-dimensional data of the human body, and the data matrix scale is (N)z，Nx，Ny) And carrying out normalization processing on the data;
step two: the forward projection is used for acquiring data of a human body in X and Y directions, wherein the data comprises height, arm length, shoulder width and head circumference data;
(1) image data processing: firstly, carrying out Z-direction cumulative summation on the human body three-dimensional data obtained in the step one to obtain a matrix (N)x，Ny) Performing Gaussian filtering on the summed image, and finally performing contour extraction to obtain a forward projection contour of the human body;
(2) taking the highest point of the human body outline as the height;
(3) dividing the human body forward projection profile data into a left part and a right part, respectively normalizing and carrying out differential processing, and taking the maximum differential positive value as an initial value to obtain two shoulder control lines; below the shoulder control line, taking the highest point of the protrusion of the thumb and the included angle between the thumb and the arm as initial values to obtain two wrist control lines; obtaining the arm length by performing least square fitting on the data of the shoulder control lines and the wrist control lines, and obtaining the shoulder width by performing difference on the intersection points of the two shoulder control lines and the outline;
(4) the highest point and the lower sharp point of the human body contour are used as initial values to obtain head circumference position information, and head circumference is obtained through elliptic Fourier fitting;
step three: acquiring circumferential data of a human body by lateral projection, wherein the circumferential data comprises hip circumference, waist height, chest circumference and abdominal circumference data;
(1) image data processing: firstly, the human body three-dimensional data obtained in the step one is taken as the maximum value in the X direction to obtain a matrix (N)z，Ny) Then carrying out median filtering and finally carrying out contour extraction to obtain a human body lateral projection contour;
(2) dividing the human body lateral projection contour data into a left part and a right part;
(3) obtaining hip and waist position data extreme values by taking the hip and waist standard values as reference points, calculating a Z-direction difference value of left and right side data in the same Y-direction downwards by taking the extreme values as initial values, taking the Z-direction difference value extreme values as Y-direction position information of the hip and the waist, and obtaining hip circumference, waist circumference and waist height through elliptic Fourier fitting;
(4) taking Y-direction position information of shoulders and waist as reference points, adjusting offset through an offset coefficient related to height, calculating a Z-direction difference value of left and right side data in the same Y-direction, taking a Z-direction difference value extreme value as Y-direction position information of a chest and an abdomen, and obtaining the chest circumference and the abdomen circumference through elliptic Fourier fitting;
the standing posture of the tested person is regulated as follows: standing upright at the center of the test point, keeping the included angle of 30-45 degrees between the arms and the two sides of the body, keeping the thumb outward, and separating the thumb from the palm;
defining: x is the human width direction, Y is the human height direction, and Z is the human thickness direction; n is a radical ofxIs the size of the human body in the width direction, NyIs the size of the human body in the height direction, NzThe size in the thickness direction of the human body.
2. The method for measuring the body size and tailoring based on millimeter waves of claim 1 wherein millimeter wave imaging technology is used to obtain the original discrete data of the human body echo, and BP imaging algorithm is used to process the original discrete data of the human body echo to obtain the three-dimensional data of the human body.
3. The millimeter wave-based body measurement and tailoring method according to claim 1 wherein the second step of obtaining the arm length by performing least squares fitting on the shoulder control line and wrist control line data comprises: if the difference value of the two groups of arm lengths is not more than 5% of the larger arm length, the average value of the two groups of arm lengths is the real arm length; and if the difference value of the two groups of arm lengths is more than 5% of the larger arm length, comparing the arm lengths with the standard arm length, and taking the value close to the standard arm length as the real arm length.
4. The millimeter wave-based sizing and tailoring method of claim 1 wherein the shift factor in step three is the ratio of the difference between the two standard sites to height.
5. The millimeter wave-based body size tailoring method according to claim 1 further comprising the steps of, according to the amount of clothing worn: and D, adding corresponding offset to the ellipse Fourier fitting results of the hip circumference, the waist circumference, the chest circumference and the abdomen circumference obtained in the step three.
6. The millimeter wave-based sizing and tailoring method according to claim 1, wherein the ellipse Fourier fitting calculation method in the second step and the third step is as follows: the points on the closed contour line of the perimeter of the human body section are described as P (t) ═ xt，yt) The points on the contour are expanded by the following elliptical Fourier series,
wherein A is0、C0X and y coordinates of the center point of the profile; n is the expansion stage number; t is the cumulative displacement of the point along the profile; t is the original contour perimeter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811303427.3A CN109288176B (en) | 2018-11-02 | 2018-11-02 | Body measuring and tailoring method based on millimeter waves |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811303427.3A CN109288176B (en) | 2018-11-02 | 2018-11-02 | Body measuring and tailoring method based on millimeter waves |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109288176A CN109288176A (en) | 2019-02-01 |
| CN109288176B true CN109288176B (en) | 2020-09-18 |
Family
ID=65145620
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811303427.3A Active CN109288176B (en) | 2018-11-02 | 2018-11-02 | Body measuring and tailoring method based on millimeter waves |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109288176B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084881A (en) * | 2019-03-13 | 2019-08-02 | 广东元一科技实业有限公司 | A kind of the 3-D image building system and its method of dress designing |
| CN110264514B (en) * | 2019-06-27 | 2021-03-30 | 杭州智珺智能科技有限公司 | Human body chest circumference and waist circumference measuring method based on random optimization strategy |
| CN111166338B (en) * | 2019-12-24 | 2022-04-08 | 天津农学院 | Pregnant sow body size calculation method based on TOF depth data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104517296A (en) * | 2014-12-25 | 2015-04-15 | 深圳市一体太赫兹科技有限公司 | Partition method and system for three-dimensional millimeter wave image |
| CN104814556A (en) * | 2015-02-25 | 2015-08-05 | 广定科技(上海)有限公司 | Collector for collecting net size of human body |
| CN107041585A (en) * | 2017-03-07 | 2017-08-15 | 上海优裁信息技术有限公司 | The measuring method of human dimension |
| CN107529420A (en) * | 2017-08-23 | 2018-01-02 | 成都天体微波科技有限公司 | It is a kind of to measure body contour line and with millimeter wave perspective for building the method and system of human body three-dimensional image |
| CN108634459B (en) * | 2018-05-08 | 2020-04-17 | 东华大学 | Female jacket sample plate generation method based on 3D human body measurement data |
-
2018
- 2018-11-02 CN CN201811303427.3A patent/CN109288176B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109288176A (en) | 2019-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109288176B (en) | Body measuring and tailoring method based on millimeter waves | |
| CN108986159B (en) | Method and equipment for reconstructing and measuring three-dimensional human body model | |
| CN102208109B (en) | Different-source image registration method for X-ray image and laser image | |
| CN102657532B (en) | Height measuring method and device based on body posture identification | |
| CN105809693B (en) | SAR image registration method based on deep neural network | |
| WO2016194161A1 (en) | Ultrasonic diagnostic apparatus and image processing method | |
| JPH10130929A (en) | Device for producing corrected underwear and its production | |
| CN108717531A (en) | Estimation method of human posture based on Faster R-CNN | |
| CN108802689A (en) | Space microphone localization method based on acoustic source array | |
| CN108509908A (en) | A kind of pupil diameter method for real-time measurement based on binocular stereo vision | |
| CN106418847A (en) | Human 3D size measuring method based on computer vision technology | |
| US11779242B2 (en) | Systems and methods to estimate human length | |
| CN105405119A (en) | Automatic fetus median sagittal plane detection method based on depth belief network and three dimensional model | |
| CN105761254A (en) | Image feature based eyeground image registering method | |
| CN104268880A (en) | Depth information obtaining method based on combination of features and region matching | |
| CN106228567A (en) | A kind of vertebra characteristic point automatic identifying method based on mean curvature flow | |
| CN204070693U (en) | A kind of three-dimensional human body measurement device of structure based light technology | |
| Zhong et al. | Automatic body measurement based on slicing loops | |
| CN112419479A (en) | Body type data calculation method based on weight, height and body image | |
| Škorvánková et al. | Automatic estimation of anthropometric human body measurements | |
| CN110349206A (en) | A kind of method and relevant apparatus of human body symmetrical detection | |
| CN107314882B (en) | The wind vibration response acquisition methods of membrane structure air spring pole based on technique of binocular stereoscopic vision | |
| CN104463825A (en) | Apparatus and method for detecting objects in three-dimensional volumetric image | |
| Sul et al. | Regeneration of 3D body scan data using semi‐implicit particle‐based method | |
| JP2017142164A (en) | Radar device, target shape estimation method, and program |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |