CN110188688A - Postural assessment method and device - Google Patents
Postural assessment method and device Download PDFInfo
- Publication number
- CN110188688A CN110188688A CN201910463521.3A CN201910463521A CN110188688A CN 110188688 A CN110188688 A CN 110188688A CN 201910463521 A CN201910463521 A CN 201910463521A CN 110188688 A CN110188688 A CN 110188688A
- Authority
- CN
- China
- Prior art keywords
- information
- matrix
- coordinate
- tierce
- positions
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/60—Rotation of a whole image or part thereof
- G06T3/604—Rotation of a whole image or part thereof using a CORDIC [COordinate Rotation Digital Compute] device
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
Abstract
The embodiment of the present invention provides a kind of postural assessment method and device, this method comprises: obtaining the second information of the prime information of the first object and the first object in the second image in the first image, prime information includes the coordinate at least two positions of the first object, and second information includes the coordinate at least two positions of the second object;Processing and/or rotation processing are zoomed in and out to the coordinate in prime information, obtain tierce information, the size of object indicated by tierce information is identical as the size of the second object, and at least two positions of object indicated by tierce information and at least two positions of the second object are corresponding;According to tierce information and the second information, the posture matching degree of the first object and the second object is determined.For improving the accuracy of determining posture matching degree.
Description
Technical field
The present embodiments relate to field of image processing more particularly to a kind of postural assessment method and devices.
Background technique
Action estimation method can be used for estimating the similarity of the posture of personage in two width pictures.
Currently, action estimation method includes: the coordinates matrix for obtaining the human body key point of the personage in two images,
According to the coordinates matrix of the human body key point in two images, the Euclidean on corresponding position between the coordinate of human body key point is determined
The Euclidean distance is determined the similarity of personage's posture in two images by distance.
In above process, personage's size difference is larger in two images, but when posture is similar, by the Euclidean away from
When similarity from the personage's posture being determined as in two images, the similarity of obtained posture is lower, and then leads to posture
The accuracy of similarity is poor.
Summary of the invention
The embodiment of the present invention provides a kind of postural assessment method and device, for improving the accurate of determining posture matching degree
Property.
In a first aspect, the embodiment of the present invention provides a kind of postural assessment method, comprising:
Obtain the second letter of the first object in the prime information and the second image of the first object in the first image
Breath, the prime information includes the coordinate at least two positions of first object, and the second information includes
The coordinate at least two positions of second object;
Processing and/or rotation processing are zoomed in and out to the coordinate in the prime information, obtain tierce information,
The size of object indicated by the tierce information is identical as the size of second object, the tierce information institute
At least two positions of the object of instruction are corresponding at least two positions of second object;
According to the tierce information and the second information, first object and second object are determined
Posture matching degree.
In a kind of possible embodiment, processing and/or rotation are zoomed in and out to the coordinate in the prime information
Turn processing, obtain tierce information, comprising:
According to the prime information and the second information, determine that adjusting parameter, the adjusting parameter include
Zooming parameter and/or rotation angle;
According to the prime information and the adjusting parameter, the tierce information is determined.
In alternatively possible embodiment, according to the prime information and the second information, determine
Adjusting parameter, comprising:
Obtain corresponding first matrix of the prime information, first matrix include first object at least
The coordinate of the coordinate at two positions, at least two positions of first object is stored in first matrix according to preset rules
In;
Obtain corresponding second matrix of the second information, second matrix include second object at least
The coordinate of the coordinate at two positions, at least two positions of second object is stored in described second according to the preset rules
In matrix;
According to the Pu Shi distance between first matrix and second matrix, the adjusting parameter is determined.
In alternatively possible embodiment, according to the Pu Shi between first matrix and second matrix away from
From determining the adjusting parameter, comprising:
Matrix manipulation operations are executed, the matrix manipulation operations include: to obtain according to initial parameter and first matrix
Third matrix;
Parameter updating operation is executed, the parameter updating operation includes according to the third matrix and second matrix
Pu Shi distance updates initial parameter;
The matrix manipulation operations and the parameter updating operation are repeated, until the third matrix and described second
The Pu Shi distance of matrix is less than or equal to distance threshold, or executes the number of the matrix manipulation operations more than or equal to pre-
If when number, the initial parameter is determined as the adjusting parameter.
In alternatively possible embodiment, according to the prime information and the adjusting parameter, determine described in
Tierce information, comprising:
By the adjusting parameter multiplied by the coordinate in the prime information, the tierce information is obtained.
It is described according to the tierce information and the second information in alternatively possible embodiment,
Determine the posture matching degree of first object and second object, comprising:
Obtain corresponding second matrix of the second information;
Obtain corresponding 4th matrix of the tierce information;
According to second matrix and the 4th matrix, the posture of first object and second object is determined
With degree.
It is described according to second matrix and the 4th matrix in alternatively possible embodiment, determine described in
The posture matching degree of first object and second object, comprising:
Obtain the Euclidean distance of the coordinate of corresponding position in second matrix and the 4th matrix;
According to the coordinate Euclidean distance of the corresponding position, the posture of first object and second object is determined
With degree.
In alternatively possible embodiment, according to the Euclidean distance of the coordinate of the corresponding position, described is determined
The posture matching degree of an object and second object, comprising:
According to the Euclidean distance of respective coordinates in second matrix and the 4th matrix, the corresponding coordinate is determined
Euclidean distance average value;
By the absolute value of the difference of the preset threshold and the average value, it is determined as first object and second pair described
The posture matching degree of elephant.
Second aspect, the embodiment of the present invention provide a kind of postural assessment device, comprising: obtain module, processing module and really
Cover half block, wherein
The acquisition module is used for, obtain the first image in the first object prime information and the second image in first
The second information of object, the prime information includes the coordinate at least two positions of first object, described
Second information includes the coordinate at least two positions of second object;
The processing module is used for, and zooms in and out processing and/or rotation processing to the coordinate in the prime information,
Tierce information is obtained, the size of object indicated by the tierce information is identical as the size of second object,
At least two positions of object indicated by the tierce information are corresponding at least two positions of second object;
The determining module is used for, and according to the tierce information and the second information, determines described first
The posture matching degree of object and second object.
In a kind of possible embodiment, the processing module is specifically used for:
According to the prime information and the second information, determine that adjusting parameter, the adjusting parameter include
Zooming parameter and/or rotation angle;
According to the prime information and the adjusting parameter, the tierce information is determined.
In alternatively possible embodiment, the processing module is specifically used for:
Obtain corresponding first matrix of the prime information, first matrix include first object at least
The coordinate of the coordinate at two positions, at least two positions of first object is stored in first matrix according to preset rules
In;
Obtain corresponding second matrix of the second information, second matrix include second object at least
The coordinate of the coordinate at two positions, at least two positions of second object is stored in described second according to the preset rules
In matrix;
According to the Pu Shi distance between first matrix and second matrix, the adjusting parameter is determined.
In alternatively possible embodiment, the processing module is specifically used for:
Matrix manipulation operations are executed, the matrix manipulation operations include: to obtain according to initial parameter and first matrix
Third matrix;
Parameter updating operation is executed, the parameter updating operation includes according to the third matrix and second matrix
Pu Shi distance updates initial parameter;
The matrix manipulation operations and the parameter updating operation are repeated, until the third matrix and described second
The Pu Shi distance of matrix is less than or equal to distance threshold, or executes the number of the matrix manipulation operations more than or equal to pre-
If when number, the initial parameter is determined as the adjusting parameter.
In alternatively possible embodiment, the determining module is specifically used for:
By the adjusting parameter multiplied by the coordinate in the prime information, the tierce information is obtained.
In alternatively possible embodiment, the determining module is specifically used for:
Obtain corresponding second matrix of the second information;
Obtain corresponding 4th matrix of the tierce information;
According to second matrix and the 4th matrix, the posture of first object and second object is determined
With degree.
In alternatively possible embodiment, the determining module is specifically used for:
Obtain the Euclidean distance of the coordinate of corresponding position in second matrix and the 4th matrix;
According to the Euclidean distance of the coordinate of the corresponding position, the posture of first object and second object is determined
Matching degree.
In alternatively possible embodiment, the determining module is specifically used for:
According to the Euclidean distance of the coordinate of the corresponding position, Euclidean distance average value is determined;
By the absolute value of the difference of the preset threshold and the Euclidean distance average value, it is determined as first object and institute
State the posture matching degree of the second object.
The third aspect, the embodiment of the present invention provide a kind of postural assessment device, comprising: processor, the processor with deposit
Reservoir coupling;
The memory is used for, and stores computer program;
The processor is used for, and executes the computer program stored in the memory, so that the postural assessment fills
It sets and executes the above-mentioned described in any item postural assessment methods of first aspect.
Fourth aspect, the embodiment of the present invention provide a kind of readable storage medium storing program for executing, including program or instruction, when described program or
When instruction is run on computers, the postural assessment method as described in above-mentioned first aspect any one is performed.
In postural assessment method and device provided in an embodiment of the present invention, the method obtains the first object in the first image
Prime information and the second image in the first object second information, prime information include the first object extremely
The coordinate at few two positions, second information includes the coordinate at least two positions of the second object, to prime information
In coordinate zoom in and out processing and/or rotation processing, obtain tierce information, object indicated by tierce information
Size is identical as the size of the second object, and at least two positions of object indicated by tierce information and the second object are extremely
Few two positions are corresponding, according to tierce information and second information, determine the posture of the first object and the second object
With degree.In above process, processing and/or rotation processing are zoomed in and out to the coordinate in prime information, obtains third appearance
Gesture information determines the posture matching degree of the first object and the second object according to tierce information and second information, can be with
Subject sizes differ greatly in two images, but when posture is similar, obtain higher posture matching degree, so that determining
The accuracy of posture matching degree out is higher.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the application scenario diagram of postural assessment method provided in an embodiment of the present invention;
Fig. 2 is the flow diagram one of postural assessment method provided in an embodiment of the present invention;
Fig. 3 is the flow diagram two of postural assessment method provided in an embodiment of the present invention;
Fig. 4 is the structural schematic diagram for the postural assessment device that present example provides;
Fig. 5 is the hardware structural diagram of postural assessment device provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Fig. 1 is the application scenario diagram of postural assessment method provided in an embodiment of the present invention.Referring to Figure 1, the first image 11
In include the first object 110, include the second object 120 in the second image 12, wherein the first object 110 and the second object 120 can
With identical or different posture.In practical applications, when needing the posture to the first object 110 and the second object 120
When matching degree is assessed, the first object 110 can be zoomed in and out, rotation processing, obtain the first object 130, and by first
The posture matching degree of object 130 and the second object 120 is determined as the matching of the posture of the first object 110 and the second object 120
Degree.
In above process, the first object 110 is zoomed in and out, rotation processing, the first obtained object 130 and second pair
As 120 size is identical, and the body part of the first object 130 is corresponding with 120 body part of the second object (for example, first
The head of object 130 is in the extreme higher position of the first image 11, then highest order of the head of the second object 120 in the second image 12
It sets, the left hand of the first object 130 is in the left-most position of the first image 11, then the left hand of the second object 120 is in the second image 12
Left-most position), therefore, by the posture matching degree of the first object 130 and the second object 120, be determined as 110 He of the first object
The accuracy of the posture matching degree got can be improved in the posture matching degree of second object 120.
It should be noted that postural assessment method shown in the application can be applied in electronic equipment, for example, dancing
Machine, during user dances, dancing machine can give a mark to the dancing posture of user.
In practical applications, during user dances, the first image of user is obtained, the first image includes user's
Dancing posture image, dancing posture image show the dancing posture of user, and the second image can be preset standard picture in dancing machine, standard
Image shows standard dancing posture, and the dancing machine can determine the dancing appearance of user by postural assessment method provided by the present application
The standard of marking can be improved to give a mark according to dancing posture of the matching degree to user in the matching degree of gesture and standard dancing posture
True property.
In the following, technical solution shown in the application is described in detail by specific embodiment.Under it should be noted that
The several specific embodiments in face can be combined with each other, and for the same or similar content, no longer carry out weight in various embodiments
Multiple explanation.
Fig. 2 is the flow diagram one of postural assessment method provided in an embodiment of the present invention.Refer to Fig. 2, postural assessment
Method includes:
S201: the second appearance of the prime information of the first object and the first object in the second image in the first image is obtained
Gesture information, prime information include the coordinate at least two positions of the first object, and second information includes the second object
At least two positions coordinate.
Optionally, the executing subject of the embodiment of the present invention can be postural assessment device.Optionally, the postural assessment dress
Setting can be realized by the combination of software and/or hardware.
Optionally, the first object and the second object can be the image of the same person or two different people, the figure
Personage as in can have identical or different gestures.
It should be noted that at least two positions of the first object and at least two positions of the second object can be head
At least two positions in portion, shoulder, left arm, right arm, trunk, left leg and right leg.
It optionally, on each position may include at least one key point.For example, head may include left eye eyeball, the right side
The key points such as eyes, nose, left arm include the key points such as left hand, left elbow.
In practical applications, the coordinate at least two positions is on each position of the first object in prime information
Coordinate of the key point in the first image, the coordinate at least two positions is each position of the second object in second information
On coordinate of the key point in the second image.
Optionally, the coordinate can be two-dimensional coordinate, or three-dimensional coordinate.
Optionally, the size of the first image and second graph can it is identical, can also be different.
It should be noted that needing in the size difference of the first image and second graph to the first image and/or second
Figure is cut out processing, so that the first image is identical with the size of second graph.
It should be noted that can be closed by human body critical point detection network to the first object in the first image
Key point detection processing obtains coordinate of the key point in the first image on each position of the first object, in the second image
The second object carry out critical point detection processing, obtain seat of the key point in the second image on each position of the second object
Mark.
Optionally, the prime information and the second information can also include that the mark at each position is believed
Breath.
For example, prime information can be expressed as
It should be noted that the element in first row is used to identify the different portions of the first object in prime information
Key point on position, the element in secondary series can indicate the corresponding coordinate of the key point of the first object,
For example, 1He1 can identify the key point-left eye eyeball on the head of the first object, 1He2 can be used for identifying first pair
The key point on the head of elephant-right eye eyeball, (a1,b1) it is coordinate of the left eye eyeball of the first object in the first image, (a1′,b1′)
For coordinate of the right eye eyeball in the first image of the first object
For example, second information can be expressed as
It should be noted that the element in first row is used to identify the different portions of the second object in second information
Key point on position, the element in secondary series can indicate the corresponding coordinate of the key point of the second object.
For example, 2He1 can identify the key point-left eye eyeball on the head of the second object, 2He2 can be used for identifying second pair
The key point on the head of elephant-right eye eyeball, (c1,d1) it is coordinate of the left eye eyeball of the second object in the second image, (c1′,d1′)
For coordinate of the right eye eyeball in the second image of the second object.
S202: zooming in and out processing and/or rotation processing to the coordinate in prime information, obtains tierce letter
The size of breath, object indicated by tierce information is identical as the size of the second object, indicated by tierce information pair
At least two positions of elephant and at least two positions of the second object are corresponding.
Optionally, can according to the first matrix of prime acquisition of information, according to the second matrix of second acquisition of information,
According to the first matrix and the second matrix, adjusting parameter is determined, by adjusting parameter multiplied by the first matrix, prime is believed with realizing
The coordinate of breath zooms in and out processing and/or rotation processing.
Optionally, according to the mark of coordinate and key point corresponding with coordinate after scaling processing and/or rotation processing
Know, obtains tierce information.
For example, tierce information can be expressed as
It should be noted that the element in first row contracts to the first object for identifying in tierce information
Put the different portions of the object (referred to as third object, the first object 130 as shown in figure 1) obtained after processing and/or rotation processing
Key point on position, the element in secondary series can indicate the corresponding coordinate of the key point of third object,
For example, 3He1 can identify the key point-left eye eyeball on the head of third object, 3Ah1 can be used for identifying third pair
Key point-left hand on the arm of elephant, (A1,B1) it is coordinate of the left eye eyeball of third object in the first image, (A2,B2) be
Coordinate of the left hand of third object in the first image.
S203: according to tierce information and second information, the posture matching of the first object and the second object is determined
Degree.
Optionally, can according to the 4th matrix of tierce acquisition of information, according to the second matrix of second acquisition of information,
According to the second matrix and the 4th matrix, the posture matching degree of the first object and the second object is determined.
It should be noted that the 4th matrix is to be determined according to the coordinate in tierce information, second square
Battle array is to be determined according to the coordinate in second information.
Optionally, after the Euclidean distance of the coordinate of the corresponding position of available second matrix and the 4th matrix, and root
According to the difference of the sum of preset threshold and the Euclidean distance, the posture matching degree of the first object and the second object is determined.
In postural assessment method provided in an embodiment of the present invention, the prime letter of the first object in the first image is obtained
The second information of first object in breath and the second image, prime information includes at least two positions of the first object
Coordinate, second information include the coordinate at least two positions of the second object, are carried out to the coordinate in prime information
Scaling processing and/or rotation processing, obtain tierce information, the size of object indicated by tierce information with second pair
The size of elephant is identical, at least two positions of object indicated by tierce information and at least two positions pair of the second object
It answers, according to tierce information and second information, determines the posture matching degree of the first object and the second object.In above-mentioned mistake
Cheng Zhong zooms in and out processing and/or rotation processing to the coordinate in prime information, obtains tierce information, according to
Three pose informations and second information determine the posture matching degree of the first object and the second object, can be in two images
Subject sizes differ greatly, but when posture is similar, obtain higher posture matching degree, so that the posture matching determined
The accuracy of degree is higher.
On the basis of any one above-mentioned embodiment, in the following, in conjunction with Fig. 3, to a kind of appearance provided in an embodiment of the present invention
Gesture appraisal procedure is described in further detail, specifically, referring to Fig. 3.
Fig. 3 is the flow diagram two of postural assessment method provided in an embodiment of the present invention.Refer to Fig. 3, postural assessment
Method includes:
S301: the second appearance of the prime information of the first object and the first object in the second image in the first image is obtained
Gesture information, prime information include the coordinate at least two positions of the first object, and second information includes the second object
At least two positions coordinate.
It should be noted that the implementation procedure of S301 is identical as the implementation procedure of S201, herein, holding for S301 is repeated no more
Row method.
S302: corresponding first matrix of prime information is obtained, the first matrix includes at least two of the first object
The coordinate of position, the coordinate at least two positions of the first object are stored in the first matrix according to preset rules.
Optionally, the seat of the key point at least two positions of the first object can be obtained from prime information
Mark, and the coordinate of the key point at least two positions of the first object is stored in the first matrix R according to preset rules.
Optionally, preset rules can for according to above and below position, left and right sequence, by the coordinate of the key point at corresponding position
It is stored in the first matrix R.
For example, at least two positions of the first object are head, shoulder, head includes left eye eyeball, right eye eyeball, nose key
Point, shoulder include left shoulder, right shoulder key point, then the first matrix R can beWherein, first
A elementFor the left eye eyeball key point coordinate of the first object, second elementFor the right eye eyeball key point of the first object
Coordinate, third elementFor the nose key point coordinate of the first object, the 4th elementFor the left shoulder of the first object
Key point coordinate, the 5th elementFor the right shoulder key point coordinate of the first object.
S303: corresponding second matrix of second information is obtained, the second matrix includes at least two of the second object
The coordinate of position, the coordinate at least two positions of the second object are stored in the second matrix according to preset rules.
It optionally, can be according to the method for obtaining corresponding first matrix of prime information in S302, to obtain second
The corresponding second matrix S of pose information is not repeating the implementation procedure in S303 herein.
It should be noted that the element in the second matrix S and the first matrix R on corresponding position indicates same key point (example
Such as, left eye eyeball, right eye eyeball) different coordinates.
For example, being in the first matrix RWhen, the second matrix S can beWherein, first elementFor the left eye eyeball key point coordinate of the second object, second
A elementFor the right eye eyeball key point coordinate of the second object, third elementFor the nose key point of the second object
Coordinate, the 4th elementFor the left shoulder key point coordinate of the second object, the 5th elementFor the right shoulder of the second object
Key point coordinate.
S304: executing matrix manipulation operations, and matrix manipulation operations include: to obtain the according to initial parameter and the first matrix
Three matrixes.
Optionally, initial vector can be determined according to S gusts of the first matrix R and the second square, according to initial vector, determined just
Beginning parameter.
Optionally, can by following feasible formula one, according to the first matrix R and the second matrix S, determine initially to
Amount:
Wherein,For initial vector, s is the element number in the first matrix R (the second matrix S), xiAnd yiFor the first square
The coordinate value of i-th of element in battle array R, may be constructed i-th of coordinate (xi,yi), miAnd niFor i-th yuan in the second matrix S
The coordinate value of element, may be constructed i-th of coordinate (mi,ni)。
Optionally, according to initial vector, determining initial parameter K can be
It should be noted that p=kcos (θ), q=ksin (θ), wherein k is zooming parameter, and θ is rotation angle.
Optionally, initial parameter K obtains third matrix T multiplied by the first matrix R.
S306: parameter updating operation is executed, parameter updating operation includes the Pu Shi according to third matrix T and the second matrix R
Distance updates initial parameter.
Optionally, can according to third matrix T and the second matrix R, by following feasible formula two, obtain Pu Shi away from
From:
Wherein, PdFor Pu Shi distance, eiAnd fiFor the coordinate value of i-th of element in third matrix T, may be constructed i-th
Coordinate (ei,fi), miAnd niFor the coordinate value of i-th of element in the second matrix S, i-th of coordinate (m may be constructedi,ni)。
Optionally, it is greater than distance threshold in Pu Shi distance, or executes the number of matrix manipulation operations less than preset times
When, update initial parameter K.
Optionally, distance threshold can be 0.05,0.06 etc..
Optionally, the preset times can be 10 times, 20 etc..
S306: judging whether the Pu Shi distance of third matrix and the second matrix is less than or equal to distance threshold, or holds
Whether the number of row matrix processing operation is greater than or equal to preset times.
If so, executing S307.
If it is not, then executing S304.
In practical applications, it needs to repeat S303~S305.
It should be noted that judge whether Pu Shi distance is less than or equal to distance threshold after having executed S304 every time, or
The number that person executes matrix manipulation operations (S303) is greater than or equal to preset times, if so, executing S307, refers to S307,
If it is not, then continuing to execute S304.
S307: initial parameter is determined as adjusting parameter.
It should be noted that the initial parameter that will complete last time update, is determined as adjusting parameter K '.
S308: by adjusting parameter multiplied by the coordinate in prime information, tierce information is obtained.
Optionally, third can be obtained by adjusting parameter K ' multiplied by the first matrix R arrived according to prime acquisition of information
Coordinate in pose information, and according to the crucial point identification on the coordinate and different parts in tierce information, obtain third
Pose information.
S309: corresponding 4th matrix of tierce information is obtained.
Optionally, coordinate extraction process can be carried out to tierce information, obtains the 4th matrix U.
For example, the 4th matrix U can beWherein, the element in the 4th matrix U with
Element in S202 is corresponding.For example,Corresponding (A1,B1), wherein u1Equal to A1, v1Equal to B1,Corresponding (A1′,B1'),
Wherein, u2Equal to A1', v2Equal to B1′。
S310: the Euclidean distance of the coordinate of corresponding position in the second matrix and the 4th matrix is obtained.
Optionally, the Europe of the coordinate of corresponding position in the second matrix and the 4th matrix can be determined by following formula three
Family name's distance Di。
S311: according to the Euclidean distance of the coordinate of corresponding position, the average value of the Euclidean distance of corresponding coordinate is determined.
Optionally, Euclidean distance average value D can be determined according to the formula four that can be gone as follows.
S312: by the absolute value of the difference of preset threshold and Euclidean distance average value, it is determined as the first object and the second object
Posture matching degree.
Optionally, preset threshold can be M, wherein the value of M can be 100, can also be other values.
Optionally, the posture matching degree X of the first object and the second object can be determined according to following feasible formula five.
X=| M-D | formula five
Fig. 4 is the structural schematic diagram for the postural assessment device that present example provides.Refer to Fig. 4, postural assessment device
10 include: to obtain module 11, processing module 12 and determining module 13, wherein
The acquisition module 11 is used for, and is obtained in the first image the in the prime information of the first object and the second image
The second information of an object, the prime information include the coordinate at least two positions of first object, institute
State the coordinate that second information includes at least two positions of second object;
The processing module 12 is used for, and is zoomed in and out at processing and/or rotation to the coordinate in the prime information
Reason, obtains tierce information, the size phase of the size of object indicated by the tierce information and second object
Together, at least two positions pair at least two positions of object indicated by the tierce information and second object
It answers;
The determining module 13 is used for, and according to the tierce information and the second information, determines described
The posture matching degree of an object and second object.
Postural assessment device provided in an embodiment of the present invention can execute technical solution shown in above method embodiment,
Realization principle and beneficial effect are similar, are no longer repeated herein.
In a kind of possible embodiment, the processing module 12 is specifically used for:
According to the prime information and the second information, determine that adjusting parameter, the adjusting parameter include
Zooming parameter and/or rotation angle;
According to the prime information and the adjusting parameter, the tierce information is determined.
In alternatively possible embodiment, the processing module 12 is specifically used for:
Obtain corresponding first matrix of the prime information, first matrix include first object at least
The coordinate of the coordinate at two positions, at least two positions of first object is stored in first matrix according to preset rules
In;
Obtain corresponding second matrix of the second information, second matrix include second object at least
The coordinate of the coordinate at two positions, at least two positions of second object is stored in described second according to the preset rules
In matrix;
According to the Pu Shi distance between first matrix and second matrix, the adjusting parameter is determined.
In alternatively possible embodiment, the processing module 12 is specifically used for:
Matrix manipulation operations are executed, the matrix manipulation operations include: to obtain according to initial parameter and first matrix
Third matrix;
Parameter updating operation is executed, the parameter updating operation includes according to the third matrix and second matrix
Pu Shi distance updates initial parameter;
The matrix manipulation operations and the parameter updating operation are repeated, until the third matrix and described second
The Pu Shi distance of matrix is less than or equal to distance threshold, or executes the number of the matrix manipulation operations more than or equal to pre-
If when number, the initial parameter is determined as the adjusting parameter.
In alternatively possible embodiment, the determining module 13 is specifically used for:
By the adjusting parameter multiplied by the coordinate in the prime information, the tierce information is obtained.
In alternatively possible embodiment, the determining module 13 is specifically used for:
Obtain corresponding second matrix of the second information;
Obtain corresponding 4th matrix of the tierce information;
According to second matrix and the 4th matrix, the posture of first object and second object is determined
With degree.
In alternatively possible embodiment, the determining module 13 is specifically used for:
Obtain the Euclidean distance of the coordinate of corresponding position in second matrix and the 4th matrix;
According to the Euclidean distance of the coordinate of the corresponding position, the posture of first object and second object is determined
Matching degree.
In alternatively possible embodiment, the determining module 13 is specifically used for:
According to the Euclidean distance of the coordinate of the corresponding position, Euclidean distance average value is determined;
By the absolute value of the difference of the preset threshold and the Euclidean distance average value, it is determined as first object and institute
State the posture matching degree of the second object.
Postural assessment device provided in an embodiment of the present invention can execute technical solution shown in above method embodiment,
Realization principle and beneficial effect are similar, are no longer repeated herein.
Fig. 5 is the hardware structural diagram of postural assessment device provided in an embodiment of the present invention.Fig. 5 is referred to, the posture
Assessing device 20 includes: at least one processor 21 and memory 22.Optionally, which further includes communication unit
Part 23.Wherein, processor 21, memory 22 and communication component 23 are connected by bus 24.
During specific implementation, at least one processor 21 executes the computer execution that the memory 22 stores and refers to
It enables, so that at least one processor 21 executes postural assessment method as above.
The specific implementation process of processor 21 can be found in above method embodiment, and it is similar that the realization principle and technical effect are similar,
Details are not described herein again for the present embodiment.
In above-mentioned embodiment shown in fig. 5, it should be appreciated that processor can be central processing unit (English: Central
Processing Unit, referred to as: CPU), it can also be other general processors, digital signal processor (English: Digital
Signal Processor, referred to as: DSP), specific integrated circuit (English: Application Specific Integrated
Circuit, referred to as: ASIC) etc..General processor can be microprocessor or the processor is also possible to any conventional place
Manage device etc..Hardware processor can be embodied directly in conjunction with the step of invention disclosed method and executes completion, or with handling
Hardware and software module combination in device execute completion.
Memory may include high speed RAM memory, it is also possible to and it further include non-volatile memories NVM, for example, at least one
Magnetic disk storage.
Bus can be industry standard architecture (Industry Standard Architecture, ISA) bus, outer
Portion's apparatus interconnection (Peripheral Component, PCI) bus or extended industry-standard architecture (Extended
Industry Standard Architecture, EISA) bus etc..Bus can be divided into address bus, data/address bus, control
Bus etc..For convenient for indicating, the bus in illustrations does not limit only a bus or a type of bus.
The application also provides a kind of computer readable storage medium, and calculating is stored in the computer readable storage medium
Machine executes instruction, and when processor executes the computer executed instructions, realizes postural assessment method as described above.
Above-mentioned computer readable storage medium, above-mentioned readable storage medium storing program for executing can be by any kind of volatibility or non-
Volatile storage devices or their combination realize that, such as static random access memory (SRAM), electrically erasable is only
It reads memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM) is read-only to deposit
Reservoir (ROM), magnetic memory, flash memory, disk or CD.Readable storage medium storing program for executing can be general or specialized computer capacity
Any usable medium enough accessed.
A kind of illustrative readable storage medium storing program for executing is coupled to processor, to enable a processor to from the readable storage medium storing program for executing
Information is read, and information can be written to the readable storage medium storing program for executing.Certainly, readable storage medium storing program for executing is also possible to the composition portion of processor
Point.Processor and readable storage medium storing program for executing can be located at specific integrated circuit (Application Specific Integrated
Circuits, referred to as: ASIC) in.Certainly, processor and readable storage medium storing program for executing can also be used as discrete assembly and be present in equipment
In.
The division of the unit, only a kind of logical function partition, there may be another division manner in actual implementation,
Such as multiple units or components can be combined or can be integrated into another system, or some features can be ignored, or not hold
Row.Another point, shown or discussed mutual coupling, direct-coupling or communication connection can be through some interfaces,
The indirect coupling or communication connection of device or unit can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence;And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can
To be done through the relevant hardware of the program instructions.Program above-mentioned can be stored in a computer readable storage medium.
When being executed, execution includes the steps that above-mentioned each method embodiment to the program;And storage medium above-mentioned includes: ROM, RAM, magnetic
The various media that can store program code such as dish or CD.
Claims (11)
1. a kind of postural assessment method characterized by comprising
Obtain the second information of the first object in the prime information and the second image of the first object in the first image, institute
The coordinate that prime information includes at least two positions of first object is stated, the second information includes described
The coordinate at least two positions of two objects;
Processing and/or rotation processing are zoomed in and out to the coordinate in the prime information, obtain tierce information, it is described
The size of object indicated by tierce information is identical as the size of second object, indicated by the tierce information
Object at least two positions it is corresponding at least two positions of second object;
According to the tierce information and the second information, the appearance of first object and second object is determined
Gesture matching degree.
2. the method according to claim 1, wherein zooming in and out place to the coordinate in the prime information
Reason and/or rotation processing, obtain tierce information, comprising:
According to the prime information and the second information, determine that adjusting parameter, the adjusting parameter include scaling
Parameter and/or rotation angle;
According to the prime information and the adjusting parameter, the tierce information is determined.
3. according to the method described in claim 2, it is characterized in that, being believed according to the prime information and the second
Breath, determines adjusting parameter, comprising:
Corresponding first matrix of the prime information is obtained, first matrix includes at least two of first object
The coordinate of the coordinate at position, at least two positions of first object is stored in first matrix according to preset rules;
Corresponding second matrix of the second information is obtained, second matrix includes at least two of second object
The coordinate of the coordinate at position, at least two positions of second object is stored in second matrix according to the preset rules
In;
According to the Pu Shi distance between first matrix and second matrix, the adjusting parameter is determined.
4. according to the method described in claim 3, it is characterized in that, according between first matrix and second matrix
Pu Shi distance determines the adjusting parameter, comprising:
Matrix manipulation operations are executed, the matrix manipulation operations include: to obtain third according to initial parameter and first matrix
Matrix;
Parameter updating operation is executed, the parameter updating operation includes the Pu Shi according to the third matrix and second matrix
Distance updates initial parameter;
The matrix manipulation operations and the parameter updating operation are repeated, until the third matrix and second matrix
Pu Shi distance be less than or equal to distance threshold, or execute the numbers of the matrix manipulation operations and be greater than or equal to default time
When number, the initial parameter is determined as the adjusting parameter.
5. according to the method described in claim 4, it is characterized in that, according to the prime information and the adjusting parameter,
Determine the tierce information, comprising:
By the adjusting parameter multiplied by the coordinate in the prime information, the tierce information is obtained.
6. method according to claim 1-5, which is characterized in that described according to the tierce information and institute
Second information is stated, determines the posture matching degree of first object and second object, comprising:
Obtain corresponding second matrix of the second information;
Obtain corresponding 4th matrix of the tierce information;
According to second matrix and the 4th matrix, the posture matching of first object and second object is determined
Degree.
7. according to the method described in claim 6, it is characterized in that, described according to second matrix and the 4th matrix,
Determine the posture matching degree of first object and second object, comprising:
Obtain the Euclidean distance of the coordinate of corresponding position in second matrix and the 4th matrix;
According to the Euclidean distance of the coordinate of the corresponding position, the posture matching of first object and second object is determined
Degree.
8. the method according to the description of claim 7 is characterized in that according to the Euclidean distance of the coordinate of the corresponding position, really
The posture matching degree of fixed first object and second object, comprising:
According to the Euclidean distance of the coordinate of the corresponding position, Euclidean distance average value is determined;
By the absolute value of the difference of preset threshold and the Euclidean distance average value, it is determined as first object and second pair described
The posture matching degree of elephant.
9. a kind of postural assessment device characterized by comprising obtain module, processing module and determining module, wherein
The acquisition module is used for, obtain the first image in the first object prime information and the second image in the first object
Second information, the prime information includes the coordinate at least two positions of first object, described second
Pose information includes the coordinate at least two positions of second object;
The processing module is used for, and is zoomed in and out processing and/or rotation processing to the coordinate in the prime information, is obtained
The size of tierce information, object indicated by the tierce information is identical as the size of second object, described
At least two positions of object indicated by tierce information are corresponding at least two positions of second object;
The determining module is used for, and according to the tierce information and the second information, determines first object
With the posture matching degree of second object.
10. a kind of postural assessment device characterized by comprising at least one processor and memory;
The memory stores computer executed instructions;
At least one described processor executes the computer executed instructions of the memory storage, so that at least one described processing
Device executes postural assessment method as claimed in any one of claims 1 to 8.
11. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium
It executes instruction, when processor executes the computer executed instructions, realizes posture as claimed in any one of claims 1 to 8
Appraisal procedure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910463521.3A CN110188688B (en) | 2019-05-30 | 2019-05-30 | Posture evaluation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910463521.3A CN110188688B (en) | 2019-05-30 | 2019-05-30 | Posture evaluation method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110188688A true CN110188688A (en) | 2019-08-30 |
CN110188688B CN110188688B (en) | 2021-12-14 |
Family
ID=67718924
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910463521.3A Active CN110188688B (en) | 2019-05-30 | 2019-05-30 | Posture evaluation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110188688B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110782482A (en) * | 2019-10-21 | 2020-02-11 | 深圳市网心科技有限公司 | Motion evaluation method and device, computer equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140132708A1 (en) * | 2011-07-22 | 2014-05-15 | Fujifilm Corporation | Panoramic image generation method and image capturing apparatus |
CN104657713A (en) * | 2015-02-09 | 2015-05-27 | 浙江大学 | Three-dimensional face calibrating method capable of resisting posture and facial expression changes |
CN109190607A (en) * | 2018-10-30 | 2019-01-11 | 维沃移动通信有限公司 | A kind of motion images processing method, device and terminal |
CN109508656A (en) * | 2018-10-29 | 2019-03-22 | 重庆中科云丛科技有限公司 | A kind of dancing grading automatic distinguishing method, system and computer readable storage medium |
CN109614899A (en) * | 2018-11-29 | 2019-04-12 | 重庆邮电大学 | A kind of human motion recognition method based on Lie group feature and convolutional neural networks |
US10258092B2 (en) * | 2012-09-11 | 2019-04-16 | L.I.F.E. Corporation S.A. | Garments having stretchable and conductive ink |
CN109684911A (en) * | 2018-10-30 | 2019-04-26 | 百度在线网络技术(北京)有限公司 | Expression recognition method, device, electronic equipment and storage medium |
-
2019
- 2019-05-30 CN CN201910463521.3A patent/CN110188688B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140132708A1 (en) * | 2011-07-22 | 2014-05-15 | Fujifilm Corporation | Panoramic image generation method and image capturing apparatus |
US10258092B2 (en) * | 2012-09-11 | 2019-04-16 | L.I.F.E. Corporation S.A. | Garments having stretchable and conductive ink |
CN104657713A (en) * | 2015-02-09 | 2015-05-27 | 浙江大学 | Three-dimensional face calibrating method capable of resisting posture and facial expression changes |
CN109508656A (en) * | 2018-10-29 | 2019-03-22 | 重庆中科云丛科技有限公司 | A kind of dancing grading automatic distinguishing method, system and computer readable storage medium |
CN109190607A (en) * | 2018-10-30 | 2019-01-11 | 维沃移动通信有限公司 | A kind of motion images processing method, device and terminal |
CN109684911A (en) * | 2018-10-30 | 2019-04-26 | 百度在线网络技术(北京)有限公司 | Expression recognition method, device, electronic equipment and storage medium |
CN109614899A (en) * | 2018-11-29 | 2019-04-12 | 重庆邮电大学 | A kind of human motion recognition method based on Lie group feature and convolutional neural networks |
Non-Patent Citations (3)
Title |
---|
CHANG WANG 等: "Manifold alignment using Procrustes analysis", 《ICML "08: PROCEEDINGS OF THE 25TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING》 * |
如梦如幻2015: "《Master Opencv...读书笔记》非刚性⼈脸跟踪II", 《HTTPS://BLOG.CSDN.NET/QQH19910525/ARTICLE/DETAILS/52287739》 * |
王富强: "基于Kinect的运动人体检测技术研究", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110782482A (en) * | 2019-10-21 | 2020-02-11 | 深圳市网心科技有限公司 | Motion evaluation method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110188688B (en) | 2021-12-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106030661B (en) | The independent 3D scene texture background in the visual field | |
WO2020119527A1 (en) | Human action recognition method and apparatus, and terminal device and storage medium | |
CN107395958B (en) | Image processing method and device, electronic equipment and storage medium | |
CN108509848A (en) | The real-time detection method and system of three-dimension object | |
CN108615247A (en) | Method for relocating, device, equipment and the storage medium of camera posture tracing process | |
CN109948397A (en) | A kind of face image correcting method, system and terminal device | |
CN111723691B (en) | Three-dimensional face recognition method and device, electronic equipment and storage medium | |
CN109840019A (en) | Control method, device and the storage medium of virtual portrait | |
CN110675487A (en) | Three-dimensional face modeling and recognizing method and device based on multi-angle two-dimensional face | |
CN109141393A (en) | Method for relocating, equipment and storage medium | |
CN107633526A (en) | A kind of image trace point acquisition methods and equipment, storage medium | |
CN105874783A (en) | Techniques for frame repetition control in frame rate up-conversion | |
CN108805859A (en) | A kind of image detecting method, image detection device and terminal device | |
CN106570482B (en) | Human motion recognition method and device | |
CN108257112A (en) | The method and apparatus for filtering hot spot | |
CN110298306A (en) | The determination method, device and equipment of target object motion information | |
CN110245671A (en) | A kind of endoscopic images characteristic point matching method and system | |
CN108629799A (en) | A kind of method and apparatus for realizing augmented reality | |
CN104573737B (en) | The method and device of positioning feature point | |
CN110163095B (en) | Loop detection method, loop detection device and terminal equipment | |
CN107534202A (en) | A kind of method and apparatus for measuring antenna attitude | |
CN110188688A (en) | Postural assessment method and device | |
CN110910326A (en) | Image processing method and device, processor, electronic device and storage medium | |
CN110222651A (en) | A kind of human face posture detection method, device, terminal device and readable storage medium storing program for executing | |
CN111460937B (en) | Facial feature point positioning method and device, terminal equipment and storage medium |
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 |