[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN114463383A - Method, equipment and storage medium for predicting rigid body mark point position - Google Patents

Method, equipment and storage medium for predicting rigid body mark point position Download PDF

Info

Publication number
CN114463383A
CN114463383A CN202111679549.4A CN202111679549A CN114463383A CN 114463383 A CN114463383 A CN 114463383A CN 202111679549 A CN202111679549 A CN 202111679549A CN 114463383 A CN114463383 A CN 114463383A
Authority
CN
China
Prior art keywords
frame
position data
predicted
mark point
mark
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.)
Pending
Application number
CN202111679549.4A
Other languages
Chinese (zh)
Inventor
黄少光
许秋子
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Realis Multimedia Technology Co Ltd
Original Assignee
Shenzhen Realis Multimedia Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Realis Multimedia Technology Co Ltd filed Critical Shenzhen Realis Multimedia Technology Co Ltd
Priority to CN202111679549.4A priority Critical patent/CN114463383A/en
Publication of CN114463383A publication Critical patent/CN114463383A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/77—Determining position or orientation of objects or cameras using statistical methods
    • 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
    • G06T2207/30204—Marker

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a method for predicting rigid body mark point position, which comprises the steps of acquiring tracking mark data set and position data set of mark points on each frame of human body limb, and when more than 3 mark points are arranged on the human body limb and at least 2 mark points can be correctly tracked, if the limb P can be correctly trackedsThe ith frame position data of the 0 th mark point
Figure DDA0003453596590000011
Traceable/visible 1 st mark point ith frame position data
Figure DDA0003453596590000012
No. 2 mark point ith frame position data to be predicted/invisible
Figure DDA0003453596590000013
The method comprises the steps of tracking/seeing, judging whether a mark point meets a preset condition, and if not, failing to predict the data of the ith frame position of the mark point to be predicted/invisible; if the position data of the ith frame of the 1 st mark point to be predicted/invisible is consistent with the position data of the 0 th traceable/visible mark point and the 2 nd traceable/visible mark point, the position data of the ith frame of the 1 st mark point to be predicted/invisible is predicted according to the scale factor, and therefore the lost position data is successfully predicted.

Description

Method, equipment and storage medium for predicting rigid body mark point position
Technical Field
The invention relates to the technical field of motion capture, in particular to a method, equipment and a storage medium for predicting positions of rigid body mark points.
Background
The optical motion capture system can be divided into two types of motion capture systems with mark points and motion capture systems without mark points, and the motion capture systems with mark points are widely adopted due to the characteristics of strong real-time performance, high precision, strong safety and the like. In the current optical motion capture system, human motion capture is generally performed by tracking and calculating a body part through rigid body mark points worn on a human body, so as to deduce information such as human motion, and therefore, the accuracy of the mark point tracking and positioning is very critical.
However, the original mark points acquired by the system are scattered point clouds, no fixed sequence exists among the mark points, and the mark points are lost and noisy due to the phenomena of blocking and sliding of a human body in the motion process. The real-time matching of the mark points in the dynamic capturing process is a key technology based on optical human motion capturing, the accuracy of motion capturing is directly determined, and due to various factors of the dynamic capturing environment, the mark points are often shielded or easily lost due to violent motion, so that the mark points are failed to track or match, and therefore, a method for preventing the mark points from being shielded or lost is provided to improve the tracking success rate of the mark points.
Disclosure of Invention
In order to solve the above technical problems, the present application provides a method for predicting rigid body mark point positions to avoid the problem of failure in tracking mark point positions due to the rigid body mark points being blocked and lost under the condition of multi-rigid body and multi-person motion capture.
According to a first aspect, an embodiment provides a method of predicting rigid body marker point positions, comprising the steps of:
s1, acquiring a tracking mark data set of mark points on each frame of human body limb
Figure RE-GDA0003584744080000011
And location data set
Figure RE-GDA0003584744080000012
Wherein i is the frame number, and s is the limb part;
s2, when there are more than 3 markers and at least 2 markers can be correctly tracked on the limb, if the limb P issThe ith frame position data of the 0 th mark point
Figure RE-GDA0003584744080000013
Traceable/visible 1 st mark point ith frame position data
Figure RE-GDA0003584744080000014
Ith frame position data of 2 nd mark point to be predicted/invisible
Figure RE-GDA0003584744080000015
Tracking/seeing, judging whether the mark point accords with a first condition, if so, entering step S3, and if not, failing to predict the ith frame position data of the mark point to be predicted/not seen;
s3, calculating the distance between the 0 th traceable/visible mark point and the 2 nd traceable/visible mark point in the i-2 th frame and the i-1 th frame, judging whether the distance meets the second condition, if so, entering the step S4, and if not, failing to predict the position data of the i-th frame of the mark point to be predicted/invisible;
s4, calculating the scale factor of the i frame and the i-1 frame of the traceable/visible mark point, judging whether the scale factor is in the threshold range, if so, entering the step S5, and if not, failing to predict the position data of the i frame of the mark point to be predicted/invisible;
and S5, predicting the position data of the 1 st mark point to be predicted/invisible according to the 0 th and the 2 nd traceable/visible mark point position data and the scale factor, and if the predicted position data meets a third condition, the prediction is successful.
The first condition includes:
tracking marker data at frame i-2 for 0 th and 2 nd trackable/visible marker points
Figure RE-GDA0003584744080000021
And
Figure RE-GDA0003584744080000022
tracking flag data at i-1 frame
Figure RE-GDA0003584744080000023
And
Figure RE-GDA0003584744080000024
all need to be true, and, for the 1 st mark point to be predicted/invisible, the tracking flag data at frame i-1
Figure RE-GDA0003584744080000025
Need to be true.
The second condition includes:
Figure RE-GDA0003584744080000026
wherein,
Figure RE-GDA0003584744080000027
for the distance between the 2 nd trackable/visible marker point at frame i-2 and frame i-1,
Figure RE-GDA0003584744080000028
d is a set threshold for the distance between the 0 th trackable/visible marker point at frame i-2 and frame i-1.
The judging whether the scale factor is within the threshold value range comprises: the calculation formula of the scale factor is as follows:
Figure RE-GDA0003584744080000029
wherein,
Figure RE-GDA00035847440800000210
it is required to be within a set threshold.
The predicting the position data of the 1 st mark point to be predicted/invisible according to the 0 th traceable/visible mark point position data and the 2 nd traceable/visible mark point position data and the scale factor respectively comprises the following steps:
combining the rotational transformation matrix R between the vectors formed by the 0 th and 2 nd traceable/visible mark points at the i-2 nd frame and the i-1 st frame, the position data
Figure RE-GDA00035847440800000211
And
Figure RE-GDA00035847440800000212
and a scale factor c, the position data of the 1 st mark point to be predicted/invisible can be predicted.
The rotation transformation matrix R is calculated by the following formula:
Figure RE-GDA00035847440800000213
Figure RE-GDA0003584744080000031
wherein the angle of rotation
Figure RE-GDA0003584744080000032
Rotating shaft
Figure RE-GDA0003584744080000033
Normalization of vectors
Figure RE-GDA0003584744080000034
Unit vector n of rotation axis is (nx, ny, nz), vector
Figure RE-GDA0003584744080000035
Or
Figure RE-GDA0003584744080000036
(Vector)
Figure RE-GDA0003584744080000037
Or
Figure RE-GDA0003584744080000038
The predicted position data of the 1 st frame to-be-predicted/invisible mark point is
Figure RE-GDA0003584744080000039
Figure RE-GDA00035847440800000310
Wherein,
Figure RE-GDA00035847440800000311
the third condition includes: the target value of the position data of the mark point to be predicted/invisible in the 1 st frame can be calculated by combining the motion speed of the mark point in the (i-1) th frame and the (i-2) th frame:
Figure RE-GDA00035847440800000312
then
Figure RE-GDA00035847440800000313
It is required to be less than a set threshold dt.
According to a second aspect, an embodiment provides an apparatus for predicting rigid body marker point positions, comprising:
store
A memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line; the at least one processor invokes the instructions in the memory to cause the apparatus to predict rigid body marker point locations to perform the method of the first aspect.
According to a third aspect, an embodiment provides a computer readable storage medium comprising a program executable by a processor to implement the method of the first aspect described above.
The beneficial effect of this application is:
a method for predicting positions of rigid body mark points according to the above embodimentsAcquiring a tracking mark data set and a position data set of mark points on each frame of human body limb, and if the human body limb has more than 3 mark points and at least 2 mark points can be correctly tracked, judging whether the limb P is a normal limbsThe ith frame position data of the 0 th mark point
Figure RE-GDA00035847440800000315
Traceable/visible 1 st mark point ith frame position data
Figure RE-GDA00035847440800000314
Ith frame position data of 2 nd mark point to be predicted/invisible
Figure RE-GDA00035847440800000316
The method comprises the steps of tracking/seeing, judging whether the mark point meets a preset condition, and if not, failing to predict the ith frame position data of the mark point to be predicted/not seen; if the position data of the ith frame of the 1 st mark point to be predicted/invisible is consistent with the position data of the 0 th traceable/visible mark point and the 2 nd traceable/visible mark point, the position data of the ith frame of the 1 st mark point to be predicted/invisible is predicted according to the scale factor, and therefore the lost position data is successfully predicted.
Drawings
FIG. 1 is a schematic representation of a rigid body structure;
FIG. 2 is a flow chart of a method of predicting rigid body marker point locations;
FIG. 3 is a schematic diagram of an apparatus for predicting rigid body marker point positions.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. Wherein like elements in different embodiments are numbered with like associated elements. In the following description, numerous details are set forth in order to provide a better understanding of the present application. However, those skilled in the art will readily recognize that some of the features may be omitted or replaced with other elements, materials, methods in different instances. In some instances, certain operations related to the present application have not been shown or described in detail in order to avoid obscuring the core of the present application from excessive description, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.
Furthermore, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. Also, the various steps or actions in the method descriptions may be transposed or transposed in order, as will be apparent to one of ordinary skill in the art. Thus, the various sequences in the specification and drawings are for the purpose of describing certain embodiments only and are not intended to imply a required sequence unless otherwise indicated where such sequence must be followed.
The numbering of the components as such, e.g., "second", etc., is used herein only to distinguish the objects as described, and does not have any sequential or technical meaning. The term "connected" and "coupled" when used in this application, unless otherwise indicated, includes both direct and indirect connections (couplings).
The inventive concept of the present application resides in: in the optical motion capture system, a plurality of rigid bodies with fixed shapes are required to be adopted for position tracking, the problems of similarity between the rigid bodies, shielding of the rigid bodies and the like are required to be avoided as much as possible, the method is used for further screening the mark points arranged on the rigid bodies so as to screen out proper mark points capable of improving the precision of the motion capture system, and subsequent matching calculation can be carried out according to the screened mark points so as to identify the corresponding rigid bodies.
The first embodiment is as follows:
referring to fig. 1, the present application discloses a structural diagram of a rigid body, which includes: the rigid body base 110, the support rods 120, the mark points 130 and the like are provided with at least 3 mark points, so that the accuracy of motion capture calculation can be ensured, the number of the mark points is the same as that of the support rods, different mark points are distinguished when the motion capture system calculates the coordinates of the mark points, the distances (such as M1, M2 and M3) between any two mark points are different as much as possible, namely similar triangles are avoided as much as possible, and the motion capture system is ensured to effectively identify the rigid body.
Example two:
referring to fig. 2, the present embodiment discloses a method for predicting rigid body mark point position information based on understanding the rigid body structure shown in fig. 1, and the claimed method includes steps S210-S250, which will be separately described below.
Step S210, acquiring a tracking mark data set of mark points on each frame of human body limb
Figure RE-GDA0003584744080000051
Figure RE-GDA0003584744080000052
And location data set
Figure RE-GDA0003584744080000053
Wherein i is the frame number, and s is the limb part;
Figure RE-GDA0003584744080000054
the position data of the ith frame of the mark point on the human body limb is shown,
Figure RE-GDA0003584744080000055
tracking mark data representing the ith frame of the mark point on the body limb, and
Figure RE-GDA0003584744080000056
and only two results are true and false, wherein true represents that the mark point is successfully tracked, and false represents that the mark point is failed to track, namely the mark point is lost.
Step S220, when there are more than 3 mark points on the human body and at least 2 mark points can be correctly tracked, if the body P issThe ith frame position data of the 0 th mark point
Figure RE-GDA0003584744080000057
Traceable/visible 1 st mark point ith frame position data
Figure RE-GDA0003584744080000058
Ith frame position data of 2 nd mark point to be predicted/invisible
Figure RE-GDA0003584744080000059
The method comprises the following steps that (1) tracking/visibility is carried out, whether mark points accord with a first condition or not is judged, if yes, the step S230 is carried out, and if not, prediction of the ith frame position data of the mark points to be predicted/invisible fails;
specifically, the first condition includes:
tracking marker data at frame i-2 for 0 th and 2 nd trackable/visible marker points
Figure RE-GDA00035847440800000510
And
Figure RE-GDA00035847440800000511
tracking flag data at i-1 frame
Figure RE-GDA00035847440800000512
And
Figure RE-GDA00035847440800000513
it is true, that is, the 0 th and 2 nd traceable/visible markers can be traced successfully at the i-2 nd frame and the i-1 st frame, and for the 1 st to-be-predicted/invisible marker, the tracing mark data at the i-1 st frame
Figure RE-GDA00035847440800000514
True, i.e. the 1 st mark point to be predicted/invisible in the ith frame for which tracking fails, and which can successfully track the corresponding position data in the (i-1) th frame
Figure RE-GDA00035847440800000515
If these conditions are met, the flow proceeds to step S230 to continue the prediction.
Step S230, calculating the distance between the 0 th traceable/visible mark point and the 2 nd traceable/visible mark point in the i-2 th frame and the i-1 th frame, judging whether the distance meets a second condition, if so, entering step S240, and if not, failing to predict the position data of the i-th frame of the mark point to be predicted/invisible;
specifically, the second condition includes:
Figure RE-GDA00035847440800000516
wherein,
Figure RE-GDA00035847440800000517
for the distance between the 2 nd trackable/visible marker point at frame i-2 and frame i-1,
Figure RE-GDA00035847440800000518
the distance between the 0 th trackable/visible marker at frame i-2 and frame i-1 is defined as d, which is a set threshold, typically the marker diameter.
For 2 traceable/visible mark points, the distance between the i-2 th frame and the i-1 th frame cannot be too small at the same time, so as to prevent extreme situations, such as when the traceable mark point rotates around two stationary traceable mark points, the failure probability of the algorithm for predicting the position of the mark point is high, if the second condition is not met at the same time, the prediction calculation is failed, otherwise, the step S240 is entered for continuing the prediction.
Step S240, calculating scale factors of the ith frame and the (i-1) th frame of the traceable/visible mark point, judging whether the scale factors are within a threshold range, if so, entering step S5, and if not, failing to predict the ith frame position data of the to-be-predicted/invisible mark point;
the scale factor is calculated by the formula:
Figure RE-GDA0003584744080000061
wherein,
Figure RE-GDA00035847440800000612
if the scale factor c is not too small, for example, not less than 0.02, it needs to be within a set threshold range, and thus the scale factor c calculated thereby also needs to be within a preset threshold range, otherwise, the calculation is ended, and if c is within the preset threshold range, the step S250 is proceeded to continue the prediction.
And S250, predicting the position data of the 1 st to-be-predicted/invisible mark point according to the 0 th traceable/visible mark point position data and the 2 nd traceable/visible mark point position data and the scale factor, wherein if the predicted position data meets a third condition, the prediction is successful.
Predicting the position data of the 1 st to-be-predicted/invisible mark point according to the 0 th traceable/visible mark point position data and the 2 nd traceable/visible mark point position data and the scale factor respectively specifically comprises the following steps:
combining the rotational transformation matrix R between the vectors formed by the 0 th and 2 nd traceable/visible mark points at the i-2 nd frame and the i-1 st frame, the position data
Figure RE-GDA0003584744080000063
And
Figure RE-GDA0003584744080000064
and a scale factor c, the position data of the 1 st mark point to be predicted/invisible can be predicted.
The rotation transformation matrix R can be calculated by the following formula:
Figure RE-GDA0003584744080000065
Figure RE-GDA0003584744080000066
wherein the angle of rotation
Figure RE-GDA0003584744080000067
Rotating shaft
Figure RE-GDA0003584744080000068
Normalization of vectors
Figure RE-GDA0003584744080000069
Unit vector n of rotation axis is (nx, ny, nz), vector
Figure RE-GDA00035847440800000610
Or
Figure RE-GDA00035847440800000611
(Vector)
Figure RE-GDA0003584744080000071
Or
Figure RE-GDA0003584744080000072
That is, different vectors v can be obtained through the 0 th traceable/visible mark point and the 2 nd traceable/visible mark point respectively1And v2Thus, two rotation transformation matrices R and R' are obtained. It should be noted that the length of any vector in the calculation process cannot be too small, otherwise, the prediction calculation is considered to fail.
Through the 0 th marking point
Figure RE-GDA0003584744080000073
The position data of the 1 st mark point missing in the ith frame is obtained by calculation as follows:
Figure RE-GDA0003584744080000074
also through the 2 nd mark point
Figure RE-GDA0003584744080000075
Calculating the missing position data of the 1 st mark point in the ith frame, and the other value is:
Figure RE-GDA0003584744080000076
the position data of the 1 st ith frame to-be-predicted/invisible mark point obtained by final prediction is as follows:
Figure RE-GDA0003584744080000077
in one embodiment, to further determine
Figure RE-GDA0003584744080000078
The third condition is also set, which comprises: can be provided with
Figure RE-GDA0003584744080000079
Corresponding target value is
Figure RE-GDA00035847440800000710
Namely, the target value of the position data of the mark point to be predicted/invisible in the 1 st ith frame can be calculated by combining the motion speed of the mark point in the (i-1) th frame and the (i-2) th frame:
Figure RE-GDA00035847440800000711
then
Figure RE-GDA00035847440800000712
It needs to be less than a set threshold dt, otherwise the predictive computation fails.
If the prediction calculation fails in any of the steps S220 to S250, the prediction calculation of the mark point to be predicted is successful, and the method can be referred to for predicting the position data of other mark points on the limb that cannot be tracked except for the position data of the mark point to be predicted/invisible in the 1 st frame listed above.
Example three:
referring to fig. 3 of the drawings, a drawing,
further, the present application also describes in detail the apparatus for predicting rigid body mark point positions in this embodiment from the perspective of hardware processing.
Fig. 3 is a schematic structural diagram of an apparatus for predicting rigid body mark point positions according to this embodiment, where the apparatus 500 may generate relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) for storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a sequence of instructions for operating on the device 500. Further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the device 500.
The device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the configuration of the apparatus 500 shown in fig. 3 does not constitute a limitation of the apparatus for predicting rigid body marker point locations provided herein, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
The present application also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the above-mentioned method for predicting rigid body marker point positions.
Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments may be implemented by hardware, or may be implemented by computer programs. When all or part of the functions of the above embodiments are implemented by a computer program, the program may be stored in a computer-readable storage medium, and the storage medium may include: a read only memory, a random access memory, a magnetic disk, an optical disk, a hard disk, etc., and the program is executed by a computer to realize the above functions. For example, the program may be stored in a memory of the device, and when the program in the memory is executed by the processor, all or part of the functions described above may be implemented. In addition, when all or part of the functions in the above embodiments are implemented by a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and may be downloaded or copied to a memory of a local device, or may be version-updated in a system of the local device, and when the program in the memory is executed by a processor, all or part of the functions in the above embodiments may be implemented.
The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention.

Claims (10)

1. A method of predicting rigid body marker point locations, comprising the steps of:
s1, acquiring a tracking mark data set of mark points on each frame of human body limb
Figure FDA0003453596560000011
And location data set
Figure FDA0003453596560000012
Wherein i is the frame number, and s is the limb part;
s2, when there are more than 3 markers and at least 2 markers can be correctly tracked on the limb, if the limb P issThe ith frame position data of the 0 th mark point
Figure FDA0003453596560000013
Traceable/visible 1 st mark point ith frame position data
Figure FDA0003453596560000014
Ith frame position data of 2 nd mark point to be predicted/invisible
Figure FDA0003453596560000015
Tracking/seeing, judging whether the mark point accords with a first condition, if so, entering step S3, and if not, failing to predict the ith frame position data of the mark point to be predicted/not seen;
s3, calculating the distance between the 0 th traceable/visible mark point and the 2 nd traceable/visible mark point in the i-2 th frame and the i-1 th frame, judging whether the distance meets the second condition, if so, entering the step S4, and if not, failing to predict the position data of the i-th frame of the mark point to be predicted/invisible;
s4, calculating the scale factor of the i frame and the i-1 frame of the traceable/visible mark point, judging whether the scale factor is in the threshold range, if so, entering the step S5, and if not, failing to predict the position data of the i frame of the mark point to be predicted/invisible;
and S5, predicting the position data of the 1 st mark point to be predicted/invisible according to the 0 th and the 2 nd traceable/visible mark point position data and the scale factor, and if the predicted position data meets a third condition, the prediction is successful.
2. The method of predicting rigid body marker point locations of claim 1, wherein the first condition comprises:
tracking marker data at frame i-2 for 0 th and 2 nd trackable/visible marker points
Figure FDA0003453596560000016
And
Figure FDA0003453596560000017
tracking flag data at i-1 frame
Figure FDA0003453596560000018
And
Figure FDA0003453596560000019
all need to be true, and, for the 1 st marker to be predicted/invisible, the following at frame i-1Trace mark data
Figure FDA00034535965600000110
Need to be true.
3. The method of predicting rigid body marker point locations of claim 1, wherein said second condition comprises:
Figure FDA00034535965600000111
wherein,
Figure FDA00034535965600000112
for the distance between the 2 nd trackable/visible marker point at frame i-2 and frame i-1,
Figure FDA00034535965600000113
d is a set threshold for the distance between the 0 th trackable/visible marker point at frame i-2 and frame i-1.
4. The method of predicting rigid body marker point locations as recited in claim 1, wherein said determining whether the scale factor is within a threshold comprises: the calculation formula of the scale factor is as follows:
Figure FDA0003453596560000021
wherein,
Figure FDA0003453596560000022
it is required to be within a set threshold.
5. A method of predicting rigid body marker point positions as described in claim 4, wherein said predicting position data for a 1 st to-be-predicted/invisible marker point based on 0 th and 2 nd trackable/visible marker point position data, respectively, and a scale factor comprises:
combining the rotational transformation matrix R between the vectors formed by the 0 th and 2 nd traceable/visible mark points at the i-2 nd frame and the i-1 st frame, the position data
Figure FDA0003453596560000023
And
Figure FDA0003453596560000024
and a scale factor c, the position data of the 1 st mark point to be predicted/invisible can be predicted.
6. A method of predicting rigid body marker point locations as defined in claim 5 wherein said rotational transformation matrix R is calculated by the formula:
Figure FDA0003453596560000025
Figure FDA0003453596560000026
wherein the angle of rotation
Figure FDA0003453596560000027
Rotating shaft
Figure FDA0003453596560000028
Normalization of vectors
Figure FDA0003453596560000029
Unit vector n of rotation axis is (nx, ny, nz), vector
Figure FDA00034535965600000210
Or
Figure FDA00034535965600000211
(Vector)
Figure FDA00034535965600000212
Or
Figure FDA00034535965600000213
7. The method for predicting rigid body marker point positions according to claim 6, wherein the predicted position data of the 1 st ith frame to-be-predicted/invisible marker point is as follows:
Figure FDA00034535965600000214
wherein,
Figure FDA00034535965600000215
8. the method of predicting rigid body marker point locations of claim 7, wherein the third condition comprises: the target value of the position data of the mark point to be predicted/invisible in the 1 st frame can be calculated by combining the motion speed of the mark point in the (i-1) th frame and the (i-2) th frame:
Figure FDA00034535965600000216
then
Figure FDA00034535965600000217
It is required to be less than a set threshold dt.
9. An apparatus for predicting rigid body marker point locations, comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line; the at least one processor invokes the instructions in the memory to cause the apparatus to predict rigid body marker point locations to perform the method of any of claims 1-8.
10. A computer-readable storage medium, characterized by comprising a program executable by a processor to implement the method of any one of claims 1-8.
CN202111679549.4A 2021-12-31 2021-12-31 Method, equipment and storage medium for predicting rigid body mark point position Pending CN114463383A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111679549.4A CN114463383A (en) 2021-12-31 2021-12-31 Method, equipment and storage medium for predicting rigid body mark point position

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111679549.4A CN114463383A (en) 2021-12-31 2021-12-31 Method, equipment and storage medium for predicting rigid body mark point position

Publications (1)

Publication Number Publication Date
CN114463383A true CN114463383A (en) 2022-05-10

Family

ID=81408623

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111679549.4A Pending CN114463383A (en) 2021-12-31 2021-12-31 Method, equipment and storage medium for predicting rigid body mark point position

Country Status (1)

Country Link
CN (1) CN114463383A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110689584A (en) * 2019-09-30 2020-01-14 深圳市瑞立视多媒体科技有限公司 Active rigid body pose positioning method in multi-camera environment and related equipment
US20200105000A1 (en) * 2018-09-28 2020-04-02 Glo Big Boss Ltd. Systems and methods for real-time rigid body motion prediction
CN111462187A (en) * 2020-04-09 2020-07-28 成都大学 Non-rigid target tracking method based on multi-feature fusion
CN111462089A (en) * 2020-04-01 2020-07-28 深圳市瑞立视多媒体科技有限公司 Virtual scene precision testing method based on optical dynamic capture system and related equipment
CN113592898A (en) * 2021-05-13 2021-11-02 黑龙江省科学院智能制造研究所 Method for reconstructing missing mark in motion capture

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200105000A1 (en) * 2018-09-28 2020-04-02 Glo Big Boss Ltd. Systems and methods for real-time rigid body motion prediction
CN110689584A (en) * 2019-09-30 2020-01-14 深圳市瑞立视多媒体科技有限公司 Active rigid body pose positioning method in multi-camera environment and related equipment
CN111462089A (en) * 2020-04-01 2020-07-28 深圳市瑞立视多媒体科技有限公司 Virtual scene precision testing method based on optical dynamic capture system and related equipment
CN111462187A (en) * 2020-04-09 2020-07-28 成都大学 Non-rigid target tracking method based on multi-feature fusion
CN113592898A (en) * 2021-05-13 2021-11-02 黑龙江省科学院智能制造研究所 Method for reconstructing missing mark in motion capture

Similar Documents

Publication Publication Date Title
US11402509B2 (en) Method and system for use in performing localisation
EP3309751B1 (en) Image processing device, method, and program
CN112215955A (en) Rigid body mark point screening method, device, system, equipment and storage medium
CN115965657B (en) Target tracking method, electronic device, storage medium and vehicle
US11403779B2 (en) Methods, apparatuses, systems, and storage media for loading visual localization maps
CN110969145A (en) Remote sensing image matching optimization method and device, electronic equipment and storage medium
US10832417B1 (en) Fusion of visual-inertial-odometry and object tracker for physically anchored augmented reality
CN110555352B (en) Interest point identification method, device, server and storage medium
CN112734827B (en) Target detection method and device, electronic equipment and storage medium
CN108304578B (en) Map data processing method, medium, device and computing equipment
CN114463383A (en) Method, equipment and storage medium for predicting rigid body mark point position
CN114638890A (en) Method, apparatus and storage medium for predicting rigid body mark point position
WO2019183928A1 (en) Indoor robot positioning method and robot
CN113112412A (en) Generation method and device of vertical correction matrix and computer readable storage medium
CN117333686A (en) Target positioning method, device, equipment and medium
CN114998755A (en) Method and device for matching landmarks in remote sensing image
KR102680209B1 (en) Apparatus for controlling posture of satellite antenna and method of operation thereof
CN118247591B (en) Dynamic mask eliminating method based on multiple geometric constraints
CN115587504B (en) Space target collision early warning method and device, electronic equipment and medium
CN111650621B (en) Method and device for calculating and detecting static drift precision, equipment and storage medium
CN118521807B (en) Mark point pairing method, medium and equipment
KR102718674B1 (en) Apparatus for coordinate transformation for satellite antenna and method of operation thereof
CN112053381B (en) Image processing method, device, electronic equipment and storage medium
CN118982567A (en) Method for registering coal mine three-dimensional point cloud and removing fixed facilities in warehouse environment
CN109785731B (en) Map construction method, system and storage medium

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