CN107577451A - More Kinect human skeletons coordinate transformation methods and processing equipment, readable storage medium storing program for executing - Google Patents
More Kinect human skeletons coordinate transformation methods and processing equipment, readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN107577451A CN107577451A CN201710657342.4A CN201710657342A CN107577451A CN 107577451 A CN107577451 A CN 107577451A CN 201710657342 A CN201710657342 A CN 201710657342A CN 107577451 A CN107577451 A CN 107577451A
- Authority
- CN
- China
- Prior art keywords
- skeleton
- coordinate
- terminal device
- mentioned
- human
- 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
- 238000011426 transformation method Methods 0.000 title claims abstract description 25
- 238000012545 processing Methods 0.000 title claims description 11
- 238000003860 storage Methods 0.000 title claims description 8
- 239000011159 matrix material Substances 0.000 claims abstract description 86
- 238000013519 translation Methods 0.000 claims abstract description 57
- 230000009466 transformation Effects 0.000 claims abstract description 43
- 238000006243 chemical reaction Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 18
- 241000208340 Araliaceae Species 0.000 claims description 9
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 9
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 9
- 235000008434 ginseng Nutrition 0.000 claims description 9
- 239000000203 mixture Substances 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 abstract description 4
- 239000002245 particle Substances 0.000 description 15
- 210000000988 bone and bone Anatomy 0.000 description 10
- 230000009471 action Effects 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 5
- 230000015572 biosynthetic process Effects 0.000 description 5
- 238000003786 synthesis reaction Methods 0.000 description 5
- 241001269238 Data Species 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 208000031872 Body Remains Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 229940050561 matrix product Drugs 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The present invention relates to computer graphical visual field, proposes a kind of more Kinect human skeletons coordinate transformation methods, it is intended to solves the problems, such as coordinate transform between multiple Kinect in human body tracking environment.This method includes：The multiframe skeleton data of the same human body transmitted by each terminal device is received, determines the weighted average skeleton data of the human skeleton of each terminal device；Calculate the confidence level of each terminal device data, determine confidence level highest terminal device be reference terminal equipment, the coordinate system of reference terminal equipment be reference frame；The Eulerian angles and translation variable between reference frame and non-reference coordinate system are determined according to coordinate of the human skeleton under reference frame and the coordinate under non-reference coordinate system；The transformation matrix between reference frame and non-reference coordinate system is determined according to Eulerian angles and translation variable；The skeleton data of each terminal device is transformed under reference frame using above-mentioned transformation matrix.It the method achieve the conversion of the coordinate continuous-stable between the human skeleton to more Kinect.
Description
Technical field
The present invention relates to computer graphical visual field, and in particular to computer graphical processing field, it is more particularly to a kind of
More Kinect human skeletons coordinate transformation methods and processing equipment, storage medium.
Background technology
, in time will detection or monitoring with the development of computer graphical vision technique and the development of human-computer interaction technology
To object or person posture or action correctly intactly show, become more and more important.Passed based on Microsoft Kinect
Sensor can obtain the image information of human body in real time, catch analysis human action information, and according to acquired human action
Information controls relevant device or the action of control machine people etc..
Due to the limitation of kinect catching ranges and angle, separate unit kinect captured informations due to object itself and object it
Between hiding relation, cause the missing of depth and visual information and substantially reduce the precision and effect of seizure.Use more
The motion capture system of Kinect compositions, can provide a bigger field range, when human body is in the Kinect visual field
In the range of when being disappeared because of blocking, system still can continue to catch the motion of human body by other Kinect.Therefore, it is necessary to
The skeleton data of more kinect catcher's bodies is transformed into unified coordinate system, but by the data conversion under different coordinates
To under the same coordinate system, the position of the Kinect placements due to catching skeleton data, angle are different, in fact it could happen that change same ginseng
Examine the problem of data error under coordinate system is big, inconvenient for use.
At present, the application for more Kinect sensor Coordinate Conversions has the KSCC calibration algorithms that Wei Tao et al. are proposed,
For calibrating the user of the optional position in long-range training system.This method is initial firstly the need of the long-range user's of collection
Position data, and utilize the initial center position coordinate and user and Kinect initial angle of primary data calculating user
Degree, can all be converted to a unified world coordinate system by all skeletons of a quaternary spin matrix afterwards.But when
The motion capture system of preceding more Kinect compositions exist institute catcher body error is larger, Kinect sensor can only be horizontal
Placement, when after human body is turned round can not normal use the problems such as.
The content of the invention
It has been the multiple Kinect sensings for solving to be arranged at diverse location to solve above mentioned problem of the prior art
The error caused by Coordinate Conversion between device is larger, Kinect sensor can only be horizontal placement, can not after human body is turned round
The problems such as normal use, the present invention use following technical scheme to solve the above problems：
In a first aspect, this application provides a kind of more Kinect human skeletons coordinate transformation methods, this method includes：Obtain
The skeleton data that multiple terminal devices are captured；Using the transformation matrix of coordinates trained, above-mentioned skeleton data is changed, wherein,
Above-mentioned transformation matrix is trained to include：The multiframe skeleton data of the same human body transmitted by multiple terminal devices is received, according to above-mentioned
Skeleton data determines the weighted average skeleton data of the skeleton data of each above-mentioned terminal device；Captured according to each terminal device
Skeleton data calculates the confidence level of each above-mentioned terminal device, determines that confidence level highest terminal is set from above-mentioned terminal device
Standby is reference terminal equipment, and the coordinate system for determining above-mentioned reference terminal equipment is reference frame, except above-mentioned reference terminal equipment
Outer start and stop designated equipment determination takes reference terminal equipment, and the coordinate system of above-mentioned non-reference terminal device is non-reference coordinate system；
According to coordinate of the human skeleton corresponding to above-mentioned weighted average skeleton data under above-mentioned reference frame and in above-mentioned non-reference
Eulerian angles between mathematic interpolation reference frame and above-mentioned non-reference coordinate system and translation between coordinate under coordinate system become
Amount；Above-mentioned Eulerian angles between the reference axis of above-mentioned reference frame and the reference axis of above-mentioned non-reference coordinate system are formed rotation
Matrix, the above-mentioned translation variable between the reference axis of above-mentioned reference frame and the reference axis of above-mentioned non-reference coordinate system are formed
Translation matrix, using the product of above-mentioned spin matrix and translation matrix as between above-mentioned reference frame and above-mentioned non-ginseng coordinate system
Transformation matrix.
In some instances, above-mentioned skeleton data includes each body joint point coordinate of composition human skeleton and above-mentioned artis is sat
Target confidence level.
In some instances, the weighting of the above-mentioned skeleton data that each above-mentioned terminal device is determined according to above-mentioned skeleton data is put down
Equal skeleton data, including：Gather the multiframe skeleton data of human skeleton respectively by multiple terminal devices；According to acquired each
The body joint point coordinate of the above-mentioned skeleton data of every frame and the confidence level of above-mentioned body joint point coordinate of terminal device, sat with above-mentioned artis
Target confidence level is the weight of above-mentioned body joint point coordinate, calculates each artis for the human skeleton that above-mentioned terminal device is detected
Artis weighted average；Determined using each above-mentioned artis weighted average by the joint point data of each above-mentioned artis
The weighted average skeleton data for the human skeleton that human skeleton data are detected by above-mentioned terminal device.
In some instances, the above-mentioned skeleton data captured according to each terminal device, each above-mentioned terminal device is calculated
Confidence level, including：Obtain the confidence level of each artis for the multiframe skeleton data that each terminal device is gathered；Calculate each above-mentioned
The average value of the confidence level of each artis for the skeleton data that terminal device is gathered；Add and operate above-mentioned terminal device and gathered
Composition human skeleton whole artis each artis confidence level average value；Determine it is above-mentioned plus and operating result be
Above-mentioned terminal device confidence level.
In some instances, the above-mentioned human skeleton according to corresponding to above-mentioned weighted average skeleton data is in above-mentioned reference coordinate
Difference between the lower coordinate of system and coordinate under above-mentioned non-reference coordinate system, calculate reference frame and each non-coordinate system it
Between Eulerian angles and translation variable, including：Calculate the weighted average for the above-mentioned human skeleton that above-mentioned reference terminal equipment is gathered
The difference of the weighted average skeleton data for the above-mentioned human skeleton that skeleton data is gathered with above-mentioned non-reference terminal device；More than
State the difference skeleton data that difference is above-mentioned human skeleton；Calculate seat of the above-mentioned difference skeleton data under above-mentioned reference frame
Mark and each reference axis angle of above-mentioned reference frame are Eulerian angles；Above-mentioned difference skeleton data is calculated under above-mentioned reference frame
The distance of each reference axis of coordinate and above-mentioned reference frame be translation variable.
In some instances, it is above-mentioned to determine reference frame and each above-mentioned non-reference according to above-mentioned Eulerian angles and translation variable
Transformation matrix between the coordinate system of terminal device, including：Determine that rotation becomes respectively according to above-mentioned Eulerian angles and translation variable
Change matrix and translation matrix；The product for determining above-mentioned rotational transformation matrix and above-mentioned translation matrix is transformation matrix.
In some instances, it is above-mentioned to determine reference frame and each above-mentioned non-reference according to above-mentioned Eulerian angles and translation variable
Transformation matrix between the coordinate system of terminal device, including：Three axles of above-mentioned reference frame are determined according to above-mentioned Eulerian angles
Xyz Eulerian angles θx、θy、θz, it is R to obtain rotational transformation matrixi(θx, θy, θz)=Riz(θz)·Riy(θy)·Rix(θx)；According to
Above-mentioned translation variable determines the variable x, y, z of three axles of above-mentioned reference frame, it can be deduced that translation matrix Ti(x, y, z)；
Using the product of above-mentioned rotational transformation matrix and above-mentioned translation matrix as transformation matrix Mi。
In some instances, the above method also includes：After weighted average skeleton is calculated, judge that above-mentioned human skeleton is
Front or back；If judged result is reverse side, the body joint point coordinate of above-mentioned human skeleton both sides is subjected to right and left mutually changing.
Second aspect, this application provides a kind of more Kinect human skeletons coordinate transform processing equipment, the equipment includes：
One or more processors, it is adapted for carrying out each bar program；Storage device, for storing one or more programs, said procedure is fitted
In being loaded as processor and being performed to realize more Kinect human skeletons coordinate transforms described in above-mentioned first aspect any example
Method.
The third aspect, this application provides a kind of readable storage medium storing program for executing, the readable storage medium storing program for executing is stored with computer program,
The program realizes more Kinect human skeletons coordinate transforms described in any example in above-mentioned first aspect when being executed by processor
Method.
The Kinect human skeletons coordinate transformation method and processing equipment that the application provides, pass through received multiframe bone
Confidence level highest terminal device is determined in rack data, the coordinate system for specifying confidence level highest terminal device is reference coordinate
System, compares the difference of coordinate of the skeleton data under reference frame and the coordinate under the coordinate of non-reference terminal, determines
Eulerian angles and translation variable between the coordinate system of reference frame and non-reference terminal device, and then transformation matrix is determined,
Using the transformation matrix, the coordinate transform between the coordinate system and reference frame of each non-reference terminal is realized.
Brief description of the drawings
Fig. 1 is that the application can apply to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of more Kinect human skeletons coordinate transformation methods of the application；
Fig. 3 is the flow chart according to another embodiment of more Kinect human skeletons coordinate transformation methods of the application；
Fig. 4 is the image in the skeleton data of the same human body of the terminal device seizure of two diverse locations；
Fig. 5 is the figure shown by the skeleton data to same human skeleton under converted matrix conversion to reference frame
Picture.
Embodiment
The preferred embodiment of the present invention described with reference to the accompanying drawings.It will be apparent to a skilled person that this
A little embodiments are used only for explaining the technical principle of the present invention, it is not intended that limit the scope of the invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1, which is shown, can apply more Kinect human skeletons coordinate transformation methods of the application or more Kinect human bodies bones
The exemplary system architecture of the embodiment of rack coordinate conversion process equipment.
As shown in figure 1, system architecture can include terminal device 101,102,103, network 104 and server 105.Network
104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can include
Various connection types, such as wired, wireless communication link or fiber optic cables etc..
Terminal device 101,102,103 can be by carrying out information exchange, to receive between network 104 and server 105
Or send information etc..Information exchange can be carried out by network 104 between terminal device 101,102,103.
Terminal device 101,102,103 can be the various electronic equipments for having display screen and supporting network service, including
But it is not limited to smart mobile phone, tablet personal computer, pocket computer on knee and desktop computer etc..It should be noted that terminal
Equipment includes being used for image identification, the sensor of speech recognition, e.g., the sensors of Kinect 2.0, wherein, Kinect 2.0 is passed
Sensor is in the body-sensing periphery peripheral hardware 3D body-sensing video cameras issued in 2014 by Microsoft.
Server 105 can be to provide the processor or server of various services, such as to terminal device 101,102,103
Information that is transmitted or providing carries out data analysis, realizes the image procossing clothes of coordinate transform between the image of different terminal equipment
Business device, above-mentioned image processing server can carry out the processing such as analyzing to the information received, and generation result is (for example, right
Each coordinate transform of human skeleton acquired in each terminal device is under reference frame, by the skeleton number under reference frame
According to display) shown in user interface.It should be noted that in the application, server 105 can be the server being separately provided,
Can also choose or specify one of terminal device from terminal device 101,102,103 as server.
It should be noted that more Kinect human skeletons coordinate transformation methods that the embodiment of the present application is provided are typically by taking
Business device 105 is performed, and correspondingly, more Kinect human skeletons coordinate transform processing equipment are generally positioned in server 105.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2, Fig. 2 shows a reality of more Kinect human skeletons coordinate transformation methods according to the application
Apply the flow of example.More Kinect human skeletons coordinate transformation methods, comprise the following steps：
Step 201, the skeleton data that multiple terminal devices are captured is received.
In the present embodiment, electronic equipment (such as the Fig. 1 of more Kinect human skeletons coordinate transformation methods operation thereon
Shown server) can be sent by wired connection mode or radio connection from terminal device receiving terminal apparatus
The skeleton data of human body.Wherein, terminal device can obtain the skeleton data of human body by connected Kinect sensor,
And obtained skeleton data is sent to server.Above-mentioned skeleton data refers to the figure of the human body detected by Kinect sensor
As data, when above-mentioned Kinect sensor is mapped under the Kinect sensor coordinate system detected by per frame image data
Data.
Step 202, using the transformation matrix of coordinates trained, above-mentioned skeleton data is changed.
In the present embodiment, using the changes in coordinates matrix trained, the skeleton number that above-mentioned each terminal device is captured
According to the coordinate data being transformed under same reference frame, to be chased after in the action of different terminal-pair human body or human body
Track.Keep position and the angle of above-mentioned each terminal device constant, the arbitrary image data (tracing Area that above-mentioned terminal device is captured
The skeleton data of the human skeleton of one or more personages in domain) it can be transformed under reference frame.Set by each terminal
The skeleton data conversion for the human skeleton that transformation matrix between the standby equipment with reference terminal is captured above-mentioned each terminal device
Coordinate under to reference frame.
Wherein, the step of above-mentioned training transformation matrix of coordinates includes：
Sub-step 2021, the multiframe skeleton data of the same human body transmitted by multiple terminal devices is received, according to above-mentioned bone
Rack data determines the weighted average skeleton data of the skeleton data of each above-mentioned terminal device.
In this sub-step, server receives the skeleton data of same human body from multiple terminal devices.Above-mentioned skeleton number
According to the view data for referring to the human body detected by Kinect sensor, above-mentioned Kinect sensor is detected by per frame figure
As data are mapped to data when under the Kinect sensor coordinate system, by the ranking operation to data, determine above-mentioned each
The weighted average of the skeleton number for the human skeleton that individual terminal device is captured.Above-mentioned skeleton data can be detected per frame
When view data is mapped under the Kinect sensor coordinate system, state above-mentioned human skeleton trunk and each artis at this
Coordinate data under Kinect sensor coordinate system.
In some optional implementations of the present embodiment, above-mentioned skeleton data includes each joint of composition human skeleton
The confidence level of point coordinates and above-mentioned body joint point coordinate.Above-mentioned skeleton data include above-mentioned human skeleton body joint point coordinate and on
The tracking state of artis is stated, state is respectively tracking, speculating, do not tracked, is the joint of above three state
The confidence level that point distribution reduces successively.In some specific examples, above-mentioned terminal device can be by the above-mentioned human body of above-mentioned statement
The skeleton data of the data of the trunk of skeleton and each artis carries out advance processing, is converted into the seat in the terminal device
Coordinate under mark system.
As an example, above-mentioned each terminal device connects a Kinect sensor, above-mentioned server can individually be set
The computer put, or, the computer of any one above-mentioned terminal device can serve as server.TCP/IP can be used to assist
View is between above-mentioned server and above-mentioned terminal device, or is communicated between more above-mentioned terminal devices.Above-mentioned Kinect sensor
The framework information of BodyFrame classes packaging human body can be used in each frame data of speed collection, target is encapsulated in Body classes
25 skeleton joint point coordinates of human body and the tracking state of above-mentioned skeleton joint point, that state respectively tracks, speculating,
Do not track, system is the confidence level that the artis distribution of three states reduces successively.For example, can be the joint tracked
It is 0.95 that point, which assigns confidence level, can be that the artis tax confidence level speculated is 0.70, can be that the artis not tracked is assigned
Confidence level is 0.15.Each Kinect sensor most multipotency identifies six human body targets simultaneously, so in each BodyFrame most
The object of six Body types can be included more.
It should be noted that each Kinect sensor is gathering same human skeleton or same human body in above-mentioned sub-step
During multiframe skeleton data, above-mentioned human skeleton or human body remains stationary is motionless.
It is above-mentioned to determine that each above-mentioned terminal is set according to above-mentioned skeleton data in some optional implementations of the present embodiment
The weighted average skeleton data for the skeleton data that preparation is sent, including：Gather the more of human skeleton respectively by multiple terminal devices
Frame skeleton data；Sat according to the body joint point coordinate of the above-mentioned skeleton data of every frame of acquired each terminal device and above-mentioned artis
Target confidence level, the weight using the confidence level of above-mentioned body joint point coordinate as above-mentioned body joint point coordinate, calculate above-mentioned terminal device institute
The artis weighted average of each artis of the human skeleton of detection；Using artis weighted average as above-mentioned each artis
Joint point data, put down using whole joint point datas included by human skeleton by the weighting for the human skeleton that terminal device detects
Equal skeleton data.Here, the above-mentioned skeleton number for accumulating N frames since being received the 1st frame data per station terminal equipment, it is specific at some
In example, N is 20 to 30, for j-th of pass of the human skeleton of the Kinect of the i-th station terminal equipment target persons caught
The weighted sum S of node coordinate in N frame skeleton datasijFor：
Wherein, the frame number of f phalanges rack data, wfjIt is the confidence level of j-th of artis in f frame skeleton datas, vfj
(x, y, z) is the coordinate of j-th of artis in f frame skeleton datas.
Corresponding to the coordinate of j-th of artis of the human skeleton of weighted average skeleton dataFor：
The weight of j-th of artis of above-mentioned human skeletonFor：
Weighted average bone corresponding to the multiframe skeleton data of target person acquired in the Kinect of above-mentioned terminal device
Rack data is：
Wherein, i is the weighted average skeleton data of the i-th station terminal equipment, and the joint points of human skeleton are j, and j can use
25。
Sub-step 2022, the skeleton data captured according to each terminal device calculate the skeleton data of each above-mentioned terminal device
Confidence level, it is reference terminal equipment that confidence level highest terminal device is determined from above-mentioned terminal device, determines above-mentioned ginseng
The coordinate system for examining terminal device is reference frame.
In this sub-step, above-mentioned server calculates the multiframe skeleton data that each above-mentioned terminal device is gathered respectively
Confidence level, here, the confidence level of included artis obtains each end in the skeleton data obtained according to each terminal device
The confidence level of end equipment.It is reference terminal equipment to determine confidence level highest terminal device, determines the coordinate of reference terminal equipment
It is for reference frame.Other-end equipment in addition to above-mentioned reference terminal equipment is appointed as non-reference terminal device, above-mentioned non-
The coordinate system of reference terminal equipment is non-reference coordinate system.
In the present embodiment in some optional implementations, the credible number of degrees of the skeleton data of above-mentioned computing terminal equipment
According to, including：Obtain the confidence level of each artis for the multiframe skeleton data that each terminal device is gathered；Calculate each terminal
The average value of the confidence level of each artis for the skeleton data that equipment is gathered；Add and operate the structure that the terminal device is gathered
The average value of the confidence level of each artis of whole artis of adult body skeleton；It is determined that it is described plus and operating result be described
Terminal device confidence level.Or in some instances, can also according to it is above-mentioned plus and operating result and human skeleton included by
Artis quantity does division arithmetic acquired results as the terminal device confidence level.Here, obtained for every station terminal equipment
The multiframe skeleton data of the same human skeleton taken, it is first determined go out being averaged for the confidence level of each artis of human skeleton
Value, then, the average value for the human skeleton whole artis confidence level that adds up, finally, select the maximum terminal of the result after adding up
Equipment is reference terminal equipment.It is understood that reference terminal equipment (terminal device of the result maximum after cumulative) is every
Each artis of the Reliability ratio others terminal device of individual artis it is with a high credibility, i.e. reference terminal equipment obtains bone
The most artis to be traceable to of each artis in rack data.
Sub-step 2023, according to human skeleton corresponding to above-mentioned weighted average skeleton data under above-mentioned reference frame
Difference between coordinate and coordinate under the coordinate system of non-reference terminal device, calculate reference frame and each terminal device
Eulerian angles and translation variable between coordinate system.
It is above-mentioned based on the reference terminal equipment and reference frame determined in sub-step 2022 in this sub-step
The coordinate data of each artis for the skeleton data that server is obtained non-reference terminal device is being joined with above-mentioned human skeleton
Each body joint point coordinate data examined under coordinate system compare, and determine the Europe between the coordinate system of reference frame and each terminal device
Draw angle and translation variable.Here it is possible to the coordinate of center knuckle point by determining human skeleton is respectively under reference coordinate
First coordinate data and the second coordinate data under the coordinate system of non-reference terminal device, determine the first coordinate data and the
The vector of two coordinate datas, determined by the vector Eulerian angles between the coordinate system of reference frame and each terminal device and
Translate variable.Wherein, it can be preassigned a, artis in human skeleton center that center knuckle point, which is,.
In some optional implementations of the present embodiment, the above-mentioned seat for determining reference frame and each terminal device
Eulerian angles and translation variable between mark system, including：More above-mentioned human skeleton is under above-mentioned non-reference terminal device coordinate system
Weighted average skeleton data and weighted average skeleton data under above-mentioned reference frame difference；Using above-mentioned difference to be upper
State the difference skeleton data of human skeleton；Calculate coordinate of the above-mentioned difference skeleton data under above-mentioned reference frame and above-mentioned ginseng
It is Eulerian angles to examine each reference axis angle of coordinate system；Calculate coordinate of the above-mentioned difference skeleton data under above-mentioned reference frame with it is upper
The distance for stating each reference axis of reference frame is translation variable.Here, difference skeleton data is the weighting of above-mentioned human skeleton
The difference of average data of the skeleton data under reference frame and the data under the coordinate system of non-reference terminal device.Above-mentioned difference
Value skeleton data is Eulerian angles in above-mentioned reference frame and each reference axis angle, and the distance with each reference axis is translation variable.
Sub-step 2024, determine that reference frame is set with each above-mentioned non-reference terminal according to above-mentioned Eulerian angles and translation variable
Transformation matrix between standby coordinate system.
In the present embodiment, based on identified Eulerian angles in sub-step 2023 and translation variable, above-mentioned server can be with
By rotate translation the above-mentioned Eulerian angles of mode and translation variable minimum mode determine reference frame with it is each above-mentioned
Transformation matrix between the coordinate system of non-reference terminal device.Specifically, with the reference axis of above-mentioned reference frame with it is above-mentioned non-
Eulerian angles between the reference axis of reference frame form spin matrix, with the reference axis of above-mentioned reference frame and above-mentioned non-ginseng
Examine translation variable between the reference axis of coordinate system and form translation matrix, using the product of above-mentioned spin matrix and translation matrix as
Transformation matrix between above-mentioned reference frame and above-mentioned non-ginseng coordinate system.
It is above-mentioned to determine reference according to above-mentioned Eulerian angles and translation variable in some optional implementations of the present embodiment
Transformation matrix between the coordinate system of coordinate system and each non-reference terminal device, including：According to above-mentioned Eulerian angles and translation variable
Spin matrix and translation matrix are determined respectively；The product for determining above-mentioned rotational transformation matrix and above-mentioned translation matrix is conversion square
Battle array.Here, above-mentioned Eulerian angles and translation variable can be expressed as Euler's angle variable θx、θy、θzWith translation variable x, y, z, according to upper
State three axle xyz of reference frame Eulerian angles θx、θy、θz, rotational transformation matrix R can be obtainedi(θx, θy, θz)=Riz
(θz)·Riy(θy)·Rix(θx), by three translation variable x, y, z, it can be deduced that translation matrix Ti(x, y, z), then, and rotation translation
Transformation matrix is Mi(θx, θy, θz, x, y, z) and=Ti(x, y, z) Ri(θx, θy, θz).Wherein, i be terminal device number, Riz
(θz)、Riy(θy)、Rix(θx) be respectively Eulerian angles and the reference axis of reference frame spin matrix.
In some specific examples, above-mentioned rotation translation transformation matrix can be optimized, match above-mentioned variable θx、
θy、θz, x, y, z so that functionThe M of minimum gainediFor the transformation matrix after optimization.
Skeleton data of the method that the above embodiments of the present application are provided according to acquired in each terminal device determines skeleton
The confidence level highest terminal device of data is reference terminal equipment, and the coordinate system of reference terminal equipment is reference frame, really
Eulerian angles and translation of the skeleton data of fixed same human skeleton under reference frame and under the coordinate system of non-reference terminal
Variable, the transformation matrix between coordinate system is determined according to Eulerian angles and translation variable.Data are sat between realizing more Kinect
Target automatic conversion.
With further reference to Fig. 3, it illustrates train coordinate conversion matrix in more Kinect human skeletons coordinate transformation methods
Another embodiment flow.The sub-step of above-mentioned training coordinate conversion matrix includes：
Sub-step 3021, the multiframe skeleton data of the same human body transmitted by multiple terminal devices is received, according to above-mentioned bone
Rack data determines the weighted average skeleton data of the skeleton data of each above-mentioned terminal device.
In the present embodiment, electronic equipment (such as the Fig. 1 of more Kinect human skeletons coordinate transformation methods operation thereon
Shown server) multiple terminal devices hair can be received from terminal device by wired connection mode or radio connection
The skeleton data of the same human body sent.Wherein, terminal device can obtain human body by connected Kinect sensor
Skeleton data, and obtained skeleton data is sent to server.Above-mentioned skeleton data refers to detected by Kinect sensor
Human body view data, above-mentioned Kinect sensor is mapped to the Kinect sensor per frame image data detected by
Data when under coordinate system, by the ranking operation to data, determine the human skeleton that above-mentioned each terminal device is captured
Skeleton number weighted average.Above-mentioned skeleton data can be that the detected Kinect that is mapped to per frame image data is sensed
When under device coordinate system, the number of coordinates of the trunk and each artis of above-mentioned human skeleton under the Kinect sensor coordinate system is stated
According to.
Sub-step 3022, above-mentioned human skeleton is judged for front or back, if judged result is reverse side, by above-mentioned human skeleton
The body joint point coordinate of trunk carries out right and left mutually changing.
In the present embodiment, above-mentioned server can judge the positive and negative of human skeleton by human skeleton posture；May be used also
The positive and negative of human skeleton is judged in a manner of by face recognition.The skeleton image of human skeleton to being judged as reverse side is carried out
Upset is handled, i.e., carries out left and right conversion to the body joint point coordinate of the trunk both sides of human skeleton.Here it is possible to preassign
Artis is joint of trunk point.
Specifically, if regulator's right hand is highly higher than left hand when regulation is calibrated, then calculate the left and right for comparing skeleton
Hand coordinate, if right hand height coordinate is more than left hand height coordinate, then this skeleton for front, it is on the contrary then be reverse side, it is necessary to enter
The exchange of row left and right coordinate.
In some specific examples, the positive and negative of human skeleton is judged above by human skeleton posture, can be rule
The asymmetric posture used during a kind of fixed calibration, each pass of above-mentioned human skeleton is then extracted from above-mentioned multiframe skeleton data
The coordinate of node.
In some instances, the front or back of human skeleton can also be judged according to body joint point coordinate.Wherein, it is above-mentioned
The coordinate of artis includes the body joint point coordinate of present frame human skeleton and the body joint point coordinate of upper frame synthesis skeleton；According to above-mentioned
The weight of body joint point coordinate and above-mentioned artis is determined to catch parameter；According to the frame synthesis seizure result of skeleton on this and above-mentioned
Catch the positive and negative that parameter determines above-mentioned present frame skeleton.Wherein, above-mentioned seizure parameter C is：
Wherein, n represents joint points, vjRepresent the coordinate in j-th of joint of present frame skeleton, v 'jFrame synthetic bone in expression
The coordinate in j-th of joint of frame, wjRepresent the weight in j-th of joint of present frame skeleton, w 'jThe jth of frame synthesis skeleton in expression
The weight in individual joint.
Front seizure parameter when above-mentioned upper frame synthesis skeleton is front is calculated respectively and above-mentioned upper frame synthesis skeleton is
Reverse side during reverse side catches parameter；More above-mentioned front catches parameter and above-mentioned reverse side catches the size of parameter；In response to above-mentioned
The difference that front catches parameter and above-mentioned reverse side seizure parameter is more than given threshold, determines above-mentioned present frame skeleton for front；Ring
The difference that parameter and above-mentioned front seizure parameter should be caught in above-mentioned reverse side is more than given threshold, determines that above-mentioned present frame skeleton is
Reverse side.
Specifically, if upper two field picture catches result for front, C is calculatedfIf upper two field picture, which is reverse side, catches knot
During fruit, C is calculatedb；If CfMuch smaller than Cb, then present frame for front catch result, it is on the contrary then for the back side seizure result.It is above-mentioned
CfMuch smaller than CbRefer to above-mentioned CbIt is CfMore times, for example, it may be CbIt is Cf10 times and more than.
Sub-step 3023 calculates the confidence level of the skeleton data of above-mentioned terminal device, and being determined from above-mentioned terminal device can
Reliability highest terminal device is reference terminal equipment, and the coordinate system for determining above-mentioned reference terminal equipment is reference frame.
In this sub-step, above-mentioned server calculates the multiframe skeleton data that each above-mentioned terminal device is gathered respectively
Confidence level, it is reference terminal equipment to determine confidence level average value highest terminal device, and remaining terminal device is non-reference
Terminal device；The coordinate system for determining reference terminal equipment is reference frame.Gathered in above-mentioned determination reference terminal equipment
Multiframe skeleton data, it is ensured that follow the trail of in environment or calibration environment with the presence of and one-man's body, each terminal device will
The human body passes to server by the skeleton data that different Kinect sensors identify, server is static not from terminal device acquisition
The multiframe skeleton data of dynamic human body.For example, every Kinect sensor can obtain 20 frame skeletons of actionless human body
Data.
Sub-step 3024, minimum optimal algorithm is applied according to average skeleton data, determines the change of each non-reference terminal device
Matrix is changed, its method is：It is calculated as follows corresponding conversion calibration matrix M when F values are minimum in formulaiFor reference frame and each institute
State the transformation matrix of coordinates between the coordinate system of non-reference terminal device：
Wherein, n is that the joint of human skeleton is counted, and i is the number of terminal device,It is the skeleton of i-th of terminal device
Coordinate of j-th of the artis of data under reference coordinate,It is that j-th of artis of the skeleton data of reference device is being joined
The coordinate under coordinate system is examined,It isJ-th of artis weight.
In the present embodiment, based on the reference terminal equipment determined in step 303 and reference frame, above-mentioned service
Device can be determined to convert calibration matrix using particle swarm optimization algorithm：
Above-mentioned conversion calibration matrix can be reduced to 3 rotating around x, the rotary variable of tri- axles of y, z, and with x, y, z tri-
Individual axle is the translation variable in direction.Particle i position is represented by six-vector Xi=(θx, θy, θz, x, y, z), particle i speed
Degree is represented by sextuple space vectorThe fitness calculation formula of particle isIt is m to set population scale, initializes all particles, including random site and at random
Speed；Pass through formulaThe adaptive value of each particle is calculated, in this n is skeleton data
Joint point value, it can use 25；By the adaptive value calculated of each particle and particle history optimal value pbestiCompare, if
The adaptive value being calculated is less than history best values, then replaces history best values；Find out the adaptive value of all particles in population
Minimum value, the history optimal value gbest with whole populationiMake comparisons, it is optimal that history is replaced if smaller than history optimal value
Value；According to formulaUpdate the speed of each particle
Degree, wherein ω are particle inertia parameter, c1、c2For " study " speed weight of particle, r1、r2To be random between 0 and 1
Number, according to formula Xi=Xi+ViUpdate each particle position；When maximum iteration reaches k times, or global optimum's adaptive value connects
When continuous φ stabilization is near a value, reach iteration termination condition, otherwise turn to continue to seek the step of jumping to renewal particle rapidity
Look for optimal location.Coordinate between each terminal device and reference terminal equipment is determined by above-mentioned particle swarm optimization algorithm iteration
The transformation matrix of coordinates of system.
As an example, as shown in figure 4, human body bone by the Kinect of the two different terminal equipments same personages caught
The skeleton data of frame, the skeleton data show that the data of the profile of human body and the artis of composition human skeleton (can use each
Represented from Kinect coordinate system), the skeleton data captured to above-mentioned two Kinect determines average skeleton, and then determines
Coordinate conversion matrix, Fig. 5 show the human body bone that two Kinect after converted matrix conversion under reference frame are captured
Rack data.
The method that the above embodiments of the present application are provided by minimum optimal algorithm, by band in multiple times relatively after determine
Transition matrix between optimal reference frame and the coordinate system of non-reference terminal device.So that each terminal device passes through conversion
Skeleton data under matrix conversion reference frame is continuously, stably.
As on the other hand, present invention also provides more Kinect human skeletons coordinate transform equipment, the equipment includes one
Individual or multiple processors；Storage device, for storing one or more programs；When said one or multiple programs by upper one or
Multiple computing devices so that said one or multiple processors：Obtain the skeleton data that multiple terminal devices are captured；Utilize
The transformation matrix of coordinates trained, above-mentioned skeleton data is changed, wherein, train above-mentioned transformation matrix to include：Receive multiple terminals
The multiframe skeleton data of same human body transmitted by equipment, the skeleton number of each above-mentioned terminal device is determined according to above-mentioned skeleton data
According to weighted average skeleton data；The skeleton data captured according to each terminal device calculates the credible of each above-mentioned terminal device
Degree, it is reference terminal equipment that confidence level highest terminal device is determined from above-mentioned terminal device, determines above-mentioned reference terminal
The coordinate system of equipment is reference frame, and the start and stop designated equipment in addition to above-mentioned reference terminal equipment determines that expense reference terminal is set
Standby, the coordinate system of above-mentioned non-reference terminal device is non-reference coordinate system；According to people corresponding to above-mentioned weighted average skeleton data
Mathematic interpolation reference between coordinate of the body skeleton under above-mentioned reference frame and the coordinate under above-mentioned non-reference coordinate system
Eulerian angles and translation variable between coordinate system and above-mentioned non-reference coordinate system；With the reference axis of above-mentioned reference frame with it is above-mentioned
Above-mentioned Eulerian angles between the reference axis of non-reference coordinate system form spin matrix, with the reference axis of above-mentioned reference frame with it is upper
The above-mentioned translation variable stated between the reference axis of non-reference coordinate system forms translation matrix, by above-mentioned spin matrix and translation matrix
Product as above-mentioned reference frame and it is above-mentioned it is non-ginseng coordinate system between transformation matrix.
On the other hand, present invention also provides a kind of computer-readable medium, the computer-readable medium can be above-mentioned
Included in server described in embodiment；Can also be individualism, and without be incorporated the server in.Above-mentioned calculating
Machine computer-readable recording medium carries one or more program, when said one or multiple programs are performed by the server so that
The server：Obtain the skeleton data that multiple terminal devices are captured；Using the transformation matrix of coordinates trained, above-mentioned bone is changed
Rack data, wherein, train above-mentioned transformation matrix to include：Receive the multiframe skeleton number of the same human body transmitted by multiple terminal devices
According to determining the weighted average skeleton data of the skeleton data of each above-mentioned terminal device according to above-mentioned skeleton data；According to each terminal
The skeleton data that equipment is captured calculates the confidence level of each above-mentioned terminal device, and confidence level is determined from above-mentioned terminal device
Highest terminal device is reference terminal equipment, and the coordinate system for determining above-mentioned reference terminal equipment is reference frame, except above-mentioned
Start and stop designated equipment determination outside reference terminal equipment takes reference terminal equipment, and the coordinate system of above-mentioned non-reference terminal device is non-
Reference frame；According to coordinate of the human skeleton corresponding to above-mentioned weighted average skeleton data under above-mentioned reference frame and
The Euler between mathematic interpolation reference frame between coordinate and above-mentioned non-reference coordinate system under above-mentioned non-reference coordinate system
Angle and translation variable；With the above-mentioned Euler between the reference axis of above-mentioned reference frame and the reference axis of above-mentioned non-reference coordinate system
Angle forms spin matrix, above-mentioned flat between the reference axis of above-mentioned reference frame and the reference axis of above-mentioned non-reference coordinate system
Move variable and form translation matrix, using the product of above-mentioned spin matrix and translation matrix as above-mentioned reference frame and above-mentioned non-ginseng
Transformation matrix between coordinate system.
So far, combined preferred embodiment shown in the drawings describes technical scheme, still, this area
Technical staff is it is easily understood that protection scope of the present invention is expressly not limited to these embodiments.Without departing from this
On the premise of the principle of invention, those skilled in the art can make equivalent change or replacement to correlation technique feature, these
Technical scheme after changing or replacing it is fallen within protection scope of the present invention.
Claims (10)
1. a kind of more Kinect human skeletons coordinate transformation methods, it is characterised in that methods described includes：
Obtain the skeleton data that multiple terminal devices are captured；
Using the transformation matrix of coordinates trained, the skeleton data is changed, wherein, train the transformation matrix to include：
Receive multiple terminal devices transmitted by same human body multiframe skeleton data, according to the skeleton data determine it is each described in
The weighted average skeleton data for the skeleton data that terminal device is sent；
The skeleton data captured according to each terminal device calculates the confidence level of each terminal device, from the terminal device
It is reference terminal equipment to determine confidence level highest terminal device, and the coordinate system for determining the reference terminal equipment is with reference to seat
Mark system, the other equipment in addition to the reference terminal equipment are appointed as non-reference terminal device, the non-reference terminal device
Coordinate system is non-reference coordinate system；
According to coordinate of the human skeleton corresponding to the weighted average skeleton data under the reference frame and described non-
The difference between coordinate under reference frame, calculate the Eulerian angles peace between reference frame and the non-reference coordinate system
Move variable；
The Eulerian angles between the reference axis of the reference frame and the reference axis of the non-reference coordinate system are formed rotation
Torque battle array, the translation variable structure between the reference axis of the reference frame and the reference axis of the non-reference coordinate system
Into translation matrix, using the product of the spin matrix and translation matrix as the reference frame and the non-ginseng coordinate system it
Between transformation matrix.
2. more Kinect human skeletons coordinate transformation methods according to claim 1, it is characterised in that the skeleton data
Including forming each body joint point coordinate of human skeleton and the confidence level of the body joint point coordinate.
3. more Kinect human skeletons coordinate transformation methods according to claim 2, it is characterised in that described in the basis
Skeleton data determines the weighted average skeleton data for the skeleton data that each terminal device is sent, including：
Gather the multiframe skeleton data of human skeleton respectively by multiple terminal devices；
According to the body joint point coordinate of skeleton data described in every frame of acquired each terminal device and the body joint point coordinate can
Reliability, the weight using the confidence level of the body joint point coordinate as the body joint point coordinate, calculate what the terminal device was detected
The artis weighted average of each artis of human skeleton；
Joint point data using the artis weighted average as the artis, with the whole included by the human skeleton
The weighted average skeleton data for the human skeleton that joint point data is detected by terminal device.
4. more Kinect human skeletons coordinate transformation methods according to claim 3, it is characterised in that described according to each end
The skeleton data that end equipment is captured, the confidence level of each terminal device is calculated, including：
Obtain the confidence level of each artis for the multiframe skeleton data that each terminal device is gathered；
Calculate the average value of the confidence level of each artis for the skeleton data that each terminal device is gathered；
Add and operate the confidence level of each artis of the whole artis for the composition human skeleton that the terminal device is gathered
Average value；
It is determined that it is described plus and operating result be the terminal device confidence level.
5. more Kinect human skeletons coordinate transformation methods according to claim 3, it is characterised in that described in the basis
Coordinate of the human skeleton corresponding to weighted average skeleton data under the reference frame and under the non-reference coordinate system
Coordinate between difference, calculate the Eulerian angles between reference frame and each non-coordinate system and translate variable, including：
Weighted average skeleton data and the non-reference for calculating the human skeleton that the reference terminal equipment is gathered are whole
The difference of the weighted average skeleton data for the human skeleton that end equipment is gathered；
Difference skeleton data using the difference as the human skeleton；
Calculate coordinate of the difference skeleton data under the reference frame and each reference axis angle of the reference frame
For Eulerian angles；
Calculate coordinate of the difference skeleton data under the reference frame and each reference axis of the reference frame
Distance is translation variable.
6. more Kinect human skeletons coordinate transformation methods according to claim 1, it is characterised in that described in the basis
Eulerian angles and translation variable determine the transformation matrix between the coordinate system of reference frame and each non-reference terminal device, bag
Include：
Three axle xyz of reference frame Eulerian angles θ is determined according to the Eulerian anglesx、θy、θz, obtain rotation transformation square
Battle array is Ri(θx, θy, θz)=Riz(θz)·Riy(θy)·Rix(θx)；
The variable x, y, z of three axles of the reference frame is determined according to the translation variable, it can be deduced that translation matrix Ti
(x, y, z)；
Using the product of the rotational transformation matrix and the translation matrix as transformation matrix Mi。
7. more Kinect human skeletons coordinate transformation methods according to claim 6, it is characterised in that methods described is also wrapped
Include and minimum optimal algorithm is applied according to average skeleton data, determine the transformation matrix of each non-reference terminal device, its method
For：It is calculated as follows corresponding conversion calibration matrix M when F values are minimum in formulai：
<mrow>
<mi>F</mi>
<mo>=</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mi>n</mi>
</mrow>
</msubsup>
<msub>
<mover>
<mi>w</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<msub>
<mover>
<mi>w</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mn>1</mn>
<mi>j</mi>
</mrow>
</msub>
<mrow>
<mo>|</mo>
<mrow>
<msub>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mn>1</mn>
<mi>j</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mover>
<mi>v</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<msub>
<mi>M</mi>
<mi>i</mi>
</msub>
</mrow>
<mo>|</mo>
</mrow>
</mrow>
Wherein, n is that the joint of human skeleton is counted, and i is the number of terminal device,It is the weighted average of i-th of terminal device
Coordinate of j-th of the artis of skeleton data under reference coordinate,It is the jth of the weighted average skeleton data of reference device
Coordinate of the individual artis under reference frame,It isJ-th of artis weight.
8. more Kinect human skeletons coordinate transformation methods according to claim 1, it is characterised in that methods described is also wrapped
Include：
After weighted average skeleton is calculated, judge the human skeleton for front or back；
If judged result is reverse side, the body joint point coordinate of the human skeleton both sides is subjected to right and left mutually changing.
9. a kind of more Kinect human skeletons coordinate transform processing equipment, including：
One or more processors, it is adapted for carrying out each bar program；And
Storage device, for storing one or more programs,
Characterized in that, described program be suitable to load by processor and is performed with realize in claim 1-8 it is any described in it is more
Kinect human skeleton coordinate transformation methods.
10. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor
More Kinect human skeletons coordinate transformation methods as described in any in claim 1-8 are realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710657342.4A CN107577451B (en) | 2017-08-03 | 2017-08-03 | Multi-Kinect human body skeleton coordinate transformation method, processing equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710657342.4A CN107577451B (en) | 2017-08-03 | 2017-08-03 | Multi-Kinect human body skeleton coordinate transformation method, processing equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107577451A true CN107577451A (en) | 2018-01-12 |
| CN107577451B CN107577451B (en) | 2020-06-12 |
Family
ID=61035867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710657342.4A Active CN107577451B (en) | 2017-08-03 | 2017-08-03 | Multi-Kinect human body skeleton coordinate transformation method, processing equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107577451B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108376405A (en) * | 2018-02-22 | 2018-08-07 | 国家体育总局体育科学研究所 | Human movement capture system and method for catching based on binary sense tracing system |
| CN108564642A (en) * | 2018-03-16 | 2018-09-21 | 中国科学院自动化研究所 | Unmarked performance based on UE engines captures system |
| CN108564643A (en) * | 2018-03-16 | 2018-09-21 | 中国科学院自动化研究所 | Performance based on UE engines captures system |
| CN108572731A (en) * | 2018-03-16 | 2018-09-25 | 中国科学院自动化研究所 | Dynamic based on more Kinect and UE4 catches Data Representation method and device |
| CN110197461A (en) * | 2019-06-06 | 2019-09-03 | 上海木木聚枞机器人科技有限公司 | A kind of coordinate transformation relation determines method, apparatus, equipment and storage medium |
| CN111079535A (en) * | 2019-11-18 | 2020-04-28 | 华中科技大学 | Human skeleton action recognition method and device and terminal |
| CN111582081A (en) * | 2020-04-24 | 2020-08-25 | 西安交通大学 | Multi-Kinect serial gait data space-time combination method and measuring device |
| CN112183506A (en) * | 2020-11-30 | 2021-01-05 | 成都市谛视科技有限公司 | Human body posture generation method and system |
| WO2023013562A1 (en) * | 2021-08-04 | 2023-02-09 | パナソニックＩｐマネジメント株式会社 | Fatigue estimation system, fatigue estimation method, posture estimation device, and program |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070160957A1 (en) * | 2004-12-14 | 2007-07-12 | Huafeng Wen | Image based dentition record digitization |
| CN103106688A (en) * | 2013-02-20 | 2013-05-15 | 北京工业大学 | Indoor three-dimensional scene rebuilding method based on double-layer rectification method |
| CN103914873A (en) * | 2014-03-13 | 2014-07-09 | 南京大学 | Method for generating sculpture three-dimensional model driven by human body movements |
| CN104589356A (en) * | 2014-11-27 | 2015-05-06 | 北京工业大学 | Dexterous hand teleoperation control method based on Kinect human hand motion capturing |
| CN104933734A (en) * | 2015-06-26 | 2015-09-23 | 西安理工大学 | Multi-Kinect-based human body gesture data fusion method |
| CN105512621A (en) * | 2015-11-30 | 2016-04-20 | 华南理工大学 | Kinect-based badminton motion guidance system |
| CN105551059A (en) * | 2015-12-08 | 2016-05-04 | 国网山西省电力公司技能培训中心 | Power transformation simulation human body motion capturing method based on optical and inertial body feeling data fusion |
| CN105988566A (en) * | 2015-02-11 | 2016-10-05 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN106340059A (en) * | 2016-08-25 | 2017-01-18 | 上海工程技术大学 | Automatic registration method based on multi-body-feeling-acquisition-device three-dimensional modeling |
| US20170148175A1 (en) * | 2015-11-20 | 2017-05-25 | Vivotek Inc. | Object matching method and camera system with an object matching function |
-
2017
- 2017-08-03 CN CN201710657342.4A patent/CN107577451B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070160957A1 (en) * | 2004-12-14 | 2007-07-12 | Huafeng Wen | Image based dentition record digitization |
| CN103106688A (en) * | 2013-02-20 | 2013-05-15 | 北京工业大学 | Indoor three-dimensional scene rebuilding method based on double-layer rectification method |
| CN103914873A (en) * | 2014-03-13 | 2014-07-09 | 南京大学 | Method for generating sculpture three-dimensional model driven by human body movements |
| CN104589356A (en) * | 2014-11-27 | 2015-05-06 | 北京工业大学 | Dexterous hand teleoperation control method based on Kinect human hand motion capturing |
| CN105988566A (en) * | 2015-02-11 | 2016-10-05 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN104933734A (en) * | 2015-06-26 | 2015-09-23 | 西安理工大学 | Multi-Kinect-based human body gesture data fusion method |
| US20170148175A1 (en) * | 2015-11-20 | 2017-05-25 | Vivotek Inc. | Object matching method and camera system with an object matching function |
| CN105512621A (en) * | 2015-11-30 | 2016-04-20 | 华南理工大学 | Kinect-based badminton motion guidance system |
| CN105551059A (en) * | 2015-12-08 | 2016-05-04 | 国网山西省电力公司技能培训中心 | Power transformation simulation human body motion capturing method based on optical and inertial body feeling data fusion |
| CN106340059A (en) * | 2016-08-25 | 2017-01-18 | 上海工程技术大学 | Automatic registration method based on multi-body-feeling-acquisition-device three-dimensional modeling |
Non-Patent Citations (2)
| Title |
|---|
| MARTIN BÜNGER: ""Evaluation of Skeleton Trackers and Gesture Recognition for Human-robot Interaction"", 《APPLIED CATALYSIS A GENERAL》 * |
| 席小霞: ""基于多台Kinect摄像机的三维重建系统研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108376405A (en) * | 2018-02-22 | 2018-08-07 | 国家体育总局体育科学研究所 | Human movement capture system and method for catching based on binary sense tracing system |
| CN108376405B (en) * | 2018-02-22 | 2020-11-17 | 国家体育总局体育科学研究所 | Human motion capture system and method based on double-body sensation tracking system |
| CN108564642A (en) * | 2018-03-16 | 2018-09-21 | 中国科学院自动化研究所 | Unmarked performance based on UE engines captures system |
| CN108564643A (en) * | 2018-03-16 | 2018-09-21 | 中国科学院自动化研究所 | Performance based on UE engines captures system |
| CN108572731A (en) * | 2018-03-16 | 2018-09-25 | 中国科学院自动化研究所 | Dynamic based on more Kinect and UE4 catches Data Representation method and device |
| CN110197461A (en) * | 2019-06-06 | 2019-09-03 | 上海木木聚枞机器人科技有限公司 | A kind of coordinate transformation relation determines method, apparatus, equipment and storage medium |
| CN110197461B (en) * | 2019-06-06 | 2022-12-30 | 上海木木聚枞机器人科技有限公司 | Coordinate conversion relation determining method, device, equipment and storage medium |
| CN111079535A (en) * | 2019-11-18 | 2020-04-28 | 华中科技大学 | Human skeleton action recognition method and device and terminal |
| CN111079535B (en) * | 2019-11-18 | 2022-09-16 | 华中科技大学 | Human skeleton action recognition method and device and terminal |
| CN111582081A (en) * | 2020-04-24 | 2020-08-25 | 西安交通大学 | Multi-Kinect serial gait data space-time combination method and measuring device |
| CN112183506A (en) * | 2020-11-30 | 2021-01-05 | 成都市谛视科技有限公司 | Human body posture generation method and system |
| WO2023013562A1 (en) * | 2021-08-04 | 2023-02-09 | パナソニックＩｐマネジメント株式会社 | Fatigue estimation system, fatigue estimation method, posture estimation device, and program |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107577451B (en) | 2020-06-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107577451A (en) | More Kinect human skeletons coordinate transformation methods and processing equipment, readable storage medium storing program for executing | |
| US11238636B2 (en) | Method and apparatus for sport-specific training with captured body motions | |
| US20200401793A1 (en) | Apparatus and methods for determining multi-subject performance metrics in a three-dimensional space | |
| JP5356690B2 (en) | Method, system, and program for tracking a range of physical movement of a user | |
| CN107563295A (en) | Comprehensive human body method for tracing and processing equipment based on more Kinect | |
| CN112005198A (en) | Hand state reconstruction based on multiple inputs | |
| CN105229666A (en) | Motion analysis in 3D rendering | |
| CN109255749B (en) | Map building optimization in autonomous and non-autonomous platforms | |
| CN105209136A (en) | Center of mass state vector for analyzing user motion in 3D images | |
| CN108875526B (en) | Method, device and system for line-of-sight detection and computer storage medium | |
| CN103514432A (en) | Method, device and computer program product for extracting facial features | |
| CN107257980A (en) | Local change in video detects | |
| CN112464918B (en) | Body-building action correcting method and device, computer equipment and storage medium | |
| CN110111363A (en) | A kind of tracking and equipment based on target detection | |
| CN112346050A (en) | Fall detection method and system based on Wi-Fi equipment | |
| CN108572731A (en) | Dynamic based on more Kinect and UE4 catches Data Representation method and device | |
| US10147218B2 (en) | System to identify and use markers for motion capture | |
| Yuan et al. | Adaptive recognition of motion posture in sports video based on evolution equation | |
| US20220362630A1 (en) | Method, device, and non-transitory computer-readable recording medium for estimating information on golf swing | |
| Lim et al. | BodyTrak: Inferring Full-Body Poses from Body Silhouettes Using a Miniature Camera on a Wristband | |
| CN113553893A (en) | Human body falling detection method and device based on deep neural network and electronic equipment | |
| US20220273984A1 (en) | Method and device for recommending golf-related contents, and non-transitory computer-readable recording medium | |
| Zhang et al. | Research on pose recognition algorithm for sports players based on machine learning of sensor data | |
| Xu et al. | Robust Abnormal Human-Posture Recognition Using OpenPose and Multi-View Cross-Information | |
| Chatzitofis et al. | Technological module for unsupervised, personalized cardiac rehabilitation exercising |
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 |