A method, device, equipment and readable storage medium for automatically binding rigid body marker points

Abstract

The present application provides a method for automatically binding rigid body marking points, including: arranging rigid bodies with optical marking points at preset distance intervals, obtaining a set of three-dimensional coordinate information of the marking points and calculating a distance matrix; setting a threshold value in combination with the maximum side length of the actual rigid body, and if the distances between the marking point and other points in the distance matrix are all greater than the threshold value, removing the corresponding point and recalculating the distance matrix; displaying the point set in an interface, using a corresponding algorithm to display multiple point sets belonging to k spatial point coordinate sets in k colors, and performing a wrong point deletion operation in the interface to obtain the point set of each rigid body; calculating the average value of the three-dimensional components of the point set of one of the rigid bodies, subtracting the average value from each three-dimensional component value in the point set, and obtaining the basic rigid body point set after binding the marking points, thereby solving the problems of time-consuming and cumbersome operation of manually binding rigid bodies.

Description

Technical Field

[0001] The present application relates to the field of motion capture, and in particular to a method, apparatus, device and readable storage medium for automatically binding rigid body marker points. Background Art

[0002] A rigid body is an object with a rigid structure. In existing optical motion capture systems, the marker points of the rigid body are detected by a capture camera group, that is, the fixed marker points on the rigid body maintain a relative relationship with the rigid body, thereby obtaining the two-dimensional coordinate points of the marker points. The three-dimensional marker points are tracked and reconstructed according to the two-dimensional coordinates of the marker points, and then the position and posture of the rigid body object to be captured are calculated according to the coordinates of the three-dimensional marker points. The posture of the rigid body object to be captured is related to the marker points initially bound on the rigid body, that is, the initial binding marker points of the rigid body determine the posture information of the motion capture. However, the initial binding information of the rigid body marker points is generally manual. If there are too many rigid bodies, such as about 100, the binding of the rigid body marker points will become very inconvenient, which will bring about problems such as long time consumption and troublesome operation. Summary of the invention

[0003] In view of this, the present invention mainly aims at the problems that rigid body binding takes a long time and is cumbersome to operate, and proposes a method, device, equipment and readable storage medium for automatically binding rigid body marker points.

[0004] In a first aspect, the present application provides a method for automatically binding rigid body marker points, the method comprising:

[0005] Arrange the rigid bodies with optical markers at preset intervals and obtain the three-dimensional coordinate information set of the markers. i}, i≤N, N is the total number of marked points, and calculate the distance matrix D ij ;

[0006] Combined with the maximum side length of the actual rigid body, a threshold T1 is set. If the distance matrix D ij If the distances between the marked point I and other points are greater than T1, then remove point I from {Pi} to obtain {Pi}′, and recalculate the distance matrix D′ of {Pi}′ ij ;

[0007] The set {Pi} is displayed on the interface, and the corresponding algorithm is used to display multiple point sets belonging to the k spatial point coordinate sets {Sc}, c=1, 2, ..., k in k colors, and the wrong point deletion operation is performed in the interface to obtain the point set S ({PN1}1, {PN2}2, ..., {PNk}k) of each rigid body, where N1, N2, ..., Nk corresponds to the number of marked points of each rigid body, and {PNk}k is the coordinate set of Nk marked points of the kth rigid body;

[0008] Calculate the average of the three-dimensional components of the point set {PNk}k of one of the rigid bodies k Subtract the mean value from each three-dimensional component value in the point set {PNk}k The basic rigid body point set S0 ({PN1}1, {PN2}2, ..., {PNk}k) after the binding marker points is obtained to complete the automatic binding process of the rigid body marker points.

[0009] The preset distance interval is 45-55cm.

[0010] The threshold value T1 is 25-50 cm.

[0011] The interface display of the set {Pi}, using a corresponding algorithm to display multiple point sets belonging to k spatial point coordinate sets {Sc}, c=1, 2, ..., k in k colors, and performing an operation of deleting wrong points in the interface includes:

[0012] Each rigid body marking point in the set {Pi} is displayed through the computer interface, and the corresponding algorithm is used to display multiple point sets belonging to k spatial point coordinate sets {Sc}, c = 1, 2, ..., k in k colors. The rigid body corresponding to the corresponding marking point can be distinguished by zooming in and out of the computer interface. If there is an erroneous point, the corresponding erroneous marking point is manually deleted.

[0013] The corresponding algorithm includes:

[0014] The kmeans algorithm is used to first randomly select k spatial points in the set {Pi}. Each spatial point initially represents the mean value or center of a class. Each remaining spatial point is assigned to the nearest class according to its distance from the center of each class. Then the mean value of each class is recalculated until the criterion function converges and the final criterion function value no longer changes.

[0015] The criterion function includes:

[0016]

[0017] Among them, u c is the set of all elements x in the spatial point coordinates {Sc} j The center of gravity or center point.

[0018] The three-dimensional components are the three-dimensional space coordinate values ​​of each coordinate point: x, y, z. The three-dimensional space coordinate values ​​of all coordinate points in the point set are added together and then divided by the number of coordinate points to obtain the average value of the three-dimensional components.

[0019] In a second aspect, the present application provides a device for automatically binding rigid body marker points, the device comprising:

[0020] The acquisition unit is used to arrange the rigid bodies with optical marking points at preset intervals and obtain the three-dimensional coordinate information set of the marking points. i}, i≤N, N is the total number of marked points, and calculate the distance matrix D ij ;

[0021] The screening unit is used to set a threshold T1 based on the maximum side length of the actual rigid body. If the distance matrix D ij If the distances between the marked point I and other points are greater than T1, then remove point I from {Pi} to obtain {Pi}′, and recalculate the distance matrix D′ of {Pi}′ ij ; Display the set {Pi} on the interface, use the corresponding algorithm to display multiple point sets belonging to k spatial point coordinate sets {Sc}, c=1, 2, ..., k in k colors, and delete the wrong points in the interface to obtain the point set S ({PN1}1, {PN2}2, ..., {PNk}k) of each rigid body, where N1, N2, ..., Nk corresponds to the number of marked points of each rigid body, and {PNk}k is the coordinate set of Nk marked points of the kth rigid body;

[0022] A calculation unit for calculating the average value of the three-dimensional components of the point set {PNk}k of one of the rigid bodies k Subtract the mean value from each three-dimensional component value in the point set {PNk}k The basic rigid body point set S0 ({PN1}1, {PN2}2, ..., {PNk}k) after the binding marker points is obtained to complete the automatic binding process of the rigid body marker points.

[0023] In a third aspect, the present application provides a device for automatically binding rigid body marker points, the device comprising a memory, a processor, and an automatic binding rigid body marker point program stored in the memory and executable on the processor, the automatic binding rigid body marker point program implementing the method described in the first aspect above when executed by the processor.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium on which an automatic binding rigid body marker point program is stored. When the automatic binding rigid body marker point program is executed by a processor, it implements the method provided in the first aspect of the present application or any possible implementation method of the first aspect.

[0025] It can be seen from the above technical solutions that this application has the following beneficial effects:

[0026] Arrange the rigid bodies with optical markers at preset intervals and obtain the three-dimensional coordinate information set of the markers. i}, and obtain the distance matrix; combined with the maximum side length of the actual rigid body, set a threshold. If the distance between the marked point I and other points in the distance matrix is ​​greater than the threshold, then remove point I from {Pi} to obtain {Pi}′, and re-calculate the distance matrix D′ of {Pi}′ ij ; Display the set {Pi} on the interface, use the corresponding algorithm to display multiple point sets belonging to the k spatial point coordinate sets {Sc} in k colors, and delete the wrong points in the interface to obtain the point set of each rigid body; calculate the average value of the three-dimensional component of the point set of one of the rigid bodies k, subtract the average value from each three-dimensional component value, and obtain the basic rigid body point set after binding the marked points to complete the automatic binding process of the rigid body marked points. Using this method, the binding of rigid bodies is more convenient and faster than pure manual binding. In the case of no noise and reasonable placement of rigid bodies, the correct rate of rigid body binding automatically classified by kmeans algorithm can reach about 95% or more, which greatly shortens the time consumption and is simple to operate. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of a process of automatically binding rigid body marker points in the present application is shown;

[0028] Figure 2 A schematic diagram of the structure of a device for automatically binding rigid body marker points of the present application is shown;

[0029] Figure 3 A structural schematic diagram of a device for automatically binding rigid body marker points in the present application is shown. DETAILED DESCRIPTION

[0030] The present application provides a method, apparatus, device and readable storage medium for automatically binding rigid body marker points, which are used to solve the problems of time-consuming and cumbersome operation of manually binding rigid bodies.

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0032] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0033] The division of modules in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in this application. In addition, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the present application.

[0034] Next, based on the above background description, the method of automatically binding rigid body marker points of the present application is introduced in detail.

[0035] See also Figure 1 , Figure 1 A schematic flow chart of a method for automatically binding rigid body marker points in the present application is shown. Specifically, the method may include the following steps:

[0036] Step S101, arranging rigid bodies with optical marking points at preset intervals, and obtaining a set of three-dimensional coordinate information of the marking points {P i}, i≤N, N is the total number of marked points, and calculate the distance matrix D ij ; The three-dimensional coordinate information set of the marker points can be obtained from the motion capture system through the existing algorithm {P i}, the distance matrix is ​​the matrix formed by the distance between the markers on the rigid body. The preset distance interval can be selected to be around 45-55cm. The distance interval should not be too close or too far, otherwise it will take a long time to bind the rigid body and reduce the calculation accuracy of the rigid body posture.

[0037] Step S102, combining the maximum side length of the actual rigid body, setting a threshold T1, if the distance matrix D ij If the distances between the marked point I and other points are greater than T1, then remove point I from {Pi} to obtain {Pi}′, and recalculate the distance matrix D′ of {Pi}′ ij ; When the distance matrix D ij When the distance between the marked point I and other points is significantly greater than T1, it means that the marked point I is a noise point and needs to be deleted from {Pi}, and then the distance matrix D′ between all the marked points in the point set {Pi}′ is recalculated. ij , repeat the above operation to continue to filter out other noise points, wherein the threshold T1 can be 25-50cm.

[0038] Step S103, display the set {Pi} on the interface, use the corresponding algorithm to display multiple point sets belonging to k spatial point coordinate sets {Sc}, c=1, 2, ..., k in k colors, and delete the wrong points in the interface to obtain the point set S ({PN1}1, {PN2}2, ..., {PNk}k) of each rigid body, where N1, N2, ..., Nk correspond to the number of marked points of each rigid body, and {PNk}k is the coordinate set of Nk marked points of the kth rigid body; adding simple manual intervention operations here can improve the accuracy of rigid body binding.

[0039] After simply filtering out independent noise points in step S102, each rigid body marking point in the set {Pi} can also be displayed through the computer interface. The corresponding algorithm is used to display multiple point sets belonging to k spatial point coordinate sets {Sc}, c=1, 2, ..., k in k colors. The rigid bodies corresponding to the corresponding marking points can be distinguished by zooming in and out of the computer interface. If there are wrong points, i.e. noise points, the corresponding erroneous marking points are further manually deleted.

[0040] The corresponding algorithm used is the kmeans algorithm, that is, the kmeans algorithm is used to first randomly select k objects (k sets of spatial point coordinates), each of which initially represents the average value or center of a class. For each remaining object, according to its distance from the center of each class, it is assigned to the nearest class, and then the average value of each class is recalculated. This process is repeated until the criterion function converges and the final criterion function value no longer changes.

[0041] In one embodiment, the criterion function may be:

[0042]

[0043] This formula represents the assumption that the object attributes come from the space vector, and the goal is to minimize the sum of the mean square error V within each group (point set), that is, the criterion function converges and the final criterion function value does not change. Assuming there are k point sets {Sc}c=1,2,...,k, then u c is all the elements x in the point set Sc j The center of gravity or center point.

[0044] Step S104, calculate the average value of the three-dimensional components of the point set {PNk}k of one rigid body k Subtract the mean value from each three-dimensional component value in the point set {PNk}k The basic rigid body point set S0 ({PN1}1, {PN2}2, ..., {PNk}k) after the binding marker points is obtained, thereby completing the automatic binding process of the rigid body marker points.

[0045] The three-dimensional components are the three-dimensional spatial coordinate values ​​of each coordinate point: x, y, z. The three-dimensional spatial coordinate values ​​of all coordinate points in the point set are added together and then divided by the number of coordinate points to obtain the average value of the three-dimensional components.

[0046] The above is an introduction to the method of automatically binding rigid body marker points of the present application. Now, the device of automatically binding rigid body marker points of the present application will be introduced.

[0047] See also Figure 2 , Figure 2 A schematic diagram of a structure of a device for automatically binding rigid body marker points is shown. Specifically, the device may include the following structure:

[0048] The acquisition unit 201 is used to arrange the rigid bodies with optical marking points at preset intervals and acquire the three-dimensional coordinate information set of the marking points {P i}, i≤N, N is the total number of marked points, and calculate the distance matrix D ij ;

[0049] The screening unit is used to set a threshold T1 based on the maximum side length of the actual rigid body. If the distance matrix D ij If the distances between the marked point I and other points are greater than T1, then remove point I from {Pi} to obtain {Pi}′, and recalculate the distance matrix D′ of {Pi}′ ij; Display the set {Pi} on the interface, use the corresponding algorithm to display multiple point sets belonging to k spatial point coordinate sets {Sc}, c=1, 2, ..., k in k colors, and delete the wrong points in the interface to obtain the point set S ({PN1}1, {PN2}2, ..., {PNk}k) of each rigid body, where N1, N2, ..., Nk corresponds to the number of marked points of each rigid body, and {PNk}k is the coordinate set of Nk marked points of the kth rigid body;

[0050] A calculation unit for calculating the average value of the three-dimensional components of the point set {PNk}k of one of the rigid bodies k Subtract the mean value from each three-dimensional component value in the point set {PNk}k The basic rigid body point set S0 ({PN1}1, {PN2}2, ..., {PNk}k) after the binding marker points is obtained to complete the automatic binding process of the rigid body marker points.

[0051] The screening, calculation and other processes involved in the above-mentioned device refer to the above-mentioned method steps S101-S104, which will not be repeated here.

[0052] See also Figure 3 , Figure 3 The present application provides a device for automatically binding rigid body marker points. Specifically, the device includes a processor 301, a memory 302, and an automatic binding rigid body marker point program stored in the memory 302 and executable on the processor 301. When the automatic binding rigid body marker point program is executed by the processor 301, the following is achieved: Figure 1 The corresponding steps of the method for automatically binding rigid body marker points in any embodiment.

[0053] Exemplarily, the automatic binding rigid body marker program, the computer program can be divided into one or more modules / units, one or more modules / units are stored in the memory 302, and executed by the processor 301 to complete the present application. One or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0054] The device for automatically binding rigid body markers may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that the illustration is merely an example of a computer device and does not constitute a limitation on the device for automatically binding rigid body markers. The device may include more or fewer components than shown in the illustration, or may combine certain components, or different components. For example, the device for automatically binding rigid body markers may also include input and output devices, network access devices, buses, etc. The processor 301, the memory 302, the input and output devices, and the network access devices are connected via a bus.

[0055] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device for automatically binding rigid body markers, and uses various interfaces and lines to connect the various parts of the device for automatically binding rigid body markers.

[0056] The memory 302 can be used to store computer programs and / or modules. The processor 301 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 302 and calling the data stored in the memory 302. The memory 302 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, video data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0057] The present application also provides a readable storage medium on which is stored a program for automatically binding rigid body marker points. When the program is executed by a processor, the following is achieved: Figure 1 Corresponding to the method of automatically binding rigid body marker points in any embodiment.

[0058] It can be understood that if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of each method embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0059] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for automatically binding rigid body marker points, characterized in that: The method comprises: Arrange the rigid bodies with optical markers at preset intervals and obtain the three-dimensional coordinate information set of the markers. i }, i≤N, N is the total number of marked points, and calculate the distance matrix D ij ; Combined with the maximum side length of the actual rigid body, a threshold T1 is set. If the distance matrix D ij If the distances between the marked point I and other points are greater than T1, then remove point I from {Pi} to obtain {Pi}', and recalculate the distance matrix D' of {Pi}' ij ; Display the set {Pi} on the interface, use the corresponding algorithm to display multiple point sets belonging to k spatial point coordinate sets {Sc}, c = 1, 2, ..., k in k colors, and delete the wrong points in the interface to obtain the point set S ({PN1}1, {PN2}2, ..., {PNk}k) of each rigid body, where N1, N2, ..., Nk corresponds to the number of marked points of each rigid body, and {PNk}k is the coordinate set of Nk marked points of the kth rigid body; Calculate the average of the three-dimensional components of the point set {PNk}k of one of the rigid bodies k Subtract the mean value from each three-dimensional component value in the point set {PNk}k Obtain the basic rigid body point set S0 ({PN1}1, {PN2}2, ..., {PNk}k) after binding the marker points to complete the automatic binding process of the rigid body marker points; The corresponding algorithm includes: The kmeans algorithm is used to first randomly select k spatial points in the set {Pi}. Each spatial point initially represents the mean value or center of a class. Each remaining spatial point is assigned to the nearest class according to its distance from the center of each class. Then the mean value of each class is recalculated until the criterion function converges and the final criterion function value no longer changes.

2. The method according to claim 1, characterized in that The preset distance interval is 45-55cm.

3. The method according to claim 1, characterized in that The threshold value T1 is 25-50 cm.

4. The method according to claim 1, characterized in that: The interface display of the set {Pi}, using a corresponding algorithm to display multiple point sets belonging to k spatial point coordinate sets {Sc}, c=1,2,...,k in k colors, and performing an operation of deleting wrong points in the interface includes: Each rigid body marking point in the set {Pi} is displayed through the computer interface, and the corresponding algorithm is used to display multiple point sets belonging to k spatial point coordinate sets {Sc}, c = 1, 2, ..., k in k colors. The rigid body corresponding to the corresponding marking point can be distinguished by zooming in and out of the computer interface. If there is an erroneous point, the corresponding erroneous marking point is manually deleted.

5. The method according to claim 1, characterized in that The criterion function includes: Among them, u c is the set of all elements x in the spatial point coordinates {Sc} j The center of gravity or center point.

6. The method according to any one of claims 1 to 5, characterized in that: The three-dimensional components are the three-dimensional space coordinate values ​​of each coordinate point: x, y, z. The three-dimensional space coordinate values ​​of all coordinate points in the point set are added together and then divided by the number of coordinate points to obtain the average value of the three-dimensional components.

7. A device for automatically binding rigid body marker points, characterized in that: The device comprises: The acquisition unit is used to arrange the rigid bodies with optical marking points at preset intervals and obtain the three-dimensional coordinate information set of the marking points. i }, i≤N, N is the total number of marked points, and calculate the distance matrix D ij ; The screening unit is used to set a threshold T1 based on the maximum side length of the actual rigid body. If the distance matrix D ij If the distances between the marked point I and other points are greater than T1, then remove point I from {Pi} to obtain {Pi}', and recalculate the distance matrix D' of {Pi}' ij ; Display the set {Pi} on the interface, use the corresponding algorithm to display multiple point sets belonging to k spatial point coordinate sets {Sc}, c=1,2,...,k in k colors, and delete the wrong points in the interface to obtain the point set S({PN1}1,{PN2}2,...,{PNk}k) of each rigid body, where N1,N2,...,Nk corresponds to the number of marked points of each rigid body, and {PNk}k is the coordinate set of Nk marked points of the kth rigid body; A calculation unit for calculating the average value of the three-dimensional components of the point set {PNk}k of one of the rigid bodies k Subtract the mean value from each three-dimensional component value in the point set {PNk}k Obtain the basic rigid body point set S0 ({PN1}1, {PN2}2, ..., {PNk}k) after binding the marker points to complete the automatic binding process of the rigid body marker points; The corresponding algorithm includes: The kmeans algorithm is used to first randomly select k spatial points in the set {Pi}. Each spatial point initially represents the mean value or center of a class. Each remaining spatial point is assigned to the nearest class according to its distance from the center of each class. Then the mean value of each class is recalculated until the criterion function converges and the final criterion function value no longer changes.

8. A device for automatically binding rigid body marker points, characterized in that: The device includes a memory, a processor, and an automatic binding rigid body marker point program stored in the memory and executable on the processor, wherein the automatic binding rigid body marker point program implements the method according to any one of claims 1 to 6 when executed by the processor.

9. A computer-readable storage medium, characterized in that: An automatic binding rigid body marker point program is stored thereon, and when the automatic binding rigid body marker point program is executed by a processor, the method as described in any one of claims 1 to 6 is implemented.

Images