WO2020232704A1

WO2020232704A1 - Rigid body identification method and apparatus, system, and terminal device

Info

Publication number: WO2020232704A1
Application number: PCT/CN2019/088160
Authority: WO
Inventors: 姚劲; 许秋子
Original assignee: 深圳市瑞立视多媒体科技有限公司
Priority date: 2019-05-23
Filing date: 2019-05-23
Publication date: 2020-11-26
Also published as: CN111213366B; CN111213366A

Abstract

The present application discloses a rigid body identification method and apparatus, a terminal device, a system, and a computer readable storage medium. The rigid body identification method comprises: acquiring coding information of a corresponding rigid body according to image data within an identification period sent by a camera; and identifying the rigid body according to the coding information and preset rigid body coding information. The technical solution provided in the present application can improve the rigid body production efficiency and the rigid body identification ability of an active optical motion capture system.

Description

Rigid body identification method, device, system and terminal equipment

Technical field

This application relates to the field of motion capture technology, and in particular to a rigid body recognition method, device, terminal equipment, system, and computer-readable storage medium.

Background technique

Motion capture is a high-tech technology that measures and records the motion trajectory or posture of an object in the real three-dimensional space, and reconstructs the state of the moving object in the virtual three-dimensional space.

The existing optical motion capture systems can be divided into active and passive. Passive rigid optical marking points are easy to wear, and are subject to heat dissipation, power supply, and reflective optical paths. The brightness of the light source received by the camera is not high, which reduces the ability of the camera to filter external redundant information and also reduces the camera’s Working distance. In addition, passive rigid bodies need to be set into different three-dimensional shapes to distinguish their differences, which makes it difficult to mass produce and difficult to configure in batches.

Some active products on the market only replace the reflective optical marking points of the original passive rigid body with light-emitting sources such as light-emitting diodes that emit light by themselves, and eliminate the camera's own light source, although this reduces the loss of optical marking points and the camera The production cost can also increase the working distance of the motion capture camera to a certain extent. However, active rigid bodies are often much more difficult to manufacture than passive rigid bodies due to power supply issues, and such active products still require rigid bodies to be configured into different three-dimensional shapes, which further increases the difficulty of mass production and batch configuration.

technical problem

In view of this, this application provides a rigid body recognition method, device, terminal equipment, system and computer readable storage medium to solve the prior art need to configure the rigid body used in the active optical motion capture system into different three-dimensional forms , Resulting in the problem that the configuration efficiency of the rigid body is too low and the recognition speed of the active optical motion capture system to the rigid body is too slow.

Technical solutions

The first aspect of the application provides a rigid body recognition method, including:

Obtain the coding information of the corresponding rigid body according to the image data from the camera in a recognition cycle;

The rigid body is identified according to the coding information and preset rigid body coding information.

The second aspect of the present application provides a rigid body recognition device, including:

The encoding information acquiring unit is configured to acquire encoding information of the corresponding rigid body according to the image data in a recognition period from the camera;

The identification unit is configured to identify the rigid body according to the coding information and preset rigid body coding information.

A third aspect of the present application provides a rigid body recognition system, which is characterized by comprising a server, a base station, a camera, and a rigid body. The base station is used to send a synchronization trigger signal to the rigid body and the camera; the rigid body includes a plurality of transmitters. The light source is used to call the coded data from the coded information stored in itself after receiving the synchronization trigger signal and assign it to each light-emitting source, so that each light-emitting source can control the light-emitting source according to the coded data. The brightness of the light-emitting source; the camera is used to expose and shoot the rigid body after receiving the synchronization trigger signal, and send the image data obtained by shooting to the server; the server is used to identify The image data in the period acquires coding information of a corresponding rigid body, and the rigid body is identified according to the coding information and preset rigid body coding information.

A fourth aspect of the present application provides a terminal device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor. The processor implements the first aspect or the first aspect when the computer program is executed by the processor. The rigid body recognition method mentioned in any of the possible implementations.

A fifth aspect of the present application provides a computer-readable storage medium having a computer program stored on the computer-readable storage medium, and the computer program implements the first aspect or any possible implementation manner of the first aspect when executed by a processor The rigid body recognition method mentioned in.

Beneficial effect

In the embodiment of the present application, firstly, the encoding information of the corresponding rigid body is obtained according to the image data sent from the camera in a recognition period, and then the rigid body is identified according to the encoding information and preset rigid body encoding information. Since the entire rigid body recognition method has nothing to do with the three-dimensional form of the rigid body, there is no need to configure the rigid body in the active optical motion capture system into different three-dimensional forms, thereby greatly improving the configuration efficiency of the rigid body and the active optical motion capture system. The ability to recognize rigid bodies.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

Figure 1 is a schematic diagram of the implementation process of a rigid body recognition method provided by this application;

Figure 2 is a schematic diagram of coding information provided by this application;

Figure 3 is a schematic diagram of a rigid body identification device provided by this application;

Figure 4 is a schematic diagram of a rigid body recognition system provided by this application;

FIG. 5 is a schematic diagram of a signal sequence diagram provided by this application;

Figure 6 is a schematic structural diagram of an embodiment of a terminal device provided by this application.

Embodiments of the invention

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are proposed for a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obstructing the description of this application.

In order to illustrate the technical solutions described in the present application, specific embodiments are used for description below.

It should be understood that when used in this specification and appended claims, the term "comprising" indicates the existence of the described features, wholes, steps, operations, elements and/or components, but does not exclude one or more other features Existence or addition of, whole, step, operation, element, component and/or its collection.

It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of this application and the appended claims, unless the context clearly indicates other circumstances, the singular forms "a", "an" and "the" are intended to include plural forms.

It should be further understood that the term "and/or" used in the specification and appended claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations .

As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "once" or "in response to determination" or "in response to detection" depending on the context . Similarly, the phrase "if determined" or "if detected [described condition or event]" can be interpreted as meaning "once determined" or "response to determination" or "once detected [described condition or event]" depending on the context ]" or "in response to detection of [condition or event described]".

In addition, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

Example one

The following describes a rigid body recognition method provided by an embodiment of the present application. Please refer to FIG. 1. The rigid body recognition method in the embodiment of the present application includes:

Step 101: Obtain coding information of a corresponding rigid body according to image data from a camera in a recognition period.

Wherein, the rigid body includes at least 3 light-emitting sources, and the light-emitting source may be a light-emitting diode (Light Emitting Diode). Emitting Diode, LED), and the coded information includes the same number of coded subsets as the number of light-emitting sources, and each coded subset includes coded data of one light-emitting source in one recognition period, and the coded data includes 0 or 1. The recognition cycle refers to the time required to complete a rigid body recognition. The recognition cycle is related to the number of exposure shots of the camera. A recognition cycle usually includes multiple exposure shots. The image data includes: the image captured by the camera containing the light source.

In specific implementation, step 101 may include: determining the identification information of the light-emitting source and the encoding data of the light-emitting source belonging to the same rigid body according to the image data sent by the camera in a recognition period, and according to the identification information of the light-emitting source and the encoding data of the light-emitting source of the same rigid body The encoding data obtains the encoding information of the corresponding rigid body.

Generally, the camera takes one frame of image data with one exposure, then processes the captured image data, and sends the processed data to the server, and then enters the next shooting. Among them, the image data may specifically include: gray data of the associated domain of the light-emitting source and the coordinate value of the center of mass of the light-emitting source. That is, the image data sent by the camera to the server is specifically: the gray data of the associated domain of the light-emitting source and the centroid coordinate value of the light-emitting source.

When the server determines the coded data of the light-emitting source on the rigid body, the operation mode may be, for example, in the same recognition cycle, according to the gray data of the associated domain of each light-emitting source in each frame of the camera image, determine each The average value of the gray data of the associated domain of the light emitting source, and the average value of the gray data of the associated domain is used as the gray value threshold of the light emitting source in the current identification period. The gray data of the associated domain includes: the average gray value of the associated domain or the total gray value of the associated domain; then, the server determines one based on the gray value threshold and the associated domain gray data of each light-emitting source in each frame of image. Encoding data of each light-emitting source in each frame of image in the recognition period; determining that it belongs to the same rigid body according to the centroid coordinate value of each light-emitting source in each frame of image in the recognition period sent by the camera The identification information of the light-emitting source; the encoding information of the corresponding rigid body is obtained according to the encoding data of each light-emitting source and the identification information of the light-emitting source belonging to the same rigid body in each frame of the image in a recognition period.

Wherein, the gray data of the correlation domain includes: the average gray value of the correlation domain or the total gray value of the correlation domain, the average gray value of the correlation domain is the average value of the gray value of the correlation domain of the light emitting source, and the total gray value of the correlation domain It is the sum of the gray values of the associated domain of the luminous source.

The method for determining the coded data of each light-emitting source may be, for example, determining whether the gray-scale data of the associated field of the light-emitting source is greater than or equal to the gray value threshold, and if the gray-scale data of the associated field of the light-emitting source is greater than or equal to the gray value threshold , The coded data of the light-emitting source is determined to be 1, if the gray-scale data of the associated domain of the light-emitting source is less than the gray value threshold, the coded data of the light-emitting source is determined to be 0, and so on, the server 44 can determine a recognition The coded data of each luminous source in each frame of image in the cycle.

Wherein, when determining the identification information of light-emitting sources belonging to the same rigid body, the operation method may be, for example, that the server can determine the relative distance between the light-emitting sources through the coordinate value of the center of mass of the light-emitting source, and reduce the relative distance of the light-emitting source whose relative distance is less than the preset distance threshold. Determine the luminous source belonging to the same rigid body to obtain identification information of the luminous source belonging to the same rigid body.

Optionally, before the step 101, the method may further include: generating coded information; sending the coded information to a corresponding rigid body to instruct the rigid body to control the brightness of the light source of the rigid body according to the coded information. Specifically, encoding information may be generated according to a preset encoding rule, and the preset encoding rule may include any one of the following: setting a frame header, a parity-check code encoding rule, and a Hamming code encoding rule. The coding information can be a binary code obtained after binary coding. The code information may include: a code subset corresponding to the number of light emitting sources. For example, if a rigid body includes N light-emitting sources, the code information of the rigid body includes N code subsets. Among them, a code subset stores coded data of a luminous source in one recognition period. It should be noted that in the process of generating unique coding information for each rigid body in advance, the principle that the server should observe when determining the coding subset included in the coding information of different rigid bodies is: try to make the coding subsets different, that is, try to Ensure the uniqueness of each code subset.

Optionally, when generating coded information, it may specifically include: generating coded information according to a preset code length and the number of light emitting sources of the rigid body. The preset encoding length is: the product of the encoding length of the encoding subset and the number of light-emitting sources. For example, assuming that the encoding length of a rigid body encoding subset is 16, and the number of light-emitting sources is 8, then the preset encoding length corresponding to the rigid body is 128. The encoding information can be as shown in Figure 2. Each line of encoding information is encoded data Form a subset of codes corresponding to a luminous source. It can be understood that the encoded information shown in FIG. 2 is only a presentation form of the encoded information.

After the coded information is generated, the coded information is also sent to the switch, and the switch sends the coded information to the base station. The base station sends the coded information to the rigid body corresponding to the coded information through wireless transmission technology, and stores it in the register of the rigid body, indicating The rigid body controls the brightness of the light source of the rigid body according to the coded information, and the wireless transmission technology may include any one of the following: wireless fidelity (Wi-Fi) and ZigBee.

Step 102: Identify the rigid body according to the coding information and preset coding information of the rigid body.

Optionally, step 102 may include: judging whether the preset rigid body coding information includes coding information, and if the preset rigid body coding information includes the coding information, determining the name or identity of the rigid body corresponding to the coding information Number (identification, ID) number. In other words, the coded information is compared with the preset coded information, and the rigid body is identified according to the comparison result to determine the name or identification number (identification, ID) of the rigid body.

In the embodiment of the present application, the encoding information of the corresponding rigid body is obtained through the image data sent by the camera in a recognition period, and then the rigid body is identified according to the encoding information and preset rigid body encoding information. The method has nothing to do with the three-dimensional form of the rigid body, so there is no need to configure the rigid body used in the active optical motion capture system into different three-dimensional forms, which greatly improves the production efficiency of rigid bodies and the ability of the active optical motion capture system to recognize rigid bodies .

Example two

Corresponding to the foregoing embodiment, FIG. 3 shows a schematic structural diagram of a rigid body recognition device provided by an embodiment of the present application. For ease of description, only the parts related to the embodiment of the present application are shown:

The rigid body identification device includes: an encoding information acquisition unit 301 and an identification unit 302. among them:

The encoding information acquiring unit 301 is configured to acquire encoding information of a corresponding rigid body according to the image data in a recognition period from the camera.

Optionally, the coded information acquiring unit 301 is specifically configured to determine the identification information of the light-emitting source belonging to the same rigid body and the coded data of the light-emitting source according to the image data in a recognition period from the camera, and according to the light-emitting source of the same rigid body The identification information and the coded data of the light-emitting source obtain the coded information of the corresponding rigid body. The operation mode for determining the identification information and the encoded data of the light-emitting source according to the image data has been described in the method embodiment, and will not be repeated here.

The identifying unit 302 is configured to identify the rigid body according to the coding information and preset rigid body coding information. During specific implementation, the identification unit 302 compares the determined encoding information with the preset encoding information of the rigid body, and recognizes the rigid body according to the comparison result.

Optionally, the rigid body identification device further includes: an encoding information generating unit and an encoding information sending unit.

The coding information generating unit is used for generating coding information; the coding information sending unit is used for sending the coding information to a corresponding rigid body, and instructing the rigid body to control the brightness of the light emitting source of the rigid body according to the coding information. Wherein, the code information generating unit may be specifically configured to generate code information according to a preset code length and the number of light emitting sources of the rigid body.

In the embodiment of the present application, the encoding information of the corresponding rigid body is obtained according to the image data sent from the camera in a recognition period, and then the rigid body is identified according to the encoding information and preset rigid body encoding information. The rigid body recognition method has nothing to do with the three-dimensional shape of the rigid body, and there is no need to configure the rigid body used in the active optical motion capture system into different three-dimensional shapes, which greatly improves the production efficiency of rigid bodies and the recognition of rigid bodies by the active optical motion capture system ability.

Example three

The embodiment of the present application also provides a rigid body recognition system. As shown in FIG. 4, for ease of description, only the parts related to the embodiment of the present application are shown:

The rigid body recognition system includes: a base station 41, a rigid body 42, a camera 43, and a server 44. Below, each component in the rigid body recognition system will be described in detail.

First of all, the main functions of the server 44 are as follows: First: generate unique code information for each rigid body 42 and send it to each rigid body 42 through the base station 41; second: receive image data from the camera 43 and identify it according to a The image data in the period acquires the coding information of the corresponding rigid body, and the rigid body 42 is identified according to the coding information and preset rigid body coding information.

In the system configuration stage, when the server 44 generates unique code information for each rigid body, the server 44 may generate unique code information for each rigid body according to the preset code length and the number of light sources of the rigid body. Among them, the preset encoding rules may include any one of the following: setting frame headers, parity check code encoding rules, and Hamming code encoding rules. The encoding information may specifically be binary encoding information. The code information may include: a code subset corresponding to the number of light emitting sources. For example, if a rigid body includes N light-emitting sources, the code information of the rigid body includes N code subsets. Among them, a code subset stores coded data of a luminous source in one recognition period. In each recognition period, the light source sequentially controls the brightness of the light source according to the instructions of the coded information. That is, the brightness of the light source of the light-emitting source, which is repeated once in a recognition cycle. It should be noted that in the process of generating unique coding information for each rigid body in advance, the principle that the server 44 should observe when determining the coding subsets included in the coding information of different rigid bodies is: try to make the coding subsets different, that is, Try to ensure the uniqueness of each code subset.

The preset encoding length is: the product of the encoding length of the encoding subset and the number of light-emitting sources. Assuming that the code length of the code subset of a rigid body is 16, and the number of light sources is 8, the preset code length corresponding to the rigid body is 128. The code information can be as shown in Figure 2. Each line of code data of the code information Form a subset of codes corresponding to a luminous source. It can be understood that the encoded information shown in FIG. 2 is only a presentation form of the encoded information.

Among them, in the system operation stage, the server 44 is also used to receive the image data from the camera, and obtain the coding information of the corresponding rigid body according to the image data in a recognition period, and to compare the rigid body 42 according to the coding information and preset rigid body coding information. Identify it. For example, the server 44 may compare the coded information with preset coded information, and identify the rigid body according to the comparison result. For example, the name or identification number (identification, ID) of the rigid body may be determined according to the comparison result.

When performing rigid body recognition, the server 44 can determine the average gray level data of each light-emitting source in a recognition period according to the gray-level data of each light-emitting source in each frame of the image sent by the camera 43. The average value of the gray data of the associated domain is used as the gray value threshold of each light source in the current identification period. And according to the gray value threshold and the associated domain gray data of each corresponding light-emitting source in each frame of image, the coded data of each light-emitting source in each frame of image in a recognition period is determined respectively. The way to determine the coded data of each luminous source can be, for example:

Determine whether the associated domain grayscale data of the light-emitting source is greater than or equal to the grayscale value threshold. If the associated domain grayscale data of the light-emitting source is greater than or equal to the grayscale value threshold, the coded data of the light-emitting source is determined to be 1. If the gray data of the associated domain is less than the gray value threshold, the coded data of the light-emitting source is determined to be 0, and by analogy, the server 44 can determine the coded data of each light-emitting source in each frame of the image in a recognition period.

After determining the coded data of each light-emitting source, the server 44 may also determine the identification information of the light-emitting source belonging to the same rigid body according to the centroid coordinate value of each light-emitting source of each frame of the image sent by the camera 43 in a recognition period; and 44 also determines the coding information of the corresponding rigid body according to the coded data of each light-emitting source in each frame of the image and the identification information of the light-emitting source belonging to the same rigid body in a recognition period. When determining the identification information of the light-emitting source, the operation mode may be, for example, that the server 44 determines the identification information of the light-emitting source belonging to the same rigid body according to the centroid coordinate value of each light-emitting source of each frame of image in a recognition period, for example, through The coordinate value of the center of mass of the luminous source determines the relative distance between the luminous sources, and confirms that the luminous sources that are closer together belong to the same rigid body.

It should be noted that since the average value of the gray data of the associated domain of different light-emitting sources in the same recognition period in different recognition periods will change, then correspondingly, the gray value thresholds of different light-emitting sources are in the same or different recognition periods. China also changes dynamically. When the server 44 determines the identification information of the light-emitting source belonging to the same rigid body according to the coordinate value of the centroid of the light-emitting source, the operation mode may be, for example, determining the relative distance between each light-emitting source according to the coordinate value of the centroid of each light-emitting source. The light-emitting source whose distance is less than the preset distance threshold is determined as the light-emitting source belonging to the same rigid body, and the identification information of the light-emitting source belonging to the same rigid body is determined; according to the identification information of the light-emitting source belonging to the same rigid body and the code data of each light-emitting source, the corresponding The encoding information of the rigid body.

Secondly, the base station 41 is introduced. Its functions include generating synchronization trigger signals and realizing the transmission of information between system components. For example, the base station 41 generates a synchronization trigger signal according to a predetermined interval period, and sends the generated synchronization trigger signal to the rigid body 42 and the camera 43 at the same time, so that the rigid body 42 can control the brightness of the light source on the rigid body 42 according to the synchronization trigger signal. At the same time, the camera 43 can capture the image data of the light-emitting source on the rigid body according to the synchronization trigger signal. During specific implementation, the base station 41 may simultaneously send a synchronization trigger signal to the rigid body 42 and the camera 43 through wireless transmission technology. Among them, the wireless transmission technology may include any of the following: wireless fidelity (Wi-Fi), ZigBee (ZigBee).

During the transmission of information between components, the base station 41 randomly allocates the multiple coded information received from the server 44 to the multiple rigid bodies 42. After each rigid body 42 receives the coded information, the coded information is registered in the rigid body 42. In the register.

Again, the rigid body 42 is introduced. The rigid body 42 includes multiple luminous sources. Its functions are as follows: first: to receive the coded information of the rigid body from the base station 41 and store it in the register of the rigid body; second: to receive the synchronization from the base station 41 After the trigger signal, the coded data is called from the coded information stored by itself and assigned to each light-emitting source, so that each light-emitting source can control the brightness of the light-emitting source according to the coded data.

The number of rigid bodies 42 in the rigid body recognition system may be one or more, and is not limited to the three shown in FIG. 4. The light source may be a light emitting diode (Light Emitting Diode, LED), and the coded data may include 0 or 1. That is, the embodiment of the present application uses the brightness of the light source to identify the corresponding encoded data as 1 or 0. The number of luminous sources on the rigid body 42 is the same as the number of coded subsets included in the coded information, and each coded subset stores the coded data of a luminous source within one identification period; the rigid body 42 performs an encoding every time it receives a synchronization trigger signal When data is distributed, after receiving the synchronization trigger signal, one bit of coded data is sequentially selected from the N coded subsets stored in itself and sent to the corresponding light emitting source. That is, after a synchronization signal is triggered, each light source only receives 1 bit of coded data. After the rigid body 42 receives the next synchronization trigger signal, it selects the next coded data from the coded information of the N light-emitting sources stored in the register and sends it to the corresponding light-emitting source, and so on, since then, a recognition cycle is completed Glowing. After a recognition cycle is completed, that is, after a round of distribution of the coded information of the light-emitting source has been completed, when the synchronization trigger signal is received again, the rigid body 42 recycles the coded information of the light-emitting source to start the coded data distribution of the next recognition cycle.

Finally, the camera 43 is introduced. After receiving the synchronization trigger signal from the base station 41, the rigid body 42 is exposed and photographed, and the photographed image data is sent to the server 44. Among them, one camera 43 can take images of multiple rigid bodies 42. It should be noted that the brightness change of the light source on the rigid body 42 is synchronized with the exposure and shooting of the camera 43, that is, the coded data is distributed every time the rigid body 42 receives a synchronization trigger signal; and the camera 43 receives a synchronization trigger every time The signal is an exposure shot. Since the synchronization trigger signal is synchronously sent to the rigid body and the camera, it can ensure that the camera can capture the brightness change of the light source. For example, as shown in FIG. 5, the rigid body performs an encoding data distribution every time a rising edge synchronization trigger signal is received; the camera 43 performs an exposure shooting every time a rising edge synchronization trigger signal is received. This ensures that the camera can capture the changes in the brightness of the light source such as LED lights.

It is understandable that the image data sent by the camera 43 to the server 44 may include the gray data of the associated domain of each light-emitting source and the coordinate value of the centroid of each light-emitting source. Therefore, before sending the image data to the server 44, the camera 43 also needs to determine the correlation domain grayscale data of each light-emitting source and the centroid coordinate value of each light-emitting source in each frame of image taken by exposure; and associate each light-emitting source The domain gray scale data and the centroid coordinate value of each light source are sent to the server 44. Optionally, the gray data of the associated domain may include: an average gray value of the associated domain or a total gray value of the associated domain.

Specifically, the camera 43 immediately determines the associated domain grayscale data of each light-emitting source and the centroid coordinate value of each light-emitting source in each frame of image taken by the exposure after each exposure and shooting, and calculates the current determined value of each light-emitting source. The gray data of the associated domain of a luminous source and the coordinate value of the centroid of each luminous source are sent to the server 44 immediately. Assuming that one recognition cycle includes F times of shooting, the camera performs F times of exposure and shooting according to the received F times of synchronization trigger signal, that is, in one recognition cycle, the camera 43 sends F times of image data (including) to the server 44.

Optionally, the rigid body recognition system may further include: a switch 45, as shown in FIG. 4, its function is to realize data exchange between the server 44 and the base station 41, and realize data exchange between the base station 41 and the camera 43. The server 44 generates unique code information, and the code information can be sent to the base station 41 through the switch 45. Of course, the switch 45 can also receive the synchronization trigger signal sent by the base station 41 and send the synchronization trigger signal to the camera 43.

It should be noted that the number N of light-emitting sources on the rigid body 42 is the same as the number of coded subsets included in the coded information, and each coded subset stores coded data for one light-emitting source within one identification period. The number of exposure shots in a recognition period is the same as the code length F of the code subset. The coding length of the coding subset may be, for example, F, where F is a positive integer equal to or greater than two. For the value of F, the smaller the F, the smaller the encoding range, and the smaller the number of identifiable rigid bodies. The larger the value of F, the more exposure and shooting times in a recognition cycle, and the time consumed will also be The more, this will reduce the recognition speed of rigid bodies. For specific implementation, F can be selected as 16.

Assuming that N is 8 and F is 16, that is, the rigid body 42 includes 8 luminous sources, and the code information includes 8 code subsets. After the rigid body 42 receives the first synchronization trigger signal, it selects the first from all code subsets. Bit coded data, and send the selected first bit of coded data to the corresponding light emitting source respectively. After receiving the second synchronization trigger signal, the second bit of coded data is selected from all the coded subsets, and all the selected second bit of coded data is sent to the corresponding light source, and so on, until a recognition Complete 16 times of synchronization trigger signal reception and 16 times of coded data distribution in the cycle.

In the following, the operation process of the rigid body recognition system will be described in detail.

When the rigid body recognition system of the embodiment of the present invention is working, it can be roughly divided into two stages, namely the configuration stage and the operation recognition stage, which will be described in detail below.

In the configuration stage, the server 44 generates unique code information for each rigid body 42 according to the preset coding length and the number of light emitting sources of the rigid body. After the server 44 generates unique coding information for each rigid body 42, it is necessary to send the coding information of a plurality of preset rigid bodies to each rigid body 42. In specific implementation, the server 44 sends to the base station 41 through the switch 45. After receiving the preset encoding information, the base station 41 randomly allocates the preset encoding information of multiple rigid bodies to the multiple rigid bodies 42 through wireless transmission technology. After each rigid body 42 receives the encoded information, it registers the received encoded information in its own register.

During the operation phase, the base station 41 broadcasts a synchronization trigger signal to all rigid bodies 42 through wireless transmission technology (such as wireless wifi, ZigBee and other wireless communication technologies). Each time a synchronization trigger signal is received, the rigid body 42 calls 1 bit of coded data from each code subset included in the coded information in the register in order and respectively allocates it to the corresponding light-emitting source (if the number of light-emitting sources is N, then a total of N bits are called Coded data, each light source receives 1 bit of coded data). After receiving the coded data, the luminous source controls its own luminous intensity according to the instructions of the coded data, that is, the embodiment of the present invention displays the corresponding code as 1 or 0 through the light or dark of the luminous source. At the same time, the same synchronization trigger signal is also sent from the base station 41 to the switch 45 and sent to the camera 43. After the camera 43 receives the synchronization trigger signal, an exposure shot is performed. That is to say, every time the rigid body receives a synchronization trigger signal, the coded data is distributed once, and the camera receives a synchronization trigger signal every time it performs an exposure shooting.

After the camera 43 performs exposure shooting, it needs to send the image data obtained by shooting to the server 44. Specifically, the image data includes the gray value of the associated domain of the light-emitting source and the coordinate value of the center of mass. Therefore, the camera 43 first needs to determine the gray value of the associated domain of each light-emitting source and the coordinate value of the centroid of each light-emitting source in each frame of images taken by exposure. When determining the gray value of the associated domain of each light-emitting source in each frame of image, the average gray value or the total gray value of the associated domain of the light-emitting source can be used as the gray value of the associated domain of the light-emitting source. After determining the gray value of the associated domain of each light-emitting source in each frame of image, the camera 43 also needs to send the determined gray value of the associated domain of each light-emitting source in the current frame image and the centroid coordinate value of each light-emitting source Give the server 44. It should be noted that each time the camera performs an exposure shooting, it needs to immediately send the associated domain gray value of each light-emitting source and the centroid coordinate value of each light-emitting source in the image frame obtained by the current exposure to the server 44. Assuming that one recognition cycle includes F times of shooting, the camera performs F times of exposure after sending F synchronization trigger signals, that is, in one recognition cycle, the camera sends F times of image data to the server 44.

The server 44 receives the gray value of the associated domain of each light-emitting source and the coordinate value of the center of mass of each light-emitting source in the F frame image in a recognition period. According to the correlation domain gray value of each light-emitting source in the F frame image in a recognition period, calculate the correlation domain gray value average value of each light-emitting source in a recognition period, and use the correlation domain gray value average value as the current The gray value threshold of the identification period. Then, according to the gray value threshold and the associated domain gray value of each light-emitting source in each frame of image, the coded information of each light-emitting source in each frame of image in a recognition period is determined. It should be noted that the gray-scale threshold of different light-emitting sources changes dynamically for different identification periods.

When determining the encoding information of each light-emitting source in each frame of the image in a recognition period according to the gray value threshold and the gray value of the associated domain of each light-emitting source in each frame of image, the specific operation method can be: determined The gray value threshold is M. If the gray value of the associated domain of the light-emitting source is greater than or equal to M, the code information of the light-emitting source is determined to be 1, and if the gray value of the associated domain of the light-emitting source is less than M, the code information of the light-emitting source is determined to be 0. In this way, the server 44 can determine the code information of each light source in each frame of the image in a recognition period. The signal timing diagram in the running phase can be represented by Figure 5.

The server 44 can also determine the identification information of the light-emitting source belonging to the same rigid body according to the centroid coordinate value of each light-emitting source of each frame of the image in a recognition period. For example, the centroid coordinate value of the light-emitting source can be used to determine the distance between the light-emitting sources. Relative distance, and confirm that the luminous sources that are closer together belong to the same rigid body.

Finally, the server 44 can determine the code information of each rigid body in a recognition period according to the determined luminous source information belonging to the same rigid body and the code information of each luminous source. The server 44 compares the determined encoding information of the rigid body with the preset encoding information, and recognizes the rigid body according to the comparison result, thereby determining the name or ID number of the rigid body. That is to say, in the embodiment of the present invention, by recording multiple frames of image data displayed in the form of bright or dark multiple luminous sources of different rigid bodies in a recognition period, different luminous sources can be distinguished by different codes, thereby distinguishing different The rigid body. Since the rigid body recognition process of the rigid body recognition system of the present invention has nothing to do with the three-dimensional form of the rigid body, there is no need to configure the rigid body in the active optical motion capture system into different three-dimensional forms, thereby greatly improving the production efficiency of rigid bodies and the active optics The ability of the motion capture system to recognize rigid bodies.

It should be understood that the size of the sequence number of each step in the foregoing embodiment does not mean the order of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present application.

Example four

Fig. 6 is a schematic diagram of a terminal device provided by an embodiment of the present application. As shown in FIG. 6, the terminal device 6 of this embodiment includes a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and running on the processor 60, such as a rigid body recognition program. When the processor 60 executes the computer program 62, the steps in the foregoing embodiments of the rigid body recognition method are implemented, for example, steps 102 to 102 shown in FIG. 1. Alternatively, when the processor 60 executes the computer program 62, the functions of the modules/units in the foregoing device embodiments, such as the functions of the units 301 to 302 shown in FIG. 3, are realized.

Exemplarily, the computer program 62 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 61 and executed by the processor 60 to complete This application. The one or more modules/units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 62 in the terminal device 6. For example, the computer program 62 can be divided into an encoding information acquisition unit and an identification unit. The specific functions of each unit are as follows: The encoding information acquisition unit is used to acquire the encoding information of the corresponding rigid body according to the image data sent from the camera in a recognition period. ; Identification unit for identifying the rigid body according to the coding information and preset rigid body coding information.

The terminal device 6 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The terminal device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that FIG. 6 is only an example of the terminal device 6 and does not constitute a limitation on the terminal device 6. It may include more or less components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

The so-called processor 60 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (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 the processor may also be any conventional processor or the like.

The memory 61 may be an internal storage unit of the terminal device 6, such as a hard disk or memory of the terminal device 6. The memory 61 may also be an external storage device of the terminal device 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), or a secure digital (Secure Digital, SD) equipped on the terminal device 6. Flash memory card Card) etc. Further, the memory 61 may also include both an internal storage unit of the terminal device 7 and an external storage device. The memory 61 is used to store the computer program and other programs and data required by the terminal device. The memory 61 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that for the convenience and conciseness of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned functions can be allocated to different functional units and modules as required. Module completion means dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist alone physically, or two or more units can be integrated into one unit. The above-mentioned integrated units can be hardware-based Formal realization can also be realized in the form of software functional units. In addition, the specific names of the functional units and modules are only used to facilitate distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the above system, please refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail or recorded in an embodiment, reference may be made to related descriptions of other embodiments.

A person of ordinary skill in the art may be aware that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.

In the embodiments provided in this application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the device/terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units. Or components can be combined or integrated into another system, or some features can be omitted or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in each embodiment of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated module/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, this application implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. It should be noted that the content contained in the computer-readable medium can be appropriately added or deleted according to the requirements of the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to the legislation and patent practice, the computer-readable medium Does not include electrical carrier signals and telecommunication signals.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still implement the foregoing The technical solutions recorded in the examples are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application, and should be included in Within the scope of protection of this application.

Claims

A rigid body recognition method, characterized in that it comprises:

Obtain the coding information of the corresponding rigid body according to the image data from the camera in a recognition cycle;

The rigid body is identified according to the coding information and preset coding information of the rigid body.
The rigid body recognition method according to claim 1, wherein the image data includes: gray-scale data of the associated domain and the center of mass coordinate value of the light-emitting source on the rigid body; the image data in a recognition cycle sent from the camera Get the coding information of the corresponding rigid body, including:

According to the correlation domain gray data of each light-emitting source in each frame of the image from the camera, determine the average value of the correlation-domain gray data of each light-emitting source in the recognition period, and compare the The average value of the gray data of the associated domain is used as the gray value threshold of the current recognition period, and the gray data of the associated domain includes: the average gray value of the associated domain or the total gray value of the associated domain;

According to the gray value threshold and the associated domain gray data of each light emitting source in each frame of image, respectively determining the coded data of each light emitting source in each frame of image in the recognition period;

Determining the identification information of the light emitting source belonging to the same rigid body according to the centroid coordinate value of each light emitting source of each frame of image in the recognition period from the camera;

According to the coded data of each light-emitting source and the identification information of the light-emitting source belonging to the same rigid body in each frame of image in one recognition period, the coded information of the corresponding rigid body is obtained.
The method for identifying a rigid body according to claim 1, wherein the identifying the rigid body according to the encoding information and preset encoding information of the rigid body comprises:

The coding information is compared with the coding information of the preset rigid body, and the rigid body is identified according to the comparison result.
5. The rigid body recognition method according to claim 1, wherein before said acquiring the coding information of the corresponding rigid body according to the image data sent from the camera in a recognition period, the method comprises:

Generate coding information;

Sending the coded information to the corresponding rigid body, instructing the rigid body to control the brightness of the light emitting source on the rigid body according to the coded information.
The rigid body recognition method according to claim 4, wherein said generating coded information comprises:

The code information is generated according to the preset code length and the number of light emitting sources of the rigid body.
A rigid body recognition device, characterized by comprising:

The encoding information acquiring unit is configured to acquire encoding information of the corresponding rigid body according to the image data in a recognition period from the camera;

The identification unit is configured to identify the rigid body according to the coding information and preset rigid body coding information.
A rigid body recognition system, characterized by comprising a server, a base station, a camera, and a rigid body. The base station is used to generate a synchronization trigger signal and send the synchronization trigger signal to the rigid body and the camera; the rigid body includes a plurality of The light-emitting source is used to call the coded data from the coded information stored in itself after receiving the synchronization trigger signal and allocate it to each light-emitting source, so that each light-emitting source can be controlled according to the coded data The brightness of the light-emitting source; the camera is used to expose and shoot the rigid body after receiving the synchronization trigger signal, and send the image data obtained by shooting to the server; the server is used to The image data in the recognition period acquires coding information of the corresponding rigid body, and the rigid body is recognized according to the coding information and preset coding information of the rigid body.
The rigid body recognition system according to claim 7, wherein the rigid body performs an encoding data distribution every time the synchronization trigger signal is received by the rigid body; and the camera performs an exposure every time the synchronization trigger signal is received by the camera. Shoot.
The rigid body identification system according to claim 8, wherein the rigid body includes N light-emitting sources, where N is a positive integer equal to or greater than three, and the code information includes N corresponding to the number of the light-emitting sources. Encoding subsets, each encoding subset stores the encoded data of a luminous source within one identification period; when the rigid body receives the synchronization trigger signal once and then allocates encoded data, it is specifically used to: After the synchronization trigger signal, one bit of coded data is sequentially selected from the N coded subsets stored by itself and sent to the corresponding light emitting source.
The rigid body recognition system according to claim 9, wherein the code length of the code subset is F, and F is a positive integer equal to or greater than two.
The rigid body recognition system according to claim 10, wherein the number of exposure shots in the one recognition period is the same as the code length of the code subset.
The rigid body recognition system according to any one of claims 7 to 11, wherein the rigid body recognition system further comprises: a switch; the server is also used to generate unique coding information for each rigid body in advance And send the coded information to the base station through the switch, and the base station randomly allocates the received multiple pieces of coded information to multiple rigid bodies.
The rigid body identification system according to claim 12, wherein when the server generates unique coding information for each rigid body in advance, it is specifically used for:

According to the preset code length and the number of light emitting sources of the rigid body, unique code information is generated for each rigid body.
The rigid body recognition system according to any one of claims 7 to 11, wherein the camera is further used for: before performing the sending of the image data obtained by shooting to the server:

Determining the associated domain gray scale data of each light-emitting source and the centroid coordinate value of each light-emitting source in each frame of images taken by exposure;

Correspondingly, the camera sending the image data obtained by shooting to the server specifically includes:

Sending the associated domain grayscale data of each light-emitting source and the centroid coordinate value of each light-emitting source to the server.
The rigid body recognition system according to claim 14, characterized by comprising:

The gray data of the correlation domain includes: an average gray value of the correlation domain or a total gray value of the correlation domain.
The rigid body recognition system according to claim 15, wherein when the server executes said obtaining the coding information of the corresponding rigid body according to the image data in a recognition period, it is specifically used for:

According to the gray data of the associated domain of each light-emitting source in each frame of the image sent by the camera, determine the average value of the gray data of the associated domain of each light-emitting source in the recognition period The average value of the gray data of the associated domain is used as the gray value threshold of each light-emitting source in the current identification period;

Respectively determine the coded data of each light-emitting source in each frame of the image in the recognition period according to the gray value threshold and the associated domain gray-scale data of the corresponding light-emitting source in each frame of image;

Determine the identification information of the light-emitting source belonging to the same rigid body according to the centroid coordinate value of each of the light-emitting sources in each frame of the image sent by the camera;

According to the coded data of each light-emitting source and the identification information of the light-emitting source belonging to the same rigid body in each frame of image in one recognition period, the coded information of the corresponding rigid body is determined.
8. The rigid body recognition system according to claim 7, wherein when the server recognizes the rigid body according to the coding information and preset rigid body coding information, it is specifically used for:

The coding information is compared with the preset coding information, and the rigid body is identified according to the comparison result.
A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program as claimed in claims 1 to 5 Steps of any of the methods.
A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the method according to any one of claims 1 to 5.