CN110717938A - Method and system for remotely acquiring human body size information based on video analysis - Google Patents

Method and system for remotely acquiring human body size information based on video analysis Download PDF

Info

Publication number
CN110717938A
CN110717938A CN201911000261.2A CN201911000261A CN110717938A CN 110717938 A CN110717938 A CN 110717938A CN 201911000261 A CN201911000261 A CN 201911000261A CN 110717938 A CN110717938 A CN 110717938A
Authority
CN
China
Prior art keywords
video
human body
size
analysis
video analysis
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.)
Withdrawn
Application number
CN201911000261.2A
Other languages
Chinese (zh)
Inventor
周书田
于海洋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Yu Shuo Yun Lian Mdt Infotech Ltd
Original Assignee
Qingdao Yu Shuo Yun Lian Mdt Infotech Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Qingdao Yu Shuo Yun Lian Mdt Infotech Ltd filed Critical Qingdao Yu Shuo Yun Lian Mdt Infotech Ltd
Priority to CN201911000261.2A priority Critical patent/CN110717938A/en
Publication of CN110717938A publication Critical patent/CN110717938A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • 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
    • 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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Graphics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Textile Engineering (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention relates to a method and a system for remotely acquiring human body dimension information based on video analysis, and belongs to the technical field of modeling measurement. The method comprises the steps of constructing a remote system, establishing a three-dimensional coordinate system, selecting a plurality of reference objects, and selecting articles with the same size as the reference objects; calculating the position of the foot of the client in a camera coordinate system according to the position of the foot of the client, and mapping the position of the foot in the camera coordinate system together with information such as height and the like into an actual three-dimensional coordinate system; calculating the size of a human body according to the pixel ratio of the human in the video; for each frame, finding a center point; for waist measurement, firstly finding the central point of the waist trunk; measuring the widest margin point of the 2D waist image; performing 3D modeling according to all marginal points of a week; and the acquisition is repeated, the precision is improved, human body segmentation is carried out in the video, different parts are independently modeled for video analysis, and the size for measuring body cutting is obtained. According to the invention, the human body size information is intelligently analyzed through the remotely acquired video information, and the method is simple, rapid, visual and accurate.

Description

Method and system for remotely acquiring human body size information based on video analysis
Technical Field
The invention relates to a method and a system for remotely acquiring human body dimension information based on video analysis, and belongs to the technical field of modeling measurement.
Background
The information collected by the history can not be continuously applied along with the change of the size of the human body with the age and the weight. The most accurate acquisition mode of human size information is often manual measurement, and this often requires that the customer can only realize with surveying personnel face to face. The measurement is carried out in a store specially for measuring the three-dimensional data of the body at one time, and the time is wasted. Therefore, a method and a system for remotely collecting and accurately analyzing the size information of the human body at any time and any place are needed. In the prior art, remote pictures are often used for analysis, and the problems of too little collected data, inaccuracy, intuition and the like exist.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method and a system for remotely acquiring the human body dimension information based on video analysis.
The invention discloses a method for remotely acquiring human body dimension information based on video analysis, which comprises the following steps:
s1: constructing a remote system: developing a user side of a remote system of an APP (application), a WeChat applet and a PC (personal computer) terminal based on a mobile phone, and uploading the obtained remote video to the PC terminal through the APP and the WeChat applet based on the mobile phone;
s2: establishing a three-dimensional coordinate system, which comprises the following steps:
s21: selection of reference: selecting a plurality of reference objects, wherein the reference objects are selected to be articles with the same size;
s22: establishing three-dimensional coordinates: firstly, detecting the size and the angle of the reference object, then calibrating a camera, establishing a camera coordinate system, calculating the position of the reference object in the camera coordinate system according to the position of the foot of a client, and mapping the reference object in the actual three-dimensional coordinate system together with information such as height and the like;
s3: obtaining the size of a human body, comprising the following steps:
s31: determining the basic size: calculating the size of a human body according to the pixel ratio of the human in the video;
s32: collecting characteristic points, comprising the following specific steps:
s321: and (3) collecting a central point: for each frame, finding a center point; for waist measurement, firstly finding the central point of the waist trunk;
s322: and (3) collecting marginal points: measuring the widest margin point of the 2D waist image;
s323: 3D modeling: performing 3D modeling according to all marginal points of a week;
s33: and (3) repeatedly collecting: in order to improve the precision, the positions of the characteristic points in the step S32 are staggered, different characteristic point precision and positions are reestablished, a plurality of 3D models of the same human body are formed, and more accurate human body sizes are obtained through measurement and calculation;
s34: determination of other dimensions: according to the action analysis of one circle of rotation of the client, the sizes of all aspects of the human body are continuously calculated;
s4: the remote analysis of the segmented video comprises the following small steps:
s41: and (3) segmentation modeling of the video: human body segmentation is carried out in the video, and different parts are independently modeled to carry out video analysis;
s42: measuring and cutting: combining the professional opinions of the body measuring engineer to guide how to obtain the size for body measuring and cutting.
In the step S1, the video acquires an APP based on the mobile phone, the APP calls a user camera, records the video, verifies the early-stage video qualification, and uploads the video; and the PC remote system performs video analysis and AI calculation to obtain the user size.
In the step S21, the reference object is preferably a mineral water bottle with a uniform height.
In the step S32, in the feature points, the marginal points are replaced by a circle of oblique lines superimposed on the central point, and the waist trunk is replaced by a vertical line on the central point.
In step S41, the human body size is obtained by analyzing the video recorded by the client through computer vision analysis, deep learning of the neural network, and the human body database.
In step S21, when the mobile terminal collects the video, the background is required to be as single as possible, no other motion noise is generated, and the light meets the requirements as much as possible.
The reference plane during video acquisition of the mobile terminal is preferably the ground.
The system for remotely acquiring the human body size information based on the video analysis comprises a PC (personal computer) end remote system and a mobile terminal;
the mobile terminal comprises an APP (application) based on a mobile phone, a WeChat small program and a camera capable of acquiring human body size information, and is used for uploading videos through video recording, early-stage video qualification verification;
and the PC-end remote system is used for carrying out video analysis on the uploaded video and obtaining the human body size by combining machine learning.
The invention has the beneficial effects that: according to the method and the system for remotely acquiring the human body size information based on the video analysis, the human body size information meeting the requirements in the video is intelligently analyzed through the remotely acquired video information, and the method and the system are simple, rapid, visual and accurate.
Drawings
FIG. 1 is a flow diagram of the method of the present invention.
Fig. 2 is a schematic diagram of the system of the present invention.
Fig. 3 is a 3D model diagram of human body size information.
FIG. 4(a) is one of the collected plots of the center point and the edge points.
FIG. 4(b) is a second collection of center points and edge points.
In the figure: 1. a mobile phone; 2. a PC end remote system; 3. a reference object; 4. a center point; 5. a marginal point; 6. the waist and the trunk.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
as shown in fig. 1, the method for remotely acquiring the human body dimension information based on video analysis according to the present invention includes the following steps:
s1: constructing a remote system: developing a user side of an APP (application), a WeChat applet and a PC (personal computer) end remote system 2 based on a mobile phone 1, and uploading the obtained remote video to the PC end through the APP and the WeChat applet based on the mobile phone 1;
s2: establishing a three-dimensional coordinate system, which comprises the following steps:
s21: selection of reference 3: selecting a plurality of reference objects 3, wherein the reference objects 3 are selected as articles with the same size;
s22: establishing three-dimensional coordinates: firstly, detecting the size and the angle of the reference object 3, then calibrating a camera, establishing a camera coordinate system, calculating the position of the reference object in the camera coordinate system according to the position of the foot of a client, and mapping the position of the reference object in the actual three-dimensional coordinate system together with information such as height and the like, as shown in figure 3;
s3: obtaining the size of a human body, comprising the following steps:
s31: determining the basic size: calculating the size of a human body according to the pixel ratio of the human in the video;
s32: collecting characteristic points, comprising the following specific steps:
s321: acquisition of the central point 4: for each frame, find the center point 4; for lumbar measurements, the central point 4 of the lumbar torso 6 is found first;
s322: acquisition of marginal point 5: measuring the widest marginal point 5 of the 2D image of the waist, as shown in fig. 4(a) and 4 (b);
s323: 3D modeling: 3D modeling is carried out according to all marginal points 5 of a week;
s33: and (3) repeatedly collecting: in order to improve the precision, the positions of the characteristic points in the step S32 are staggered, different characteristic point precision and positions are reestablished, a plurality of 3D models of the same human body are formed, and more accurate human body sizes are obtained through measurement and calculation;
s34: determination of other dimensions: according to the action analysis of one circle of rotation of the client, the sizes of all aspects of the human body are continuously calculated;
s4: the remote analysis of the segmented video comprises the following small steps:
s41: and (3) segmentation modeling of the video: human body segmentation is carried out in the video, and different parts are independently modeled to carry out video analysis;
s42: measuring and cutting: combining the professional opinions of the body measuring engineer to guide how to obtain the size for body measuring and cutting.
In the step S1, the video acquires an APP based on the mobile phone 1, the APP calls a user camera, records the video, verifies the early-stage video qualification, and uploads the video; and the PC end remote system 2 performs video analysis and AI calculation to obtain the user size.
In the step S21, the reference object 3 is preferably a mineral water bottle with a uniform height.
In the step S32, in the feature points, the marginal point 5 is replaced by a circle of oblique lines superimposed on the central point 4, and the waist trunk 6 is replaced by a vertical line on the central point 4.
In step S41, the human body size is obtained by analyzing the video recorded by the client through computer vision analysis, deep learning of the neural network, and the human body database.
In step S21, when the mobile terminal collects the video, the background is required to be as single as possible, no other motion noise is generated, and the light meets the requirements as much as possible.
The reference plane during video acquisition of the mobile terminal is preferably the ground.
Example 2:
as shown in fig. 2, the system for remotely obtaining human body dimension information based on video analysis according to the present invention includes a PC remote system 2 and a mobile terminal;
the mobile terminal comprises an APP (application) based on the mobile phone 1, a WeChat applet and a camera capable of acquiring human body size information, and is used for uploading videos through video recording, early-stage video qualification verification;
and the PC end remote system 2 is used for carrying out video analysis on the uploaded video and obtaining the human body size by combining machine learning.
According to the method and the system for remotely acquiring the human body size information based on the video analysis, the human body size information meeting the requirements in the video is intelligently analyzed through the remotely acquired video information, and the method and the system are simple, rapid, visual and accurate.
The invention can be widely applied to modeling measurement occasions.
It is well within the skill of those in the art to implement and protect the present invention without undue experimentation and without undue experimentation that the present invention is directed to software and process improvements.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (8)

1. A method for remotely acquiring human body size information based on video analysis is characterized by comprising the following steps:
s1: constructing a remote system: developing a user side of an APP (application), a WeChat applet and a PC (personal computer) end remote system (2) based on a mobile phone (1), and uploading the obtained remote video to the PC end through the APP and the WeChat applet based on the mobile phone (1);
s2: establishing a three-dimensional coordinate system, which comprises the following steps:
s21: selection of reference (3): selecting a plurality of reference objects (3), wherein the reference objects (3) are selected to be articles with the same size;
s22: establishing three-dimensional coordinates: firstly, detecting the size and the angle of the reference object (3), then calibrating a camera, establishing a camera coordinate system, calculating the position of the reference object in the camera coordinate system according to the position of the foot of a client, and mapping the position of the reference object in the actual three-dimensional coordinate system together with information such as height and the like;
s3: obtaining the size of a human body, comprising the following steps:
s31: determining the basic size: calculating the size of a human body according to the pixel ratio of the human in the video;
s32: collecting characteristic points, comprising the following specific steps:
s321: acquisition of the central point (4): for each frame, finding a central point (4); for waist measurement, firstly finding a central point (4) of a waist trunk (6);
s322: acquisition of the marginal point (5): measuring the widest margin point (5) of the 2D image of the waist;
s323: 3D modeling: 3D modeling is carried out according to all marginal points (5) of a week;
s33: and (3) repeatedly collecting: in order to improve the precision, the positions of the characteristic points in the step S32 are staggered, different characteristic point precision and positions are reestablished, a plurality of 3D models of the same human body are formed, and more accurate human body sizes are obtained through measurement and calculation;
s34: determination of other dimensions: according to the action analysis of one circle of rotation of the client, the sizes of all aspects of the human body are continuously calculated;
s4: the remote analysis of the segmented video comprises the following small steps:
s41: and (3) segmentation modeling of the video: human body segmentation is carried out in the video, and different parts are independently modeled to carry out video analysis;
s42: measuring and cutting: combining the professional opinions of the body measuring engineer to guide how to obtain the size for body measuring and cutting.
2. The method for remotely acquiring the human body size information based on the video analysis as claimed in claim 1, wherein in the step S1, the video acquires an APP based on the mobile phone (1), the APP calls a user camera, the video is recorded, the previous video is qualified, and the video is uploaded; and the PC end remote system (2) performs video analysis and AI calculation to obtain the user size.
3. The method for remotely obtaining human body size information based on video analysis according to claim 1, wherein in step S21, the reference object (3) is preferably a highly uniform mineral water bottle.
4. The method for remotely acquiring the human body size information based on the video analysis according to claim 1, wherein in the step S32, the marginal point (5) in the collected feature points is replaced by a circle of oblique lines superposed by the central point (4), and the waist trunk (6) is replaced by a vertical line on the central point (4).
5. The method for remotely obtaining the human body dimension information based on the video analysis as claimed in claim 1, wherein in the step S41, the human body dimension is obtained by the computer vision analysis, the deep learning of the neural network, and the human body database to use the video analysis of the customer-specified recording.
6. The method for remotely acquiring the human body dimension information based on the video analysis as claimed in claim 6, wherein in the step S21, the background is required to be as single as possible, no other motion noise is generated, and the light is required to be as good as possible when the mobile terminal collects the video.
7. The method for remotely acquiring the human body dimension information based on the video analysis as claimed in claim 1, wherein the reference plane of the mobile terminal during the video acquisition is preferably the ground.
8. A system for remotely acquiring human body size information based on video analysis is characterized by comprising a PC (personal computer) end remote system (2) and a mobile terminal;
the mobile terminal comprises an APP (application), a WeChat applet and a camera, wherein the APP and the WeChat applet are based on the mobile phone (1), the camera can acquire human body size information, and the mobile terminal is used for uploading videos through video recording and early-stage video qualification verification;
and the PC end remote system (2) is used for carrying out video analysis on the uploaded video and obtaining the human body size by combining machine learning.
CN201911000261.2A 2019-10-21 2019-10-21 Method and system for remotely acquiring human body size information based on video analysis Withdrawn CN110717938A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911000261.2A CN110717938A (en) 2019-10-21 2019-10-21 Method and system for remotely acquiring human body size information based on video analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911000261.2A CN110717938A (en) 2019-10-21 2019-10-21 Method and system for remotely acquiring human body size information based on video analysis

Publications (1)

Publication Number Publication Date
CN110717938A true CN110717938A (en) 2020-01-21

Family

ID=69213908

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911000261.2A Withdrawn CN110717938A (en) 2019-10-21 2019-10-21 Method and system for remotely acquiring human body size information based on video analysis

Country Status (1)

Country Link
CN (1) CN110717938A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB202109126D0 (en) 2021-06-24 2021-08-11 Aistetic Ltd Method and system for obtaining human body size information from image data

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB202109126D0 (en) 2021-06-24 2021-08-11 Aistetic Ltd Method and system for obtaining human body size information from image data
GB2608170A (en) 2021-06-24 2022-12-28 Aistetic Ltd Method and system for obtaining human body size information from image data
WO2022269219A1 (en) 2021-06-24 2022-12-29 Aistetic Limited Method and system for obtaining human body size information from image data

Similar Documents

Publication Publication Date Title
CN111060023B (en) High-precision 3D information acquisition equipment and method
US10813715B1 (en) Single image mobile device human body scanning and 3D model creation and analysis
KR102290040B1 (en) Imaging a body
Liu et al. Tracking-based 3D human skeleton extraction from stereo video camera toward an on-site safety and ergonomic analysis
US11145130B2 (en) Method for automatically capturing data from non-networked production equipment
US20180082414A1 (en) Methods Circuits Assemblies Devices Systems Platforms and Functionally Associated Machine Executable Code for Computer Vision Assisted Construction Site Inspection
CN103003845B (en) Pose estimation device, pose estimation system and pose estimation method
CN107924461B (en) Method, circuit, equipment, system and the correlation computer executable code for being registrated and tracking for multifactor characteristics of image
CN108053476B (en) Human body parameter measuring system and method based on segmented three-dimensional reconstruction
CN111292239B (en) Three-dimensional model splicing equipment and method
CN102833486B (en) The method and device of face displaying ratio in a kind of real-time adjusting video images
US20170053422A1 (en) Mobile device human body scanning and 3d model creation and analysis
CN112304222B (en) Background board synchronous revolution's 3D information acquisition equipment
CN110874583A (en) Passenger flow statistics method and device, storage medium and electronic equipment
US11450148B2 (en) Movement monitoring system
CN112016570A (en) Three-dimensional model generation method used in background plate synchronous rotation acquisition
CN112818925A (en) Urban building and crown identification method
CN111412842A (en) Method, device and system for measuring cross-sectional dimension of wall surface
US20240029372A1 (en) Method for automatically capturing data from non-networked production equipment
JP2022046210A (en) Learning device, processing device, learning method, posture detection model, program and storage medium
CN111208138A (en) Intelligent wood recognition device
CN110717938A (en) Method and system for remotely acquiring human body size information based on video analysis
CN109740458B (en) Method and system for measuring physical characteristics based on video processing
US20240013415A1 (en) Methods and systems for representing a user
JP3637416B2 (en) Three-dimensional measurement method, three-dimensional measurement system, image processing apparatus, and computer 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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20200121