CN102657532A - Height measuring method and device based on body posture identification - Google Patents
Height measuring method and device based on body posture identification Download PDFInfo
- Publication number
- CN102657532A CN102657532A CN2012101372318A CN201210137231A CN102657532A CN 102657532 A CN102657532 A CN 102657532A CN 2012101372318 A CN2012101372318 A CN 2012101372318A CN 201210137231 A CN201210137231 A CN 201210137231A CN 102657532 A CN102657532 A CN 102657532A
- Authority
- CN
- China
- Prior art keywords
- human body
- image
- height
- pixel
- coordinate
- 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
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a height measuring method and a height measuring device based on body posture identification. The method comprises the following steps of: acquiring a scene image comprising a body posture; automatically identifying the body posture, wherein different height measuring methods are adopted for bodies of different postures; when a human body is in a posture which is difficult for measuring height directly, partitioning different positions constructing the height or arm reach in a body image to obtain the physical lengths of different positions constructing the height or arm reach respectively; and further summarizing and estimating the height of the human body. According to the method and the device, the automatic degree and height measuring efficiency of body height measurement are increased greatly.
Description
Technical field
The present invention relates to the computer vision treatment technology, be specifically related to height measuring method and device based on human body attitude identification.
Background technology
Height is very important human parameters, in a lot of projects, as needing to measure human body height in human body constitution detection, the people's volume modeling etc.Traditional height metering system needs people to be tested to measure height to health check-up is on-the-spot through scale or optical device.Though this traditional height metering system degree of accuracy is higher, efficient is lower, needs survey crew to carry out on-the-spot operation and record, can not carry out height in batches and measure.When carrying out people's volume modeling, need measure batch height especially, utilize traditional approach to be difficult to satisfy the demands.
Simultaneously, the human body attitude recognition technology is obtaining application more and more widely as the branch of computer vision treatment technology.The different parts that the human body attitude recognition technology is partitioned into human body in the image through digital processing judgement human body attitude and identification to human body image, for example, head and trunk etc.
But, do not provide in the prior art and can directly carry out the method and apparatus that human body height is measured according to image.
Summary of the invention
The object of the present invention is to provide a kind of based on the method and apparatus of human body attitude recognition technology automatic batch according to Image Acquisition human body height measurement data.
The invention discloses a kind of height measuring method, comprising based on human body attitude identification:
Obtain the scene image that comprises human body attitude through image acquiring device;
Remove scene background, cut apart the human body image that obtains in the scene image;
Human body image is carried out human body attitude identification, judge whether human body attitude is upright, if then obtain human body height through the space actual range that calculates between the human body image highs and lows;
Wherein, convert the space actual coordinate of corresponding human body into, and calculate the space actual range between the corresponding human body of human body image pixel based on being converted to the space actual coordinate through pixel coordinate with the pixel of human body image.
Preferably, said method also comprises:
If judge that human body attitude is not an erectility, then human body image is carried out human body attitude identification, judge that whether human body attitude is for opening one's arms, if then obtain human body height through the space actual range that calculates between the most left point of human body image and the rightest point; If not; Then cut apart the different body part that constitute height or arm exhibition in the human body image through human body attitude identification; And calculate the space physical length of the different body part of said formation height or arm exhibition respectively, the height or the arm exhibition of the space physical length summation estimation human body of the different body part of said formation height or arm exhibition obtained human body height;
Wherein, convert the space actual coordinate of corresponding human body into, and calculate the space actual range between the corresponding human body of human body image pixel based on the space actual coordinate through pixel coordinate with the pixel of human body image.
Preferably, said image acquiring device is a depth transducer, and said scene image is a depth image, and the Pixel Information of said depth image comprises the space actual coordinate of the scene point that pixel coordinate and this pixel are corresponding;
The space actual coordinate that the pixel coordinate of said pixel with human body image converts corresponding human body into comprises, pixel coordinate is converted into the space actual coordinate of corresponding human body according to the Pixel Information of said depth image.
Preferably, said image acquiring device is the two dimensional image filming apparatus, and said scene graph is a two dimensional image, and said method is obtained image through under the said two dimensional image filming apparatus preset distance situation of human body distance, taking;
The space actual coordinate that the pixel coordinate of said pixel with human body image converts corresponding human body into comprises, comes to find the solution based on pixel coordinate the space actual coordinate of imaging object point through following formula:
Wherein, (X
w, Y
w, Z
w) be scene point space actual coordinate, the initial point of space actual coordinates is got the camera lens photocentre position of said two dimensional image filming apparatus, and (u v) is the pixel coordinate of respective pixel, (u
o, v
o) be the pixel coordinate of picture centre, f
u, f
vBe respectively the equivalent focal length of X and Y direction, f
u, f
v, u
o, v
oBe the inner parameter of two dimensional image filming apparatus, Z
wEqual said preset distance.
Preferably; Said image acquiring device is the consecutive image filming apparatus that obtains image sequence; Said method is calculated at least two human body height values respectively according at least two pairing images of the moment in the said image sequence; With the meansigma methods of said at least two human body height values as height measurements; Human body height values that perhaps will occurrence number is maximum in the human body height values that is calculated is as height measurements, and weighted mean that perhaps will human body height values that occurrence number is maximum in the said human body height values that calculates and the human body height values that obtains according to the consecutive frame image calculation is as height measurements.
Preferably, the different body part of said formation height are head, trunk, thigh and shank;
The different body part of said formation arm exhibition are shoulder breadth, left upper arm, left underarm, the left hand palm, right upper arm, bottom right arm, the right hand palm.
The invention also discloses a kind of height measuring device, comprising based on human body attitude identification:
The scene image acquisition module is used for obtaining the scene image that comprises human body attitude through image acquiring device;
The human body image acquisition module is used to remove scene background, cuts apart the human body image that obtains in the scene image;
The first height computing module is used for human body image is carried out human body attitude identification, judges whether human body attitude is upright, if then obtain human body height through the space actual range that calculates between the human body image highs and lows;
Wherein, convert the space actual coordinate of corresponding human body into, and calculate the space actual range between the corresponding human body of human body image pixel based on being converted to the space actual coordinate through pixel coordinate with the pixel of human body image.
Preferably, said device also comprises:
The second height computing module; Be used for when judging that human body attitude is not erectility, human body image is carried out human body attitude identification, judge that whether human body attitude is for opening one's arms; If then obtain human body height through the actual range that calculates between the most left point of human body image and the rightest point; If not; Then cut apart the different body part that constitute height or arm exhibition in the human body image through human body attitude identification; And calculate the space physical length of the different body part of said formation height or arm exhibition respectively, and the height or the arm exhibition of the space physical length summation estimation human body of the different body part of said formation height or arm exhibition obtained human body height;
Wherein, convert the space actual coordinate of corresponding human body into, and calculate the space actual range between the corresponding human body of human body image pixel based on being converted to the space actual coordinate through pixel coordinate with the pixel of human body image.
Preferably; Said image acquiring device is a depth transducer; Said scene image is a depth image; The Pixel Information of said depth image comprises the space actual coordinate of the pixel coordinate and the scene point of correspondence, and the said first height computing module and the second height computing module convert pixel coordinate into according to the Pixel Information of said depth image the space actual coordinate of corresponding human body.
Preferably; Said image acquiring device is the two dimensional image filming apparatus; Said scene graph is a two dimensional image; Said two dimensional image filming apparatus obtains image through under the said two dimensional image filming apparatus preset distance situation of human body distance, taking, and the said first height computing module and the second height computing module come to find the solution based on pixel coordinate the space actual coordinate of imaging object point through following formula:
Wherein, (X
w, Y
w, Z
w) being imaging object point space actual coordinate, the initial point of space actual coordinates is got the camera lens photocentre position of said two dimensional image filming apparatus, and (u v) is the pixel coordinate of pixel, (u
o, v
o) be the pixel coordinate of picture centre, f
u, f
vBe respectively the equivalent focal length of X and Y direction, f
u, f
v, u
o, v
oBe the inner parameter of two dimensional image filming apparatus, Z
wBe said preset distance.
The present invention is through the automatic identification to human body attitude; To upright, open one's arms and adopt different height account forms with the human body image of other attitude; Human body in image is in when being difficult to directly estimate the attitude of its height; Utilize its length that constitutes the different parts of height or arm exhibition to sue for peace and estimate human body height, automaticity is high, and treatment effeciency is much higher than prior art.
Description of drawings
Fig. 1 a is that the embodiment of the invention is carried out the schematic diagram that the height summation is measured;
Fig. 1 b is that another embodiment of the present invention is carried out the schematic diagram that the height summation is measured;
Fig. 2 is the method flow diagram of the embodiment of the invention based on the height measuring method of human body attitude identification;
Fig. 3 is the sketch map of embodiment of the invention depth image imaging model;
Fig. 4 is the sketch map of embodiment of the invention ordinary two-dimensional image imaging model;
Fig. 5 is the system block diagram of the embodiment of the invention based on the height measuring device of human body attitude identification.
The specific embodiment
Further specify technical scheme of the present invention below in conjunction with accompanying drawing and through the specific embodiment.
Fig. 1 a and Fig. 1 b are that the embodiment of the invention is carried out height summation measuring principle figure.
Human body is upright, that is, human body is vertical standing state, this moment human body head, trunk, thigh and shank roughly linearly and this straight line perpendicular to the ground.When human body was upright, human body height can be calculated through the difference in height of human body peak and minimum point.
Simultaneously, find that through statistics length and height when human body opens one's arms are more approaching, approximate the trying to achieve of arm exhibition length when height can open one's arms with human body.Open one's arms, be meant that the human body both arms launch, the arm of human body and trunk plane are positioned at same plane, and with the shoulder of human body linearly state roughly.When human body opened one's arms, human body height can obtain through the space actual range that calculates between the most left point of human body and the rightest point.
When human body is in non-erectility, during the also non-state that opens one's arms, human body height can shown in Fig. 1 a, can be asked for height through the different body part length that constitute human body height are sued for peace through the human body different piece being sued for peace come approximate the acquisition:
The height of height=head+trunk height+thigh length+shank length (1)
Perhaps, shown in Fig. 1 b, open up through anded human body arm and to obtain approximate height:
Height=shoulder breadth+left upper arm length+left side is arm lengths+left hand palm length+right upper arm length+bottom right arm lengths+right hand palm length (2) down
Wherein, gage beam exhibition and summation estimation arm are opened up and are measured height and be applicable to and do not show all occasions of part of human body in the image.
Fig. 2 is that the embodiment of the invention is carried out the method flow diagram that height is measured.Said method comprises the steps:
In this step; Can obtain the Pixel Information of human body in the image through connected domain detection or image detection; After other background information beyond the human body pixel in the scene image removed, remaining image just had only human body, made that the numerical value of the pixel except human body image all is zero in the image.
One Chinese patent application CN101576953A discloses a kind of sorting technique of human body attitude; Through the human region in the tracking image; Human region is carried out the extraction of body shape; Obtain the human body outline, and recently the human body attitude in the image is classified according to number of people positional information, image length and width, this application also discloses the training module that is input to grader according to the characteristic vector of the external profile of lineup of manual work demarcation as training sample; Set up the grader of human body attitude through training, and further realize classification for the human body attitude in the image according to grader.The grader of this human body attitude can be Adaboost (self-adaptive enhancement algorithm) grader, SVM (SVMs) grader or neutral net etc.
One Chinese patent application CN101989326A discloses a kind of recognition methods of human body attitude, matees the swooping template action attitude of mating most with search through the template database that extracts characteristic information and reservation in the depth image.
Can realize human body attitude identification through above method, thereby judge that human body attitude is upright or is in other attitudes for depth image or ordinary two-dimensional image.Certainly, the present invention is not limited to the disclosed method of above document for the judgement of human body attitude.Any method that can supply in any prior art to utilize all can be used to carry out the human body attitude identification of this step.
In this step; Can be through directly in image pixel, searching for the highs and lows that the minimum and maximum non-zero pixels of vertical coordinate value promptly obtains human body image; Can obtain the space actual coordinate of the corresponding human body of said highs and lows through pixel coordinate-space coordinate transformation, thereby thereby can calculate its space actual range according to the space actual coordinate of the highs and lows of upright human body obtains human body height.Here; Pixel coordinate is meant the coordinate of remarked pixel present position in image; Pixel coordinate system is the coordinate system of a two dimension; Be meant the coordinate of representing object present position in real world with the time space actual coordinate, space actual coordinates (being also referred to as world coordinate system) is a three-dimensional system of coordinate.The space actual range is meant in reality scene, the air line distance between 2, and it can calculate through the space actual coordinate.
In this step; Can be through directly in image pixel, searching for the most left point and the rightest point that the minimum and maximum non-zero pixels of horizontal coordinate value promptly obtains human body image; Can obtain the space actual coordinate of the most left said point and the human body of the rightest some correspondence through image coordinate-space coordinate transformation; Thereby can calculate its space actual range according to the left side point of the human body that opens one's arms and the space actual coordinate of right point and obtain its arm exhibition length, thus obtain to estimate human body height.
Document " Articulated Human Pose Estimation and Search in (Almost) Unconstrained Still Images " Eichner; M.and Marin-Jimenez, M.and Zisserman, A.and Ferrari; V.; ETH Zurich, D-ITET, BIWI; Technical Report No.272; September 2010 and corresponding website disclose a kind of human body recognizer and system (http://www.vision.ee.ethz.ch/ ~ calvin/articulated_human_pose_estima tion_code/), and said algorithm can be cut apart the each several part of the human body that obtains the different attitudes in the image through handling the two-dimension human body image recognition with system, for example the head of human body, trunk, big arm, forearm, hands and thigh and shank etc.
Document " Real-Time Human Pose Recognition in Parts from Single Depth Images " .Jamie Shotton; Andrew Fitzgibbon, Mat Cook, Toby Sharp; Mark Finocchio; Richard Moore, Alex Kipman, and Andrew Blake.CVPR; 2011 disclose the recognition methods of the real-time human body attitude part of a kind of depth image, are converted into and have simply realized from depth image, separating the purpose of obtaining the human synovial location information by the pixel classification problem through depth image being handled attitude estimation problem with difficulty.
Can realize cutting apart through above method for the human body key point identification of depth image or ordinary two-dimensional image.Certainly, the present invention is not limited to the disclosed method of above document for the judgement of human body attitude.
Human body key point with the identification acquisition; For example; The pixel coordinate of the shoulder joint of formation upper arm and the pixel of elbow joint extracts and obtains; Each several part image coordinate-the space coordinate transformation that then identification is obtained can obtain the space actual coordinate of the corresponding scene point (also being above-mentioned human body key point) of pixel, calculates its space physical length according to the space actual coordinate, for example obtains the physical length of human body upper arm through the space actual range that calculates shoulder joint and elbow joint.
Wherein, in above-mentioned steps 400, when human body is upright, require image acquiring device can take the image of human body whole body.Obtain peak pixel coordinate and minimum point pixel coordinate in the human body image through search.Through pixel coordinate-space actual coordinate conversion, according to the pixel coordinate (u of upright human body peak in the image
Max, v
Max) and the pixel coordinate (u of minimum point
Min, v
Min), calculate the human body peak space actual coordinate (x that acquires
Max, y
Max, z
Max) and the space actual coordinate (x of minimum point
Min, y
Min, z
Min).According to the upright human body height of computes:
H=y
max-y
min （3）
In above-mentioned steps 600, when human body in the image when opening one's arms, require image acquiring device can take the depth image of upper half of human body this moment.Obtain the rightest some pixel coordinate and the most left some pixel coordinate in the human body image through search.Change through pixel coordinate-space actual coordinate, according to the pixel coordinate (u of the rightest point of upright human body in the image
Right, v
Right) and the most left pixel coordinate (u that puts
Left, v
Left), calculate the rightest space of points actual coordinate of the human body (x that acquires
Right, y
Right, z
Right), the most left point (x
Left, y
Left, z
Left).According to the upright human body height of computes:
H=x
right-x
left （4）
Depth transducer is when obtaining the scene depth image, and each point (scene point) in the scene is projected to imaging plane, forms the pixel of image, and therefore, all there is corresponding with it scene point in each pixel of depth image.For instance, among Fig. 1 b the pixel at the finger tip place of human body image corresponding to the fingertip location of human body in the reality scene.Depth transducer can calculate the space actual coordinate between the pixel coordinate that obtains depth image and the corresponding scene point when forming depth image.The information of each pixel in the depth image comprise (u, v) (x, y, z) }; Wherein (u v) is used for representing the position of this pixel at image, (x, y; Z) be used for representing scene point that this pixel is corresponding in the position in space, that is, and the space actual coordinate of the part that this pixel is corresponding.Depth image for present embodiment; Difference according to depth transducer institute operation technique; The mode of choosing of the initial point of its space actual coordinate can have difference, for example, adopts the depth transducer of structured light range finding; The zero of its space actual coordinates (also can be described as world coordinate system) is set in the focal length of camera place usually, and is as shown in Figure 3.Thus, through the one-to-one relationship of image pixel coordinate and space actual coordinate, can obtain the space actual coordinate of pixel according to the image pixel coordinate.
What need further specify is; In the present embodiment; Because during subsequent calculations human body height, employing be the mode of the space actual range between the pairing scene point of the crucial pixel of computed image, its only with scene point between relative distance relevant; Location independent with coordinate origin; Therefore, the mode of choosing of pixel coordinate and space coordinates initial point is in fact for the not influence of subsequent calculations human body height, as long as depth transducer comprises corresponding pixel coordinate and scene point space actual coordinate in the Pixel Information of the depth image that forms.
Fig. 4 is the model sketch map of two dimensional image imaging.As shown in Figure 4; In another embodiment of the present invention; Adopt the two dimensional image filming apparatus to obtain the scene image that comprises human body as described image acquiring device, at this moment, when requiring to obtain image; Human body is a known preset distance apart from the distance of two dimensional image filming apparatus, for example 2.5 meters.When the said two dimensional image filming apparatus distance of human body distance is known, can pixel coordinate be converted into the space actual coordinate of human body through changes in coordinates.The image that the two dimensional image filming apparatus obtains can be divided into gray level image and coloured image, in the black white image, the information of each pixel comprise (u, v), I (u; V) }, in the coloured image information of each pixel comprise (u, v) (r, g, b) }; Wherein, (u v) is the pixel coordinate of this pixel, I (u; V) be the gray value of this pixel, (r, g b) are the color value of this pixel.
In the present embodiment, use the pinhole imaging system model to carry out the conversion of pixel coordinate-space actual coordinate.As shown in Figure 4, the scene point in the scene forms images on the imaging plane of image acquiring device and forms corresponding image slices vegetarian refreshments, (X
w, Y
w, Z
w) be the space actual coordinate of scene point, (u v) is the pixel coordinate of the imaging point pixel of correspondence.Wherein, be the initial point of space actual coordinates with the camera lens optical center of lens place of image acquiring device, then according to the pinhole imaging system principle, the said space of imaging plane distance actual coordinates initial point distance is a focal distance f.
According to Similar Principle of Triangle, there is following relation in the space actual coordinate at pixel coordinate and corresponding fields sight spot:
(5)
Wherein, (u
o, v
o) be picture centre (intersection point of the optical axis and the plane of delineation) coordinate; In fact the picture centre coordinate has explained the position of pixel coordinate system with respect to said picture centre; As long as provide the picture centre coordinate, the initial point of pixel coordinate system can be selected to the planar optional position of picture as required.f
u=f/d
x, f
v=f/d
yBe defined as the equivalent focal length of X and Y direction respectively, in the following formula, f is the camera lens focal length, d
x, d
yFor the camera review pixel in x axle and the axial size of y.f
u, f
v, u
o, v
oThese 4 parameters are only relevant with the video camera internal structure, therefore are called the inner parameter of video camera, and these parameters can directly obtain from video camera.
Known human body apart from video camera apart from Z
wAnd under the situation of the inner parameter of above-mentioned video camera, can calculate corresponding space actual coordinate (X according to pixel coordinate through formula (5)
w, Y
w, Z
w).
In another embodiment of the present invention, can from video, also be to add up height in the continuous images sequence, to obtain higher precision.In this embodiment; Can select and corresponding respectively multiple image of the different moment from image sequence; Calculate a plurality of human body height values respectively according to the multiple image of choosing, then the human body height values that calculates asked on average, with this meansigma methods as the human body height measurements.For example, the t of selecting video
1, t
2... T
nN constantly corresponding image calculates n human body height values respectively according to the n that a chooses image, this n human body height values asked on average, with meansigma methods as the human body height measurements.
Except calculating mean value comes from multiple image obtains accurate more human body height measurements; Can also calculate a plurality of human body height values according to the different corresponding respectively constantly multiple images of video; Set up the rectangular histogram of these a plurality of height values that calculate, the height numerical value that cylinder that occurrence number in the rectangular histogram is maximum is corresponding (also promptly in this a plurality of human body height values appearance/number of repetition maximum/height values that frequency is the highest) be the human body height measurements.For example, the t of selecting video
1, t
2... T
nN corresponding constantly image calculates n human body height values respectively according to the n that a chooses image, and wherein a certain height values x has occurred m time in n estimation, is the maximum human body height values of occurrence number, chooses height values x so as the human body height measurements.
In addition, the weighted average that can also ask the adjacent corresponding height numerical value of a plurality of cylinders of occurrence number is the highest in the rectangular histogram cylinder is as the human body height measurements, and wherein the weighting weight of each height numerical value is the occurrence number of this cylinder numerical value in whole rectangular histogram.For example, in the n that calculates a human body height values, wherein a certain height values x has occurred m time in n estimation, is the maximum human body height values of occurrence number, then chooses the adjacent height values x in moment both sides that this height values x occurs
1, x
2... x
2m, these height values are carried out weighted average according to the number of times that in n estimation, occurs, with the result as the human body height measurements.
Fig. 5 is the block diagram of height measuring device of the present invention.As shown in Figure 5, said height measuring device comprises that scene image acquisition module, human body image acquisition module, the first attitude judge module, the second attitude judge module, upright height computing module, arm are opened up the height computing module, human body image is cut apart module and height summation module.
Wherein, the scene image acquisition module is used for obtaining the scene image that comprises human body attitude through image acquiring device;
The human body image acquisition module is used to handle said scene image, cuts apart the human body image that obtains in the image;
The first attitude judge module is used to carry out human body attitude identification and judges whether human body attitude is upright;
The second attitude judge module is used to carry out human body attitude identification and judges that whether human body attitude is for opening one's arms;
Upright height computing module is used for when the first attitude judge module judges that human body attitude is upright, obtaining human body height through the space actual range that calculates between the human body pixel highs and lows;
Arm exhibition height computing module is used for judging human body attitude when opening one's arms at the second attitude judge module, through calculating the space actual range acquisition human body height between left side point and the rightest point of human body image;
Human body image is cut apart module and is used for judging that at the first attitude judge module human body attitude is not for upright; And the second attitude judge module judges that human body attitude is not when opening one's arms; Cut apart the different body part that constitute height or arm exhibition in the human body image through human body attitude identification, represent corresponding human body part or identify the human synovial position with key point with line segment.
The height summation module is used for calculating respectively the space physical length of said different body part, and the height or the arm exhibition of the length summation estimation human body of the different body part of said formation height or arm exhibition obtained human body height.
Wherein, the first attitude judge module has constituted the first height computing module jointly with upright height computing module; The second attitude judge module, arm exhibition height computing module, human body image are cut apart module and the common formation of the height summation module second height computing module.
The present invention is through the automatic identification to human body attitude; To upright, open one's arms and adopt different height account forms with the human body image of other attitude; Human body in image is in when being difficult to directly estimate the attitude of its height; Utilize its length that constitutes the different parts of height or arm exhibition to sue for peace and estimate human body height, automaticity is high, and treatment effeciency is much higher than prior art.
Obviously; It will be understood by those skilled in the art that above-mentioned each module of the present invention or each step can realize that they can concentrate on the single accountant with the general calculation device; Perhaps be distributed on the network that a plurality of accountant forms; Alternatively, they can realize with the executable program code of computer installation, carried out by accountant thereby can they be stored in the storage device; Perhaps they are made into each integrated circuit modules respectively, perhaps a plurality of modules in them or step are made into the single integrated circuit module and realize.Like this, the present invention is not restricted to the combination of any specific hardware and software.
The above is merely the preferred embodiments of the present invention, is not limited to the present invention, and to those skilled in the art, the present invention can have various changes and variation.All any modifications of within spirit of the present invention and principle, being done, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. height measuring method based on human body attitude identification comprises:
Obtain the scene image that comprises human body attitude through image acquiring device;
Remove scene background, cut apart the human body image that obtains in the scene image;
Human body image is carried out human body attitude identification, judge whether human body attitude is upright, if then obtain human body height through the space actual range that calculates between the human body image highs and lows;
Wherein, convert the space actual coordinate of corresponding human body into, and calculate the space actual range between the corresponding human body of human body image pixel based on being converted to the space actual coordinate through pixel coordinate with the pixel of human body image.
2. the height measuring method based on human body attitude identification as claimed in claim 1 is characterized in that said method also comprises:
If judge that human body attitude is not an erectility, then human body image is carried out human body attitude identification, judge that whether human body attitude is for opening one's arms, if then obtain human body height through the space actual range that calculates between the most left point of human body image and the rightest point; If not; Then cut apart the different body part that constitute height or arm exhibition in the human body image through human body attitude identification; And calculate the space physical length of the different body part of said formation height or arm exhibition respectively, the height or the arm exhibition of the space physical length summation estimation human body of the different body part of said formation height or arm exhibition obtained human body height;
Wherein, convert the space actual coordinate of corresponding human body into, and calculate the space actual range between the corresponding human body of human body image pixel based on the space actual coordinate through pixel coordinate with the pixel of human body image.
3. according to claim 1 or claim 2 height measuring method based on human body attitude identification; It is characterized in that; Said image acquiring device is a depth transducer; Said scene image is a depth image, and the Pixel Information of said depth image comprises the space actual coordinate of the scene point that pixel coordinate and this pixel are corresponding;
The space actual coordinate that the pixel coordinate of said pixel with human body image converts corresponding human body into comprises, pixel coordinate is converted into the space actual coordinate of corresponding human body according to the Pixel Information of said depth image.
4. according to claim 1 or claim 2 height measuring method based on human body attitude identification; It is characterized in that; Said image acquiring device is the two dimensional image filming apparatus; Said scene graph is a two dimensional image, and said method is obtained image through under the said two dimensional image filming apparatus preset distance situation of human body distance, taking;
The space actual coordinate that the pixel coordinate of said pixel with human body image converts corresponding human body into comprises, comes to find the solution based on pixel coordinate the space actual coordinate of imaging object point through following formula:
Wherein, (X
w, Y
w, Z
w) be scene point space actual coordinate, the initial point of space actual coordinates is got the camera lens photocentre position of said two dimensional image filming apparatus, and (u v) is the pixel coordinate of respective pixel, (u
o, v
o) be the pixel coordinate of picture centre, f
u, f
vBe respectively the equivalent focal length of X and Y direction, f
u, f
v, u
o, v
oBe the inner parameter of two dimensional image filming apparatus, Z
wEqual said preset distance.
5. according to claim 1 or claim 2 height measuring method based on human body attitude identification; It is characterized in that; Said image acquiring device is the consecutive image filming apparatus that obtains image sequence; Said method is calculated at least two human body height values respectively according at least two pairing images of the moment in the said image sequence; With the meansigma methods of said at least two human body height values as height measurements; Human body height values that perhaps will occurrence number is maximum in the human body height values that is calculated is as height measurements, and weighted mean that perhaps will human body height values that occurrence number is maximum in the said human body height values that calculates and the human body height values that obtains according to the consecutive frame image calculation is as height measurements.
6. the height measuring method based on human body attitude identification as claimed in claim 2 is characterized in that,
The different body part of said formation height are head, trunk, thigh and shank;
The different body part of said formation arm exhibition are shoulder breadth, left upper arm, left underarm, the left hand palm, right upper arm, bottom right arm, the right hand palm.
7. height measuring device based on human body attitude identification comprises:
The scene image acquisition module is used for obtaining the scene image that comprises human body attitude through image acquiring device;
The human body image acquisition module is used to remove scene background, cuts apart the human body image that obtains in the scene image;
The first height computing module is used for human body image is carried out human body attitude identification, judges whether human body attitude is upright, if then obtain human body height through the space actual range that calculates between the human body image highs and lows;
Wherein, convert the space actual coordinate of corresponding human body into, and calculate the space actual range between the corresponding human body of human body image pixel based on being converted to the space actual coordinate through pixel coordinate with the pixel of human body image.
8. the height measuring device based on human body attitude identification as claimed in claim 7 is characterized in that, also comprises:
The second height computing module; Be used for when judging that human body attitude is not erectility, human body image is carried out human body attitude identification, judge that whether human body attitude is for opening one's arms; If then obtain human body height through the actual range that calculates between the most left point of human body image and the rightest point; If not; Then cut apart the different body part that constitute height or arm exhibition in the human body image through human body attitude identification; And calculate the space physical length of the different body part of said formation height or arm exhibition respectively, and the height or the arm exhibition of the space physical length summation estimation human body of the different body part of said formation height or arm exhibition obtained human body height;
Wherein, convert the space actual coordinate of corresponding human body into, and calculate the space actual range between the corresponding human body of human body image pixel based on being converted to the space actual coordinate through pixel coordinate with the pixel of human body image.
9. like claim 7 or 8 described height measuring devices based on human body attitude identification; It is characterized in that; Said image acquiring device is a depth transducer; Said scene image is a depth image, and the Pixel Information of said depth image comprises the space actual coordinate of the pixel coordinate and the scene point of correspondence, and the said first height computing module and the second height computing module convert pixel coordinate into according to the Pixel Information of said depth image the space actual coordinate of corresponding human body.
10. like claim 7 or 8 described height measuring devices based on human body attitude identification; It is characterized in that; Said image acquiring device is the two dimensional image filming apparatus; Said scene graph is a two dimensional image, and said two dimensional image filming apparatus obtains image through under the said two dimensional image filming apparatus preset distance situation of human body distance, taking, and the said first height computing module and the second height computing module come to find the solution based on pixel coordinate the space actual coordinate of imaging object point through following formula:
Wherein, (X
w, Y
w, Z
w) being imaging object point space actual coordinate, the initial point of space actual coordinates is got the camera lens photocentre position of said two dimensional image filming apparatus, and (u v) is the pixel coordinate of pixel, (u
o, v
o) be the pixel coordinate of picture centre, f
u, f
vBe respectively the equivalent focal length of X and Y direction, f
u, f
v, u
o, v
oBe the inner parameter of two dimensional image filming apparatus, Z
wBe said preset distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210137231.8A CN102657532B (en) | 2012-05-04 | 2012-05-04 | Height measuring method and device based on body posture identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210137231.8A CN102657532B (en) | 2012-05-04 | 2012-05-04 | Height measuring method and device based on body posture identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102657532A true CN102657532A (en) | 2012-09-12 |
| CN102657532B CN102657532B (en) | 2014-09-17 |
Family
ID=46767206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210137231.8A Active CN102657532B (en) | 2012-05-04 | 2012-05-04 | Height measuring method and device based on body posture identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102657532B (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104257385A (en) * | 2014-10-16 | 2015-01-07 | 辽宁省颅面复原技术重点实验室 | Method for measuring height of human body in video images |
| CN104688237A (en) * | 2015-02-11 | 2015-06-10 | 深圳泰山在线科技有限公司 | Time measuring method and system for physique test |
| CN105054936A (en) * | 2015-07-16 | 2015-11-18 | 河海大学常州校区 | Height and weight rapid measuring method based on Kinect depth-of-field image |
| CN106377264A (en) * | 2016-10-20 | 2017-02-08 | 广州视源电子科技股份有限公司 | Human height measuring method and device and intelligent mirror |
| CN106529400A (en) * | 2016-09-26 | 2017-03-22 | 深圳奥比中光科技有限公司 | Mobile terminal and human body monitoring method and device |
| CN106683070A (en) * | 2015-11-04 | 2017-05-17 | 杭州海康威视数字技术股份有限公司 | Body height measurement method and body height measurement device based on depth camera |
| CN106859652A (en) * | 2017-02-25 | 2017-06-20 | 深圳市赛亿科技开发有限公司 | A kind of Human Height measuring method |
| CN107169262A (en) * | 2017-03-31 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Recommend method, device, equipment and the computer-readable storage medium of body shaping scheme |
| CN107192342A (en) * | 2017-05-11 | 2017-09-22 | 广州帕克西软件开发有限公司 | A kind of measuring method and system of contactless build data |
| CN107507213A (en) * | 2016-06-13 | 2017-12-22 | 北京理工大学 | A kind of method and device based on end point extraction image information |
| CN107590830A (en) * | 2017-09-21 | 2018-01-16 | 北京小米移动软件有限公司 | Method for determining height, device and storage medium based on image |
| JP2018023749A (en) * | 2016-08-10 | 2018-02-15 | タタ コンサルタンシー サービシズ リミテッドＴＡＴＡ Ｃｏｎｓｕｌｔａｎｃｙ Ｓｅｒｖｉｃｅｓ Ｌｉｍｉｔｅｄ | Systems and methods for identifying body joint locations based on sensor data analysis |
| CN108209925A (en) * | 2017-12-28 | 2018-06-29 | 北京安云世纪科技有限公司 | A kind of measuring method of Human Height, device and mobile terminal |
| CN108289636A (en) * | 2015-11-20 | 2018-07-17 | 皇家飞利浦有限公司 | Method and apparatus for the respiratory rate for determining object |
| CN108444584A (en) * | 2018-04-13 | 2018-08-24 | 山东华宇工学院 | A kind of intelligence height and weight measuring system and method |
| CN108663957A (en) * | 2018-04-23 | 2018-10-16 | 靳霞 | The anti-control method bottomed out of swing based on image recognition |
| CN108786119A (en) * | 2018-04-23 | 2018-11-13 | 靳霞 | Swing based on image recognition is anti-to bottom out control platform |
| CN108921929A (en) * | 2018-06-26 | 2018-11-30 | 开放智能机器（上海）有限公司 | A kind of recognition methods of identifying system and training method and individual monocular image |
| WO2019052318A1 (en) * | 2017-09-13 | 2019-03-21 | 杭州海康威视数字技术股份有限公司 | Method, apparatus and system for monitoring elevator car |
| US10424078B2 (en) | 2016-03-18 | 2019-09-24 | Boe Technology Group Co., Ltd. | Height measuring system and method |
| CN110443154A (en) * | 2019-07-15 | 2019-11-12 | 北京达佳互联信息技术有限公司 | Three-dimensional coordinate localization method, device, electronic equipment and the storage medium of key point |
| CN110475510A (en) * | 2017-03-27 | 2019-11-19 | 韩国斯诺有限公司 | Obtain the method and device of the shape information of object |
| CN110604574A (en) * | 2019-09-16 | 2019-12-24 | 河北微幼趣教育科技有限公司 | Human body height measuring method based on video imaging principle |
| CN110672016A (en) * | 2019-09-12 | 2020-01-10 | 四川农业大学 | Cattle body size measuring system and method based on image recognition |
| CN110874572A (en) * | 2019-10-29 | 2020-03-10 | 北京海益同展信息科技有限公司 | Information detection method and device and storage medium |
| CN111664795A (en) * | 2020-05-22 | 2020-09-15 | 维沃移动通信有限公司 | Height measuring method and device and electronic equipment |
| CN112363626A (en) * | 2020-11-25 | 2021-02-12 | 广州魅视电子科技有限公司 | Large screen interaction control method based on human body posture and gesture posture visual recognition |
| WO2022012019A1 (en) * | 2020-07-15 | 2022-01-20 | 华为技术有限公司 | Height measuring method, height measuring device, and terminal |
| CN114005199A (en) * | 2021-10-26 | 2022-02-01 | 珠海格力电器股份有限公司 | Door lock control method and device, electronic equipment and storage medium |
| CN114375177A (en) * | 2019-09-01 | 2022-04-19 | Lg电子株式会社 | Body measurement device and control method thereof |
| CN114625048A (en) * | 2022-03-16 | 2022-06-14 | 江阴市晶磁电子有限公司 | Space adjustment management control system and method |
| WO2022216973A1 (en) * | 2021-04-08 | 2022-10-13 | Universal City Studios Llc | Guest measurement systems and methods |
| CN117078735A (en) * | 2023-08-14 | 2023-11-17 | 广州广电运通智能科技有限公司 | Height detection method, system, electronic device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593410A (en) * | 2008-05-29 | 2009-12-02 | 上海理工大学 | Security monitoring system of coach bus |
| JP2010122078A (en) * | 2008-11-20 | 2010-06-03 | Nippon Signal Co Ltd:The | Height detection system, and automatic ticket gate using the same |
| CN102324041A (en) * | 2011-09-09 | 2012-01-18 | 深圳泰山在线科技有限公司 | Pixel classification method, joint body gesture recognition method and mouse instruction generating method |
-
2012
- 2012-05-04 CN CN201210137231.8A patent/CN102657532B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593410A (en) * | 2008-05-29 | 2009-12-02 | 上海理工大学 | Security monitoring system of coach bus |
| JP2010122078A (en) * | 2008-11-20 | 2010-06-03 | Nippon Signal Co Ltd:The | Height detection system, and automatic ticket gate using the same |
| CN102324041A (en) * | 2011-09-09 | 2012-01-18 | 深圳泰山在线科技有限公司 | Pixel classification method, joint body gesture recognition method and mouse instruction generating method |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104257385B (en) * | 2014-10-16 | 2016-05-11 | 辽宁省颅面复原技术重点实验室 | The measuring method of Human Height in video image |
| CN104257385A (en) * | 2014-10-16 | 2015-01-07 | 辽宁省颅面复原技术重点实验室 | Method for measuring height of human body in video images |
| CN104688237A (en) * | 2015-02-11 | 2015-06-10 | 深圳泰山在线科技有限公司 | Time measuring method and system for physique test |
| CN105054936B (en) * | 2015-07-16 | 2017-07-14 | 河海大学常州校区 | Quick height and body weight measurement based on Kinect depth images |
| CN105054936A (en) * | 2015-07-16 | 2015-11-18 | 河海大学常州校区 | Height and weight rapid measuring method based on Kinect depth-of-field image |
| CN106683070A (en) * | 2015-11-04 | 2017-05-17 | 杭州海康威视数字技术股份有限公司 | Body height measurement method and body height measurement device based on depth camera |
| CN106683070B (en) * | 2015-11-04 | 2020-05-12 | 杭州海康威视数字技术股份有限公司 | Height measuring method and device based on depth camera |
| CN108289636B (en) * | 2015-11-20 | 2021-07-13 | 皇家飞利浦有限公司 | Method and apparatus for determining the breathing rate of a subject |
| CN108289636A (en) * | 2015-11-20 | 2018-07-17 | 皇家飞利浦有限公司 | Method and apparatus for the respiratory rate for determining object |
| US10424078B2 (en) | 2016-03-18 | 2019-09-24 | Boe Technology Group Co., Ltd. | Height measuring system and method |
| CN107507213A (en) * | 2016-06-13 | 2017-12-22 | 北京理工大学 | A kind of method and device based on end point extraction image information |
| JP2018023749A (en) * | 2016-08-10 | 2018-02-15 | タタ コンサルタンシー サービシズ リミテッドＴＡＴＡ Ｃｏｎｓｕｌｔａｎｃｙ Ｓｅｒｖｉｃｅｓ Ｌｉｍｉｔｅｄ | Systems and methods for identifying body joint locations based on sensor data analysis |
| CN106529400A (en) * | 2016-09-26 | 2017-03-22 | 深圳奥比中光科技有限公司 | Mobile terminal and human body monitoring method and device |
| CN106377264A (en) * | 2016-10-20 | 2017-02-08 | 广州视源电子科技股份有限公司 | Human height measuring method and device and intelligent mirror |
| CN106859652A (en) * | 2017-02-25 | 2017-06-20 | 深圳市赛亿科技开发有限公司 | A kind of Human Height measuring method |
| CN110475510B (en) * | 2017-03-27 | 2022-08-02 | 韩国斯诺有限公司 | Method and device for acquiring shape information of object |
| CN110475510A (en) * | 2017-03-27 | 2019-11-19 | 韩国斯诺有限公司 | Obtain the method and device of the shape information of object |
| CN107169262B (en) * | 2017-03-31 | 2021-11-23 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and computer storage medium for recommending body shaping scheme |
| CN107169262A (en) * | 2017-03-31 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Recommend method, device, equipment and the computer-readable storage medium of body shaping scheme |
| CN107192342A (en) * | 2017-05-11 | 2017-09-22 | 广州帕克西软件开发有限公司 | A kind of measuring method and system of contactless build data |
| WO2019052318A1 (en) * | 2017-09-13 | 2019-03-21 | 杭州海康威视数字技术股份有限公司 | Method, apparatus and system for monitoring elevator car |
| CN107590830A (en) * | 2017-09-21 | 2018-01-16 | 北京小米移动软件有限公司 | Method for determining height, device and storage medium based on image |
| CN108209925A (en) * | 2017-12-28 | 2018-06-29 | 北京安云世纪科技有限公司 | A kind of measuring method of Human Height, device and mobile terminal |
| CN108444584A (en) * | 2018-04-13 | 2018-08-24 | 山东华宇工学院 | A kind of intelligence height and weight measuring system and method |
| CN108663957A (en) * | 2018-04-23 | 2018-10-16 | 靳霞 | The anti-control method bottomed out of swing based on image recognition |
| CN108786119A (en) * | 2018-04-23 | 2018-11-13 | 靳霞 | Swing based on image recognition is anti-to bottom out control platform |
| CN108921929A (en) * | 2018-06-26 | 2018-11-30 | 开放智能机器（上海）有限公司 | A kind of recognition methods of identifying system and training method and individual monocular image |
| CN110443154B (en) * | 2019-07-15 | 2022-06-03 | 北京达佳互联信息技术有限公司 | Three-dimensional coordinate positioning method and device of key point, electronic equipment and storage medium |
| CN110443154A (en) * | 2019-07-15 | 2019-11-12 | 北京达佳互联信息技术有限公司 | Three-dimensional coordinate localization method, device, electronic equipment and the storage medium of key point |
| CN114375177A (en) * | 2019-09-01 | 2022-04-19 | Lg电子株式会社 | Body measurement device and control method thereof |
| CN110672016A (en) * | 2019-09-12 | 2020-01-10 | 四川农业大学 | Cattle body size measuring system and method based on image recognition |
| CN110604574A (en) * | 2019-09-16 | 2019-12-24 | 河北微幼趣教育科技有限公司 | Human body height measuring method based on video imaging principle |
| CN110874572A (en) * | 2019-10-29 | 2020-03-10 | 北京海益同展信息科技有限公司 | Information detection method and device and storage medium |
| CN111664795A (en) * | 2020-05-22 | 2020-09-15 | 维沃移动通信有限公司 | Height measuring method and device and electronic equipment |
| WO2022012019A1 (en) * | 2020-07-15 | 2022-01-20 | 华为技术有限公司 | Height measuring method, height measuring device, and terminal |
| CN112363626A (en) * | 2020-11-25 | 2021-02-12 | 广州魅视电子科技有限公司 | Large screen interaction control method based on human body posture and gesture posture visual recognition |
| WO2022216973A1 (en) * | 2021-04-08 | 2022-10-13 | Universal City Studios Llc | Guest measurement systems and methods |
| CN114005199A (en) * | 2021-10-26 | 2022-02-01 | 珠海格力电器股份有限公司 | Door lock control method and device, electronic equipment and storage medium |
| CN114625048A (en) * | 2022-03-16 | 2022-06-14 | 江阴市晶磁电子有限公司 | Space adjustment management control system and method |
| CN117078735A (en) * | 2023-08-14 | 2023-11-17 | 广州广电运通智能科技有限公司 | Height detection method, system, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102657532B (en) | 2014-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102657532B (en) | Height measuring method and device based on body posture identification | |
| JP5618569B2 (en) | Position and orientation estimation apparatus and method | |
| KR101519940B1 (en) | Three-dimensional object modelling fitting & tracking | |
| CN108717531B (en) | Human body posture estimation method based on Faster R-CNN | |
| JP6507046B2 (en) | Three-dimensional object detection device and three-dimensional object authentication device | |
| JP3560670B2 (en) | Adaptive recognition system | |
| US10466797B2 (en) | Pointing interaction method, apparatus, and system | |
| CN109102547A (en) | Robot based on object identification deep learning model grabs position and orientation estimation method | |
| CN104200200B (en) | Fusion depth information and half-tone information realize the system and method for Gait Recognition | |
| CN106952335B (en) | Method and system for establishing human body model library | |
| JP2019096113A (en) | Processing device, method and program relating to keypoint data | |
| CN108628306B (en) | Robot walking obstacle detection method and device, computer equipment and storage medium | |
| CN111652047B (en) | Human body gesture recognition method based on color image and depth image and storage medium | |
| CN105740781A (en) | Three-dimensional human face in-vivo detection method and device | |
| CN102833486A (en) | Method and device for real-time adjusting face display scale in video image | |
| CN106529399A (en) | Human body information acquisition method, device and system | |
| CN105760809A (en) | Method and apparatus for head pose estimation | |
| CN109636779A (en) | Identify the method, apparatus and storage medium of poultry volume ruler | |
| CN112016497A (en) | Single-view Taijiquan action analysis and assessment system based on artificial intelligence | |
| CN105335699B (en) | Read-write scene is read and write intelligent identification and the application thereof of element three-dimensional coordinate | |
| CN106933976B (en) | Method for establishing human body 3D net model and application thereof in 3D fitting | |
| JP2011113398A (en) | Attitude estimation device | |
| CN106296797A (en) | A kind of spatial digitizer characteristic point modeling data processing method | |
| CN108388854A (en) | A kind of localization method based on improvement FAST-SURF algorithms | |
| CN111241936A (en) | Human body posture estimation method based on depth and color image feature fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C56 | Change in the name or address of the patentee | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 518054, Guangdong Shenzhen hi tech Industrial Park, South District, Fangda building, 4 floor, Shenzhen Taishan Online Technology Co., Ltd. Patentee after: SHENZHEN TAISHAN SPORTS TECHNOLOGY CORP., LTD. Address before: 518054, Guangdong Shenzhen hi tech Industrial Park, South District, Fangda building, 4 floor, Shenzhen Taishan Online Technology Co., Ltd. Patentee before: Shenzhen Tol Technology Co., Ltd. |
|
| CP01 | Change in the name or title of a patent holder |
Address after: 518054 Shenzhen Taishan Online Technology Co., Ltd Patentee after: Shenzhen Taishan Sports Technology Co.,Ltd. Address before: 518054 Shenzhen Taishan Online Technology Co., Ltd Patentee before: SHENZHEN TAISHAN SPORTS TECHNOLOGY Corp.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |