CN106959747B - Three-dimensional human body measuring method and apparatus thereof - Google Patents
Three-dimensional human body measuring method and apparatus thereof Download PDFInfo
- Publication number
- CN106959747B CN106959747B CN201710079457.XA CN201710079457A CN106959747B CN 106959747 B CN106959747 B CN 106959747B CN 201710079457 A CN201710079457 A CN 201710079457A CN 106959747 B CN106959747 B CN 106959747B
- Authority
- CN
- China
- Prior art keywords
- depth
- human body
- measurement
- depth camera
- dimensional
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Abstract
The invention discloses a three-dimensional human body measuring method and equipment thereof, wherein the three-dimensional human body measuring method comprises the following steps: setting a first depth camera for real-time somatosensory measurement and a second depth camera for non-real-time somatosensory measurement in the equipment; when the equipment is in a state to be measured, detecting the somatosensory instruction in real time according to the depth image of the somatosensory instruction acquired by the first depth camera; the somatosensory instruction is a gesture or action of a user interacting with the measuring equipment in a measuring area of the measuring equipment to start the equipment to carry out next measurement; if the somatosensory instruction is detected to correspond to the preset activation instruction, switching the equipment to a human body model measurement state, and otherwise, continuously detecting the somatosensory instruction in real time; when the equipment is in a human body model measuring state, the whole three-dimensional human body model is obtained through measurement according to the depth image obtained by the second depth camera.
Description
Technical Field
The invention relates to the field of optical measurement, in particular to a three-dimensional human body measuring method and equipment thereof.
Background
With the advent of the era of online shopping and private customization, the traditional shop try-and-buy mode of a physical store gradually changes to the network try-and/private customization-and-buy mode. The establishment of the human body three-dimensional model is the premise of realizing network fitting and private customization, the accurate acquisition of the human body net model is favorable for realizing the accuracy of clothes size matching, and meanwhile, hundreds of characteristic attributes of human body which represent the human body appearance can be acquired at one time by utilizing the human body net model, so that the human body three-dimensional model can be used for realizing the private customization service of clothes.
In addition, the existing three-dimensional human body scanning needs to be executed according to a certain step sequence, a person to be measured generally needs to control the cooperation between a staff of a measuring device and the person to be measured, during the process, the staff informs the person to be measured of the action or posture needed to be made in the three-dimensional human body measuring device, the person to be measured executes according to the informed content, the measuring process can influence the scanning efficiency of the three-dimensional human body scanning, the application environment is limited, and the intelligent degree is not high.
The above background disclosure is only for the purpose of assisting understanding of the inventive concept and technical solutions of the present invention, and does not necessarily belong to the prior art of the present patent application, and should not be used for evaluating the novelty and inventive step of the present application in the case that there is no clear evidence that the above content is disclosed at the filing date of the present patent application.
Disclosure of Invention
The invention aims to provide a three-dimensional human body measuring method and equipment thereof, which are used for solving the technical problem that the three-dimensional human body cannot be measured by one person in the measuring process in the prior art.
For this purpose, the invention provides a method for setting a first depth camera for real-time somatosensory measurement and a second depth camera for non-real-time somatosensory measurement in three-dimensional human body measurement equipment;
when the equipment is in a state to be measured, detecting the somatosensory instruction in real time according to the depth image of the somatosensory instruction acquired by the first depth camera; the somatosensory instruction is a gesture or action of a user interacting with the measuring equipment in a measuring area of the measuring equipment to start the equipment to carry out next measurement;
if the somatosensory instruction is detected to correspond to a preset activation instruction, switching the equipment to a human body model measurement state, and otherwise, continuously detecting the somatosensory instruction in real time;
and when the equipment is in a human body model measuring state, measuring to obtain the whole three-dimensional human body model according to the depth image acquired by the second depth camera.
Preferably, the first and second depth cameras are set to the same model; when the equipment is in a human body model measuring state, the method further comprises the step of acquiring a depth image according to the first depth camera to obtain the whole three-dimensional human body model through measurement.
Preferably, when the first depth camera and the second depth camera are of the same type, at least one second depth camera is selected from the plurality of second depth cameras as the first depth camera for obtaining the depth image of the somatosensory instruction.
Preferably, when the first depth camera and the second depth camera are set to different models, the first depth camera having a measurement view angle larger than that of the second depth camera acquires a depth image of the somatosensory instruction.
Preferably, the step of detecting that the somatosensory instruction corresponds to a preset activation instruction includes:
preprocessing a depth image acquired by a first depth camera to obtain a preprocessed depth image;
according to the preprocessed depth image, performing skeleton processing to obtain a skeleton model;
and identifying whether the somatosensory instruction corresponds to the obtained skeleton model and a preset activation instruction.
Preferably, the measuring to obtain the whole three-dimensional human body model comprises the following steps:
acquiring a plurality of local depth images of different parts of a human body of the object through a plurality of second depth cameras;
preprocessing the multiple local depth images to obtain multiple preprocessed depth images;
extracting a plurality of human body depth images from the plurality of preprocessed depth images;
and fusing the obtained multiple human body depth images into the whole human body so as to obtain a human body three-dimensional net model.
In addition, the invention provides three-dimensional human body measuring equipment which comprises a first depth camera for real-time somatosensory measurement and a second depth camera for non-real-time somatosensory measurement; the first device can be used for detecting the somatosensory instruction in real time according to the depth image acquired by the first depth camera when the equipment is in a state to be measured; the second device can be used for switching the equipment to a human body model measurement state if the somatosensory instruction is detected to correspond to a preset activation instruction, and otherwise, continuously detecting the somatosensory instruction in real time; and the third device can be used for measuring and obtaining the whole three-dimensional human body model according to the depth image acquired by the second depth camera when the equipment is in the human body model measuring state.
Preferably, the first and second depth cameras are of the same model, and the third means comprises means for acquiring depth images from the first depth camera to measure the entire three-dimensional phantom.
Preferably, the first depth camera is at least one of a plurality of second depth cameras.
Preferably, the first and second depth cameras are set to different models, the first depth camera having a measurement view angle greater than the second depth camera.
Preferably, the second means comprises:
means operable to pre-process a depth image acquired by a first depth camera to obtain a pre-processed depth image;
a device for performing skeleton processing according to the preprocessed depth image to obtain a skeleton model;
and the device can be used for identifying whether the somatosensory instruction corresponds to the somatosensory instruction according to the obtained skeleton model and a preset activation instruction.
Preferably, the third means comprises:
a plurality of second depth cameras operable to acquire a plurality of local depth images of different parts of the subject's body;
a device for preprocessing a plurality of local depth images to obtain a plurality of preprocessed depth images;
means for extracting a plurality of depth images of the human body from the plurality of preprocessed depth images;
the device can be used for fusing a plurality of obtained human body depth images into the whole human body so as to obtain a human body three-dimensional net model.
In addition, the invention also provides three-dimensional human body measuring equipment, which comprises a first depth camera for real-time somatosensory measurement and a second depth camera for non-real-time somatosensory measurement; and one or more processors configured to perform any of the methods described above.
Meanwhile, the invention also provides three-dimensional human body measuring equipment which comprises a first depth camera for real-time somatosensory measurement and a second depth camera for non-real-time somatosensory measurement; and a memory for storing a program; a processor running the program for controlling the dimensional anthropometric device to perform any of the methods described above.
Finally, the invention also proposes a computer-readable storage medium containing a computer program operable to cause a computer to perform any of the methods described above.
Compared with the prior art, the invention has the advantages that: compared with the prior art, the three-dimensional human body measuring device has the advantages that the defects that the process is complicated and the control of the whole three-dimensional human body measuring device can be completed only by the cooperation of working personnel due to the fact that the three-dimensional human body measuring needs to be operated according to the preset flow, are overcome, the scanning efficiency is high, the application environment is wider, and the intelligent degree is higher.
Drawings
FIG. 1 is a flow chart of a three-dimensional body measurement method according to an embodiment of the present invention;
FIG. 2 is a flow chart of an embodiment of the present invention including a first depth camera and a second depth camera together acquiring depth images to measure an entire three-dimensional human model.
Fig. 3 is a flowchart illustrating that when the somatosensory instruction is detected to correspond to a preset activation instruction according to an embodiment of the present invention.
FIG. 4 is a flowchart illustrating the measurement of the entire three-dimensional human body model according to the first embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a three-dimensional body measurement device according to a second embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. It should be emphasized that the following description is merely exemplary in nature and is not intended to limit the scope of the invention or its application.
Non-limiting and non-exclusive embodiments will be described with reference to the following figures, wherein like reference numerals refer to like parts, unless otherwise specified.
The first embodiment is as follows:
acquiring three-dimensional human body models of a measured user in different postures according to specific application requirements; generally, the model in the posture with both hands and feet slightly opened can relatively comprehensively acquire the size information of each part of the human body. In the measurement, there is a method in which a worker activates a depth camera to perform measurement after a human body is prepared for a corresponding posture. In this embodiment, automatic measurement in the corresponding posture can be performed without a worker.
In order to achieve the purpose of automatic measurement, the present embodiment provides a three-dimensional human body measurement method, as shown in fig. 1, including the following steps:
setting a first depth camera for real-time somatosensory measurement and a second depth camera for non-real-time somatosensory measurement in three-dimensional human body measurement equipment;
when the equipment is in a state to be measured, detecting the somatosensory instruction in real time according to the depth image of the somatosensory instruction acquired by the first depth camera; the somatosensory instruction is a gesture or action of a user interacting with the measuring equipment in a measuring area of the measuring equipment to start the equipment to carry out next measurement;
if the somatosensory instruction is detected to correspond to a preset activation instruction, switching the equipment to a human body model measurement state, and otherwise, continuously detecting the somatosensory instruction in real time;
and when the equipment is in a human body model measuring state, measuring to obtain the whole three-dimensional human body model according to the depth image acquired by the second depth camera.
The method may specifically be that, after the user enters the measurement area, the posture of the hand is raised, the posture is acquired by the first depth camera and recognized by the computer, and after the posture is recognized, the second depth camera of the device may be activated for scanning measurement after a predetermined time (for example, 2 seconds), and simultaneously, within the predetermined time, the human body is switched to the posture to be measured (measurement posture), so as to obtain the final three-dimensional human body model.
By applying the activation function, the three-dimensional body measurement device of the embodiment can have a single-person operation function, so that the labor cost is saved.
In the embodiment, a depth camera is adopted to obtain a depth image;
at present, the cameras for acquiring depth images mainly comprise depth cameras based on a structured light triangulation method, a time flight method or a binocular vision principle.
The depth camera based on the structured light trigonometry utilizes a laser projector to project coded standard structured light patterns into a space, the standard structured light patterns are modulated according to different target depths in the space, the difference between the modulated structured light image and the standard structured light patterns is obtained through algorithms such as image correlation, and the like, and the depth image of the whole target space can be solved by establishing the relation between the difference and the target depths according to the structured light trigonometry.
The depth camera based on the time flight method utilizes a laser transmitter to transmit laser pulses to a target, a light receiving device acquires the pulses and records the flight time of the transmitted and received light, and the depth image of the target can be calculated according to the flight time.
The depth camera based on the binocular vision principle is essentially similar to the structured light triangulation principle, and is different in that the structured light triangulation is active measurement, and the binocular vision is passive measurement. The difference of images acquired by the left camera and the right camera on the parallax is utilized, the parallax is acquired by a visual algorithm, and then the depth value of the target is calculated by utilizing a trigonometry measurement principle.
The three depth acquisition methods are good and bad respectively, the structured light triangulation method is low in cost and high in depth acquisition efficiency, but interference exists when a plurality of cameras measure one target space simultaneously. Whereas the depth camera of the time-of-flight method is costly. The binocular vision depth camera has a complex algorithm and has certain requirements on the environment where the target is located. Thus, different depth cameras may be appropriately selected for specific application environments, and there is no limitation on the depth cameras in the present embodiment, wherein the depth cameras of the principle may also be applied to the present embodiment.
The present embodiment selects by default a depth camera based on the principle of structured light triangulation in the following description.
A separate depth camera may be used to acquire the depth image and a separate RGB camera may acquire the RGB image. Generally, in order to acquire an RGBD image of a target object without parallax, there are mainly two ways:
firstly, a depth camera and an RGB camera are respectively utilized to independently acquire a depth image and an RGB image, and then registration is carried out according to the position relation of the depth camera and the RGB camera and respective internal parameters, such as focal length, resolution, image sensor size and the like, so as to eliminate parallax between the two cameras, and further, an RGBD image of a target object is acquired.
The second is an image sensor using RGB-IR. A conventional RGB camera assembly is composed of an image sensor, an optical filter, and a lens as shown in fig. 1. Generally, an image sensor is used to convert light intensity into a corresponding digital signal, and a filter is used to convert a light signal of a specific wavelength into a corresponding digital signal. The ordinary RGB camera adopts a Bayer filter, the filter has filter units which are the same as the number of pixels of the image sensor and correspond to the pixels of the image sensor one by one, the Bayer filter is respectively provided with filter units for passing red light, green light and blue light, and the ratio of the Bayer filter to the red light, the green light and the blue light is R (25%), G (50%) and B (25%) considering that human eyes are more sensitive to the green light.
After the image sensor in the camera acquires the information of each component (e.g. R, G, B, IR), since each information only occupies a part of the pixels, the intensity information of the other three components on each pixel needs to be restored by interpolation, so as to finally realize the synchronous acquisition of RGB image and IR image. There are various methods of interpolation, such as weighted averaging, etc., and they are not described in detail herein because they are prior art. The acquired IR image is used to calculate a depth image, so that an RGBD image without parallax can be acquired.
The method of RGBD image acquisition is not limited in this embodiment.
In other embodiments, the first depth camera may be selected from the second depth cameras, and the first depth camera and the second depth camera are set to be the same model; when the device is in a manikin measurement state, as shown in fig. 2, acquiring a depth image according to the first depth camera to obtain a whole three-dimensional manikin by measurement. Therefore, after the first depth camera acquires the depth image, the first depth camera can participate in the measurement of the human body model at the same time.
At this time, when the first depth camera and the second depth camera are of the same model, at least one second depth camera may be selected from the plurality of second depth cameras as the first depth camera for acquiring the depth image of the somatosensory instruction.
In other embodiments, when the first depth camera and the second depth camera are set to different models, the first depth camera with a measurement view angle larger than that of the second depth camera acquires a depth image of a somatosensory instruction.
In this embodiment, as shown in fig. 3, the step of detecting that the somatosensory instruction corresponds to a preset activation instruction includes:
preprocessing a depth image acquired by a first depth camera to obtain a preprocessed depth image;
according to the preprocessed depth image, performing skeleton processing to obtain a skeleton model;
and identifying whether the somatosensory instruction corresponds to the obtained skeleton model and a preset activation instruction.
In this embodiment, as shown in fig. 4, the step of obtaining the whole three-dimensional human body model by measurement includes the following steps:
acquiring a plurality of local depth images of different parts of a human body of the object through a plurality of second depth cameras;
preprocessing the multiple local depth images to obtain multiple preprocessed depth images;
extracting a plurality of human body depth images from the plurality of preprocessed depth images;
and fusing the obtained multiple human body depth images into the whole human body so as to obtain a human body three-dimensional net model.
The method specifically comprises the following steps:
background segmentation
After the RGBD images of the respective parts of the human body are acquired, since the images also include the background, the background segmentation is performed first, and only the images of the parts of the human body are retained.
Camera calibration
And uniformly calibrating all the second depth cameras. After calibration, the coordinate systems of all the second depth cameras are unified, so that subsequent image fusion is facilitated.
The calibration mode can be used for calibrating between every two cameras, one of the cameras can be used as a standard, and the other second depth cameras and the standard camera are calibrated. In this embodiment, a two-by-two calibration method is adopted, and finally the calibration results are calculated to be unified in the same coordinate system.
Depth image fusion
The depth image fusion, namely registration, is to register images of all parts of a human body to form a complete human body image. The registration algorithm currently has a rigid registration and a non-rigid registration. Considering that the image capturing task of all the second depth cameras of this embodiment is completed in a short time, in which the human body can be regarded as a rigid stationary object, after calibration by the second depth cameras in the above steps, a reference coordinate system is selected, and after all the images are transformed by rigid coordinates, all the images can be fused into an integral three-dimensional human body image.
Example two:
the implementation provides three-dimensional body measurement equipment for executing the method provided by the first embodiment, and the three-dimensional body measurement equipment comprises a first depth camera for real-time somatosensory measurement and a second depth camera for non-real-time somatosensory measurement; the first device can be used for detecting the somatosensory instruction in real time according to the depth image acquired by the first depth camera when the equipment is in a state to be measured; the second device can be used for switching the equipment to a human body model measurement state if the somatosensory instruction is detected to correspond to a preset activation instruction, and otherwise, continuously detecting the somatosensory instruction in real time; and the third device can be used for measuring and obtaining the whole three-dimensional human body model according to the depth image acquired by the second depth camera when the equipment is in the human body model measuring state.
The real-time somatosensory measurement refers to the measurement of an activation instruction appearing in a human body in a measurement area in real time, the non-real-time measurement is the measurement of a depth image only after the first depth camera identifies and detects the activation instruction appearing in the measurement area, and in addition, the measurement is not carried out; as shown in fig. 5, a plurality of second depth cameras 2 are equally provided on a plurality of stands 1 in number, the plurality of stands 1 enclosing a measurement area 3 at the center of the apparatus; in this embodiment, the first to third apparatuses may be classified as a computing device 5, the first depth camera and the second depth camera 2 are connected to the computing device 5, and the first depth camera acquires a depth image of a human body in the measurement region in real time to activate the computing device and the second depth camera to enter a measurement state from a state to be measured; the plurality of second depth cameras are used for acquiring depth images of all parts of the human body in the measuring area, and the received depth images are fused in the computing equipment to obtain a complete human body three-dimensional model; the three-dimensional anthropometric equipment of this embodiment is provided with two kinds of depth cameras to realize gesture or action instruction and control the conversion of whole three-dimensional anthropometric equipment state, compare in prior art, this embodiment has overcome because three-dimensional anthropometric survey need operate according to predetermined flow, and the process is loaded down with trivial details, and need the staff cooperation just can accomplish the shortcoming of the control of whole three-dimensional anthropometric equipment.
In the embodiment, the number of the plurality of supports is 4, and the supports are arranged around the measuring area in a surrounding manner; the number of the second depth cameras is 16, and the brackets are provided with 4 second depth cameras, wherein the number of the brackets and the arrangement of the second depth cameras can be specially set according to the size and the precision requirement of a specific measured object; generally, the number of the supports and the number of the second depth cameras are increased along with the increase of the measured object and the increase of the precision requirement; the second depth camera is arranged to cover all parts of the human body. Typically, there needs to be some overlap between two adjacent second depth cameras in order to facilitate subsequent point cloud fusion.
The first and second depth cameras are set to the same model, and the third means includes means for acquiring a depth image from the first depth camera to measure the entire three-dimensional phantom. And the first depth camera is at least one of a plurality of second depth cameras.
In other embodiments, the first and second depth cameras are set to different models, the first depth camera having a measured viewing angle that is greater than the measured viewing angle of the second depth camera.
The second apparatus of this embodiment includes:
means operable to pre-process a depth image acquired by a first depth camera to obtain a pre-processed depth image;
a device for performing skeleton processing according to the preprocessed depth image to obtain a skeleton model;
and the device can be used for identifying whether the somatosensory instruction corresponds to the somatosensory instruction according to the obtained skeleton model and a preset activation instruction.
The third apparatus of this embodiment includes:
a plurality of second depth cameras operable to acquire a plurality of local depth images of different parts of the subject's body;
a device for preprocessing a plurality of local depth images to obtain a plurality of preprocessed depth images;
means for extracting a plurality of depth images of the human body from the plurality of preprocessed depth images;
the device can be used for fusing a plurality of obtained human body depth images into the whole human body so as to obtain a human body three-dimensional net model.
The embodiment further includes a connector 4, and the first depth camera and the second depth camera are both connected to the computing device 5 through the connector, and of course, may also be connected through other manners, for example: USB interface, wireless network, etc.;
example three:
the embodiment provides three-dimensional human body measuring equipment which comprises a first depth camera used for real-time somatosensory measurement and a second depth camera used for non-real-time somatosensory measurement; and one or more processors configured to perform the method of embodiment one.
Example four:
the embodiment provides three-dimensional human body measuring equipment which comprises a first depth camera used for real-time somatosensory measurement and a second depth camera used for non-real-time somatosensory measurement; and a memory for storing a program; and the processor runs the program to control the dimension human body measuring equipment to execute the method in the first embodiment.
The present embodiments provide a computer readable storage medium containing a computer program operable to cause a computer to perform the method of the first embodiment.
Those skilled in the art will recognize that numerous variations are possible in light of the above description, and thus the examples are intended to describe one or more specific embodiments.
While there has been described and illustrated what are considered to be example embodiments of the present invention, it will be understood by those skilled in the art that various changes and substitutions may be made therein without departing from the spirit of the invention. In addition, many modifications may be made to adapt a particular situation to the teachings of the present invention without departing from the central concept described herein. Therefore, it is intended that the invention not be limited to the particular embodiments disclosed, but that the invention will include all embodiments and equivalents falling within the scope of the invention.
Claims (13)
1. A three-dimensional human body measuring method is characterized in that a first depth camera for real-time somatosensory measurement and a second depth camera for non-real-time somatosensory measurement are set in a three-dimensional human body measuring device;
when the equipment is in a state to be measured, detecting the somatosensory instruction in real time according to the depth image of the somatosensory instruction acquired by the first depth camera;
if the somatosensory instruction is detected to correspond to a preset activation instruction, switching the equipment to a human body model measurement state, and otherwise, continuously detecting the somatosensory instruction in real time;
when the equipment is in a human body model measuring state, measuring according to the depth image under the measuring posture acquired by the second depth camera to obtain a whole three-dimensional human body model;
therefore, automatic measurement under corresponding postures is completed, and three-dimensional human body models of the measured user under different postures are obtained;
the real-time somatosensory measurement is to measure an activation instruction of a human body in a measurement area in real time, and the non-real-time somatosensory measurement is to measure a depth image only after the first depth camera identifies and detects the activation instruction in the measurement area, and in addition, the measurement is not carried out.
2. The three-dimensional anthropometric method of claim 1, wherein the first depth camera and the second depth camera are set to the same model; when the equipment is in a human body model measuring state, obtaining a depth image according to the first depth camera to obtain a whole three-dimensional human body model through measurement, so that the first depth camera also participates in the measurement of the human body model after obtaining the depth image; and selecting at least one second depth camera from the plurality of second depth cameras as a first depth camera for obtaining the depth image of the somatosensory instruction.
3. The three-dimensional human body measurement method according to claim 1, wherein when the first depth camera and the second depth camera are set to different models, acquisition of a depth image of the somatosensory instruction is performed by the first depth camera having a measurement angle of view larger than that of the second depth camera.
4. The three-dimensional human body measurement method according to any one of claims 1 to 3, wherein the step of detecting that the somatosensory instruction corresponds to a preset activation instruction comprises the steps of:
preprocessing a depth image acquired by a first depth camera to obtain a preprocessed depth image;
according to the preprocessed depth image, performing skeleton processing to obtain a skeleton model;
and identifying whether the somatosensory instruction corresponds to the obtained skeleton model and a preset activation instruction.
5. A three-dimensional human body measurement method according to any one of claims 1-3, wherein said measuring to obtain the entire three-dimensional human body model comprises the steps of:
acquiring a plurality of local depth images of different parts of a human body of the object through a plurality of second depth cameras;
preprocessing the multiple local depth images to obtain multiple preprocessed depth images;
extracting a plurality of human body depth images from the plurality of preprocessed depth images;
fusing the obtained multiple human body depth images into a whole human body so as to obtain a human body three-dimensional net model; the method specifically comprises the following steps: and after the calibration is carried out by the second depth camera, selecting a reference coordinate system, and fusing all images into an integral three-dimensional human body image after all images are transformed by rigid coordinates.
6. A three-dimensional body measurement device is characterized by comprising a first depth camera for real-time body sensing measurement and a second depth camera for non-real-time body sensing measurement; the first device can be used for detecting the somatosensory instruction in real time according to the depth image acquired by the first depth camera when the equipment is in a state to be measured; the second device can be used for switching the equipment to a human body model measurement state if the somatosensory instruction is detected to correspond to a preset activation instruction, and otherwise, continuously detecting the somatosensory instruction in real time; the third device can be used for measuring and obtaining the whole three-dimensional human body model according to the depth image acquired by the second depth camera when the equipment is in a human body model measuring state; therefore, automatic measurement under corresponding postures can be completed, and three-dimensional human body models of the measured user under different postures can be obtained;
the first depth camera is used for measuring an activation instruction of a human body in a measurement area in real time, the second depth camera is used for measuring a depth image after the first depth camera identifies and detects the activation instruction in the measurement area, and the second depth camera does not measure the depth image except the first depth camera.
7. The three-dimensional human body measuring apparatus according to claim 6, wherein the first and second depth cameras are set to the same model, and the third means includes means for acquiring a depth image from the first depth camera to measure the entire three-dimensional human body model; the first depth camera is at least one of a plurality of second depth cameras.
8. The three-dimensional anthropometric device of claim 6, wherein the first and second depth cameras are set to different models, the first depth camera having a measurement view angle greater than that of the second depth camera.
9. The three-dimensional anthropometric device of any one of claims 6 to 8, wherein the second means comprises:
means operable to pre-process a depth image acquired by a first depth camera to obtain a pre-processed depth image;
a device for performing skeleton processing according to the preprocessed depth image to obtain a skeleton model;
and the device can be used for identifying whether the somatosensory instruction corresponds to the somatosensory instruction according to the obtained skeleton model and a preset activation instruction.
10. The three-dimensional anthropometric device of any one of claims 6 to 8, wherein the third means comprises:
a plurality of second depth cameras operable to acquire a plurality of local depth images of different parts of the subject's body;
a device for preprocessing a plurality of local depth images to obtain a plurality of preprocessed depth images;
means for extracting a plurality of depth images of the human body from the plurality of preprocessed depth images;
the device can be used for fusing a plurality of obtained human body depth images into the whole human body so as to obtain a human body three-dimensional net model.
11. A three-dimensional body measurement device is characterized by comprising a first depth camera for real-time body sensing measurement and a second depth camera for non-real-time body sensing measurement; and one or more processors configured to perform the method of any one of claims 1-5.
12. A three-dimensional body measurement device is characterized by comprising a first depth camera for real-time body sensing measurement and a second depth camera for non-real-time body sensing measurement; and a memory for storing a program; a processor running the program for controlling the dimensional anthropometric device to perform the method of any one of claims 1-5.
13. A computer-readable storage medium containing a computer program, characterized in that: the computer program is operable to cause a computer to perform the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710079457.XA CN106959747B (en) | 2017-02-14 | 2017-02-14 | Three-dimensional human body measuring method and apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710079457.XA CN106959747B (en) | 2017-02-14 | 2017-02-14 | Three-dimensional human body measuring method and apparatus thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106959747A CN106959747A (en) | 2017-07-18 |
| CN106959747B true CN106959747B (en) | 2020-02-18 |
Family
ID=59481169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710079457.XA Active CN106959747B (en) | 2017-02-14 | 2017-02-14 | Three-dimensional human body measuring method and apparatus thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106959747B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111199576B (en) * | 2019-12-25 | 2023-08-18 | 中国人民解放军军事科学院国防科技创新研究院 | Outdoor large-range human body posture reconstruction method based on mobile platform |
| CN111968165B (en) * | 2020-08-19 | 2024-01-23 | 北京拙河科技有限公司 | Dynamic human body three-dimensional model complement method, device, equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102681661A (en) * | 2011-01-31 | 2012-09-19 | 微软公司 | Using a three-dimensional environment model in gameplay |
| CN104008571A (en) * | 2014-06-12 | 2014-08-27 | 深圳奥比中光科技有限公司 | Human body model obtaining method and network virtual fitting system based on depth camera |
| CN104040464A (en) * | 2012-01-10 | 2014-09-10 | 戴姆勒股份公司 | Method and device for operating functions in a vehicle using gestures performed in three-dimensional space, and related computer program product |
-
2017
- 2017-02-14 CN CN201710079457.XA patent/CN106959747B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102681661A (en) * | 2011-01-31 | 2012-09-19 | 微软公司 | Using a three-dimensional environment model in gameplay |
| CN104040464A (en) * | 2012-01-10 | 2014-09-10 | 戴姆勒股份公司 | Method and device for operating functions in a vehicle using gestures performed in three-dimensional space, and related computer program product |
| CN104008571A (en) * | 2014-06-12 | 2014-08-27 | 深圳奥比中光科技有限公司 | Human body model obtaining method and network virtual fitting system based on depth camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106959747A (en) | 2017-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107025635B (en) | Depth-of-field-based image saturation processing method and device and electronic device | |
| EP3665506B1 (en) | Apparatus and method for generating a representation of a scene | |
| CN110458897B (en) | Multi-camera automatic calibration method and system and monitoring method and system | |
| CN111345029B (en) | Target tracking method and device, movable platform and storage medium | |
| JP7255718B2 (en) | Information processing device, recognition support method, and computer program | |
| CN108234984A (en) | Binocular depth camera system and depth image generation method | |
| US8179448B2 (en) | Auto depth field capturing system and method thereof | |
| CN110827392A (en) | Monocular image three-dimensional reconstruction method, system and device with good scene usability | |
| CN106959747B (en) | Three-dimensional human body measuring method and apparatus thereof | |
| EP3371780A1 (en) | System and methods for imaging three-dimensional objects | |
| CN102316355A (en) | Generation method of 3D machine vision signal and 3D machine vision sensor | |
| US11250592B2 (en) | Information processing apparatus | |
| EP3756164B1 (en) | Methods of modeling a 3d object, and related devices and computer program products | |
| CN101980299B (en) | Chessboard calibration-based camera mapping method | |
| CN109618085A (en) | Electronic equipment and mobile platform | |
| JP2019022147A (en) | Light source direction estimation device | |
| CN103442183A (en) | Automatic visual navigation method based on infrared thermal imaging principle | |
| US9633279B2 (en) | Free space positioning method and system | |
| CN208079276U (en) | binocular depth camera system | |
| CN107067468B (en) | Information processing method and electronic equipment | |
| KR102017949B1 (en) | Apparatus and method for calibrating camera using rectangular parallelepiped with led | |
| KR101326095B1 (en) | Apparatus for uniting images and method thereof | |
| JP2006331009A (en) | Image processor and image processing method | |
| CN114727075B (en) | Projection control method and device, projection equipment and storage medium | |
| CN111536895B (en) | Appearance recognition device, appearance recognition system, and appearance recognition method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: A808, Zhongdi building, industry university research base, China University of Geosciences, No.8, Yuexing Third Road, Nanshan District, Shenzhen, Guangdong 518000 Patentee after: Obi Zhongguang Technology Group Co., Ltd Address before: A808, Zhongdi building, industry university research base, China University of Geosciences, No.8, Yuexing Third Road, Nanshan District, Shenzhen, Guangdong 518000 Patentee before: SHENZHEN ORBBEC Co.,Ltd. |