CN107016697A - A kind of height measurement method and device - Google Patents
A kind of height measurement method and device Download PDFInfo
- Publication number
- CN107016697A CN107016697A CN201710232959.1A CN201710232959A CN107016697A CN 107016697 A CN107016697 A CN 107016697A CN 201710232959 A CN201710232959 A CN 201710232959A CN 107016697 A CN107016697 A CN 107016697A
- Authority
- CN
- China
- Prior art keywords
- point
- picture
- points
- calculated
- background
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1072—Measuring physical dimensions, e.g. size of the entire body or parts thereof measuring distances on the body, e.g. measuring length, height or thickness
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Dentistry (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
This application discloses a kind of height measurement method and device, wherein, the height measurement method is realized based on depth camera, specifically, multiframe background depth picture is obtained first with the depth camera and is converted to multiframe background point cloud chart piece, then the height of testee, realizes the purpose of contactless elevation carrection during the extracting of marginal information, the matching of default template and the calculating of world coordinates and height to be measured are obtained per two field picture in extraction using the multiframe background point cloud chart piece Jing Guo background model, the extraction of foreground picture, foreground picture;And the height measurement method has the advantages that preferable replicability, preferable robustness, round-the-clock elevation carrection can be achieved, the front and rear calibration process of application need not be carried out to depth camera, in the absence of leakage of personal information risk.
Description
Technical field
The application is related to technical field of computer vision, more specifically to a kind of height measurement method and device.
Background technology
In production and life, the measurement of height is very universal, such as in child's developmental process, the measurement child of height
The whether normal important parameter of growth and development;Also for example in various interviews and physical examination, height is even more as one person of measurement
The important parameter of material.
The measuring method of the height such as traditional height is still contact type measurement, for example, carried out using slide calliper rule or ultrasonic wave high
The measurement of degree;Contact type measurement needs the cooperation of testee, and synchronization is only capable of carrying out the measurement of single testee;
A kind of Human Height measuring method based on binocular vision is disclosed in Chinese patent CN104173054A, this method can be real
The existing non-contact measurement of many people, but disclosed Human Height measuring method needs to answer two cameras in that patent
Miscellaneous parameter calibration and typing, greatly reduce the user friendly degree and replicability of scheme;In addition, the program is dependent on can
See light and binocular vision, very sensitive to light and distance change, when light and distance change, measurement result can also be sent out
Raw larger change, makes the robustness of the program poor.
Therefore, one kind is needed badly to be easily used and robustness preferably contactless height measurement method.
The content of the invention
In order to solve the above technical problems, the invention provides a kind of height measurement method and device, providing a kind of to realize
Be easily used and robustness preferably contactless height measurement method purpose.
To realize above-mentioned technical purpose, the embodiments of the invention provide following technical scheme:
A kind of height measurement method, including:
Multiframe background depth picture is obtained using depth camera;
The multiframe background depth picture is converted into multiframe background point cloud chart piece;
The ground equation under camera coordinates system is obtained using stochastical sampling consensus method according to the background point cloud chart piece;
Each 3D point datas in the multiframe background point cloud chart piece are averaged, the background mould of the background depth picture is obtained
Type;
Testee is shot using the depth camera, multiframe depth picture to be measured is obtained;
Testee height is calculated using depth picture to be measured described in every frame;
It is described highly to be included using depth picture calculating testee to be measured described in every frame:
The depth picture to be measured is converted into point cloud chart piece to be measured, acquisition prospect is calculated according to the point cloud chart piece to be measured
Picture;
The marginal information of the foreground picture is extracted, and extracts the local maximum in the marginal information as to be matched
Point;
The point to be matched is matched using default template, candidate is obtained and calculates point;
Calculate the candidate and calculate coordinate of each 3D points under image coordinate system in point, and calculated according to the candidate in point
Coordinate of each 3D points under image coordinate system determines point to be calculated;
According to coordinate of the point to be calculated under image coordinate system, the generation of point to be calculated is calculated using the first preset formula
Boundary's coordinate;
First preset formula is:Wherein, Xworld、Yworld、ZworldRepresent
The world coordinates of the point to be calculated, deep represents the depth value at point (x, the y) pixel to be calculated, cxAnd cyDifference table
Show the coordinate value of the depth camera central point under pixel coordinate system;Tx and Ty represent the point x directions to be calculated and y side respectively
To size, fxAnd fyIt is the focal length in x directions and y directions respectively;
According to the world coordinates and the ground equation parameter of the point to be calculated, calculate tested using the second preset formula
Object height;
Second preset formula is:Wherein, H represents the testee
Highly, a, b, c, d are the ground equation parameter.
Optionally, the ground obtained according to the background point cloud chart piece using stochastical sampling consensus method under camera coordinates system
Face equation includes:
One is chosen as picture to be calculated from the multiframe background point cloud chart piece, and by the institute in the picture to be calculated
There are 3D points to be put into 3D point sets;
3 3D points are randomly selected from the 3D point sets, according to the 3 of selection 3D point Calculation Plane equations, and according to
Obtained plane equation calculates the distance that other 3D points define plane apart from the plane equation, will be less than with the plan range pre-
If the 3D points of distance are set as the 3D points of the plane;
Judge whether the 3D points quantity in the plane exceedes predetermined number, if it is, the plane is preserved, and should
All 3D points in plane are rejected from the 3D point sets;If it is not, then determining the ground in the plane of all preservations
Equation;
Judge whether the point in the 3D point sets is less than 3, if it is, being determined in the plane of all preservations described
Ground equation;3 3D points are randomly selected from the 3D point sets if it is not, then returning, calculate flat according to the 3 of selection 3D points
The step of face equation;
It is described to determine that the ground equation includes in the plane of all preservations:Choose 3D points in the plane preserved most
Plane judges whether the 3D points quantity on the ground exceedes lowest threshold as ground, if it is, putting down the ground
Face equation is used as the ground equation under camera coordinates system.
Optionally, it is described to be included according to the point cloud chart piece calculating acquisition foreground picture to be measured:
3D points in the point cloud chart piece to be measured and the background model are substituted into the 3rd preset formula and calculated before acquisition
Scape picture point;
The foreground picture is obtained using the foreground picture point and the 4th preset formula;
3rd preset formula is:Wherein, i and j are respectively figure
As the abscissa and ordinate under coordinate system;Pc (i, j) is the 3D at (i, j) place under the point cloud chart picture coordinate system to be measured
Point;Bg (i, j) is the 3D points at (i, j) place under image coordinate system in the background model, and τ is pre-determined distance threshold value;
4th preset formula is:Wherein, fgMask (i, j) is (i, j)
The pixel value at place.
Optionally, it is described to be averaged each 3D point datas in the multiframe background point cloud chart piece, obtain the background depth
The background model of picture includes:
Each 3D point datas in the multiframe background point cloud chart piece are substituted into the 5th preset formula, calculates and obtains background mould
Each 3D point coordinates of type;
The background model is constituted according to each 3D point coordinates of the background model;
5th preset formula is:Wherein, bg (i, j) is the background model (i, j)
The 3D points at place;pcl(i, j) is the 3D points at l frame background point cloud chart piece (i, j) place, and k is the number of the multiframe background point cloud chart piece
Amount.
Optionally, the default template is human head and shoulder template.
A kind of height measuring device, including:
First picture acquisition module, for obtaining multiframe background depth picture using depth camera;
Point cloud chart piece modular converter, for the multiframe background depth picture to be converted into multiframe background point cloud chart piece;
Ground equation determining module, sits for obtaining camera using stochastical sampling consensus method according to the background point cloud chart piece
Ground equation under mark system;
Background model determining module, for each 3D point datas in the multiframe background point cloud chart piece to be averaged, obtains institute
State the background model of background depth picture;
Second picture acquisition module, for shooting testee using the depth camera, obtains depth picture to be measured;
High computational module, for calculating testee height using depth picture to be measured described in every frame;
The high computational module includes:
Foreground picture acquisition module, for the depth picture to be measured to be converted into point cloud chart piece to be measured, is treated according to described
Measuring point cloud atlas piece, which is calculated, obtains foreground picture;
Edge extracting module, for extracting the marginal information of the foreground picture, and extracts the office in the marginal information
Portion's maximum is used as point to be matched;
Template matches module, for being matched using default template to the point to be matched, is obtained candidate and calculates point;
Point determining module is calculated, coordinate of each 3D points under image coordinate system in point is calculated for calculating the candidate, and
Coordinate of each 3D points under image coordinate system in point is calculated according to the candidate and determines point to be calculated;
World coordinates determining module, it is pre- using first for the coordinate according to the point to be calculated under image coordinate system
If formula calculates the world coordinates of point to be calculated;
First preset formula is:Wherein, Xworld、Yworld、ZworldRepresent
The world coordinates of the point to be calculated, deep represents the depth value at point (x, the y) pixel to be calculated, cxAnd cyDifference table
Show the coordinate value of the depth camera central point under pixel coordinate system;Tx and Ty represent the point x directions to be calculated and y side respectively
To size, fxAnd fyIt is the focal length in x directions and y directions respectively;
Calculating sub module, for the world coordinates and the ground equation parameter according to the point to be calculated, utilizes second
Preset formula calculates testee height;
Second preset formula is:Wherein, H represents the testee
Highly, a, b, c, d are the ground equation parameter.
Optionally, the ground equation determining module includes:
3D point set determining units, for choosing one from the multiframe background point cloud chart piece as picture to be calculated,
And all 3D points in the picture to be calculated are put into 3D point sets;
Unit is iterated to calculate, for randomly selecting 3 3D points from the 3D point sets, according to the 3 of selection 3D point meters
Plane equation is calculated, and the distance that other 3D points define plane apart from the plane equation is calculated according to obtained plane equation, will
The 3D points for being less than pre-determined distance with the plan range are set as the 3D points of the plane;
Judge whether the 3D points quantity in the plane exceedes predetermined number, if it is, the plane is preserved, and should
All 3D points in plane are rejected from the 3D point sets;If it is not, then determining the ground in the plane of all preservations
Equation;
Judge whether the point in the 3D point sets is less than 3, if it is, being determined in the plane of all preservations described
Ground equation;3 3D points are randomly selected from the 3D point sets if it is not, then returning, calculate flat according to the 3 of selection 3D points
The step of face equation;
It is described to determine that the ground equation includes in the plane of all preservations:Choose 3D points in the plane preserved most
Plane judges whether the 3D points quantity on the ground exceedes lowest threshold as ground, if it is, putting down the ground
Face equation is used as the ground equation under camera coordinates system.
Optionally, the foreground picture acquisition module includes:
Foreground picture point computing unit, for the 3D points in the point cloud chart piece to be measured and the background model to be substituted into the
Calculated in three preset formulas and obtain foreground picture point;
Foreground picture computing unit, for obtaining the foreground picture using the foreground picture point and the 4th preset formula
Piece;
3rd preset formula is:Wherein, i and j are respectively figure
As the abscissa and ordinate under coordinate system;Pc (i, j) is the 3D at (i, j) place under the point cloud chart picture coordinate system to be measured
Point;Bg (i, j) is the 3D points at (i, j) place under image coordinate system in the background model, and τ is pre-determined distance threshold value;
4th preset formula is:Wherein, fgMask (i, j) is (i, j)
The pixel value at place.
Optionally, the background model determining module includes:
Picture converting unit, for the multiframe background depth picture to be converted into multiframe background point cloud chart piece;
Background dot computing unit, for each 3D point datas in the multiframe background point cloud chart piece to be substituted into the 5th default public affairs
In formula, each 3D point coordinates for obtaining background model is calculated;
Model construction unit, for constituting the background model according to each 3D point coordinates of the background model;
5th preset formula is:Wherein, bg (i, j) is the background model (i, j)
The 3D points at place;pcl(i, j) is the 3D points at l frame background point cloud chart piece (i, j) place, and k is the number of the multiframe background point cloud chart piece
Amount.
Optionally, the default template is human head and shoulder template.
It can be seen from the above technical proposal that the embodiments of the invention provide a kind of height measurement method and device, wherein,
The height measurement method is realized based on depth camera, specifically, multiframe background depth is obtained first with the depth camera
Picture is simultaneously converted to multiframe background point cloud chart piece, then using extraction of the multiframe background point cloud chart piece Jing Guo background model,
The extracting of marginal information, the matching of default template and world coordinates and height to be measured in the extraction of foreground picture, foreground picture
Calculating obtain height per testee in two field picture, realize the purpose of contactless elevation carrection;Also, the height
Measuring method compared to the Human Height measuring method based on binocular vision disclosed in Chinese patent CN104173054A by with
Lower advantage:
1st, the measurement process due to the height measurement method for testee height does not need depth camera parameter
Participate in, it is achieved thereby that the process that need not be additionally demarcated to depth camera, adds friendly journey of this programme to user
Degree and replicability;
2nd, because this programme realizes the acquisition of background depth picture and depth picture to be measured, the depth using depth camera
Camera uses active illumination, and the acquisition of picture is independent of visible ray, it is to avoid the change of light is to height measurement results
Influence, improves the robustness of this programme, and also due to above-mentioned characteristic, this programme can realize that round-the-clock height is surveyed
Amount;
3rd, because this programme realizes the measurement of height using a depth camera, independent of binocular vision, so as to avoid
Testee further increases the robust of this programme apart from influence of the change to measurement accuracy of the distance of depth camera
Property;
4th, likewise, because this programme realizes the measurement of height using a depth camera, in the absence of based on binocular vision
Human Height measuring method in caused due to extraneous physical factor caused by the physical parameter between " binocular " changes
Measurement error, it also avoid the trouble that the later stage frequently debugged to the parameter of depth camera;
5th, when testee is human body, because this programme is using depth camera shooting testee, human body will not be recorded
The equal details of length, in the absence of the risk of leakage of personal information.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
A kind of schematic flow sheet for height measurement method that Fig. 1 provides for one embodiment of the application;
The schematic diagram for the human head and shoulder template that Fig. 2 provides for one embodiment of the application;
Foreground edge figure and the schematic diagram of point to be matched that Fig. 3 provides for one embodiment of the application;
A kind of structural representation for height measuring device that Fig. 4 provides for one embodiment of the application;
A kind of structural representation for ground equation determining module that Fig. 5 provides for one embodiment of the application;
A kind of structural representation for foreground picture acquisition module that Fig. 6 provides for one embodiment of the application.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
The embodiment of the present application provides a kind of height measurement method, as shown in figure 1, including:
S101:Multiframe background depth picture is obtained using depth camera;
S102:The multiframe background depth picture is converted into multiframe background point cloud chart piece;
S103:The ground side under camera coordinates system is obtained using stochastical sampling consensus method according to the background point cloud chart piece
Journey;
S104:The multiframe background depth picture is converted into multiframe background point cloud chart piece, by the multiframe background dot cloud
Each 3D point datas are averaged in picture, obtain the background model of the background depth picture;
S105:Testee is shot using the depth camera, multiframe depth picture to be measured is obtained;
S106:Testee height is calculated using depth picture to be measured described in every frame;
It is described highly to be included using depth picture calculating testee to be measured described in every frame:
The depth picture to be measured is converted into point cloud chart piece to be measured, acquisition prospect is calculated according to the point cloud chart piece to be measured
Picture;
The marginal information of the foreground picture is extracted, and extracts the local maximum in the marginal information as to be matched
Point;
The point to be matched is matched using default template, candidate is obtained and calculates point;
Calculate the candidate and calculate coordinate of each 3D points under image coordinate system in point, and calculated according to the candidate in point
Coordinate of each 3D points under image coordinate system determines point to be calculated;
According to coordinate of the point to be calculated under image coordinate system, the generation of point to be calculated is calculated using the first preset formula
Boundary's coordinate;
First preset formula is:Wherein, Xworld、Yworld、ZworldRepresent
The world coordinates of the point to be calculated, deep represents the depth value at point (x, the y) pixel to be calculated, cxAnd cyDifference table
Show the coordinate value of the depth camera central point under pixel coordinate system;Tx and Ty represent the point x directions to be calculated and y side respectively
To size, fxAnd fyIt is the focal length in x directions and y directions respectively;
According to the world coordinates and the ground equation parameter of the point to be calculated, calculate tested using the second preset formula
Object height;
Second preset formula is:Wherein, H represents the testee
Highly, a, b, c, d are the ground equation parameter.
, can after step S101, S102, S103 and S104 demarcation it should be noted that in actual application
To be shot always using the depth camera, the multiframe depth picture to be measured of acquisition may after step S105 and S106
Multiple testee height values can be exported, the sequencing that now can enter depth camera according to testee determines each quilt
Survey the parameter which testee is object height value be;
The species of testee needs to match with the default template, when testee is that human body, i.e. testee are high
When spending for height, the default template is needed for human head and shoulder template, as shown in Figure 2.Of course, when the default template is it
When he plants class template, the elevation carrection of other kinds of testee can also be realized.Tool of the application to the default template
Body species is not limited, specifically depending on actual conditions.
It should also be noted that, the height measurement method compared to the Human Height measuring method based on binocular vision by
Following advantage:
1st, the measurement process due to the height measurement method for testee height does not need depth camera parameter
Participate in, it is achieved thereby that the process that need not be additionally demarcated to depth camera, adds friendly journey of this programme to user
Degree and replicability;
2nd, because this programme realizes the acquisition of background depth picture and depth picture to be measured, the depth using depth camera
Camera uses active illumination, and the acquisition of picture is independent of visible ray, it is to avoid the change of light is to height measurement results
Influence, improves the robustness of this programme, and also due to above-mentioned characteristic, this programme can realize that round-the-clock height is surveyed
Amount;
3rd, because this programme realizes the measurement of height using a depth camera, independent of binocular vision, so as to avoid
Testee further increases the robust of this programme apart from influence of the change to measurement accuracy of the distance of depth camera
Property;
4th, likewise, because this programme realizes the measurement of height using a depth camera, in the absence of based on binocular vision
Human Height measuring method in caused due to extraneous physical factor caused by the physical parameter between " binocular " changes
Measurement error, it also avoid the trouble that the later stage frequently debugged to the parameter of depth camera;
5th, when testee is human body, because this programme is using depth camera shooting testee, human body will not be recorded
The equal details of length, in the absence of the risk of leakage of personal information.
It is described according to the background depth picture in one embodiment of the application on the basis of above-described embodiment
Obtaining the ground equation under camera coordinates system using stochastical sampling consensus method includes:
One is chosen from the multiframe background point cloud chart piece as picture to be calculated, and by the picture to be calculated
All 3D points are put into 3D point sets;
3 3D points are randomly selected from the 3D point sets, according to the 3 of selection 3D point Calculation Plane equations, and according to
Obtained plane equation calculates the distance that other 3D points define plane apart from the plane equation, will be less than with the plan range pre-
If the 3D points of distance are set as the 3D points of the plane;
Judge whether the 3D points quantity in the plane exceedes predetermined number, if it is, the plane is preserved, and should
All 3D points in plane are rejected from the 3D point sets;If it is not, then determining the ground in the plane of all preservations
Equation;
Judge whether the point in the 3D point sets is less than 3, if it is, being determined in the plane of all preservations described
Ground equation;3 3D points are randomly selected from the 3D point sets if it is not, then returning, calculate flat according to the 3 of selection 3D points
The step of face equation;
It is described to determine that the ground equation includes in the plane of all preservations:Choose 3D points in the plane preserved most
Plane judges whether the 3D points quantity on the ground exceedes lowest threshold as ground, if it is, putting down the ground
Face equation is used as the ground equation under camera coordinates system.
It should be noted that the expression formula of the ground equation finally given is:Ax+by+cz+d=0, wherein, a, b, c, d
For the ground equation parameter, multiple data point coordinates that these ground equation parameters can be in the ground substitute into expression
It is fitted in formula and obtains optimal value.
In the preferred embodiment of the application, the span of the pre-determined distance is 0.5cm-1.5cm, including is held
Point value.
The span of the predetermined number is 500-1000, including endpoint value.
The span of the lowest threshold is 10000-15000, including endpoint value.
The application is not limited the specific value of the pre-determined distance, predetermined number and lowest threshold, specific to regard real
Depending on the situation of border.
It is described by the multiframe background dot cloud in another embodiment of the application on the basis of above-described embodiment
Each 3D point datas are averaged in picture, are obtained the background model of the background depth picture and are included:
Each 3D point datas in the multiframe background point cloud chart piece are substituted into the 5th preset formula, calculates and obtains background mould
Each 3D point coordinates of type;
The background model is constituted according to each 3D point coordinates of the background model;
5th preset formula is:Wherein, bg (i, j) is the background model (i, j)
The 3D points at place;pcl(i, j) is the 3D points at l frame background point cloud chart piece (i, j) place, and k is the number of the multiframe background point cloud chart piece
Amount.
It is described according to the point cloud chart to be measured in another embodiment of the application on the basis of above-described embodiment
Piece, which calculates acquisition foreground picture, to be included:
3D points in the point cloud chart piece to be measured and the background model are substituted into the 3rd preset formula and calculated before acquisition
Scape picture point;
The foreground picture is obtained using the foreground picture point and the 4th preset formula;
3rd preset formula is:Wherein, i and j are respectively figure
As the abscissa and ordinate under coordinate system;Pc (i, j) is the 3D at (i, j) place under the point cloud chart picture coordinate system to be measured
Point;Bg (i, j) is the 3D points at (i, j) place under image coordinate system in the background model, and τ is pre-determined distance threshold value;
4th preset formula is:Wherein, fgMask (i, j) is (i, j)
The pixel value at place.
In the 3rd preset formula, depending on the value of the pre-determined distance threshold value can be according to actual conditions, at this
In one specific embodiment of application, the value of the pre-determined distance threshold value is 10cm;Of course, in other implementations of the application
In example, the pre-determined distance threshold value can also be 9cm or 11cm, the application to the specific value of the pre-determined distance threshold value not
Limit.
In the present embodiment, it is described to extract the marginal information of the foreground picture, and extract the office in the marginal information
Portion's maximum includes as point to be matched:
The foreground picture is handled using Canny operators, foreground edge figure is obtained;The foreground edge obtained
Figure is as shown in figure 3, in figure 3, label A0 represents the foreground edge figure;
The foreground edge figure is carried out to extract local maximum processing, point to be matched is obtained, as shown in figure 3, in Fig. 3
In, the point of the circle mark shown in label A1 is the point to be matched.
It is described to be calculated according to the candidate in the specific embodiment of the application on the basis of above-described embodiment
Coordinate of each 3D points under image coordinate system determines that point to be calculated includes in point:
The candidate is calculated into the maximum point of each 3D points y-coordinate value under image coordinate system in point, is defined as described waiting to count
Calculate point.
Accordingly, the embodiment of the present application additionally provides a kind of height measuring device, as shown in figure 4, including:
First picture acquisition module 100, for obtaining multiframe background depth picture using depth camera;
Point cloud chart piece modular converter 200, for the multiframe background depth picture to be converted into multiframe background point cloud chart piece;
Ground equation determining module 300, for obtaining phase using stochastical sampling consensus method according to the background point cloud chart piece
Ground equation under machine coordinate system;
Background model determining module 400, for each 3D point datas in the multiframe background point cloud chart piece to be averaged, is obtained
The background model of the background depth picture;
Second picture acquisition module 500, for shooting testee using the depth camera, obtains depth map to be measured
Piece;
High computational module 600, for calculating testee height using depth picture to be measured described in every frame;
The high computational module 600 includes:
Foreground picture acquisition module 610, for the depth picture to be measured to be converted into point cloud chart piece to be measured, according to described
Point cloud chart piece to be measured, which is calculated, obtains foreground picture;
Edge extracting module 620, for extracting the marginal information of the foreground picture, and is extracted in the marginal information
Local maximum is used as point to be matched;
Template matches module 630, for being matched using default template to the point to be matched, is obtained candidate and calculated
Point;
Point determining module 640 is calculated, coordinate of each 3D points under image coordinate system in point is calculated for calculating the candidate,
And point to be calculated is determined according to coordinate of each 3D points under image coordinate system in candidate calculating point;
World coordinates determining module 650, for the coordinate according to the point to be calculated under image coordinate system, utilizes first
Preset formula calculates the world coordinates of point to be calculated;
First preset formula is:Wherein, Xworld、Yworld、ZworldRepresent
The world coordinates of the point to be calculated, deep represents the depth value at point (x, the y) pixel to be calculated, cxAnd cyDifference table
Show the coordinate value of the depth camera central point under pixel coordinate system;Tx and Ty represent the point x directions to be calculated and y side respectively
To size, fxAnd fyIt is the focal length in x directions and y directions respectively;
Calculating sub module 660, for the world coordinates and the ground equation parameter according to the point to be calculated, utilizes
Two preset formulas calculate testee height;
Second preset formula is:Wherein, H represents the testee
Highly, a, b, c, d are the ground equation parameter.
It should be noted that in actual application, turning by the first picture acquisition module 100, point cloud chart piece
After the demarcation for changing the mold block 200, ground equation determining module 300 and background model determining module 400, it is possible to use the depth phase
Machine is shot always, and the multiframe depth picture to be measured of acquisition passes through the second picture acquisition module 500 and high computational mould
Multiple testee height values may be exported after block 600, the priority that now can enter depth camera according to testee is suitable
Sequence determines the parameter which testee each testee height value is;
The species of testee needs to match with the default template, when testee is that human body, i.e. testee are high
When spending for height, the default template is needed for human head and shoulder template, as shown in Figure 2.Of course, when the default template is it
When he plants class template, the elevation carrection of other kinds of testee can also be realized.Tool of the application to the default template
Body species is not limited, specifically depending on actual conditions.
It should also be noted that, the height measurement method compared to the Human Height measuring method based on binocular vision by
Following advantage:
1st, the measurement process due to the height measurement method for testee height does not need depth camera parameter
Participate in, it is achieved thereby that the process that need not be additionally demarcated to depth camera, adds friendly journey of this programme to user
Degree and replicability;
2nd, because this programme realizes the acquisition of background depth picture and depth picture to be measured, the depth using depth camera
Camera uses active illumination, and the acquisition of picture is independent of visible ray, it is to avoid the change of light is to height measurement results
Influence, improves the robustness of this programme, and also due to above-mentioned characteristic, this programme can realize that round-the-clock height is surveyed
Amount;
3rd, because this programme realizes the measurement of height using a depth camera, independent of binocular vision, so as to avoid
Testee further increases the robust of this programme apart from influence of the change to measurement accuracy of the distance of depth camera
Property;
4th, likewise, because this programme realizes the measurement of height using a depth camera, in the absence of based on binocular vision
Human Height measuring method in caused due to extraneous physical factor caused by the physical parameter between " binocular " changes
Measurement error, it also avoid the trouble that the later stage frequently debugged to the parameter of depth camera;
5th, when testee is human body, because this programme is using depth camera shooting testee, human body will not be recorded
The equal details of length, in the absence of the risk of leakage of personal information.
On the basis of above-described embodiment, in one embodiment of the application, as shown in figure 5, the ground equation is true
Cover half block 300 includes:
3D point sets determining unit 310, figure to be calculated is used as choosing one from the multiframe background depth picture
Piece, and all 3D points in the picture to be calculated are put into 3D point sets;
Unit 320 is iterated to calculate, for randomly selecting 3 3D points from the 3D point sets, according to the 3 of selection 3D points
Calculation Plane equation, and the distance that other 3D points define plane apart from the plane equation is calculated according to obtained plane equation,
The 3D points for being less than pre-determined distance with the plan range are set as to the 3D points of the plane;
Judge whether the 3D points quantity in the plane exceedes predetermined number, if it is, the plane is preserved, and should
All 3D points in plane are rejected from the 3D point sets;If it is not, then determining the ground in the plane of all preservations
Equation;
Judge whether the point in the 3D point sets is less than 3, if it is, being determined in the plane of all preservations described
Ground equation;3 3D points are randomly selected from the 3D point sets if it is not, then returning, calculate flat according to the 3 of selection 3D points
The step of face equation;
It is described to determine that the ground equation includes in the plane of all preservations:Choose 3D points in the plane preserved most
Plane judges whether the 3D points quantity on the ground exceedes lowest threshold as ground, if it is, putting down the ground
Face equation is used as the ground equation under camera coordinates system.
It should be noted that the expression formula of the ground equation finally given is:Ax+by+cz+d=0, wherein, a, b, c, d
For the ground equation parameter, multiple data point coordinates that these ground equation parameters can be in the ground substitute into expression
It is fitted in formula and obtains optimal value.
In the preferred embodiment of the application, the span of the pre-determined distance is 0.5cm-1.5cm, including is held
Point value.
The span of the predetermined number is 500-1000, including endpoint value.
The span of the lowest threshold is 10000-15000, including endpoint value.
The application is not limited the specific value of the pre-determined distance, predetermined number and lowest threshold, specific to regard real
Depending on the situation of border.
On the basis of above-described embodiment, in another embodiment of the application, as shown in fig. 6, the foreground picture
Acquisition module 610 includes:
Foreground picture point computing unit 611, for by the 3D points in the point cloud chart piece to be measured and the background model generation
Enter to calculate in the 3rd preset formula and obtain foreground picture point;
Foreground picture computing unit 612, for obtaining the prospect using the foreground picture point and the 4th preset formula
Picture;
3rd preset formula is:Wherein, i and j are respectively figure
As the abscissa and ordinate under coordinate system;Pc (i, j) is the 3D at (i, j) place under the point cloud chart picture coordinate system to be measured
Point;Bg (i, j) is the 3D points at (i, j) place under image coordinate system in the background model, and τ is pre-determined distance threshold value;
4th preset formula is:Wherein, fgMask (i, j) is (i, j)
The pixel value at place.
In the 3rd preset formula, depending on the value of the pre-determined distance threshold value can be according to actual conditions, at this
In one specific embodiment of application, the value of the pre-determined distance threshold value is 10cm;Of course, in other implementations of the application
In example, the pre-determined distance threshold value can also be 9cm or 11cm, the application to the specific value of the pre-determined distance threshold value not
Limit.
In the present embodiment, the edge extracting module 620 using Canny operators to the foreground picture specifically for being entered
Row processing, obtains foreground edge figure;The foreground edge figure obtained is as shown in figure 3, in figure 3, before label A0 represents described
Scape edge graph;
The foreground edge figure is carried out to extract local maximum processing, point to be matched is obtained, as shown in figure 3, in Fig. 3
In, the point of the circle mark shown in label A1 is the point to be matched.
On the basis of above-described embodiment, in the specific embodiment of the application, the template matches module 630 has
Body is used to the candidate calculating each 3D points maximum point of y-coordinate value under image coordinate system in point, is defined as described to be calculated
Point.
In summary, the embodiment of the present application provides a kind of height measurement method and device, wherein, the elevation carrection side
Method is realized based on depth camera, specifically, is obtained multiframe background depth picture first with the depth camera and is converted to many
Frame background point cloud chart piece, then using extraction of the multiframe background point cloud chart piece Jing Guo background model, the extraction of foreground picture,
The matching extracted, preset template of marginal information and the calculating of world coordinates and height to be measured are obtained per frame figure in foreground picture
The height of testee, realizes the purpose of contactless elevation carrection as in;Also, the height measurement method is compared in
The Human Height measuring method based on binocular vision disclosed in state patent CN104173054A is by following advantage:
1st, the measurement process due to the height measurement method for testee height does not need depth camera parameter
Participate in, it is achieved thereby that the process that need not be additionally demarcated to depth camera, adds friendly journey of this programme to user
Degree and replicability;
2nd, because this programme realizes the acquisition of background depth picture and depth picture to be measured, the depth using depth camera
Camera uses active illumination, and the acquisition of picture is independent of visible ray, it is to avoid the change of light is to height measurement results
Influence, improves the robustness of this programme, and also due to above-mentioned characteristic, this programme can realize that round-the-clock height is surveyed
Amount;
3rd, because this programme realizes the measurement of height using a depth camera, independent of binocular vision, so as to avoid
Testee further increases the robust of this programme apart from influence of the change to measurement accuracy of the distance of depth camera
Property;
4th, likewise, because this programme realizes the measurement of height using a depth camera, in the absence of based on binocular vision
Human Height measuring method in caused due to extraneous physical factor caused by the physical parameter between " binocular " changes
Measurement error, it also avoid the trouble that the later stage frequently debugged to the parameter of depth camera;
5th, when testee is human body, because this programme is using depth camera shooting testee, human body will not be recorded
The equal details of length, in the absence of the risk of leakage of personal information.
The embodiment of each in this specification is described by the way of progressive, and what each embodiment was stressed is and other
Between the difference of embodiment, each embodiment identical similar portion mutually referring to.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (10)
1. a kind of height measurement method, it is characterised in that including:
Multiframe background depth picture is obtained using depth camera;
The multiframe background depth picture is converted into multiframe background point cloud chart piece;
The ground equation under camera coordinates system is obtained using stochastical sampling consensus method according to the background point cloud chart piece;
Each 3D point datas in the multiframe background point cloud chart piece are averaged, the background model of the background depth picture is obtained;
Testee is shot using the depth camera, multiframe depth picture to be measured is obtained;
Testee height is calculated using depth picture to be measured described in every frame;
It is described highly to be included using depth picture calculating testee to be measured described in every frame:
The depth picture to be measured is converted into point cloud chart piece to be measured, is calculated according to the point cloud chart piece to be measured and obtains foreground picture
Piece;
The marginal information of the foreground picture is extracted, and extracts the local maximum in the marginal information as point to be matched;
The point to be matched is matched using default template, candidate is obtained and calculates point;
Calculate the candidate and calculate coordinate of each 3D points under image coordinate system in point, and each 3D in point is calculated according to the candidate
Coordinate of the point under image coordinate system determines point to be calculated;
According to coordinate of the point to be calculated under image coordinate system, the world for calculating point to be calculated using the first preset formula is sat
Mark;
First preset formula is:Wherein, Xworld、Yworld、ZworldRepresent described
The world coordinates of point to be calculated, deep represents the depth value at point (x, the y) pixel to be calculated, cxAnd cyPicture is represented respectively
The coordinate value of the depth camera central point under plain coordinate system;Tx and Ty represent the point x directions to be calculated and y directions respectively
Size, fxAnd fyIt is the focal length in x directions and y directions respectively;
According to the world coordinates and the ground equation parameter of the point to be calculated, testee is calculated using the second preset formula
Highly;
Second preset formula is:Wherein, H represents that the testee is high
Degree, a, b, c, d are the ground equation parameter.
2. according to the method described in claim 1, it is characterised in that described that stochastical sampling is used according to the background point cloud chart piece
The ground equation that consensus method is obtained under camera coordinates system includes:
One is chosen as picture to be calculated from the multiframe background point cloud chart piece, and by all 3D in the picture to be calculated
Point is put into 3D point sets;
3 3D points are randomly selected from the 3D point sets, according to the 3 of selection 3D point Calculation Plane equations, and according to obtaining
Plane equation calculate the distance that other 3D points define plane apart from the plane equation, will be less than with the plan range it is default away from
From 3D points be set as the 3D points of the plane;
Judge whether 3D points quantity in the plane exceedes predetermined number, if it is, the plane is preserved, and by the plane
On all 3D points rejected from the 3D point sets;If it is not, then determining the ground equation in the plane of all preservations;
Judge whether the point in the 3D point sets is less than 3, if it is, determining the ground in the plane of all preservations
Equation;3 3D points are randomly selected from the 3D point sets if it is not, then returning, according to the 3 of selection 3D points Calculation Plane sides
The step of journey;
It is described to determine that the ground equation includes in the plane of all preservations:Choose the most plane of 3D points in the plane preserved
As ground, and judge whether the 3D points quantity on the ground exceedes lowest threshold, if it is, by the plane side on the ground
Ground equation under Cheng Zuowei camera coordinates systems.
3. according to the method described in claim 1, it is characterised in that described that acquisition prospect is calculated according to the point cloud chart piece to be measured
Picture includes:
3D points in the point cloud chart piece to be measured and the background model are substituted into calculate in the 3rd preset formula and obtain foreground picture
Piece point;
The foreground picture is obtained using the foreground picture point and the 4th preset formula;
3rd preset formula is:Wherein, i and j are respectively that image is sat
Abscissa and ordinate under mark system;Pc (i, j) is the 3D points at (i, j) place under the point cloud chart picture coordinate system to be measured;bg
(i, j) is the 3D points at (i, j) place under image coordinate system in the background model, and τ is pre-determined distance threshold value;
4th preset formula is:Wherein, fgMask (i, j) is (i, j) place
Pixel value.
4. according to the method described in claim 1, it is characterised in that described that each 3D in the multiframe background point cloud chart piece counts
According to being averaged, obtaining the background model of the background depth picture includes:
Each 3D point datas in the multiframe background point cloud chart piece are substituted into the 5th preset formula, calculates and obtains background model
Each 3D point coordinates;
The background model is constituted according to each 3D point coordinates of the background model;
5th preset formula is:Wherein, bg (i, j) is background model (i, the j) place
3D points;pcl(i, j) is the 3D points at l frame background point cloud chart piece (i, j) place, and k is the quantity of the multiframe background point cloud chart piece.
5. according to the method described in claim 1, it is characterised in that the default template is human head and shoulder template.
6. a kind of height measuring device, it is characterised in that including:
First picture acquisition module, for obtaining multiframe background depth picture using depth camera;
Point cloud chart piece modular converter, for the multiframe background depth picture to be converted into multiframe background point cloud chart piece;
Ground equation determining module, for obtaining camera coordinates system using stochastical sampling consensus method according to the background point cloud chart piece
Under ground equation;
Background model determining module, for each 3D point datas in the multiframe background point cloud chart piece to be averaged, obtains the back of the body
The background model of depth of field degree picture;
Second picture acquisition module, for shooting testee using the depth camera, obtains depth picture to be measured;
High computational module, for calculating testee height using depth picture to be measured described in every frame;
The high computational module includes:
Foreground picture acquisition module, for the depth picture to be measured to be converted into point cloud chart piece to be measured, according to the tested point
Cloud atlas piece, which is calculated, obtains foreground picture;
Edge extracting module, for extracting the marginal information of the foreground picture, and extracts the local pole in the marginal information
Big value is used as point to be matched;
Template matches module, for being matched using default template to the point to be matched, is obtained candidate and calculates point;
A point determining module is calculated, coordinate of each 3D points under image coordinate system in point is calculated for calculating the candidate, and according to
The candidate calculates coordinate of each 3D points under image coordinate system in point and determines point to be calculated;
World coordinates determining module, for the coordinate according to the point to be calculated under image coordinate system, utilizes the first default public affairs
Formula calculates the world coordinates of point to be calculated;
First preset formula is:Wherein, Xworld、Yworld、ZworldRepresent described
The world coordinates of point to be calculated, deep represents the depth value at point (x, the y) pixel to be calculated, cxAnd cyPicture is represented respectively
The coordinate value of the depth camera central point under plain coordinate system;Tx and Ty represent the point x directions to be calculated and y directions respectively
Size, fxAnd fyIt is the focal length in x directions and y directions respectively;
Calculating sub module, it is default using second for the world coordinates and the ground equation parameter according to the point to be calculated
Formula calculates testee height;
Second preset formula is:Wherein, H represents that the testee is high
Degree, a, b, c, d are the ground equation parameter.
7. system according to claim 6, it is characterised in that the ground equation determining module includes:
3D point set determining units, for choosing one from the multiframe background point cloud chart piece as picture to be calculated, and will
All 3D points in the picture to be calculated are put into 3D point sets;
Unit is iterated to calculate, for randomly selecting 3 3D points from the 3D point sets, calculates flat according to the 3 of selection 3D points
Face equation, and the distance that other 3D points define plane apart from the plane equation is calculated according to obtained plane equation, will be with this
Plan range is set as the 3D points of the plane less than the 3D points of pre-determined distance;
Judge whether 3D points quantity in the plane exceedes predetermined number, if it is, the plane is preserved, and by the plane
On all 3D points rejected from the 3D point sets;If it is not, then determining the ground equation in the plane of all preservations;
Judge whether the point in the 3D point sets is less than 3, if it is, determining the ground in the plane of all preservations
Equation;3 3D points are randomly selected from the 3D point sets if it is not, then returning, according to the 3 of selection 3D points Calculation Plane sides
The step of journey;
It is described to determine that the ground equation includes in the plane of all preservations:Choose the most plane of 3D points in the plane preserved
As ground, and judge whether the 3D points quantity on the ground exceedes lowest threshold, if it is, by the plane side on the ground
Ground equation under Cheng Zuowei camera coordinates systems.
8. system according to claim 6, it is characterised in that the foreground picture acquisition module includes:
Foreground picture point computing unit, it is pre- for the 3D points in the point cloud chart piece to be measured and the background model to be substituted into the 3rd
If being calculated in formula and obtaining foreground picture point;
Foreground picture computing unit, for obtaining the foreground picture using the foreground picture point and the 4th preset formula;
3rd preset formula is:Wherein, i and j are respectively that image is sat
Abscissa and ordinate under mark system;Pc (i, j) is the 3D points at (i, j) place under the point cloud chart picture coordinate system to be measured;bg
(i, j) is the 3D points at (i, j) place under image coordinate system in the background model, and τ is pre-determined distance threshold value;
4th preset formula is:Wherein, fgMask (i, j) is (i, j) place
Pixel value.
9. system according to claim 6, it is characterised in that the background model determining module includes:
Picture converting unit, for the multiframe background depth picture to be converted into multiframe background point cloud chart piece;
Background dot computing unit, for each 3D point datas in the multiframe background point cloud chart piece to be substituted into the 5th preset formula
In, calculate each 3D point coordinates for obtaining background model;
Model construction unit, for constituting the background model according to each 3D point coordinates of the background model;
5th preset formula is:Wherein, bg (i, j) is background model (i, the j) place
3D points;pcl(i, j) is the 3D points at l frame background point cloud chart piece (i, j) place, and k is the quantity of the multiframe background point cloud chart piece.
10. system according to claim 6, it is characterised in that the default template is human head and shoulder template.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710232959.1A CN107016697B (en) | 2017-04-11 | 2017-04-11 | A kind of height measurement method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710232959.1A CN107016697B (en) | 2017-04-11 | 2017-04-11 | A kind of height measurement method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107016697A true CN107016697A (en) | 2017-08-04 |
CN107016697B CN107016697B (en) | 2019-09-03 |
Family
ID=59446009
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710232959.1A Active CN107016697B (en) | 2017-04-11 | 2017-04-11 | A kind of height measurement method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107016697B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108209926A (en) * | 2018-01-08 | 2018-06-29 | 西安科技大学 | Human Height measuring system based on depth image |
CN109448057A (en) * | 2018-11-02 | 2019-03-08 | 宁夏巨能机器人股份有限公司 | A kind of safe positioning method based on three-dimensional point cloud |
CN110276801A (en) * | 2019-06-24 | 2019-09-24 | 深圳前海达闼云端智能科技有限公司 | Object positioning method and device and storage medium |
CN110310459A (en) * | 2019-04-04 | 2019-10-08 | 桑尼环保(江苏)有限公司 | Multi-parameter extract real-time system |
CN110930411A (en) * | 2019-11-20 | 2020-03-27 | 杭州光珀智能科技有限公司 | Human body segmentation method and system based on depth camera |
CN111586299A (en) * | 2020-05-09 | 2020-08-25 | 北京华捷艾米科技有限公司 | Image processing method and related equipment |
CN111712855A (en) * | 2019-05-06 | 2020-09-25 | 深圳市大疆创新科技有限公司 | Ground information processing method and device and unmanned vehicle |
TWI759069B (en) * | 2021-01-12 | 2022-03-21 | 鴻海精密工業股份有限公司 | Method and device for measuring plant growth height, computer device and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102884395A (en) * | 2010-05-07 | 2013-01-16 | 株式会社尼康 | Height measuring method and height measuring device |
CN103389042A (en) * | 2013-07-11 | 2013-11-13 | 夏东 | Ground automatic detecting and scene height calculating method based on depth image |
CN103697857A (en) * | 2013-12-05 | 2014-04-02 | 北京邮电大学 | Height measuring method and height measuring device |
CN104173054A (en) * | 2013-05-21 | 2014-12-03 | 杭州海康威视数字技术股份有限公司 | Measuring method and measuring device for height of human body based on binocular vision technique |
CN104720814A (en) * | 2013-12-19 | 2015-06-24 | 天津市天大百睿精密仪器技术有限公司 | Non-contact height automatic measuring system and non-contact height automatic measuring method |
-
2017
- 2017-04-11 CN CN201710232959.1A patent/CN107016697B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102884395A (en) * | 2010-05-07 | 2013-01-16 | 株式会社尼康 | Height measuring method and height measuring device |
CN104173054A (en) * | 2013-05-21 | 2014-12-03 | 杭州海康威视数字技术股份有限公司 | Measuring method and measuring device for height of human body based on binocular vision technique |
CN103389042A (en) * | 2013-07-11 | 2013-11-13 | 夏东 | Ground automatic detecting and scene height calculating method based on depth image |
CN103697857A (en) * | 2013-12-05 | 2014-04-02 | 北京邮电大学 | Height measuring method and height measuring device |
CN104720814A (en) * | 2013-12-19 | 2015-06-24 | 天津市天大百睿精密仪器技术有限公司 | Non-contact height automatic measuring system and non-contact height automatic measuring method |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108209926A (en) * | 2018-01-08 | 2018-06-29 | 西安科技大学 | Human Height measuring system based on depth image |
CN109448057A (en) * | 2018-11-02 | 2019-03-08 | 宁夏巨能机器人股份有限公司 | A kind of safe positioning method based on three-dimensional point cloud |
CN109448057B (en) * | 2018-11-02 | 2022-02-25 | 宁夏巨能机器人股份有限公司 | Safety positioning method based on three-dimensional point cloud |
CN110310459A (en) * | 2019-04-04 | 2019-10-08 | 桑尼环保(江苏)有限公司 | Multi-parameter extract real-time system |
CN111712855A (en) * | 2019-05-06 | 2020-09-25 | 深圳市大疆创新科技有限公司 | Ground information processing method and device and unmanned vehicle |
WO2020223868A1 (en) * | 2019-05-06 | 2020-11-12 | 深圳市大疆创新科技有限公司 | Terrain information processing method and apparatus, and unmanned vehicle |
CN110276801B (en) * | 2019-06-24 | 2021-09-28 | 达闼机器人有限公司 | Object positioning method and device and storage medium |
CN110276801A (en) * | 2019-06-24 | 2019-09-24 | 深圳前海达闼云端智能科技有限公司 | Object positioning method and device and storage medium |
CN110930411A (en) * | 2019-11-20 | 2020-03-27 | 杭州光珀智能科技有限公司 | Human body segmentation method and system based on depth camera |
CN110930411B (en) * | 2019-11-20 | 2023-04-28 | 浙江光珀智能科技有限公司 | Human body segmentation method and system based on depth camera |
CN111586299A (en) * | 2020-05-09 | 2020-08-25 | 北京华捷艾米科技有限公司 | Image processing method and related equipment |
CN111586299B (en) * | 2020-05-09 | 2021-10-19 | 北京华捷艾米科技有限公司 | Image processing method and related equipment |
TWI759069B (en) * | 2021-01-12 | 2022-03-21 | 鴻海精密工業股份有限公司 | Method and device for measuring plant growth height, computer device and medium |
Also Published As
Publication number | Publication date |
---|---|
CN107016697B (en) | 2019-09-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107016697B (en) | A kind of height measurement method and device | |
CN103913131B (en) | Free curve method vector measurement method based on binocular vision | |
CN101322589B (en) | Non-contact type human body measuring method for clothing design | |
CN104173054B (en) | Measuring method and measuring device for height of human body based on binocular vision technique | |
CN110991266B (en) | Binocular face living body detection method and device | |
CN104036488B (en) | Binocular vision-based human body posture and action research method | |
CN110599540A (en) | Real-time three-dimensional human body shape and posture reconstruction method and device under multi-viewpoint camera | |
CN102178530A (en) | Method for automatically measuring human body dimensions on basis of three-dimensional point cloud data | |
CN109758355A (en) | One kind is based on the processing of human acupoint two dimensional image and 3 D stereo localization method | |
CN105832336A (en) | Body height measurement system and method | |
CN105913013A (en) | Binocular vision face recognition algorithm | |
CN103535960B (en) | Human body three-dimensional measurement method based on digital images | |
CN105066877A (en) | Tree measuring method based on intelligent terminal lens | |
CN101398886A (en) | Rapid three-dimensional face identification method based on bi-eye passiveness stereo vision | |
CN112220444B (en) | Pupil distance measuring method and device based on depth camera | |
CN110074788B (en) | Body data acquisition method and device based on machine learning | |
CN101814185A (en) | Line structured light vision sensor calibration method for micro-size measurement | |
CN105740781A (en) | Three-dimensional human face in-vivo detection method and device | |
CN106327536B (en) | A kind of collar measurement method based on section point cloud | |
CN109425348A (en) | A kind of while positioning and the method and apparatus for building figure | |
CN108961330A (en) | The long measuring method of pig body and system based on image | |
Wuhrer et al. | Landmark-free posture invariant human shape correspondence | |
CN105354825A (en) | Intelligent device for automatically identifying position of reading material in read-write scene and application of intelligent device | |
CN107631782A (en) | A kind of level testing methods based on Harris Corner Detections | |
CN109359537A (en) | Human face posture angle detecting method neural network based and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP03 | Change of name, title or address |
Address after: 323000 room 303-5, block B, building 1, No. 268, Shiniu Road, nanmingshan street, Liandu District, Lishui City, Zhejiang Province Patentee after: Zhejiang Guangpo Intelligent Technology Co., Ltd Address before: Hangzhou City, Zhejiang province 310030 Xihu District three Town Shi Xiang Road No. 859 Zijin and building 3 building 1301-1 room Patentee before: HANGZHOU GENIUS PROS TECHNOLOGY Co.,Ltd. |
|
CP03 | Change of name, title or address |