CN104173054B - Measuring method and measuring device for height of human body based on binocular vision technique - Google Patents
Measuring method and measuring device for height of human body based on binocular vision technique Download PDFInfo
- Publication number
- CN104173054B CN104173054B CN201310192474.6A CN201310192474A CN104173054B CN 104173054 B CN104173054 B CN 104173054B CN 201310192474 A CN201310192474 A CN 201310192474A CN 104173054 B CN104173054 B CN 104173054B
- Authority
- CN
- China
- Prior art keywords
- people
- cusp
- height
- camera
- binocular
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of computer vision and discloses a measuring method and a measuring device for the height of a human body based on a binocular vision technique. According to the measuring method and the measuring device disclosed by the invention, the height of a human body target is measured by acquiring image coordinates of a human head sharp point of the human body target in a scene image shot by a binocular camera and depth information corresponding to the image coordinates and calculating world coordinates of the human head sharp point under a coordinate system of the camera. According to the measuring method and the measuring device, the requirement on the compatibility of a measured person is low, and the height measurement can be finished by a mode that the person stands within the measurable range for shooting by the camera; the body heights of multiple persons in the scene can be simultaneously measured; in addition, the measurement precision is higher.
Description
Technical field
The present invention relates to technical field of computer vision, more particularly to a kind of Human Height survey based on binocular vision technology
Amount technology.
Background technology
Computer vision is one kind simulation for using computer and relevant device to biological vision.Its main task is exactly
Processed to obtain the three-dimensional information of corresponding scene by the picture or video to gathering, just as the mankind and many other classes are given birth to
As thing is done daily.
Binocular vision technology, is a kind of important form of computer vision, and it is based on principle of parallax and utilizes diverse location
Two cameras Same Scene is shot, by binocular calibration and matching technique, obtain the three-dimensional information of target in scene.
Binocular calibration, refers to according to camera model, the relation set up between camera review location of pixels and scene point location, by
The image coordinate and world coordinates for knowing characteristic point solves the model parameter of binocular camera, and calibrating parameters are joined for the inside of binocular camera
Number and external parameter.The inner parameter of binocular camera mainly includes that lens focus, distortion coefficients of camera lens, picture dot size and principal point are sat
Mark, external parameter includes the spin matrix and translation vector of camera, and binocular camera setting height(from bottom), the camera angle of pitch and inclination
Angle.Binocular ranging refers to the alignment of the impact point set up under same scene two width projected image impact points under different visual angles.It is double
Mesh vision measuring method has that efficiency high, precision are suitable, system architecture is simple, low cost and other advantages, is very suitable for manufacture existing
The online of field, noncontact Product checking and quality control.Because image is obtained completed in moment in moving object measurement
, therefore, binocular vision method is a kind of more effective measuring method.
It was found by the inventors of the present invention that existing Human Height measurement is all confined to the contact type measurement with equipment, and need
The accurate measurement Human Height of cooperation ability of itself, the such as measurement of slide calliper rule formula and ultrasonic sensing instrument for measuring height is wanted to be required to
Human body station just can complete on the platform that equipment is specified, and can only measure one by one.
The content of the invention
It is an object of the invention to provide a kind of Human Height measuring method and its device based on binocular vision technology, can
To complete the measurement of the height of multiple human body targets in measurable range in the case where coordinating without the need for personnel.
To solve above-mentioned technical problem, embodiments of the present invention disclose a kind of human body body based on binocular vision technology
High measurement method, comprises the following steps:
Using binocular camera photographed scene image, the image coordinate of the number of people cusp of human body target in scene image is obtained;
The corresponding depth information of number of people cusp that binocular camera is generated is obtained according to the image coordinate of number of people cusp;
Calculate world coordinates of the number of people cusp under camera coordinate system;
According to the world coordinates of number of people cusp, and the angle of pitch, the inclination angle of binocular camera, measure the height of human body target.
Embodiments of the present invention also disclose a kind of Human Height measurement apparatus based on binocular vision technology, including:
Image coordinate acquiring unit, for the number of people cusp for obtaining human body target in the scene image that shoots from binocular camera
Image coordinate;
Depth Information Acquistion unit, the image coordinate of the number of people cusp for obtaining according to image coordinate acquiring unit is obtained
The corresponding depth information of number of people cusp that binocular camera is generated;
World coordinates computing unit, for according to the image coordinate and depth of the number of people cusp of image coordinate acquiring unit acquisition
The corresponding depth information of number of people cusp that degree information acquisition unit is obtained calculates the world of the number of people cusp under camera coordinate system
Coordinate;
Height measuring unit, for the number of people cusp that calculates according to the world coordinates computing unit in camera coordinates
World coordinates under system, and the angle of pitch, the inclination angle of binocular camera, measure the height of human body target.
Compared with prior art, the main distinction and its effect are embodiment of the present invention:
Human Height based on binocular vision technology is measured, and the method coordinates without the need for personnel, need to only stand what is shot to camera
Just height measurement can be completed in measurable range, the height of multiple human body targets can be simultaneously measured, and certainty of measurement is higher.
The demarcation of setting height(from bottom) and attitude angle parameter further, to binocular camera, can improve height measurement
Precision, effective compensation measure error.
Further, the angle of pitch of binocular camera and inclination angle are difficult to be measured by instrument, multiple known high using arranging
The method of scale fixed point can just estimate the angle of pitch and the inclination angle of camera, and precision is higher.
Description of the drawings
Fig. 1 is a kind of flow process of the Human Height measuring method based on binocular vision technology in first embodiment of the invention
Schematic diagram;
Fig. 2 is a kind of structure of the Human Height measurement apparatus based on binocular vision technology in second embodiment of the invention
Schematic diagram;
Fig. 3 is a kind of flow process of the Human Height measuring method based on binocular vision technology in third embodiment of the invention
Schematic diagram;
Fig. 4 is a kind of binocular of the Human Height measuring method based on binocular vision technology in third embodiment of the invention
The schematic flow sheet of the demarcating steps of camera setting height(from bottom) and setting angle;
Fig. 5 is the schematic diagram that a kind of binocular camera measures Human Height in third embodiment of the invention.
Specific embodiment
In the following description, in order that reader more fully understands the application and proposes many ins and outs.But, this
Even if the those of ordinary skill in field is appreciated that many variations without these ins and outs and based on following embodiment
And modification, it is also possible to realize each claim of the application technical scheme required for protection.
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with enforcement of the accompanying drawing to the present invention
Mode is described in further detail.
First embodiment of the invention is related to a kind of Human Height measuring method based on binocular vision technology.Fig. 1 is this
Schematic flow sheet based on the Human Height measuring method of binocular vision technology.
As shown in figure 1, the Human Height measuring method that should be based on binocular vision technology is comprised the following steps:
In a step 101, using binocular camera photographed scene image, the number of people cusp of human body target in scene image is obtained
Image coordinate.
Before implementation steps 101, the setting height(from bottom) of binocular camera and setting angle should be demarcated, setting angle bag
Include the angle of pitch and the inclination angle of binocular camera.
Specifically, in the step of demarcating to the setting height(from bottom) and setting angle of binocular camera, including following sub-step
Suddenly:
By the use of rule measure scene ground to camera vertical range as binocular camera setting height(from bottom).
The image of target multiple location points in the scene of known altitude is captured using binocular camera.
Obtain the depth information that binocular camera captures multigroup diverse location point target of image.
Construction minimization problem, solves the angle of pitch and the inclination angle of one group of binocular camera, makes utilization to be based on binocular vision
The object height and the variance of the actual height of target that the Human Height measuring method of technology is tried to achieve is minimum, finally gives one group most
The angle of pitch and inclination angle of the excellent binocular camera angle of pitch and inclination angle as binocular camera.
The demarcation of setting height(from bottom) and angle parameter to binocular camera, can improve the precision of height measurement, effective compensation
Measure error.The angle of pitch of camera and inclination angle are difficult to be measured by instrument, using the side for arranging multiple known altitude calibration points
Method can just estimate the angle of pitch and the inclination angle of camera, and precision is higher.
It should be noted that in each method embodiment of the present invention, the setting height(from bottom) and established angle to binocular camera
The carrying out of degree only need to be performed once the step of demarcate, to obtain the setting height(from bottom) and setting angle of the binocular camera of optimum, with
Need not repeat in measurement afterwards and be demarcated.
Furthermore, it is to be understood that in some other embodiments of the present invention, it is also possible to take other demarcation modes,
And be not limited.
Further, obtain scene image in human body target number of people cusp image coordinate the step of in, including with
Lower sub-step:
The scene image for shooting is detected using the good number of people detector of training in advance;
Obtain the number of people area data in number of people detection block region;
Calculate the gradient map of number of people area data;
On the basis of the gradient map of number of people area data, outline point is extracted, found and outline point using circle fitting
The best circle of degree of fitting is used as number of people point circular arc;
Peak using number of people point circular arc determines the image coordinate of the number of people cusp as the position of number of people cusp.
Furthermore, it is to be understood that in some other embodiments of the present invention, it is also possible to obtain field by another way
The image coordinate of the number of people cusp of human body target in scape image, and be not limited in the method mentioned in present embodiment.
Then into step 102, the number of people cusp pair that binocular camera is generated is obtained according to the image coordinate of the number of people cusp
The depth information answered.
Then into step 103, world coordinates of the number of people cusp under camera coordinate system is calculated.
It is using the number of people cusp correspondence in the step of calculating world coordinates of the number of people cusp under camera coordinate system
Depth information, with reference to the internal and external parameter of binocular camera, calculate world coordinates of the number of people cusp under camera coordinate system, meter
Calculate formula as follows:
In formula, XleftFor number of people cusp in left image and image center deviation, XrightIt is number of people cusp in right figure
As the deviation of neutralization image center;Y is longitudinal coordinate of the number of people cusp in left image, and impact point is in two images of left and right
Longitudinal coordinate is identical;F is the lens focus of binocular camera;B is the base length of binocular camera;P(xc, yc, zc) exist for number of people cusp
World coordinates under camera coordinate system.
Then into step 104, according to the world coordinates of number of people cusp, and the angle of pitch, the inclination angle of binocular camera, measurement
The height of human body target.
Preferably, measure equation is:In formula
θ is the angle of pitch of binocular camera,For inclination angle;HcamFor the setting height(from bottom) of binocular camera, HstaFor the height of human body target, P
(xc, yc, zc) it is world coordinates of the number of people cusp under camera coordinate system.
In addition, measure equation can also be: θ is the angle of pitch of binocular camera in formula,For inclination angle;HcamFor the setting height(from bottom) of binocular camera, HstaFor human body
The height of target, P (xc, yc, zc) it is world coordinates of the number of people cusp under camera coordinate system.
Furthermore, it is to be understood that measure equation includes but is not limited to the two in the present invention.
Hereafter process ends.
Human Height based on binocular vision technology is measured, and the method coordinates without the need for personnel, need to only stand what is shot to camera
Just height measurement can be completed in measurable range, the height of multiple human body targets can be simultaneously measured, and certainty of measurement is higher.
The each method embodiment of the present invention can be realized in modes such as software, hardware, firmwares.No matter the present invention be with
Software, hardware or firmware mode realize that instruction code may be stored in the addressable memory of any kind of computer
In (such as it is permanent or revisable, it is volatibility or non-volatile, it is solid-state or non-solid, it is fixed or
Removable medium of person etc.).Equally, memory may, for example, be programmable logic array (Programmable Array
Logic, referred to as " PAL "), random access memory (Random Access Memory, referred to as " RAM "), programmable read-only deposit
Reservoir (Programmable Read Only Memory, referred to as " PROM "), read-only storage (Read-Only Memory, letter
Claim " ROM "), Electrically Erasable Read Only Memory (Electrically Erasable Programmable ROM, referred to as
" EEPROM "), disk, CD, digital versatile disc (Digital Versatile Disc, referred to as " DVD ") etc..
Second embodiment of the invention is related to a kind of Human Height measurement apparatus based on binocular vision technology.Fig. 2 is this
Structural representation based on the Human Height measurement apparatus of binocular vision technology.
As shown in Fig. 2 the Human Height measurement apparatus of binocular vision technology should be based on including:
Image coordinate acquiring unit, for the number of people for obtaining human body target from the scene image of binocular camera captured in real-time
The image coordinate of cusp.
Specifically, the image coordinate acquiring unit further includes following subelement:
Image detection subelement, is detected using the good number of people detector of training in advance to the scene image for shooting.
Data acquisition subelement, for obtaining the number of people number of regions in the number of people detection block region of image detection subelement output
According to.
Gradient map computation subunit, for calculating the gradient map of the number of people area data of data acquisition subelement output.
Number of people point circular fitting unit, the gradient map base of the number of people area data for exporting in gradient map computation subunit
Outline point is extracted on plinth, and is found with the best circle of outline point degree of fitting as number of people point circular arc by the use of circle fitting.
Image coordinate determination subelement, for being made with the peak of the number of people point circular arc of number of people point circular fitting unit output
For the final position of number of people cusp, and determine the image coordinate of number of people cusp.
Furthermore, it is to be understood that in some other embodiments of the present invention, it is also possible to by number of people cusp image coordinate
The other structures mode of acquiring unit obtains the image coordinate of the number of people cusp of human body target in scene image.
Depth Information Acquistion unit, the image coordinate of the number of people cusp for obtaining according to above-mentioned image coordinate acquiring unit
Obtain the corresponding depth information of number of people cusp that binocular camera is generated.
World coordinates computing unit, for the image coordinate of number of people cusp that obtains according to the image coordinate acquiring unit and
The corresponding depth information of number of people cusp and the internal and external parameter of other binocular cameras that the Depth Information Acquistion unit is obtained, meter
Calculate world coordinates of the number of people cusp under camera coordinate system.Computing formula is as follows:
In formula, XleftFor number of people cusp in left image and image center deviation, XrightIt is number of people cusp in right figure
As the deviation of neutralization image center;Y is longitudinal coordinate of the number of people cusp in left image, and impact point is in two images of left and right
Longitudinal coordinate is identical;F is the lens focus of binocular camera;B is the base length of binocular camera;P(xc, yc, zc) exist for number of people cusp
World coordinates under camera coordinate system.
Height measuring unit, for the number of people cusp that calculates according to the world coordinates computing unit in camera coordinates
World coordinates under system, and the angle of pitch, the inclination angle of binocular camera, measure the height of human body target.
Preferably, the height measuring unit measure human body target height when, the measure equation for being utilized include with
Lower two:
Measure equation one is:θ is double in formula
The angle of pitch of mesh camera,For inclination angle;HcamFor the setting height(from bottom) of binocular camera, HstaFor the height of human body target, P (xc, yc,
zc) it is world coordinates of the number of people cusp under camera coordinate system.
Measure equation two is:
θ is the angle of pitch of binocular camera in formula,For inclination angle;HcamFor the setting height(from bottom) of binocular camera, HstaFor the body of human body target
Height, P (xc, yc, zc) it is world coordinates of the number of people cusp under camera coordinate system.
Additionally, also include, binocular calibration unit, for demarcating the setting height(from bottom) and setting angle of binocular camera, established angle
Degree includes the angle of pitch and the inclination angle of binocular camera.
Further, the binocular calibration unit, including following subelement:
Subelement is highly demarcated, for the setting height(from bottom) of calibration for cameras;
Angle calibration subelement, for the setting angle of calibration for cameras;
Highly demarcate subelement, by the use of rule measure scene ground to camera vertical range as binocular camera peace
Dress height;
Angle calibration subelement, the figure of target multiple location points in the scene of known altitude is captured using binocular camera
Picture.Obtain the depth information that binocular camera captures multigroup diverse location point target of image.Construction minimization problem, solves one group
The angle of pitch of binocular camera and inclination angle, make the target tried to achieve based on the Human Height measuring method of binocular vision technology using this
The variance of the actual height of height and target is minimum, finally gives one group of optimum binocular camera angle of pitch and tilt values.
It should be noted that in each method embodiment of the present invention, the binocular calibration unit of binocular camera is only the
Height is demarcated when measuring, to obtain the setting height(from bottom) and setting angle of the binocular camera of optimum, measurement afterwards
In the unit be not repeated to be demarcated.
Furthermore, it is to be understood that in some other embodiments of the present invention, it is also possible to take other demarcation units,
And be not limited.
The Human Height measurement apparatus of binocular vision technology should be based on, be coordinated without the need for personnel, and need to only stand what is shot to camera
Just height measurement can be completed in measurable range, the height of multiple human body targets can be simultaneously measured, and certainty of measurement is higher.
First embodiment is the method embodiment corresponding with present embodiment, and present embodiment can be implemented with first
Mode is worked in coordination enforcement.The relevant technical details mentioned in first embodiment are still effective in the present embodiment, in order to
Reduce and repeat, repeat no more here.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in the first enforcement
In mode.
Third embodiment of the invention is related to a kind of Human Height measuring method based on binocular vision technology.Fig. 3 is this
Schematic flow sheet based on the Human Height measuring method of binocular vision technology.
Present embodiment, by captured in real-time scene image, obtains the generation of scene objects point using binocular camera as hardware
Boundary's coordinate;Setting height(from bottom) and attitude angle information by processing unit by the world coordinates for getting with reference to binocular camera is carried out
Analytical calculation, completes the accurate measurement of Human Height.
As shown in figure 3, the Human Height measuring method that should be based on binocular vision technology is comprised the following steps:
In step 301, the inner parameter and external parameter of binocular camera are demarcated.In the inner parameter for demarcating binocular camera
And in the step of external parameter, including following sub-step:
The installation site and angle of binocular camera are determined according to monitoring distance and monitoring height;
Because binocular camera typically adopts tight shot, it is therefore desirable to determine binocular phase according to monitoring distance and monitoring height
The type selecting of machine, installation site and setting angle, to ensure that the target head part of monitor area middle position separates present image
Center.
By the higher Zhang Zhengyou scaling method calibration for cameras spin matrixs of stated accuracy and translation vector, wherein scaling board
Choose chessboard calibration plate or with the certain scaling board of other shapes spacing.
Camera spin matrix and translation vector in the inner parameter and external parameter of binocular camera can pass through Zhang Zhengyou
Scaling method completes to demarcate, and stated accuracy is higher, and wherein scaling board chooses chessboard calibration plate or certain with other shapes spacing
Scaling board.
Demarcating the setting height(from bottom) and setting angle of binocular camera is carried out, and wherein setting angle includes the angle of pitch of binocular camera
And inclination angle;
Remaining parameter is mainly the parameter after binocular camera is installed, by the setting height(from bottom) of binocular camera, the pitching of camera
Angle and inclination angle constitute, and because this group of parameter affects larger to binocular height certainty of measurement, therefore need strict demarcation.
The setting height(from bottom) of camera can be difficult by instrument by rule accurate measuring, the angle of pitch of camera and inclination angle
Measure, therefore a kind of method that can be estimated the camera angle of pitch and incline angular dimensions is realized in present embodiment.Fig. 4 is this pair
The schematic flow sheet of mesh camera part parameter calibration, including following sub-step:
In step 401, camera is arrived on the ground for measuring camera local environment using rule when binocular camera is installed
Setting height(from bottom) of the vertical range as binocular camera;
Then into step 402, the target or people using known altitude, with binocular camera its multiple position in the scene is captured
Put image a little;
Then into step 403, the depth information that binocular camera captures multigroup diverse location point target of image is obtained;
Then into step 404, minimization problem is constructed, solve pitching angle theta and the inclination angle of one group of binocular cameraMake
The variance of the height of the target tried to achieve using binocular and the actual height of target is minimum, finally gives one group of optimum binocular camera
The angle of pitch and tilt values.
The setting height(from bottom) of binocular camera needs to be measured using rule when installing, and it is highly the ground of the environment
To the vertical range of camera;Target or people using known altitude, with binocular camera its multiple location point in the scene is captured
Image.Obtain the depth information that binocular camera captures multigroup diverse location point target of image;Construction minimization problem, solves one
The pitching angle theta of group binocular camera and inclination angleMake the variance of the actual height of the height and target of target tried to achieve using binocular
Minimum, finally gives one group of optimum binocular camera angle of pitch and tilt values.
Then into step 302, scene objects depth data is obtained.
The depth data of binocular camera is expressed as parallax data, is internally generated by binocular camera.
Then into step 303, the image coordinate I (x of number of people cusp in scene image is searchedi, yi), searching the number of people
In the step of image coordinate of cusp, including following sub-step:
The scene image for shooting is detected using number of people detector has been trained;
Obtain the number of people data in number of people detection block region;Calculate the gradient map of number of people area data;
On the basis of number of people region gradient figure, outline point is extracted, found and outline point degree of fitting using circle fitting
Best circle is used as number of people point circular arc;
Using the peak of circular arc as the final position of number of people cusp, the final image coordinate I (x for determining number of people cuspi,
yi)。
Furthermore, it is to be understood that in some other embodiments of the present invention, it is also possible to obtain field by another way
The image coordinate of the number of people cusp of human body target in scape image.
Then into step 304, the world coordinates of number of people cusp is calculated.
According to the number of people position of cusp coordinate I (x got in step 303i, yi) and binocular camera generate scene depth
Figure determines the corresponding parallax information of number of people cusp, and with reference to the internal and external parameter of binocular camera, completes number of people cusp world coordinates P
(xc, yc, zc) calculating.
The corresponding depth information of number of people cusp that generates according to the number of people cusp image coordinate and above-mentioned binocular camera and
Other internal and external parameters of binocular camera, complete number of people cusp world coordinates P (xc, yc, zc) calculating, computing formula is as follows:
In formula, XleftFor number of people cusp in left image and image center deviation, XrightIt is number of people cusp in right figure
As the deviation of neutralization image center;Y is longitudinal coordinate of the number of people cusp in left image, and impact point is in two images of left and right
Longitudinal coordinate is identical;F is the lens focus of binocular camera;B is the base length of binocular camera;P(xc, yc, zc) exist for number of people cusp
World coordinates under camera coordinate system.
Then into step 305, Human Height measurement.
Fig. 5 is the schematic diagram that a kind of binocular camera measures Human Height in present embodiment.
When monitor area of the target by binocular camera, binocular camera is captured to target automatically, gets target
Head cusp information, complete to measure the height of human body target using height computing formula.
In this application, two kinds of binocular cameras are enumerated and measures the measure equation of Human Height, but be not limited.
The first Human Height measure equation is as follows:
θ is the pitching of binocular camera in formula
Angle,For inclination angle;HcamFor the setting height(from bottom) of binocular camera, HstaFor the height of human body target, P (xc, yc, zc) it is number of people point
World coordinates of the point under camera coordinate system.
The first formula is the computational methods carried out by geometrical relationship.
Second Human Height measure equation be:
World coordinates of the number of people cusp under camera coordinate system is transformed into into ground level coordinate system.
The point on ground level is set as the origin of world coordinate system, the point in camera coordinate system is passed through into Euler's angle formula
Under being transformed into the coordinate system of ground level, then the Y value of the target three-dimensional point after changing is the actual height of target.
The present invention is set to the origin of world coordinate system with the origin of camera coordinate system in the subpoint of ground level, sets up and sits
Marking the transformational relation after system is:
(X, Y, Z) is the point under world coordinate system, (x in formulac, yc, zc) for the point under camera coordinate system, the reality of target
Border is highly Y, and expression formula is:
In formula, Y is equal to HstaFor the height of human body target, θ is the angle of pitch of binocular camera,For inclination angle, HcamFor double
The setting height(from bottom) of mesh camera, P (xc, yc, zc) it is world coordinates of the number of people cusp under camera coordinate system.
Due toBe worth in actual applications it is less, therefore by above formulaApproximate processing is 1, can obtain following formula:
Hereafter process ends.
All of the embodiments of the present invention completes effective measurement of Human Height, should be based on the human body of binocular vision technology
Height measurement method is different from traditional height measurement methods such as the measurement of slide calliper rule formula and ultrasonic measurement, and the present invention is based on binocular
The Human Height measurement that stereovision technique is carried out, it is desirable to which measured personnel's fitness is low, can simultaneously measure the height of many people, and
Certainty of measurement is higher.
All of the embodiments of the present invention may be incorporated for public and particular place face bayonet socket, using height as personnel
One adeditive attribute of target, for criminal investigation or demographic data statistical analysis;It is used to the higher advertisement of specific aim in market throw
Put, such as intelligent dressing is carried out according to personnel's height.
It should be noted that each unit mentioned in each equipment embodiment of the invention is all logical block, physically,
One logical block can be a part for a physical location, or a physical location, can be with multiple physics
The combination of unit realizes, these logical blocks Physical realizations of itself is not most important, and these logical blocks institutes are real
The combination of existing function is only the key of the technical problem for solving proposed by the invention.Additionally, the innovation in order to project the present invention
Part, the above-mentioned each equipment embodiment of the present invention is not less close by the technical problem relation proposed by the invention with solution
Unit introduce, this is not intended that the said equipment embodiment does not have other units.
It should be noted that in the claim and specification of this patent, such as first and second or the like relation
Term is used merely to make a distinction an entity or operation with another entity or operation, and not necessarily requires or imply
There is any this actual relation or order between these entities or operation.And, term " including ", "comprising" or its
Any other variant is intended to including for nonexcludability so that process, method, article including a series of key elements or
Equipment not only includes those key elements, but also including other key elements being not expressly set out, or also include for this process,
The intrinsic key element of method, article or equipment.In the absence of more restrictions, by wanting that sentence " including " is limited
Element, it is not excluded that also there is other identical element in the process including the key element, method, article or equipment.
Although by referring to some of the preferred embodiment of the invention, being shown and described to the present invention,
It will be understood by those skilled in the art that can in the form and details to it, various changes can be made, without departing from this
Bright spirit and scope.
Claims (14)
1. a kind of Human Height measuring method based on binocular vision technology, it is characterised in that comprise the following steps:
Using binocular camera photographed scene image, the image coordinate of the number of people cusp of human body target in scene image is obtained;
The corresponding depth information of number of people cusp that binocular camera is generated is obtained according to the image coordinate of number of people cusp;
Using the corresponding image coordinate of the number of people cusp and depth information, seat of the number of people cusp under camera coordinate system is calculated
Mark;
According to coordinate of the number of people cusp under camera coordinate system, and setting height(from bottom), the angle of pitch, the inclination of binocular camera
Angle, measures the height of human body target.
2. the Human Height measuring method based on binocular vision technology according to claim 1, it is characterised in that in the basis
Coordinate of the number of people cusp under camera coordinate system, and setting height(from bottom), the angle of pitch, the inclination angle of binocular camera, measure human body
In the step of height of target, measure equation is:
θ is the angle of pitch of binocular camera in formula,For inclination angle;HcamFor the setting height(from bottom) of binocular camera, HstaFor the body of human body target
Height, P (xc,yc,zc) it is coordinate of the number of people cusp under camera coordinate system.
3. the Human Height measuring method based on binocular vision technology according to claim 1, it is characterised in that in the basis
Coordinate of the number of people cusp under camera coordinate system, and setting height(from bottom), the angle of pitch, the inclination angle of binocular camera, measure human body mesh
In the step of target height, measure equation is:
θ is the angle of pitch of binocular camera in formula,For inclination angle;HcamFor the setting height(from bottom) of binocular camera, HstaFor the body of human body target
Height, P (xc,yc,zc) it is coordinate of the number of people cusp under camera coordinate system.
4. the Human Height measuring method based on binocular vision technology according to any one of claim 1 to 3, its feature
Be, the step of the utilization binocular camera photographed scene image before, it is further comprising the steps of:
The setting height(from bottom) and setting angle of binocular camera are demarcated, setting angle includes the angle of pitch of binocular camera and inclination
Angle.
5. the Human Height measuring method based on binocular vision technology according to claim 4, it is characterised in that described
In the step of demarcating to the setting height(from bottom) and setting angle of binocular camera, including following sub-step:
By the use of rule measure scene ground to camera vertical range as binocular camera setting height(from bottom);
The image of target multiple location points in the scene of known altitude is captured using binocular camera;
Obtain the depth information that binocular camera captures multigroup diverse location point target of image;
Construction minimization problem, solves the angle of pitch and the inclination angle of one group of binocular camera, makes utilization to be based on binocular vision technology
The object height tried to achieve of Human Height measuring method and target actual height variance it is minimum, finally give one group it is optimum
The angle of pitch and inclination angle of the binocular camera angle of pitch and inclination angle as binocular camera.
6. the Human Height measuring method based on binocular vision technology according to claim 5, it is characterised in that described
In the step of obtaining the image coordinate of the number of people cusp of human body target in scene image, including following sub-step:
The scene image for shooting is detected using the good number of people detector of training in advance;
Obtain the number of people area data in number of people detection block region;
Calculate the gradient map of number of people area data;
On the basis of the gradient map of number of people area data, outline point is extracted, found using circle fitting and the fitting of outline point
The best circle of degree is used as number of people point circular arc;
Peak using number of people point circular arc determines the image coordinate of the number of people cusp as the position of number of people cusp.
7. the Human Height measuring method based on binocular vision technology according to claim 6, it is characterised in that described
It is to utilize the corresponding depth information of the number of people cusp in the step of calculating coordinate of the number of people cusp under camera coordinate system,
With reference to the internal and external parameter of binocular camera, coordinate of the number of people cusp under camera coordinate system is calculated, computing formula is as follows:
In formula, XleftFor number of people cusp in left image and image center deviation, XrightIt is number of people cusp in right image
With the deviation of image center;Y be longitudinal coordinate of the number of people cusp in left image, impact point left and right two images in longitudinal direction
Coordinate is identical;F is the lens focus of binocular camera;B is the base length of binocular camera;P(xc,yc,zc) taking the photograph for number of people cusp
Coordinate under camera coordinate system.
8. a kind of Human Height measurement apparatus based on binocular vision technology, it is characterised in that include:
Image coordinate acquiring unit, the figure of the number of people cusp for obtaining human body target in the scene image that shoots from binocular camera
As coordinate;
Depth Information Acquistion unit, the image coordinate of the number of people cusp for obtaining according to described image coordinate acquiring unit is obtained
The corresponding depth information of number of people cusp that binocular camera is generated;
Coordinate calculating unit, for according to the image coordinate of the number of people cusp of described image coordinate acquiring unit acquisition and depth letter
The corresponding depth information of number of people cusp that breath acquiring unit is obtained calculates coordinate of the number of people cusp under camera coordinate system;
Height measuring unit, the seat for the number of people cusp that calculates according to the coordinate calculating unit under camera coordinate system
Mark, and setting height(from bottom), the angle of pitch, the inclination angle of binocular camera, measure the height of human body target.
9. Human Height measurement apparatus based on binocular vision technology according to claim 8, it is characterised in that the body
The measure equation of high measurement unit is: θ is in formula
The angle of pitch of binocular camera,For inclination angle;HcamFor the setting height(from bottom) of binocular camera, HstaFor the height of human body target, P (xc,
yc,zc) it is coordinate of the number of people cusp under camera coordinate system.
10. Human Height measurement apparatus based on binocular vision technology according to claim 8, it is characterised in that the height
The measure equation of measuring unit is:
θ is the angle of pitch of binocular camera in formula,For inclination angle;HcamFor the setting height(from bottom) of binocular camera, HstaFor the body of human body target
Height, P (xc,yc,zc) it is coordinate of the number of people cusp under camera coordinate system.
The 11. Human Height measurement apparatus based on binocular vision technology according to any one of claim 8 to 10, it is special
Levy and be, also include:
Binocular calibration unit, for demarcating the setting height(from bottom) and setting angle of binocular camera, setting angle includes binocular camera
The angle of pitch and inclination angle.
The 12. Human Height measurement apparatus based on binocular vision technology according to claim 11, it is characterised in that described
Binocular calibration unit includes following subelement:
Subelement is highly demarcated, for the setting height(from bottom) of calibration for cameras;
Angle calibration subelement, for the setting angle of calibration for cameras, setting angle includes the angle of pitch of binocular camera and inclination
Angle;
The height demarcates subelement, by the use of rule measure scene ground to camera vertical range as binocular camera peace
Dress height;
The angle calibration subelement, the figure of target multiple location points in the scene of known altitude is captured using binocular camera
Picture;Obtain the depth information that binocular camera captures multigroup diverse location point target of image;Construction minimization problem, solves one group
The angle of pitch of binocular camera and inclination angle, make the target tried to achieve based on the Human Height measuring method of binocular vision technology using this
The variance of the actual height of height and target is minimum, finally gives one group of optimum binocular camera angle of pitch and tilt values.
The 13. Human Height measurement apparatus based on binocular vision technology according to claim 12, it is characterised in that described
Image coordinate acquiring unit includes following subelement:
Image detection subelement, is detected using the good number of people detector of training in advance to the scene image for shooting;
Data acquisition subelement, for obtaining the number of people number of regions in the number of people detection block region of described image detection sub-unit output
According to;
Gradient map computation subunit, for calculating the gradient map of the number of people area data of the data acquisition subelement output;
Number of people point circular fitting unit, the gradient map base of the number of people area data for exporting in the gradient map computation subunit
Outline point is extracted on plinth, and is found with the best circle of outline point degree of fitting as number of people point circular arc by the use of circle fitting;
Image coordinate determination subelement, for being made with the peak of the number of people point circular arc of number of people point circular fitting unit output
For the final position of number of people cusp, and determine the image coordinate of the number of people cusp.
The 14. Human Height measurement apparatus based on binocular vision technology according to claim 13, it is characterised in that described
Coordinate calculating unit, with reference to the internal and external parameter of binocular camera, calculates the number of people according to the corresponding depth information of the number of people cusp
Coordinate of the cusp under camera coordinate system, computing formula is as follows:
In formula, XleftFor number of people cusp in left image and image center deviation, XrightIt is number of people cusp in right image
With the deviation of image center;Y be longitudinal coordinate of the number of people cusp in left image, impact point left and right two images in longitudinal direction
Coordinate is identical;F is the lens focus of binocular camera;B is the base length of binocular camera;P(xc,yc,zc) taking the photograph for number of people cusp
Coordinate under camera coordinate system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310192474.6A CN104173054B (en) | 2013-05-21 | 2013-05-21 | Measuring method and measuring device for height of human body based on binocular vision technique |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310192474.6A CN104173054B (en) | 2013-05-21 | 2013-05-21 | Measuring method and measuring device for height of human body based on binocular vision technique |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104173054A CN104173054A (en) | 2014-12-03 |
CN104173054B true CN104173054B (en) | 2017-04-12 |
Family
ID=51954593
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310192474.6A Active CN104173054B (en) | 2013-05-21 | 2013-05-21 | Measuring method and measuring device for height of human body based on binocular vision technique |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104173054B (en) |
Families Citing this family (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104765292B (en) * | 2015-03-16 | 2017-07-07 | 广东美的暖通设备有限公司 | A kind of fool proof method of controller |
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 |
CN105286871B (en) * | 2015-11-27 | 2017-04-26 | 西安交通大学 | Video processing-based body height measurement method |
CN105832336B (en) | 2016-03-18 | 2019-01-22 | 京东方科技集团股份有限公司 | height measuring system and method |
CN106289161A (en) * | 2016-08-01 | 2017-01-04 | 北京小米移动软件有限公司 | Height measurement method and device |
CN106580329A (en) * | 2016-12-28 | 2017-04-26 | 天津众阳科技有限公司 | Height measurement system and method based on binocular stereovision technology |
CN107093182B (en) * | 2017-03-23 | 2019-10-11 | 东南大学 | A kind of human height's estimation method based on feature corners |
CN107016697B (en) * | 2017-04-11 | 2019-09-03 | 杭州光珀智能科技有限公司 | A kind of height measurement method and device |
CN107374638A (en) * | 2017-07-07 | 2017-11-24 | 华南理工大学 | A kind of height measuring system and method based on binocular vision module |
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 |
CN107680130A (en) * | 2017-09-30 | 2018-02-09 | 深圳市云之梦科技有限公司 | One kind is based on the somatometric method and system of image |
CN107798685B (en) * | 2017-11-03 | 2019-12-03 | 北京旷视科技有限公司 | Pedestrian's height determines method, apparatus and system |
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 |
CN108628572B (en) * | 2018-04-10 | 2020-03-31 | 平安科技(深圳)有限公司 | Method and device for adjusting volume by robot, computer equipment and storage medium |
CN108648228A (en) * | 2018-05-16 | 2018-10-12 | 武汉纺织大学 | A kind of binocular infrared human body dimension measurement method and system |
CN108665471A (en) * | 2018-05-30 | 2018-10-16 | 高鹏 | A kind of human body back curve acquisition methods and system based on camera |
CN108917617A (en) * | 2018-09-19 | 2018-11-30 | 贵州电网有限责任公司 | A method of for ice-melt operation field transmission line of electricity ice-shedding vision measurement |
CN110940029A (en) * | 2019-10-28 | 2020-03-31 | 珠海格力电器股份有限公司 | Kitchen air conditioner projection device and control method thereof |
CN112287869A (en) * | 2020-11-10 | 2021-01-29 | 上海依图网络科技有限公司 | Image data detection method and device |
CN112419390A (en) * | 2020-11-26 | 2021-02-26 | 北京华捷艾米科技有限公司 | Method and system for measuring height of human body |
CN113511115A (en) * | 2021-05-28 | 2021-10-19 | 南昌智能新能源汽车研究院 | Binocular vision-based intelligent control method for automobile seat posture |
CN113538803A (en) * | 2021-06-30 | 2021-10-22 | 圣奥科技股份有限公司 | Office furniture distribution adjusting method based on automatic height measurement |
CN113670421B (en) * | 2021-08-25 | 2023-07-07 | 聊城大学 | Horse animal body ruler and weight rapid measuring instrument |
CN115147193B (en) * | 2022-09-02 | 2022-12-27 | 深圳前海鹏影数字软件运营有限公司 | Commodity purchasing recommendation method and device, electronic purchasing terminal and medium |
CN116631022A (en) * | 2023-04-11 | 2023-08-22 | 广东德融汇科技有限公司 | Face accurate recognition method, device, equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SU1561976A1 (en) * | 1986-11-20 | 1990-05-07 | Иркутский Государственный Медицинский Институт | Device for examining binocular vision |
CN1566900A (en) * | 2003-06-11 | 2005-01-19 | 北京航空航天大学 | Vision measuring method for spaced round geometrical parameters |
CN101144705A (en) * | 2007-07-25 | 2008-03-19 | 中国农业大学 | Method for monitoring pig growth using binocular vision technology |
CN101581569A (en) * | 2009-06-17 | 2009-11-18 | 北京信息科技大学 | Calibrating method of structural parameters of binocular visual sensing system |
CN102813516A (en) * | 2012-08-24 | 2012-12-12 | 武汉世纪金桥安全技术有限公司 | Non-contact type human body height measuring method based on optical imaging |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080273760A1 (en) * | 2007-05-04 | 2008-11-06 | Leonard Metcalfe | Method and apparatus for livestock assessment |
JP2009168453A (en) * | 2008-01-10 | 2009-07-30 | Shigeki Kobayashi | Inspection device |
-
2013
- 2013-05-21 CN CN201310192474.6A patent/CN104173054B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
SU1561976A1 (en) * | 1986-11-20 | 1990-05-07 | Иркутский Государственный Медицинский Институт | Device for examining binocular vision |
CN1566900A (en) * | 2003-06-11 | 2005-01-19 | 北京航空航天大学 | Vision measuring method for spaced round geometrical parameters |
CN101144705A (en) * | 2007-07-25 | 2008-03-19 | 中国农业大学 | Method for monitoring pig growth using binocular vision technology |
CN101581569A (en) * | 2009-06-17 | 2009-11-18 | 北京信息科技大学 | Calibrating method of structural parameters of binocular visual sensing system |
CN102813516A (en) * | 2012-08-24 | 2012-12-12 | 武汉世纪金桥安全技术有限公司 | Non-contact type human body height measuring method based on optical imaging |
Non-Patent Citations (3)
Title |
---|
Body mass index and binocular vision skills;Hamed等;《Saudi Journal of Ophthalmology》;20121231;第2012卷(第26期);全文 * |
WMFVR身高肩宽识别;熊运余等;《光电工程》;20030731;第33卷(第7期);摘要,正文第106页第1行到第108页第15行及图1-4 * |
基于双目立体视觉的大尺寸测量系统的研究;熊志;《信息科技辑》;20070815(第02期);正文第11页第1行到第21页最后一行,第42页第1行到第79页最后一行 * |
Also Published As
Publication number | Publication date |
---|---|
CN104173054A (en) | 2014-12-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104173054B (en) | Measuring method and measuring device for height of human body based on binocular vision technique | |
CN110322702B (en) | Intelligent vehicle speed measuring method based on binocular stereo vision system | |
CN110285793B (en) | Intelligent vehicle track measuring method based on binocular stereo vision system | |
US9965870B2 (en) | Camera calibration method using a calibration target | |
TWI555379B (en) | An image calibrating, composing and depth rebuilding method of a panoramic fish-eye camera and a system thereof | |
CN102252653B (en) | Position and attitude measurement method based on time of flight (TOF) scanning-free three-dimensional imaging | |
EP3273412B1 (en) | Three-dimensional modelling method and device | |
CN106361345A (en) | System and method for measuring height of human body in video image based on camera calibration | |
CN103983186B (en) | Binocular vision system bearing calibration and calibration equipment | |
CN103099623B (en) | Extraction method of kinesiology parameters | |
CN109859272A (en) | A kind of auto-focusing binocular camera scaling method and device | |
CN106529495A (en) | Obstacle detection method of aircraft and device | |
CN104089628B (en) | Self-adaption geometric calibration method of light field camera | |
CN100417231C (en) | Three-dimensional vision semi-matter simulating system and method | |
CN109919975B (en) | Wide-area monitoring moving target association method based on coordinate calibration | |
CN104665836A (en) | length measuring method and length measuring device | |
CN104036488A (en) | Binocular vision-based human body posture and action research method | |
CN107084680A (en) | Target depth measuring method based on machine monocular vision | |
CN106705849A (en) | Calibration method of linear-structure optical sensor | |
CN109523595A (en) | A kind of architectural engineering straight line corner angle spacing vision measuring method | |
CN106033614B (en) | A kind of mobile camera motion object detection method under strong parallax | |
CN105335699B (en) | Read-write scene is read and write intelligent identification and the application thereof of element three-dimensional coordinate | |
CN106643567B (en) | A kind of method of calibration and system of lane shift system producing line scaling board | |
CN105354822B (en) | The intelligent apparatus of read-write element position and application in automatic identification read-write scene | |
CN106447733A (en) | Cervical vertebra motion degree and motion axial line position determining method, system and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |