CN107192342A - A kind of measuring method and system of contactless build data - Google Patents
A kind of measuring method and system of contactless build data Download PDFInfo
- Publication number
- CN107192342A CN107192342A CN201710331941.7A CN201710331941A CN107192342A CN 107192342 A CN107192342 A CN 107192342A CN 201710331941 A CN201710331941 A CN 201710331941A CN 107192342 A CN107192342 A CN 107192342A
- Authority
- CN
- China
- Prior art keywords
- characteristic point
- space length
- space
- build
- multiframe
- 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
Classifications
-
- 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
- G01B11/03—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by measuring coordinates of points
-
- 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
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- 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
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind of measuring method and system of contactless build data, the measuring method includes:Obtain multiframe build image, and by described in every frame build image obtain one to multiple group of physical characteristic point group space coordinate;According to one or more build data of the spatial coordinates calculation of physical characteristic point group described in one to multiple group, so as to obtain every idiotype data multiframe calculated value corresponding with the multiframe build image;Calculate the arithmetic mean of instantaneous value of the multiframe calculated value of each build data.The invention has the beneficial effect that:The measurement of contactless build data can be achieved by the collocation of depth transducer and processor, hardware cost is relatively low, and measuring speed is fast, measurement accuracy is high and measurement can be automatically finished, measurement process is simple, requires low to operating personnel, and the posture to the measured requires low.
Description
Technical field
The present invention relates to human body measurement technology field, more particularly to a kind of contactless build data measuring method and be
System.
Background technology
Traditional-handwork measuring method is mainly using instruments such as tape, altimeter, range-viewfinder, goniometers, and direct measurement goes out people
Each position of body is horizontal, longitudinal, oblique, the length surface of girth etc..Its method is easy, and instrument is simple, but its time of measuring is long,
Error is big, and limit by the degree of being skilled in technique of gauger, be unfavorable on a large scale, rapidly measure human body.
The content of the invention
The technical problem to be solved in the present invention is, for the above-mentioned measuring method time of measuring of traditional-handwork in the prior art
Long, error is big, and is limited by the degree of being skilled in technique of gauger, and there is provided one for the problem of being unfavorable on a large scale, rapidly measuring human body
Plant the measuring method and system of contactless build data.
The technical solution adopted for the present invention to solve the technical problems is:
On the one hand there is provided a kind of measuring method of contactless build data, including:
Multiframe build image is obtained, and the space that build image described in every frame is obtained into one to multiple group of physical characteristic point group is sat
Mark;
According to one or more build data of the spatial coordinates calculation of physical characteristic point group described in one to multiple group, so as to obtain every
Idiotype data multiframe calculated value corresponding with the multiframe build image;
Calculate the arithmetic mean of instantaneous value of the multiframe calculated value of each build data.
It is described according to acquisition multiframe build image in measuring method of the present invention, and will be per build figure described in frame
Space coordinate as obtaining one to multiple group of physical characteristic point group, including:
Build image described in multiframe is obtained by depth transducer;
The space coordinate of one to multiple group of physical characteristic point group is obtained according to acquired every frame type image.
In measuring method of the present invention, every frame type image acquired in the foundation obtains one to multiple group of build
The space coordinate of feature point group, including:
Extracted by the depth transducer per the depth information in frame type image;
The depth information is learnt according to Exemplar-SVM models and recognized special to obtain one to multiple group of build
Levy the space coordinate of a group.
In measuring method of the present invention, the space coordinate meter according to physical characteristic point group described in one to multiple group
One or more build data is calculated, so as to obtain every idiotype data multiframe calculated value corresponding with the multiframe build image, is wrapped
Include:
The space length between the space coordinate of physical characteristic point group described in one to multiple group is calculated to obtain one to multiple individual
Type data;
Judge whether the build data per frame exceed default threshold range, if so, the build data of present frame are then abandoned,
And go to it is described acquisition multiframe build image, and by described in every frame build image obtain one to multiple group of physical characteristic point group space
The step of coordinate, if it is not, then adding the build data of present frame to data pool;
Judge whether the frame number of the build data in the data pool exceedes default threshold value, if so, then obtaining per individual
Type data multiframe calculated value corresponding with the multiframe build image, goes to the multiframe meter for calculating each build data
The step of arithmetic mean of instantaneous value of calculation value, if it is not, then going to the acquisition multiframe build image, and it will be obtained per build image described in frame
The step of taking the space coordinate of one to multiple group of physical characteristic point group.
In measuring method of the present invention, the arithmetic of the multiframe calculated value for calculating each build data is put down
Average, including:
The arithmetic mean of instantaneous value of multiframe calculated value of each build data is calculated using the measurement as the build data
Value;
Show the measured value.
In measuring method of the present invention, physical characteristic point group described in one to multiple group includes head feature point, left hand
Characteristic point, right hand characteristic point, left wrist characteristic point, right wrist characteristic point, left elbow characteristic point, right elbow characteristic point, left shoulder characteristic point, right shoulder
Characteristic point, middle shoulder characteristic point, backbone characteristic point, left stern characteristic point, right stern characteristic point, middle stern characteristic point, left knee characteristic point, right knee
Characteristic point, left ankle characteristic point, right ankle characteristic point, left foot characteristic point and right crus of diaphragm characteristic point.
In measuring method of the present invention, it is described calculate one to multiple group described in physical characteristic point group space coordinate it
Between space length to obtain one or more build data, including:
The first space length between the space coordinate of the left wrist characteristic point and the left elbow characteristic point is calculated to obtain
Upper left brachium, calculates the second space distance between the right wrist characteristic point and the space coordinate of the right elbow characteristic point to obtain
Upper right brachium;
The 3rd space length between the space coordinate of the left shoulder characteristic point and the right shoulder characteristic point is calculated to obtain
Shoulder breadth;
The 4th space length between the space coordinate of the left stern characteristic point and the left knee characteristic point is calculated to obtain
Left thigh is long, calculates the 5th space length between the right stern characteristic point and the space coordinate of the right knee characteristic point to obtain
Right thigh is long;
The 6th space length between the space coordinate of the i.e. described right stern characteristic point of the left stern characteristic point is calculated to obtain
Hip breadth;
The 7th space length between the space coordinate of the left ankle characteristic point and the left knee characteristic point is calculated to obtain
Left leg is long, calculates the 8th space length between the right ankle characteristic point and the space coordinate of the right knee characteristic point to obtain
Right leg is long;
The 9th space length between the space coordinate of the head feature point and the middle shoulder characteristic point is calculated, institute is calculated
State the tenth space length between the space coordinate of shoulder characteristic point and the backbone characteristic point, calculate the backbone characteristic point and
The 11st space length between the space coordinate of the middle stern characteristic point, calculates the left ankle characteristic point and the left foot feature
The 12nd space length between the space coordinate of point, calculates the space coordinate of the right ankle characteristic point and the right crus of diaphragm characteristic point
Between the 13rd space length;
According to the 9th space length, the tenth space length, the 11st space length, the 4th space
Distance, the 7th space length and the 12nd space length obtain height, or, according to the 9th space length,
Tenth space length, the 11st space length, the 5th space length, the 8th space length and described
13 space lengths obtain height.
It is described according to the 9th space length, the tenth space length, institute in measuring method of the present invention
State the 11st space length, the 4th space length, the 7th space length and the 12nd space length and obtain body
Height, or, according to the 9th space length, the tenth space length, the 11st space length, the 5th space
Distance, the 8th space length and the 13rd space length obtain height, including:
By the 9th space length, the tenth space length, the 11st space length, the 4th space away from
It is added from, the 7th space length and the 12nd space length to obtain the height;Or
By the 9th space length, the tenth space length, the 11st space length, the 5th space away from
It is added from, the 8th space length and the 13rd space length to obtain the height.
On the other hand there is provided a kind of measuring system of contactless build data, including:
Depth transducer, for obtaining multiframe build image, and will generate one to multiple group of build per build image described in frame
The space coordinate of feature point group;
Processing unit, for according to one or more build number of the spatial coordinates calculation of physical characteristic point group described in one to multiple group
According to, so that the multiframe calculated value of every idiotype data is obtained, and the arithmetic of the multiframe calculated value of each build data of calculating
Average value.
In measuring system of the present invention, in addition to:
Display, the measured value for showing the build data, wherein the measured value is each build data
Multiframe calculated value arithmetic mean of instantaneous value.
The measuring method and system of a kind of contactless build data disclosed above have the advantages that:Pass through depth
The measurement of the i.e. achievable contactless build data of the collocation of sensor and processor is spent, hardware cost is relatively low, and measuring speed is fast,
Measurement accuracy is high and measurement can be automatically finished, and measurement process is simple, requires low to operating personnel, and the posture to the measured will
Ask low.
Brief description of the drawings
A kind of flow chart of the measuring method for contactless build data that Fig. 1 provides for one embodiment of the invention;
The depth schematic diagram for the depth transducer that Fig. 2 provides for one embodiment of the invention;
The schematic diagram of the space coordinate for the one to multiple group of physical characteristic point group that Fig. 3 provides for one embodiment of the invention.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, not
For limiting the present invention.
The invention provides a kind of measuring method and system of contactless build data, it is intended that passing through depth
The measurement of contactless build data can be achieved in the collocation of sensor and processor, and hardware cost is relatively low, and measuring speed is fast, surveys
Accuracy of measurement is high and measurement can be automatically finished, and measurement process is simple, requires low to operating personnel, the posture requirement to the measured
It is low.
Referring to Fig. 1, a kind of flow of the measuring method for contactless build data that Fig. 1 provides for one embodiment of the invention
Figure, the measuring method includes step S1-S3:
S1, obtain multiframe build image, and by described in every frame build image obtain one to multiple group of physical characteristic point group sky
Between coordinate;Step S1 includes sub-step S11-S12:
S11, pass through depth transducer obtain multiframe described in build image;General, by depth transducer with per second 30
The speed of frame obtains the build image of human body, it may for example comprise the human body data cloud of absolute coordinate space.It is referring to Fig. 2, Fig. 2
The depth schematic diagram for the depth transducer that one embodiment of the invention is provided.Show the three-dimensional coordinate and body of rectangular coordinate system in space
Spatial coordinated information of the type image in three-dimensional coordinate.
S12, the space coordinate according to acquired every frame type image one to multiple group of physical characteristic point group of acquisition.Step
S12 includes sub-step S121-S122:
S121, the depth information passed through during the depth transducer is extracted per frame type image;
S122, foundation Exemplar-SVM models are learnt to the depth information and recognize to obtain one to multiple group of body
The space coordinate of type feature point group.For example, carrying out machine learning by Exemplar-SVM models and recognizing to get artis
Space coordinate, in machine learning field, support vector machines (Support Vector Machine), which are one, supervision
Learning model, commonly used to carry out pattern-recognition, classification and regression analysis.Carried referring to Fig. 3, Fig. 3 for one embodiment of the invention
The schematic diagram of the space coordinate of the one to multiple group of physical characteristic point group supplied, it is special that physical characteristic point group described in one to multiple group includes head
Levy a little 1, left hand characteristic point 9, right hand characteristic point 10, left wrist characteristic point 7, right wrist characteristic point 8, left elbow characteristic point 5, right elbow characteristic point
6th, left shoulder characteristic point 3, right shoulder characteristic point 4, middle shoulder characteristic point 2, backbone characteristic point 11, left stern characteristic point 13, right stern characteristic point 14,
Middle stern characteristic point 12, left knee characteristic point 15, right knee characteristic point 16, left ankle characteristic point 17, right ankle characteristic point 18, left foot characteristic point 19
And right crus of diaphragm characteristic point 20.Physical characteristic point can also include other artis or other characteristic points.
S2, according to one or more build data of the spatial coordinates calculation of physical characteristic point group described in one to multiple group, so as to obtain
Take every idiotype data multiframe calculated value corresponding with the multiframe build image;Step S2 includes sub-step S21-S23:
S21, the space length calculated between the space coordinate of physical characteristic point group described in one to multiple group are one to multiple to obtain
Idiotype data.The step S21 includes sub-step S211-S217:
The first space length between S211, the calculating left wrist characteristic point 7 and the left elbow characteristic point 5 space coordinate
To obtain upper left brachium, calculate second space between the right wrist characteristic point 8 and the space coordinate of the right elbow characteristic point 6 away from
From to obtain upper right brachium;That is the first space length is upper left brachium, and second space distance is upper right brachium, for example, left upper arm
A length of d, the space coordinate of left wrist characteristic point 7 is (x1,y1,z1), the space coordinate of left elbow characteristic point 5 is (x2,y2,z2), then
The 3rd space length between S212, the calculating left shoulder characteristic point 3 and the right shoulder characteristic point 4 space coordinate
To obtain shoulder breadth;
S213, calculate the 4th space between the space coordinate of the left stern characteristic point 13 and the left knee characteristic point 15 away from
From left thigh is long to obtain, the 5th sky between the right stern characteristic point 14 and the space coordinate of the right knee characteristic point 16 is calculated
Between distance it is long to obtain right thigh;
S214, calculate the 6th space between the space coordinate that the left stern characteristic point 13 is the right stern characteristic point 14 away from
From to obtain hip breadth;
S215, calculate the 7th space between the space coordinate of the left ankle characteristic point 17 and the left knee characteristic point 15 away from
From left leg is long to obtain, the 8th sky between the right ankle characteristic point 18 and the space coordinate of the right knee characteristic point 16 is calculated
Between distance it is long to obtain right leg;
S216, calculate the 9th space between the space coordinate of the head feature point 1 and the middle shoulder characteristic point 2 away from
From the tenth space length between the calculating middle shoulder characteristic point 2 and the space coordinate of the backbone characteristic point 11 calculates described
The 11st space length between the space coordinate of backbone characteristic point 11 and the middle stern characteristic point 12, calculates the left ankle feature
The 12nd space length between point 17 and the space coordinate of the left foot characteristic point 19, calculates the right ankle characteristic point 18 and institute
State the 13rd space length between the space coordinate of right crus of diaphragm characteristic point 20;
S217, according to the 9th space length, the tenth space length, the 11st space length, described
Four space lengths, the 7th space length and the 12nd space length obtain height, or, according to the 9th space
Distance, the tenth space length, the 11st space length, the 5th space length, the 8th space length and
13rd space length obtains height.In step S217, height can be calculated according to sub-step S2171, also can be according to sub-step
Rapid S2172 calculates height.
S2171, by the 9th space length, the tenth space length, the 11st space length, the described 4th
Space length, the 7th space length and the 12nd space length are added to obtain the height.
S2172, by the 9th space length, the tenth space length, the 11st space length, the described 5th
Space length, the 8th space length and the 13rd space length are added to obtain the height.
Height is calculated in the way of step S2171 or step S2172, the posture to the measured requires very low, is tested
Amount person can also go out what each was calculated by physical characteristic point no matter the posture such as station, seat or crouching can measure height
Span access location length.
Whether the build data of S22, judgement per frame exceed default threshold range, if so, then abandoning the build of present frame
Data, and step S1 is gone to, if it is not, then adding the build data of present frame to data pool, go to step S23.Threshold range
Setting purpose for reject depth transducer noise data, when build data are excessive or too small, be judged as abnormal
Data, the step is to reject abnormal data in these build data.
Whether S23, the frame number of the build data judged in the data pool exceed default threshold value, if so, then obtaining every
Idiotype data multiframe calculated value corresponding with the multiframe build image, goes to step S3, if it is not, then going to step S1.
S3, the arithmetic mean of instantaneous value for calculating each multiframe calculated value of the build data.Step S3 includes sub-step S31-
S32:
S31, the arithmetic mean of instantaneous value of the multiframe calculated value of each build data of calculating are to be used as the build data
Measured value;The purpose for calculating arithmetic mean of instantaneous value is the stability for ensureing measurement data, reduction limbs shake institute band in motion
The influence come.
S32, the measured value shown by display.
On the other hand there is provided a kind of measuring system of contactless build data, including depth transducer and processing unit.
Depth transducer, is controlled by processing unit, for obtaining multiframe build image, and will be per build image life described in frame
Into the space coordinate of one to multiple group of physical characteristic point group;
Processing unit, for according to one or more build number of the spatial coordinates calculation of physical characteristic point group described in one to multiple group
According to, so that the multiframe calculated value of every idiotype data is obtained, and the arithmetic of the multiframe calculated value of each build data of calculating
Average value.It is preferred that, by storing a plurality of instruction in the storage device in processing unit, the instruction is filled by the processing
Put and load and run.Wherein, processing unit instruction is realized as follows:
It is described to obtain one to multiple group of physical characteristic point group according to acquisition multiframe build image, and by build image described in every frame
Space coordinate, including:
Build image described in multiframe is obtained by depth transducer;
The space coordinate of one to multiple group of physical characteristic point group is obtained according to acquired every frame type image.
In measuring method of the present invention, every frame type image acquired in the foundation obtains one to multiple group of build
The space coordinate of feature point group, including:
Extracted by the depth transducer per the depth information in frame type image;
The depth information is learnt according to Exemplar-SVM models and recognized special to obtain one to multiple group of build
Levy the space coordinate of a group.
In measuring method of the present invention, the space coordinate meter according to physical characteristic point group described in one to multiple group
One or more build data is calculated, so as to obtain every idiotype data multiframe calculated value corresponding with the multiframe build image, is wrapped
Include:
The space length between the space coordinate of physical characteristic point group described in one to multiple group is calculated to obtain one to multiple individual
Type data;
Judge whether the build data per frame exceed default threshold range, if so, the build data of present frame are then abandoned,
And go to it is described acquisition multiframe build image, and by described in every frame build image obtain one to multiple group of physical characteristic point group space
The step of coordinate, if it is not, then adding the build data of present frame to data pool;
Judge whether the frame number of the build data in the data pool exceedes default threshold value, if so, then obtaining per individual
Type data multiframe calculated value corresponding with the multiframe build image, goes to the multiframe meter for calculating each build data
The step of arithmetic mean of instantaneous value of calculation value, if it is not, then going to the acquisition multiframe build image, and it will be obtained per build image described in frame
The step of taking the space coordinate of one to multiple group of physical characteristic point group.
In measuring method of the present invention, the arithmetic of the multiframe calculated value for calculating each build data is put down
Average, including:
The arithmetic mean of instantaneous value of multiframe calculated value of each build data is calculated using the measurement as the build data
Value;
Show the measured value.
In measuring method of the present invention, physical characteristic point group described in one to multiple group includes head feature point 1, left hand
Characteristic point 9, right hand characteristic point 10, left wrist characteristic point 7, right wrist characteristic point 8, left elbow characteristic point 5, right elbow characteristic point 6, left shoulder feature
Point 3, right shoulder characteristic point 4, middle shoulder characteristic point 2, backbone characteristic point 11, left stern characteristic point 13, right stern characteristic point 14, middle stern characteristic point
12nd, left knee characteristic point 15, right knee characteristic point 16, left ankle characteristic point 17, right ankle characteristic point 18, left foot characteristic point 19 and right crus of diaphragm feature
Point 20.
In measuring method of the present invention, it is described calculate one to multiple group described in physical characteristic point group space coordinate it
Between space length to obtain one or more build data, including:
The first space length between the space coordinate of the left wrist characteristic point 7 and the left elbow characteristic point 5 is calculated to obtain
Take upper left brachium, calculate the second space distance between the right wrist characteristic point 8 and the space coordinate of the right elbow characteristic point 6 with
Obtain upper right brachium;
The 3rd space length between the space coordinate of the left shoulder characteristic point 3 and the right shoulder characteristic point 4 is calculated to obtain
Take shoulder breadth;
Calculate the 4th space length between the space coordinate of the left stern characteristic point 13 and the left knee characteristic point 15 with
Obtain that left thigh is long, calculate the 5th space between the space coordinate of the right stern characteristic point 14 and the right knee characteristic point 16 away from
It is long to obtain right thigh;
Calculate the 6th space length between the space coordinate of the i.e. described right stern characteristic point 14 of the left stern characteristic point 13 with
Obtain hip breadth;
Calculate the 7th space length between the space coordinate of the left ankle characteristic point 17 and the left knee characteristic point 15 with
Obtain that left leg is long, calculate the 8th space between the space coordinate of the right ankle characteristic point 18 and the right knee characteristic point 16 away from
It is long to obtain right leg;
The 9th space length between the space coordinate of the head feature point 1 and the middle shoulder characteristic point 2 is calculated, is calculated
The tenth space length between the space coordinate of the middle shoulder characteristic point 2 and the backbone characteristic point 11, calculates the backbone special
Levy a little 11 and the middle stern characteristic point 12 space coordinate between the 11st space length, calculate the left ankle characteristic point 17 and
The 12nd space length between the space coordinate of the left foot characteristic point 19, calculates the right ankle characteristic point 18 and the right crus of diaphragm
The 13rd space length between the space coordinate of characteristic point 20;
According to the 9th space length, the tenth space length, the 11st space length, the 4th space
Distance, the 7th space length and the 12nd space length obtain height, or, according to the 9th space length,
Tenth space length, the 11st space length, the 5th space length, the 8th space length and described
13 space lengths obtain height.
It is described according to the 9th space length, the tenth space length, institute in measuring method of the present invention
State the 11st space length, the 4th space length, the 7th space length and the 12nd space length and obtain body
Height, or, according to the 9th space length, the tenth space length, the 11st space length, the 5th space
Distance, the 8th space length and the 13rd space length obtain height, including:
By the 9th space length, the tenth space length, the 11st space length, the 4th space away from
It is added from, the 7th space length and the 12nd space length to obtain the height;Or
By the 9th space length, the tenth space length, the 11st space length, the 5th space away from
It is added from, the 8th space length and the 13rd space length to obtain the height.
It is preferred that.The measuring system also includes display, and display is controlled by the processing unit, described for showing
The measured value of build data, wherein the measured value is the arithmetic mean of instantaneous value of the multiframe calculated value of each build data.
Embodiments of the invention are described above in conjunction with accompanying drawing, but the invention is not limited in above-mentioned specific
Embodiment, above-mentioned embodiment is only schematical, rather than restricted, one of ordinary skill in the art
Under the enlightenment of the present invention, in the case of present inventive concept and scope of the claimed protection is not departed from, it can also make a lot
Form, these are belonged within the protection of the present invention.
Claims (10)
1. a kind of measuring method of contactless build data, it is characterised in that including:
Obtain multiframe build image, and by described in every frame build image obtain one to multiple group of physical characteristic point group space coordinate;
According to one or more build data of the spatial coordinates calculation of physical characteristic point group described in one to multiple group, so as to obtain every individual
Type data multiframe calculated value corresponding with the multiframe build image;
Calculate the arithmetic mean of instantaneous value of the multiframe calculated value of each build data.
2. measuring method according to claim 1, it is characterised in that described according to acquisition multiframe build image, and will be every
Build image described in frame obtains the space coordinate of one to multiple group of physical characteristic point group, including:
Build image described in multiframe is obtained by depth transducer;
The space coordinate of one to multiple group of physical characteristic point group is obtained according to acquired every frame type image.
3. measuring method according to claim 2, it is characterised in that every frame type image acquired in the foundation is obtained
The space coordinate of one to multiple group of physical characteristic point group, including:
Extracted by the depth transducer per the depth information in frame type image;
The depth information is learnt and recognizes to obtain one to multiple group of physical characteristic point according to Exemplar-SVM models
The space coordinate of group.
4. measuring method according to claim 1, it is characterised in that described according to physical characteristic point group described in one to multiple group
Spatial coordinates calculation one or more build data, so as to obtain every idiotype data and the multiframe build image is corresponding more
Frame calculated value, including:
The space length between the space coordinate of physical characteristic point group described in one to multiple group is calculated to obtain one or more build number
According to;
Judge whether the build data per frame exceed default threshold range, if so, then abandoning the build data of present frame, and turn
To it is described acquisition multiframe build image, and by described in every frame build image obtain one to multiple group of physical characteristic point group space coordinate
The step of, if it is not, then the build data of present frame are added to data pool;
Judge whether the frame number of the build data in the data pool exceedes default threshold value, if so, then obtaining per idiotype number
According to multiframe calculated value corresponding with the multiframe build image, the multiframe calculated value for calculating each build data is gone to
Arithmetic mean of instantaneous value the step of, if it is not, then going to the acquisition multiframe build image, and one will be obtained per build image described in frame
To multigroup physical characteristic point group space coordinate the step of.
5. measuring method according to claim 4, it is characterised in that the multiframe meter of each build data of the calculating
The arithmetic mean of instantaneous value of calculation value, including:
The arithmetic mean of instantaneous value of multiframe calculated value of each build data is calculated using the measured value as the build data;
Show the measured value.
6. measuring method according to claim 4, it is characterised in that physical characteristic point group described in one to multiple group includes head
Characteristic point, left hand characteristic point, right hand characteristic point, left wrist characteristic point, right wrist characteristic point, left elbow characteristic point, right elbow characteristic point, left shoulder
Characteristic point, right shoulder characteristic point, middle shoulder characteristic point, backbone characteristic point, left stern characteristic point, right stern characteristic point, middle stern characteristic point, left knee
Characteristic point, right knee characteristic point, left ankle characteristic point, right ankle characteristic point, left foot characteristic point and right crus of diaphragm characteristic point.
7. measuring method according to claim 6, it is characterised in that physical characteristic point group described in one to multiple group of the calculating
Space coordinate between space length to obtain one or more build data, including:
The first space length between the space coordinate of the left wrist characteristic point and the left elbow characteristic point is calculated to obtain upper left
Brachium, calculates the second space distance between the right wrist characteristic point and the space coordinate of the right elbow characteristic point to obtain upper right
Brachium;
The 3rd space length between the space coordinate of the left shoulder characteristic point and the right shoulder characteristic point is calculated to obtain shoulder breadth;
It is left big to obtain to calculate the 4th space length between the space coordinate of the left stern characteristic point and the left knee characteristic point
Leg is long, and it is right big to obtain to calculate the 5th space length between the right stern characteristic point and the space coordinate of the right knee characteristic point
Leg is long;
The 6th space length between the space coordinate of the i.e. described right stern characteristic point of the left stern characteristic point is calculated to obtain hip breadth;
It is left small to obtain to calculate the 7th space length between the space coordinate of the left ankle characteristic point and the left knee characteristic point
Leg is long, and it is right small to obtain to calculate the 8th space length between the right ankle characteristic point and the space coordinate of the right knee characteristic point
Leg is long;
The 9th space length between the space coordinate of the head feature point and the middle shoulder characteristic point is calculated, during calculating is described
The tenth space length between the space coordinate of shoulder characteristic point and the backbone characteristic point, calculates the backbone characteristic point and described
The 11st space length between the space coordinate of middle stern characteristic point, the calculating left ankle characteristic point and the left foot characteristic point
The 12nd space length between space coordinate, is calculated between the right ankle characteristic point and the space coordinate of the right crus of diaphragm characteristic point
The 13rd space length;
According to the 9th space length, the tenth space length, the 11st space length, the 4th space away from
Height is obtained from, the 7th space length and the 12nd space length, or, according to the 9th space length, institute
State the tenth space length, the 11st space length, the 5th space length, the 8th space length and the described tenth
Three space lengths obtain height.
8. measuring method according to claim 7, it is characterised in that it is described according to the 9th space length, described
Ten space lengths, the 11st space length, the 4th space length, the 7th space length and the 12nd sky
Between distance obtain height, or, according to the 9th space length, the tenth space length, the 11st space length,
5th space length, the 8th space length and the 13rd space length obtain height, including:
By the 9th space length, the tenth space length, the 11st space length, the 4th space length,
7th space length and the 12nd space length are added to obtain the height;Or
By the 9th space length, the tenth space length, the 11st space length, the 5th space length,
8th space length and the 13rd space length are added to obtain the height.
9. a kind of measuring system of contactless build data, it is characterised in that including:
Depth transducer, for obtaining multiframe build image, and will generate one to multiple group of physical characteristic per build image described in frame
The space coordinate of point group;
Processing unit, for according to one or more build data of the spatial coordinates calculation of physical characteristic point group described in one to multiple group,
So as to obtain the multiframe calculated value of every idiotype data, and calculate the arithmetic average of the multiframe calculated value of each build data
Value.
10. measuring system according to claim 8, it is characterised in that also include:
Display, the measured value for showing the build data, wherein the measured value is many of each build data
The arithmetic mean of instantaneous value of frame calculated value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710331941.7A CN107192342A (en) | 2017-05-11 | 2017-05-11 | A kind of measuring method and system of contactless build data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710331941.7A CN107192342A (en) | 2017-05-11 | 2017-05-11 | A kind of measuring method and system of contactless build data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107192342A true CN107192342A (en) | 2017-09-22 |
Family
ID=59872529
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710331941.7A Pending CN107192342A (en) | 2017-05-11 | 2017-05-11 | A kind of measuring method and system of contactless build data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107192342A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115633956A (en) * | 2022-11-08 | 2023-01-24 | 华南理工大学 | Method, system, device and storage medium for automatically measuring height of baby |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110249865A1 (en) * | 2010-04-08 | 2011-10-13 | Samsung Electronics Co., Ltd. | Apparatus, method and computer-readable medium providing marker-less motion capture of human |
CN102657532A (en) * | 2012-05-04 | 2012-09-12 | 深圳泰山在线科技有限公司 | Height measuring method and device based on body posture identification |
CN102708372A (en) * | 2012-02-29 | 2012-10-03 | 北京无线电计量测试研究所 | Automatic detection and identification method for hidden articles |
CN103310191A (en) * | 2013-05-30 | 2013-09-18 | 上海交通大学 | Human body action identification method for motion information imaging |
US20130343657A1 (en) * | 2010-06-15 | 2013-12-26 | Apple Inc. | Object detection metadata |
CN105447466A (en) * | 2015-12-01 | 2016-03-30 | 深圳市图灵机器人有限公司 | Kinect sensor based identity comprehensive identification method |
CN105816182A (en) * | 2016-03-24 | 2016-08-03 | 西安交通大学 | Method for measuring cervical vertebra motion degree on basis of Kinect sensor |
CN106022213A (en) * | 2016-05-04 | 2016-10-12 | 北方工业大学 | Human body motion recognition method based on three-dimensional bone information |
-
2017
- 2017-05-11 CN CN201710331941.7A patent/CN107192342A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110249865A1 (en) * | 2010-04-08 | 2011-10-13 | Samsung Electronics Co., Ltd. | Apparatus, method and computer-readable medium providing marker-less motion capture of human |
US20130343657A1 (en) * | 2010-06-15 | 2013-12-26 | Apple Inc. | Object detection metadata |
CN102708372A (en) * | 2012-02-29 | 2012-10-03 | 北京无线电计量测试研究所 | Automatic detection and identification method for hidden articles |
CN102657532A (en) * | 2012-05-04 | 2012-09-12 | 深圳泰山在线科技有限公司 | Height measuring method and device based on body posture identification |
CN103310191A (en) * | 2013-05-30 | 2013-09-18 | 上海交通大学 | Human body action identification method for motion information imaging |
CN105447466A (en) * | 2015-12-01 | 2016-03-30 | 深圳市图灵机器人有限公司 | Kinect sensor based identity comprehensive identification method |
CN105816182A (en) * | 2016-03-24 | 2016-08-03 | 西安交通大学 | Method for measuring cervical vertebra motion degree on basis of Kinect sensor |
CN106022213A (en) * | 2016-05-04 | 2016-10-12 | 北方工业大学 | Human body motion recognition method based on three-dimensional bone information |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115633956A (en) * | 2022-11-08 | 2023-01-24 | 华南理工大学 | Method, system, device and storage medium for automatically measuring height of baby |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103637807B (en) | Method for sensing and monitoring human body three-dimensional attitude and behavior state | |
CN106821391A (en) | Body gait acquisition analysis system and method based on inertial sensor information fusion | |
US10126108B2 (en) | Apparatus and method for classifying orientation of a body of a mammal | |
CN108245164A (en) | A kind of wearable inertia device body gait information collection computational methods | |
CN108447225A (en) | A kind of tumble detection method for human body and device | |
CN111709277A (en) | Human body tumbling detection method and device, computer equipment and storage medium | |
WO2017004403A1 (en) | Biomechanical information determination | |
Bonnet et al. | Fast determination of the planar body segment inertial parameters using affordable sensors | |
US20200297243A1 (en) | System for estimating body motion of person or the like | |
CN106952335A (en) | Set up the method and its system in manikin storehouse | |
CN105771224B (en) | A kind of locomotion evaluation system based on multisensor | |
US20220222975A1 (en) | Motion recognition method, non-transitory computer-readable recording medium and information processing apparatus | |
Harada et al. | Pressure distribution image based human motion tracking system using skeleton and surface integration model | |
CN107192342A (en) | A kind of measuring method and system of contactless build data | |
CN116740618A (en) | Motion video action evaluation method, system, computer equipment and medium | |
CN208876547U (en) | A kind of gait analysis device based on IMU inertial sensor | |
US11497962B2 (en) | System and method for human motion detection and tracking | |
KR20210075451A (en) | Electronic Device, Method, and System for Diagnosing Musculoskeletal Symptoms | |
JP7172733B2 (en) | Human Posture Estimation Device | |
JP7335199B2 (en) | Analysis device, analysis method, program, and calibration method | |
CN115568823A (en) | Method, system and device for evaluating human body balance ability | |
Liu et al. | Preimpact fall detection for elderly based on fractional domain | |
CN105606058B (en) | A kind of according to pressing depth test method, device and the relevant device of cardiopulmonary resuscitation | |
CN111724901A (en) | Method, system and device for predicting structure body parameters based on vision and storage medium | |
CN105575239B (en) | A kind of reduction of the fracture training pattern angle detection device and its method |
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: 20170922 |