WO2024039069A1

WO2024039069A1 - Method and device for supporting tactical training, by using visual localization

Info

Publication number: WO2024039069A1
Application number: PCT/KR2023/009562
Authority: WO
Inventors: 최성광
Original assignee: 주식회사 브이알크루
Priority date: 2022-08-17
Filing date: 2023-07-06
Publication date: 2024-02-22
Also published as: KR102651994B1; KR20240024685A; KR20240046445A

Abstract

The method which is performed by a first computing device and reflects information about an object in a virtual reality space may comprise the steps of: acquiring first query data related to a space comprising an object which is scanned or an image of which is captured by an imaging device; receiving the first query data and receiving object-related information comprising pre-stored object material information and object recognition information from a second computing device which performs categorization for the first query data; and reflecting the object material information in a virtual reality space, if the virtual reality space is generated on the basis of the first query data.

Description

Method and apparatus for supporting tactical training using visual localization

This disclosure relates to image processing and more specifically to visual localization.

As the demand for Location Based Services increases, the need for accurate location information has increased. The most common way to determine location on mobile devices and mobile platforms is GNSS (Global Navigation Satellite System). However, because GNSS signals may be blocked by obstacles in an indoor environment, there is a limitation that they can only be easily used in an outdoor environment.

Although various technologies have been proposed to perform location recognition indoors, the reality is that many indoor location recognition techniques do not go beyond the fingerprint printing-based location recognition algorithm using wireless signals. In this method, the collected data related to Wi-Fi RSS (Received Signal Strength) or MFS (Magnetic Field Strength) is compared with data from a fingerprinting database. Fingerprinting-based systems have the advantage of being easy to build, but it can be difficult to maintain good performance because the signal pattern itself is affected by changes in the system environment. To overcome the deficiencies of these fingerprint-based systems, many alternatives have been proposed, including Optical, RFID (Radio Frequency Identification), Bluetooth Beacons, ZigBee, and Pseudo Satellite, but these alternatives also have difficulty achieving high accuracy in complex indoor environments. It is evaluated as difficult.

Recently, research on VPS (Visual Positioning System) has been actively conducted as an alternative to implement highly accurate position estimation even in indoor environments. VPS technology can also be expressed as visual localization technology, which refers to a technology that estimates the current location or pose of a device using images taken indoors or outdoors. Pose estimation of a device (or camera) refers to determining the translation and rotation information of a dynamically changing camera viewpoint. This camera pose estimation technology is being used in a variety of fields such as mixed reality, augmented reality, robot navigating, and 3-Dimensional Scene Reconstruction.

Augmented reality technology is a technology that enhances work efficiency by augmenting virtual information in real space in real time and allowing users to interact with the augmented virtual information. As augmented reality technology has recently developed, and in order to solve the situation where practical training is limited due to public damage, noise, etc., or safety accidents during training, research is being conducted to introduce a training system based on augmented reality technology. is in progress. In relation to this, Republic of Korea Patent No. 10-2225093 has been issued.

This disclosure was created in response to the above-described background technology, and is intended to efficiently support tactical training using visual localization.

The present disclosure is intended to efficiently support tactical training in a virtual reality space by determining the user's pose and the firearm's pose.

The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

According to some embodiments of the present disclosure for solving the problems described above, a method for reflecting information about an object in a virtual reality space, performed by a first computing device, includes: an object scanned or photographed by an imaging device; Obtaining first query data related to a space containing; Receiving information about an object including pre-stored object material information and object recognition information from a second computing device that receives the first query data and performs classification on the first query data; and when generating a virtual reality space based on the first query data, reflecting material information of the object in the virtual reality space.

In one embodiment, the material information of the object may include at least one of temperature, viscosity, absorption rate, reflectance, transmittance, scattering rate, attenuation rate, elastic coefficient, or friction coefficient at the volume or surface of the object.

In one embodiment, the material information of the object may include at least one of information about whether the object is blocking, blocking channel information, information about whether a trigger exists, information about a trigger channel, or tag information for programming. there is.

In one embodiment, the step of reflecting the material information of the object may include mapping information about the object to an area corresponding to recognition information of the object in the virtual reality space.

In one embodiment, obtaining first real location information corresponding to the first query data based on the first query data; Receiving first spatial information corresponding to the first real location information from a third computing device storing spatial information corresponding to the real location; and reflecting the first spatial information on the virtual reality space, based on the first spatial information.

In one embodiment, the first spatial information may include first weather information corresponding to the first actual location information.

In one embodiment, the first spatial information includes gravitational field, magnetic field, electric field, Coriolis force, wind direction, wind speed, temperature, humidity, air resistance, altitude above sea level, air density, viscosity, scattering rate, atmospheric pressure, elastic coefficient, It may include at least one of a friction coefficient, vector field, or tensor field.

In one embodiment, the first space information includes at least one of information about whether there is blocking in the first space, blocking channel information, information about whether there is a trigger, information about a trigger channel, or tag information for programming. can do.

In one embodiment, the step of reflecting the first space information on the virtual reality space includes changing material information of the object reflected on the virtual reality space based on the first space information. can do.

In one embodiment, the material information and space information of the object reflected on the virtual reality space may change with time based on a rule preset in the virtual reality space.

In one embodiment, the second computing device classifies the object included in the first query data using a pre-learned classification model, and material information of the pre-stored object corresponding to the classified object and Information about the object including recognition information of the object can be obtained.

In one embodiment, when placing a virtual object in the virtual reality space, the method may further include determining material information of the virtual object in a preset manner.

In one embodiment, receiving second query data from a user device worn by a user; Based on the second query data, determining a pose including a location and orientation related to the user; determining a relative pose of a firearm linked to the user device based on the pose; and calculating an expected path of a bullet fired through the muzzle of the firearm in the virtual reality space based on the pose and the relative pose.

In one embodiment, a computer program stored in a computer-readable storage medium, wherein the computer program includes instructions for causing a processor of a first computing device to perform the following steps to reflect information about an object in a virtual reality space: The steps include: obtaining first query data related to a space containing an object scanned or photographed by an imaging device; Receiving information about an object including pre-stored object material information and object recognition information from a second computing device that receives the first query data and performs classification on the first query data; and when generating a virtual reality space based on the first query data, reflecting material information of the object in the virtual reality space.

In one embodiment, a first computing device for reflecting information about an object in a virtual reality space, comprising: a processor; Memory; and a network unit, wherein the processor acquires first query data related to a space containing an object scanned or photographed by an imaging device, receives the first query data, and performs a query for the first query data. When receiving information about an object including pre-stored object material information and object recognition information from a second computing device that performs classification, and generating a virtual reality space based on the first query data, the virtual The material information of the object can be reflected in real space.

A technique according to an embodiment of the present disclosure can efficiently support tactical training using visual localization.

A technique according to an embodiment of the present disclosure can efficiently support tactical training in a virtual reality space by determining the user's pose and the firearm's pose.

The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below. .

Various aspects will now be described with reference to the drawings, where like reference numerals are used to collectively refer to like elements. In the following examples, for purposes of explanation, numerous specific details are set forth to provide a comprehensive understanding of one or more aspects. However, it will be clear that such aspect(s) may be practiced without these specific details.

1 schematically shows a block diagram of a computing device according to an embodiment of the present disclosure.

Figure 2 is a schematic diagram illustrating a network function according to an embodiment of the present disclosure.

Figure 3 exemplarily shows a method for supporting tactical training using visual localization according to an embodiment of the present disclosure.

Figure 4 exemplarily shows a method for estimating a pose through visual localization according to an embodiment of the present disclosure.

Figure 5 exemplarily shows a method for estimating a user's pose according to an embodiment of the present disclosure.

Figure 6 exemplarily shows a method of determining the relative pose of a firearm using a tag according to an embodiment of the present disclosure.

Figure 7 exemplarily shows a method of determining the relative pose of a firearm using a tag according to an embodiment of the present disclosure.

FIG. 8 exemplarily shows an aiming line in a virtual reality space generated according to a relative pose of a firearm determined according to an embodiment of the present disclosure.

FIG. 9 exemplarily shows a method for reflecting information about an object in a virtual reality space according to an embodiment of the present disclosure.

Figure 10 shows a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the disclosure. However, it is clear that these embodiments may be practiced without these specific descriptions.

As used herein, the terms “component,” “module,” “system,” and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an implementation of software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. A component may be distributed between two or more computers. Additionally, these components can execute from various computer-readable media having various data structures stored thereon. Components can transmit signals, for example, with one or more data packets (e.g., data and/or signals from one component interacting with other components in a local system, a distributed system, to other systems and over a network such as the Internet). Depending on the data being transmitted, they may communicate through local and/or remote processes.

Additionally, the term “or” is intended to mean an inclusive “or” and not an exclusive “or.” That is, unless otherwise specified or clear from context, “X utilizes A or B” is intended to mean one of the natural implicit substitutions. That is, either X uses A; X uses B; Or, if X uses both A and B, “X uses A or B” can apply to either of these cases. Additionally, the term “and/or” as used herein should be understood to refer to and include all possible combinations of one or more of the related listed items.

Additionally, the terms “comprise” and/or “comprising” should be understood to mean that the corresponding feature and/or element is present. However, the terms “comprise” and/or “comprising” should be understood as not excluding the presence or addition of one or more other features, elements and/or groups thereof. Additionally, unless otherwise specified or the context is clear to indicate a singular form, the singular terms herein and in the claims should generally be construed to mean “one or more.”

And, the term “at least one of A or B” should be interpreted to mean “if it contains only A,” “if it contains only B,” or “if it is a combination of A and B.”

Those skilled in the art will additionally recognize that the various illustrative logical blocks, components, modules, circuits, means, logic, and algorithm steps described in connection with the embodiments disclosed herein may be implemented using electronic hardware, computer software, or a combination of both. It must be recognized that it can be implemented with To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or software will depend on the specific application and design constraints imposed on the overall system. A skilled technician can implement the described functionality in a variety of ways for each specific application. However, such implementation decisions should not be construed as causing a departure from the scope of the present disclosure.

The description of the presented embodiments is provided to enable anyone skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Therefore, the present invention is not limited to the embodiments presented herein. The present invention is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

In the present disclosure, terms represented by N, such as first, second, or third, are used to distinguish a plurality of entities. For example, the entities expressed as first and second may be the same or different from each other. Terms expressed as 1-1, 1-2, and 2-1, 2-2 may also be used to distinguish a plurality of entities.

In the present disclosure, visual localization refers to a technology for estimating the current location or pose of a device using images taken indoors or outdoors. Pose estimation for a user device (or camera) refers to determining translation and rotation information of a dynamically changing camera viewpoint. As an exemplary implementation method rather than a limitation on visual localization, a Visual Positioning System (VPS) can be used.

The query image in the query data in the present disclosure includes an image captured by a device, and a reference image stored in a computing device (e.g., server, etc.) and a device corresponding to the query image using the query image. The pose of can be determined or estimated.

A reference image in the present disclosure may include a pre-stored image used for pose estimation of the device that captured the query image. The reference image may include actual images taken in a specific area to implement, for example, augmented reality or virtual reality. These reference images may be stored in computing device 100. Metadata mapped to the reference image can also be used to estimate the pose of the user device.

Metadata that may be included in query data in the present disclosure may mean additional information used in performing visual localization. For example, metadata may include additional information other than the image, such as information related to the device, pixel coordinate information of feature points, descriptor of feature points, landmark information obtained from the image, character information obtained from the image, etc. . For example, by utilizing metadata of the query image and/or reference image, the candidate group of reference images to be matched with the query image may be reduced. As another example, by utilizing metadata of the query image and/or reference image, a more suitable camera pose estimation method may be used.

The pose in the present disclosure may refer to result information obtained through visual localization, including, for example, the position and direction of a user device (eg, a device including a camera).

As another example, a pose in the present disclosure may include state information corresponding to, for example, the user's appearance and/or movements. In this example, the pose may be obtained by a deep learning module that includes an algorithm for estimating the user's pose. In this example, the pose may be obtained based on visual localization and/or inverse kinematics.

The relative pose in the present disclosure may include pose information in a relative concept based on the pose determined by visual localization. For example, a pose determined by visual localization may be referred to as an absolute pose, and a relative coordinate value using the 3D coordinate value of this absolute pose as a reference point may correspond to the relative pose.

1 schematically shows a block diagram of a computing device 100 according to an embodiment of the present disclosure.

Computing device 100 according to an embodiment of the present disclosure may include a processor 110 and a memory 130.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include different configurations for performing the computing environment of the computing device 100, and only some of the disclosed configurations may configure the computing device 100.

The computing device 100 in the present disclosure may refer to any type of node constituting a system for implementing embodiments of the present disclosure. Computing device 100 may refer to any type of user terminal or any type of server. The components of the computing device 100 described above are exemplary and some may be excluded or additional components may be included. For example, when the above-described computing device 100 includes a user terminal, an output unit (not shown) and an input unit (not shown) may be included within the scope of the computing device 100.

Computing device 100 in the present disclosure may include, for example, a first computing device, a second computing device, a third computing device, etc. For example, the first computing device may include a digital twin server and/or a VPS server. As another example, the second computing device may include a classification server that performs classification on specific data. As another example, the third computing device may include a server containing weather-related information.

A user device in the present disclosure may refer to a device for generating query data. Information captured by the user device may include query data including a query image. The query image captured by the user device may be used for comparison with a reference image within a computing device (eg, a server), and thus the pose of the user device at the time of capture may be determined.

User devices in this disclosure may include any type of mobile device, including cameras and/or lidar. For example, the user device may include a head mounted device (HMD), augmented reality (AR) glasses, and/or virtual reality (VR) glasses.

Hereinafter, for convenience of explanation, the user device and the computing device 100 will be distinguished, and a methodology for visual localization for the computing device 100 to receive shooting information from the user device and estimate the pose of the user device will be described. It will be explained. However, embodiments that perform visual localization on a user device that generates query data may also be included within the scope of the present disclosure. In this embodiment, the user device may perform at least part of the role of the computing device 100.

The computing device 100 in the present disclosure may perform technical features according to embodiments of the present disclosure, which will be described later. For example, computing device 100 may perform visual localization based on query data obtained from a first user device worn by a first user, thereby generating a first user device that includes a location and orientation with respect to the first user device. Determining a pose, based on interaction between a first set of tags located proximal to the first user device and a second set of tags located on a first firearm used by the first user, the determined Determine a first relative pose of the first gun based on the first pose, and based on the first pose and the first relative pose, determine a first character corresponding to the first user in virtual reality space. can be created. The virtual reality space in the present disclosure may include a digital twin corresponding to a predefined real space for tactical training.

Proximity in this disclosure is used to express a location closer to the user's device than the user's firearm when relative to the user's device. For example, a helmet worn by a user may be proximal from the perspective of the user device relative to the firearm the user is holding, and the firearm may be distal from the perspective of the user device.

In one embodiment, the processor 110 may consist of at least one core, including a central processing unit (CPU) and a general purpose graphics processing unit (GPGPU) of the computing device 100. , may include a processor for data analysis and/or processing, such as a tensor processing unit (TPU).

The processor 110 may read the computer program stored in the memory 130 and perform methods for supporting visual localization and/or tactical training according to an embodiment of the present disclosure. Additionally, the processor 110 may read a computer program stored in the memory 130 and perform methods for supporting visual localization and/or tactical training according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 is used for learning neural networks, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. Calculations can be performed. At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, CPU and GPGPU can work together to process learning of network functions and data classification using network functions. Additionally, in one embodiment of the present disclosure, processors of a plurality of computing devices may be used together to process learning of a network function and data classification using a network function. Additionally, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program. Operations for a neural network according to an embodiment of the present disclosure will be described later with reference to FIG. 2.

Additionally, processor 110 may typically handle overall operations of computing device 100. For example, the processor 110 processes data, information, or signals input or output through components included in the computing device 100 or runs an application program stored in the storage to provide information or information appropriate to the user. Functions can be provided or processed.

According to one embodiment of the present disclosure, the memory 130 may store any type of information generated or determined by the processor 110 and any type of information received by the computing device 100. According to an embodiment of the present disclosure, the memory 130 may be a storage medium that stores computer software that allows the processor 110 to perform operations according to embodiments of the present disclosure. Accordingly, the memory 130 may refer to computer readable media for storing software codes required to perform embodiments of the present disclosure, data to be executed by the codes, and execution results of the codes.

According to one embodiment of the present disclosure, the memory 130 may refer to any type of storage medium. For example, the memory 130 may be a flash memory type or a hard disk type. ), multimedia card micro type, card type memory (e.g. SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only) Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk. The computing device 100 may operate in connection with web storage that performs a storage function of the memory 130 on the Internet. The description of the memory described above is only an example, and the memory 130 used in the present disclosure is not limited to the examples described above.

The communication unit (not shown) in the present disclosure can be configured regardless of the communication mode, such as wired or wireless, and can be used in various communication networks such as a personal area network (PAN) and a wide area network (WAN). It can be configured. In addition, the communication unit may operate based on the known World Wide Web (WWW), and may also use wireless transmission technology used for short-distance communication, such as Infrared Data Association (IrDA) or Bluetooth. there is.

Computing device 100 in the present disclosure may include any type of user terminal and/or any type of server. Accordingly, embodiments of the present disclosure may be performed by a server and/or a user device.

Additionally, a user device may include any type of terminal capable of interacting with a server or other computing device. User devices include, for example, mobile phones, smart phones, laptop computers, personal digital assistants (PDAs), slate PCs, tablet PCs, and ultrabooks. It can be included.

Additionally, modules for generating depth maps may be included on the user device. Accordingly, the user device may generate an image and/or depth map and transmit it to computing device 100. In one embodiment, a user device may refer to any type of equipment for detecting an optical image, converting it into an electrical signal, and transmitting it to the computing device 100. For example, the client's device may include at least one of a camera, scanner, Lidar, and/or vision sensor. The computing device 100 may include a device or may be linked to an external device wirelessly or wired.

Servers may include any type of computing system or computing device, such as, for example, microprocessors, mainframe computers, digital processors, portable devices, and device controllers.

In an additional embodiment, the above-described server may include a storage unit (not shown) that stores and manages a reference image, metadata corresponding to the reference image, 3D map, etc. This storage may be included within the server or may exist under the management of the server. As another example, the storage unit may be implemented in a form that exists outside the server and can communicate with the server. In this case, the storage may be managed and controlled by an external server that is different from the server.

In one embodiment, the feature point acquisition model may include a neural network built through deep learning or machine learning. The feature point acquisition model may acquire feature points from a query image and/or depth map included in the input data. As another example, the feature point acquisition model may correspond to a model pre-trained based on supervised learning to recognize as a feature point a point where the amount of change in at least one of color or geometric patterns in the object exceeds a predetermined threshold.

For example, the query image may include at least one red-green-blue (RGB) image and/or at least one grayscale image.

For example, a depth map may include an image or information indicating the relative distances of each pixel within a specific image. Accordingly, the depth map may include information related to the distance from the location where the query image is taken to the surface of the subject.

Figure 2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.

In this disclosure, the feature point acquisition model may correspond to an artificial intelligence-based model. In additional embodiments of the present disclosure, an artificial intelligence-based model may be used to estimate the pose of a character (e.g., a first character) and/or create a character.

Throughout this disclosure, the terms artificial intelligence-based model, model, computational model, neural network, network function, and neural network may be used interchangeably. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node. Nodes (or neurons) that make up neural networks may be interconnected by one or more links.

Within a neural network, one or more nodes connected through a link may form a relative input node and output node relationship. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the data of the output node may be determined based on the data input to the input node. Here, the link connecting the input node and the output node may have a weight. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network can be determined according to the number of nodes and links within the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if the same number of nodes and links exist and two neural networks with different weight values of the links exist, the two neural networks may be recognized as different from each other.

A neural network may consist of a set of one or more nodes. A subset of nodes that make up a neural network can form a layer. Some of the nodes constituting the neural network may form one layer based on the distances from the first input node. For example, a set of nodes with a distance n from the initial input node may constitute n layers. The distance from the initial input node can be defined by the minimum number of links that must be passed to reach the node from the initial input node. However, this definition of a layer is arbitrary for explanation purposes, and the order of a layer within a neural network may be defined in a different way than described above. For example, a layer of nodes may be defined by distance from the final output node.

The initial input node may refer to one or more nodes in the neural network through which data is directly input without going through links in relationships with other nodes. Alternatively, in a neural network network, in the relationship between nodes based on links, it may mean nodes that do not have other input nodes connected by links. Similarly, the final output node may refer to one or more nodes that do not have an output node in their relationship with other nodes among the nodes in the neural network. Additionally, hidden nodes may refer to nodes constituting a neural network other than the first input node and the last output node.

The neural network according to an embodiment of the present disclosure is a neural network in which the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. You can. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be less than the number of nodes in the output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. You can. A neural network according to another embodiment of the present disclosure may be a neural network that is a combination of the above-described neural networks.

A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to the input layer and output layer. Deep neural networks allow you to identify latent structures in data. In other words, it is possible to identify the potential structure of a photo, text, video, voice, or music (e.g., what object is in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.) . Deep neural networks include convolutional neural network (CNN), recurrent neural network (RNN), auto encoder, restricted Boltzmann machine (RBM), and deep trust network ( It may include deep belief network (DBN), Q network, U network, Siamese network, generative adversarial network (GAN), etc. The description of the deep neural network described above is only an example and the present disclosure is not limited thereto.

A neural network may be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Learning of a neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

Neural networks can be trained to minimize output errors. In neural network learning, learning data is repeatedly input into the neural network, the output of the neural network and the error of the target for the learning data are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. This is the process of updating the weight of each node in the neural network through backpropagation. In the case of supervised learning, learning data in which the correct answer is labeled in each learning data is used (i.e., labeled learning data), and in the case of unsupervised learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning regarding data classification, the learning data may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network, and the error can be calculated by comparing the output (category) of the neural network with the label of the training data. As another example, in the case of unsupervised learning on data classification, the error can be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the reverse direction (i.e., from the output layer to the input layer) in the neural network, and the connection weight of each node in each layer of the neural network can be updated according to backpropagation. The amount of change in the connection weight of each updated node may be determined according to the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently depending on the number of repetitions of the learning cycle of the neural network. For example, in the early stages of neural network training, a high learning rate can be used to increase efficiency by allowing the neural network to quickly achieve a certain level of performance, and in the later stages of training, a low learning rate can be used to increase accuracy.

In the learning of neural networks, the training data can generally be a subset of real data (i.e., the data to be processed using the learned neural network), and thus the error for the training data is reduced, but the error for the real data is reduced. There may be an incremental learning cycle. Overfitting is a phenomenon in which errors in actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that learned a cat by showing a yellow cat fails to recognize that it is a cat when it sees a non-yellow cat may be a type of overfitting. Overfitting can cause errors in machine learning algorithms to increase. To prevent such overfitting, various optimization methods can be used. To prevent overfitting, methods such as increasing the learning data, regularization, dropout to disable some of the network nodes during the learning process, and use of a batch normalization layer can be applied. You can.

A computer-readable medium storing a data structure according to an embodiment of the present disclosure is disclosed.

Data structure can refer to the organization, management, and storage of data to enable efficient access and modification of data. Data structure can refer to the organization of data to solve a specific problem (e.g., retrieving data, storing data, or modifying data in the shortest possible time). A data structure may be defined as a physical or logical relationship between data elements designed to support a specific data processing function. Logical relationships between data elements may include connection relationships between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements that are physically stored in a computer-readable storage medium (e.g., a persistent storage device). A data structure may specifically include a set of data, relationships between data, and functions or instructions applicable to the data. Effectively designed data structures allow computing devices to perform computations while minimizing the use of the computing device's resources. Specifically, computing devices can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and search through effectively designed data structures.

Data structures can be divided into linear data structures and non-linear data structures depending on the type of data structure. A linear data structure may be a structure in which only one piece of data is connected to another piece of data. Linear data structures may include List, Stack, Queue, and Deque. A list can refer to a set of data that has an internal order. The list may include a linked list. A linked list may be a data structure in which data is connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer may contain connection information to the next or previous data. Depending on its form, a linked list can be expressed as a singly linked list, a doubly linked list, or a circularly linked list. A stack may be a data listing structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (for example, inserted or deleted) at only one end of the data structure. Data stored in the stack may have a data structure (LIFO-Last in First Out) where the later it enters, the sooner it comes out. A queue is a data listing structure that allows limited access to data. Unlike the stack, it can be a data structure (FIFO-First in First Out) where data stored later is released later. A deck can be a data structure that can process data at both ends of the data structure.

A non-linear data structure may be a structure in which multiple pieces of data are connected behind one piece of data. Nonlinear data structures may include graph data structures. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices. Graph data structure may include a tree data structure. A tree data structure may be a data structure in which there is only one path connecting two different vertices among a plurality of vertices included in the tree. In other words, it may be a data structure that does not form a loop in the graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Below, it is described in a unified manner as a neural network. Data structures may include neural networks. And the data structure including the neural network may be stored in a computer-readable medium. Data structures including neural networks also include data preprocessed for processing by a neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may include a loss function for learning. A data structure containing a neural network may include any of the components disclosed above. In other words, the data structure including the neural network includes preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may be configured to include all or any combination of the loss function for learning. In addition to the configurations described above, a data structure containing a neural network may include any other information that determines the characteristics of the neural network. Additionally, the data structure may include all types of data used or generated in the computational process of a neural network and is not limited to the above. Computer-readable media may include computer-readable recording media and/or computer-readable transmission media. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node.

The data structure may include data input to the neural network. A data structure containing data input to a neural network may be stored in a computer-readable medium. Data input to the neural network may include learning data input during the neural network learning process and/or input data input to the neural network on which training has been completed. Data input to the neural network may include data that has undergone pre-processing and/or data subject to pre-processing. Preprocessing may include a data processing process to input data into a neural network. Therefore, the data structure may include data subject to preprocessing and data generated by preprocessing. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, weights and parameters may be used with the same meaning.) And the data structure including the weights of the neural network may be stored in a computer-readable medium. A neural network may include multiple weights. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. Based on the weight, the data value output from the output node can be determined. The above-described data structure is only an example and the present disclosure is not limited thereto.

As an example and not a limitation, the weights may include weights that are changed during the neural network learning process and/or weights for which neural network learning has been completed. Weights that change during the neural network learning process may include weights that change at the start of the learning cycle and/or weights that change during the learning cycle. Weights for which neural network training has been completed may include weights for which a learning cycle has been completed. Therefore, the data structure including the weights of the neural network may include weights that are changed during the neural network learning process and/or the data structure including the weights for which neural network learning has been completed. Therefore, the above-mentioned weights and/or combinations of each weight are included in the data structure including the weights of the neural network. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be the process of converting a data structure into a form that can be stored on the same or a different computing device and later reorganized and used. Computing devices can transmit and receive data over a network by serializing data structures. Data structures containing the weights of a serialized neural network can be reconstructed on the same computing device or on a different computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure to increase computational efficiency while minimizing the use of computing device resources (e.g., in non-linear data structures, B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree) may be included. The foregoing is merely an example and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of a neural network. And the data structure including the hyperparameters of the neural network can be stored in a computer-readable medium. A hyperparameter may be a variable that can be changed by the user. Hyperparameters include, for example, learning rate, cost function, number of learning cycle repetitions, weight initialization (e.g., setting the range of weight values subject to weight initialization), Hidden Unit. It may include a number (e.g., number of hidden layers, number of nodes in hidden layers). The above-described data structure is only an example and the present disclosure is not limited thereto.

At least some of the steps shown in FIG. 3 may be performed, for example, by computing device 100. Depending on the implementation aspect, some of the steps shown in FIG. 3 may be omitted or additional steps may be added.

In one embodiment, computing device 100 performs visual localization based on query data obtained from a first user device worn by a first user, thereby providing a first user device that includes a location and orientation related to the first user device. 1 The pose can be determined (310).

Computing device 100 may provide an augmented reality and/or virtual reality platform. The computing device 100 may allow the client to enjoy activities on an augmented reality and/or virtual reality platform by obtaining captured data from the client's device and estimating the current location and direction of the client device.

In one embodiment, the first user device may include an HMD device, AR glasses, and/or VR glasses used by a first user among a plurality of users participating in tactical training. The query data may include a query image and metadata obtained by the first user device.

In one embodiment, the query image may include a two-dimensional RGB image or a grayscale image. In one embodiment, the query image may include a two-dimensional RGB image or gray scale image and a depth map. Metadata may include location information of the user device. Location information is, for example, geodetic datum or geodetic system (or geodetic reference datum, geodetic reference system, or geodetic reference frame), spatial reference system (SRS) or coordinate reference system (CRS) used in a specific region or country. , or may include coordinate values and/or direction values for a geographic coordinate system (GCS), etc. Other examples of location information may include GPS.

Additionally, metadata may include hardware-related information of the user device, such as focal length, principal point, resolution, etc. In addition, if there is a record of estimating the past camera pose of the user device, the user metadata includes preliminary estimation information about the camera pose of the user device calculated from the value of the IMU (Inertial Measurement Unit) of the user device. It can be included. This preliminary estimate information about the camera pose of the user device may include an approximate camera pose estimated using IMU information, and this preliminary estimate information may include approximate location information and direction information about the user device. . When this preliminary estimation information is used, the candidate group of reference images to be matched with the query image may be reduced.

In one embodiment of the present disclosure, metadata may further include camera information of the user device, and an example of such camera information may include intrinsic parameters of the camera. The computing device 100 may determine a pose estimation algorithm used to perform the visual localization among a plurality of pose estimation algorithms based on the camera information of the user device. For example, pose estimation for a user device (eg, camera) may estimate 6DoF in a direction that minimizes reprojection error.

For example, when the camera's internal parameters are not given (i.e., an uncalibrated camera), the pose estimation algorithm uses the Direct Linear Transformation (DLT) methodology to determine the elements of the rotation matrix and the translation vector. The reprojection error equation, which includes the elements of (vector) elements and the internal parameters of the camera as unknowns, can be changed to a linear equation and the rotation matrix, translation vector, and camera matrix can be estimated through QR decomposition.

For example, given the camera's internal parameters (i.e., a calibrated camera), the pose estimation algorithm uses the Perspective-n-Point (PnP) methodology to transform the reprojection error, a non-linear equation, into a linear equation, which is different from DLT. Similarly, pose estimation can be performed by directly solving the reprojection error, which is a non-linear equation, using the Gauss-Newton methodology or the Levenberg-Marquardt methodology. In this example, representative PnP methodologies may include P3P, EPnP, and SQPnP methodologies.

In an additional example, the DLT and PnP methodologies described above may introduce RANSAC to minimize camera pose errors resulting from inaccuracies in the 3D coordinates of reference feature points or inaccuracies in query feature points.

Therefore, as described above, the technique according to an embodiment of the present disclosure can apply the camera pose estimation algorithm differently depending on the presence or absence of camera information, for example, DLT or PnP depending on the presence or absence of camera information. By using the methodology, camera pose estimation can be performed.

In one embodiment, the first pose, including a position and orientation relative to the first user device, may be determined based on query data obtained by the first user device, for example, via a VPS. This first pose may include information about where the first user device is currently located and where it is pointing. In one embodiment, the first pose may include the position and direction of the helmet worn by the first user. That is, the first pose may include the position and orientation of equipment (eg, helmet, hat, etc.) located proximally of the first user device.

In one embodiment, computing device 100 is based on interaction between a first set of tags located proximally on a first user device and a second set of tags located on a first firearm used by the first user. Thus, the first relative pose of the first gun can be determined based on the first pose (320).

In this specification, tags can be used to determine the relative pose of the firearm being used by the user. For example, tags may include UWB (Ultra Wide Band) based devices. UWB refers to a short-range wireless communication technology that transmits large amounts of information at low power over a wider band than existing frequency bands.

In one embodiment, the first set of tags may be located on equipment (eg, a helmet) located proximal to the first user device. The second set of tags may be located on equipment (eg, a firearm) located distal to the first user device. By way of example and not limitation, the first set of tags may include three tags and the second set of tags may include two tags. A measurement value including at least one of Time Difference Of Arrival (TDOA) or Round Trip Time (RTT) between the tags may be determined through communication between the first set of tags and the second set of tags. Based on these measured values, the computing device 100 may determine the first relative pose of the firearm based on the first pose. In a further embodiment, the user device or another user terminal connected to the user device may determine the first relative pose of the firearm using measurements obtained through communication between tags.

For example, computing device 100 (or user device) provides a first measurement comprising at least one of TDOA or RTT between a first tag of the first set of tags and a second tag of the second set of tags. and TDOA or RTT between a third tag of the first set of tags and a fourth tag of the second set of tags, based on the determined first pose. The first relative pose including the relative direction and relative position of the first firearm may be determined.

As described above, a technique according to an embodiment of the present disclosure uses a VPS to estimate the pose of a user device (e.g., HMD or AR glasses, etc.) and utilizes the estimated pose of the user device to allow the user to hold and The relative pose of a gun (for example, the direction the gun's muzzle is facing, etc.) can be estimated efficiently and accurately.

A specific methodology for determining the relative pose of a gun using tags will be described later with reference to FIGS. 6 and 7.

In one embodiment, the computing device 100 may generate a first character corresponding to the first user in the virtual reality space based on the first pose and the first relative pose (330).

The first character is a character corresponding to the first user in the virtual reality space, and is used to communicate the first character to other users in the same space who participate in tactical training or to other users who exist in a different space and direct and supervise tactical training. A character corresponding to the user or the first user may be displayed. In this example, the pose estimation result of the first user device and/or additional information according to the pose estimation result of the first user along with the actual appearance of the first user on the user devices of other users in the same space participating in tactical training. can be displayed in augmented reality. This additional information may include the generated first character. In this example, the first character according to the pose estimation result of the first user device and/or the first user's pose estimation result is displayed in virtual reality on the user devices of other users who are present in a different space and direct and supervise the tactical training. It can be. Such a character may be created, for example, by pose estimation for the first user.

For example, the computing device 100 may determine the position and direction of the first user's neck based on the first pose and predetermined body information of the first user. Computing device 100 may determine the relative position and orientation of both hands of the first user based on the relative orientation of the first firearm, the relative position of the first firearm, and the location of the predetermined grip area with respect to the first firearm. there is. The computing device 100 determines the first user's neck based on the determined position and direction of the first user's neck, the determined relative positions and directions of both hands of the first user, and topographical information within the virtual reality space where the first user is located. The upper body pose can be determined. The computing device 100 may determine the position and direction of the first user's pelvis based on the determined upper body pose and body information of the first user. The computing device 100 may determine the lower body pose of the first user based on the determined position and direction of the pelvis and topographical information within the virtual reality space where the first user is located. Based on the determined position and direction of the first user's neck, the determined relative positions and directions of both hands of the first user, the determined upper body pose, the determined lower body pose, and the first user's body information, the computing device 100 creates a virtual A first character corresponding to the first user in real space can be created.

A specific method of generating the first character through pose estimation for the first user will be described later with reference to FIG. 5.

As described above, a technique according to an embodiment of the present disclosure estimates the pose for the user's user device (e.g., HMD, AR glasses, and/or VR glasses, etc.) through visual localization and determines the pose for the user's firearm. Since the relative pose can be estimated, efficient tactical training can be achieved by accurately determining the location and facing direction of the user device as well as the direction of the muzzle.

The computing device 100 uses the pre-trained feature point acquisition model 420 to obtain at least one

feature point

430 and 440 and/or each of the at least one

feature point

430 and 440 from the query data 410. At least one descriptor can be obtained. For example, the feature points 430 and 440 may be coordinates for each of the characteristic parts or points on the query image and/or depth map of the query data 410. For example, the descriptor may include at least one of information about the directionality and size of each feature point, and/or the relationship between pixels surrounding each feature point.

In one embodiment, the feature point acquisition model 420 is based on supervised learning to recognize as a feature point a point where the amount of change in at least one of color or geometric pattern in an object within the query image or depth map exceeds a predetermined threshold. Thus, a pre-trained model can be included. For example, the feature point acquisition model 420 may correspond to a model pre-trained using an image-based neural network. As another example, the feature point acquisition model 420 may correspond to a pre-trained model using a transformer-based neural network.

In one embodiment, the query data 410 includes a query image obtained by the user device, a descriptor corresponding to the query image, a depth map obtained by the user device, a descriptor corresponding to the depth map, and/or additional information of the user device. may include.

In one embodiment, the computing device 100 may perform visual localization 450 based on the first feature points 430 corresponding to the query image of the query data 410. The computing device 100 may acquire first feature points 430 for the query image included in the query data 410 using an artificial intelligence-based feature point acquisition model 420. The computing device 100 may perform visual localization 450 based on the first feature points 430, descriptors corresponding to the first feature points 430, and a plurality of pre-stored reference images. As a result of this visual localization 450, the pose 460 for the user device can be estimated. The pose 460 for the user device is determined based on the pose for the HMD, AR glasses, or VR glasses corresponding to the user device. It may include the location and direction of the helmet.

In one embodiment, visual localization 450 may include a methodology for determining the location and facing direction of a user device on query data based on a comparison between the query data and a pre-stored reference image. Specific methodologies for visual localization 450 are described in Korean Patent Application No. 10-2022-0081908 filed on July 4, 2022, which is incorporated by reference into this patent application.

In one embodiment, the computing device 100 may perform visual localization 450 based on the second feature points 440 corresponding to the depth map of the query data 410. The computing device 100 may acquire second feature points 440 for the depth map included in the query data 410 using an artificial intelligence-based feature point acquisition model 420. The computing device 100 performs the visual localization 450 based on the second feature points 440, descriptors corresponding to the second feature points 440, and a plurality of pre-stored reference images, thereby providing visual localization to the user device. The pose 460 can be determined.

In one embodiment, the computing device 100 performs visual localization 450 based on the first feature points 430 corresponding to the query image of the query data 410 and the second feature points 440 corresponding to the depth map. can be performed. For example, the computing device 100 compares the first feature points 430 and the second feature points 440 to determine pixel coordinates corresponding to each other among the first feature points 430 and the second feature points 440. Third feature points having values can be determined. For example, the third feature points may include overlapping feature points among the first feature points 430 and the second feature points 440 . The computing device 100 may determine reference images having feature points corresponding to third feature points among a plurality of pre-stored reference images, and determine a pose 460 for the user device based on the determined reference images. . As another example, the computing device 100 compares first feature points 430 and descriptors corresponding to the first feature points 430 with a pre-stored reference image and compares the second feature points 440 and the first feature points 430 with a pre-stored reference image. 2 Visual localization 450 may be performed by comparing descriptors corresponding to the feature points 440 and a pre-stored reference image.

In one embodiment, when the computing device 100 performs visual localization 450 on a user device that has acquired the query data 410, the reference image and query data 410 stored in the database of the computing device 100 ) Based on the feature points 430 and/or 440 on the image and additional information of the user device, visual localization 450 may be performed on the user device that obtained the query data 410.

In one embodiment, when performing visual localization 450 on a user device that has acquired query data 410, the computing device 100 selects query image feature points and feature points of the reference image from among a plurality of reference images. A pose reference image can be determined based on matching between the pose reference images. The computing device 100 determines the determined pose reference image according to a comparison result between the 3D camera coordinates assigned to the pose reference image and the coordinates (e.g., two-dimensional coordinates) of the feature points 430 and/or 440 of the query data, Camera pose information for the query data 410 may be determined. The pose reference image in the present disclosure may refer to a reference image that is subject to matching with the query data 410 among reference images. For example, the pose reference image may mean an image with the highest matching rate with the query data 410 among a plurality of candidate images to be compared with the query data 410. In this example, computing device 100 may perform visual localization on query data 410 using 3D camera coordinates assigned to the pose reference image.

In one embodiment, computing device 100, when performing visual localization 450 for the user device that obtained query data 410, uses camera pose information (e.g., 3D camera coordinates) assigned to the pose reference image. and determine absolute camera pose information of the query image with respect to the origin based on relative camera pose information for the query data 410 determined through the pose reference image, and determine absolute camera pose information for the query data 410 based on the absolute camera pose information. ) can be performed on the user device that has obtained the visual localization 450.

Absolute camera pose information in the present disclosure may be, for example, a geodetic datum or geodetic system (or geodetic reference datum, geodetic reference system, or geodetic reference frame), spatial reference system (SRS) used in a specific region or a specific country. ) or coordinate reference system (CRS), or geographic coordinate system (GCS), etc. may include coordinate values and/or direction values. Relative camera pose information in the present disclosure may include camera pose information generated by a comparison result between 3D coordinates of camera pose information assigned to a reference image and 2D coordinates between feature points of the query data 410.

In one embodiment, when the computing device 100 obtains the feature points and extracts the feature points 430 and/or 440 for the query data 410 from the query data 410, the feature points 430 and/or It may include obtaining pixel coordinates and descriptors corresponding to 440). The computing device 100 obtains the query data 410 by comparing the descriptor corresponding to the feature points 430 and/or 440 of the query data 410 with the descriptor corresponding to the feature points of the reference image stored in the database. Visual localization 450 can be performed for one user device. The descriptors are mapped to the query data 410 and can be compared with the descriptors mapped to the reference image to determine a candidate reference image to be compared with the query data 410 among the plurality of reference images. Descriptors can be used to efficiently perform a comparison between the reference image and query data 410.

In one embodiment, the computing device 100 compares the descriptor corresponding to the feature points of the query data 410 with the descriptor corresponding to the feature points of the reference image stored in the database, thereby providing information about the user device among the plurality of reference images. Determine a pose reference image for visual localization 450, and apply 3D coordinate information mapped to the pose reference image, matching information between feature points, and feature points 430 and/or 440 of the query data 410. Based on the corresponding pixel coordinates, visual localization 450 including camera pose estimation for the user device may be performed.

In the manner described above, a technique according to an embodiment of the present disclosure applies visual localization 450 (e.g., pose estimation for a VPS-based user device) to the output of the artificial intelligence-based feature point acquisition model 420. , the pose 460 of the user device that transmitted the query data 410 can be estimated in an accurate manner. This pose 460 of the user device can be used to accurately determine the current location of combatants in a tactical training system, and can further be used to identify enemies. In addition, the pose 460 of the user device can be used to estimate the direction of the combatant's firearm in a tactical training system, and thus the expected arrival point of the fired bullet can be efficiently determined.

In the present disclosure, an estimate of a user's pose may include an estimate of the posture the user is currently taking. For reference, the pose of the user device in this disclosure is intended to include the position and viewing direction of the user device determined based on VPS-based visual localization.

FIG. 5 exemplarily shows a method for estimating a user's pose, and a user's character in a virtual reality space may be created based on the estimation of the user's pose.

In one embodiment, computing device 100 may acquire an image captured by a user device (510). As an example, the image here may be included in the query data.

In one embodiment, the computing device 100 may estimate the position and direction of the user's head by performing visual localization on the acquired image (520). For example, during a virtual tactical training process, a user may be wearing a user device (eg, HMD device, AR glasses, or VR glasses). When visual localization is performed on an image acquired through a photographing unit of a user device worn by a user, a pose including the location and viewing direction of the user device may be estimated. The position and direction of the user's head may be estimated from the estimated pose of the user device. For example, the pose of the user's head may be estimated so that the pose of the user device and the position and direction of the user's head correspond to each other. As another example, the position and direction of the user's head may be determined from the pose of the user device based on pre-stored body information of the user.

In one embodiment, physical information about the user (eg, height, weight, waist circumference, and/or body size information) may be registered in advance. The computing device 100 may determine where the user's neck is located and the direction the neck is facing by applying body information to the user's head position and direction (530). For example, estimating the pose of the neck from the pose of the head may be implemented by determining the distance information between the neck and the head that is predetermined from the user's height information.

In one embodiment, the position and orientation of a weapon (e.g., a firearm) being held by the user may be estimated 540 from the position and orientation of the user's head or the position and orientation of the user device. For example, based on the interaction between tags attached to a user's weapon (e.g., a firearm) and tags attached to equipment (e.g., a helmet, etc.) corresponding to the user's head position, the location and orientation of the weapon may be determined. can be estimated. For example, the tags may include an Ultra Wide Band (UWB) tag and a first set of tags may be located on a helmet worn by the user and a second set of tags may be located on a firearm used by the user.

In one embodiment, the computing device 100 is configured to determine a link between a first tag of a first set of tags attached to a device corresponding to the position of the user's head and a second tag of the second set of tags attached to the user's weapon. A first measurement value including at least one of Time Difference Of Arrival (TDOA) or Round Trip Time (RTT) and TDOA between a third tag of the first set of tags and a fourth tag of the second set of tags Or, based at least in part on the second measurement value including at least one of the RTT, a relative pose including a relative direction and a relative position of the weapon based on the determined pose of the user device may be determined. For example, based on the first measurement, a first distance is determined between a second tag located at a first location on the firearm and a first tag located on the helmet, and based on the second measurement, a first distance between the first tag located on the helmet and the first tag located on the firearm are determined. A second distance between the fourth tag located at the second location and the third tag located on the helmet may be determined. Accordingly, a third position of the second tag from the helmet is determined from a first distance and a fourth position of the fourth tag from the helmet is determined from the second distance, and the third position and the Based on the relative relationship between the fourth positions, the relative direction in which the firearm is pointed based on the determined pose of the user device may be determined.

More specifically, the first set of tags attached to equipment worn by the user may be at least three (e.g., a 1-1 tag, a 1-2 tag, and a 1-3 tag) and held by the user. The second set of tags attached to the firearm may be at least two (eg, a 2-1 tag and a 2-2 tag). The 1-1 tag, the 1-2 tag, and the 1-3 tag may exist in different positions on the equipment worn by the user. The 2-1 tag and the 2-2 tag may exist in different positions on the firearm held by the user.

In one embodiment, a first distance between the 1-1 tag of the first set of tags and the 2-1 tag of the second set of tags, the 1-2 tag of the first set of tags and the A second distance between the 2-1 tags and a third distance between the 2-1 tag and a 1-3 tag among the tags of the first set may be determined. The first distance, second distance, and third distance may represent the distance from the first location of the gun where the 2-1 tag is located to each of the tags on the user's worn equipment (eg, helmet). Based on the first distance, the second distance, and the third distance, the location of the 2-1 tag with respect to each of the tags of the first set may be determined.

In one embodiment, a fourth distance between the 1-1 tag of the first set of tags and the 2-2 tag of the second set of tags, the 1-2 tag of the first set of tags and the A fifth distance between the 2-2 tags and a sixth distance between the 1-3 tag among the tags of the first set and the 2-2 tag may be determined. These fourth distances, fifth distances, and sixth distances may represent the distances for each of the tags on the user's worn equipment (eg, helmet) from the second location of the gun where the 2-2 tag is located. Based on the fourth distance, the fifth distance, and the sixth distance, the location of the 2-2 tag with respect to each of the tags of the first set may be determined.

In one embodiment, based on the location of the 2-1 tag relative to each of the first set of tags and the location of the 2-2 tag relative to each of the first set of tags, the 2- The relative position between tag 1 and the 2-2 tag may be determined. The movement and direction of the firearm can be estimated through changes in the relative positions between the two tags attached to the firearm. For example, the location of the 2-1 tag with respect to each of the tags in the first set, the location of the 2-2 tag with respect to each of the tags in the first set, and the location of the 2-1 tag and the Based on the relative position between the 2-2 tags, a relative pose including a relative direction and relative position of the firearm based on the pose with respect to the user device may be determined. For example, these relative poses can be expressed in three-dimensional coordinates.

In one embodiment, computing device 100 may determine the relative position and orientation of both or one hand of the user based on the relative orientation of the firearm, the relative position of the firearm, and the location of the predetermined grip area relative to the firearm. There is (550). For example, the position and pose of the user's hand may be estimated according to the direction in which the muzzle of the gun is facing and the position of the trigger portion of the gun, for example, along with information on the current position of the gun. In one example, it may be determined that one hand of the user is positioned on the trigger portion of the firearm and the other hand is positioned on the other grip portion of the firearm. In additional embodiments, the position and pose of the hand holding the firearm may be determined based on the user's body information (e.g., left-handed or right-handed information).

In one embodiment, the user's upper body pose is based on the position and direction of the user's neck determined in step 530, the relative positions and orientations of the user's both hands determined in step 550, and topographical information within the virtual reality space in which the user is located. can be determined (560). For example, terrain information within the virtual reality space may include information including the location, material, and shape of a specific object within the virtual reality space. The virtual reality space here may include a space (eg, digital twin) in virtual reality that corresponds to a specific space for tactical training. The user's upper body pose, which changes as the user moves in the virtual reality space and interacts with the corresponding object, may be determined based on the topographic information of the object. For example, preset dynamics and physics laws may be applied to terrain information in virtual reality space. Terrain information in this virtual reality space may include terrain attributes mapped to objects in real space. This topographical information includes material information including at least one of the height of the object, whether it is blocked, surface temperature, viscosity, absorption rate, reflectance, transmittance, scattering rate, attenuation rate, elastic coefficient and/or friction coefficient, and gravitational field, magnetic field, electric field, Coriolis force, It can be used to encompass spatial information including at least one of wind direction, wind speed, temperature, humidity, air resistance, altitude, air density, viscosity, scattering rate, atmospheric pressure, elastic coefficient, friction coefficient, or vector field. For example, based on a method of mapping information about the object to an area corresponding to the recognition information of the object in the virtual reality space, objects in the virtual reality space can have the properties of objects in the real space. Pose estimation of the user's upper body can be determined based on inverse kinematics that reflects topographical information.

In one embodiment, the position and direction of the user's pelvis may be determined based on the upper body pose determined in step 560 and the user's body information (570). Pose estimation of the user's pelvis may be determined based on inverse kinematics that reflects topographical information. For example, the computing device 100 displays the pelvis in a manner that reflects the user's body information (e.g., height information and/or statistical information in which the pelvis position is defined among the body) predefined in the pose for the user's upper body information. The location and/or direction of can be determined. Additionally, the direction the pelvis is facing can be determined to correspond to the direction the upper body is facing.

In one embodiment, the user's lower body pose may be determined based on the location and direction of the pelvis determined in step 570 and topographical information in the virtual reality space where the user is located (580). Pose estimation of the user's lower body can be determined based on inverse kinematics that reflects topographical information. For example, the computing device 100 may determine the position and direction of the lower body in a manner that reflects topographical information corresponding to the user's location, which is predefined in the user's pelvis pose.

In the above-described manner, the computing device 100 may create a character in a virtual reality space corresponding to a user performing tactical training in a real space. This virtual reality space can correspond to a digital twin corresponding to the actual space. Information about the character may be displayed as an augmented reality object to other users located with the user in the actual space, and information about the character may be displayed as a virtual object to other users located in a space other than the actual space. Can be displayed as a real object. The computing device 100 operates in the virtual reality based on the determined position and direction of the user's neck, the determined relative position and direction of both hands of the user, the determined upper body pose, the determined lower body pose, and the user's body information. You can create a character corresponding to a user in space.

As shown in FIG. 6, three tags (A, B, and C) may be placed on the helmet 620 of the user 600. For example, the tags described above may include UWB tags.

The user 600 may have query data generated by the user device 610 . As the query data is transmitted to the outside (eg, digital twin server and/or VPS server, etc.), pose estimation for the user device 610 and pose estimation for the gun 640 may be performed. The display unit 630 of the user 600 may output information about objects and other users in the virtual reality space. There may be two tags, a and b, in the firearm 640.

Each of the three tags (A, B, and C) attached to the helmet 620 is capable of communicating with each of the two tags (a and b) attached to the firearm 640. Accordingly, communication results between tags aA, aB, and aC can be obtained from the perspective of tag a attached to the firearm 640. The results of aA, aB, and aC allow distance information to be derived for each of the a tag attached to the first location of the firearm 640 and the three tags (A, B, and C) attached to the helmet 620. do. From the perspective of tag b attached to the firearm 640, communication results between tags bA, bB, and bC can be obtained. The results of bA, bB, and bC allow distance information to be derived for each of the b tag attached to the second location of the firearm 640 and the three tags (A, B, and C) attached to the helmet 620. do. Movement information of the firearm 640 may be determined based on the helmet 620 according to information on changes in distances in these two distance information sets. In this way, the position of the firearm 640 can be determined relative to its position relative to the helmet 620. In this way, the direction in which the muzzle of the firearm 640 faces can be determined based on the position of the helmet 620. In the manner described above, for example, using VPS, the direction and position of the user device 610 are estimated, the direction and position of the helmet 620 are determined according to the direction and position of the user device 610, and the helmet 620 ) The direction and position of the firearm 640 can be accurately estimated.

At least some of the example operations shown in FIG. 7 may be performed by computing device 100 and/or a user device.

As shown in FIG. 7, the relative position of the a tag can be determined from the A, B, and C tags from the TDoA or RTT of aA, aB, and aC (710). The relative position of the b tag from the A, B, and C tags can be determined from the TDoA or RTT of bA, bB, and bC (720). In the above-described manner, the relative position of the a tag located at the first position of the firearm and the relative position of the b tag located at the second position of the firearm can be determined. The relative position of the a tag can be accurately determined based on the distances between the a tag and each of the three tags (A, B, and C) located on the helmet. The relative position of the b tag can be accurately determined based on the distances between and the b tag. Based on the relative position of the a tag and the relative position of the b tag, the relative position of the b tag from the a tag (and/or the relative position of the a tag from the b tag) may be determined (730).

In one embodiment, as described above with reference to FIGS. 3 and 4 , the absolute position and direction of the user device (e.g., HMD or AR glasses) may be determined through visual localization (e.g., VPS) (740). The position and direction of the firearm may be determined from the relative position of the b tag from the a tag (and/or the relative position of the a tag from the b tag) using the absolute position and direction of the user device as a reference point. The relative pose of the gun determined based on the determined pose of the user device may correspond to the absolute position and direction of the gun.

In the manner described above, the technique according to an embodiment of the present disclosure estimates the current location and facing direction of a user participating in tactical training through a combination of visual localization (e.g., VPS) and UWB tags, and determines the user's firearm. The location and direction of the muzzle can be efficiently estimated. Accordingly, when implementing tactical training in virtual reality or augmented reality, tactical training participants can be accurately represented as objects in the virtual reality space or augmented reality space.

For example, the example shown in FIG. 8 may include the actions of the first user 810 that are visible to users other than the first user 810. In this example, the aiming line 830 may be expressed as an augmented reality object to other users. As another example, the example shown in FIG. 8 may include the actions of the first user 810 in a virtual reality space that is visible to a third party who is not located in the space for tactical training. In this example, the first user 810 as well as the aiming line 830 may be represented to a third party as a virtual reality object.

In one embodiment, as described above in FIGS. 6 and 7 , based on the relative direction determined with respect to the firearm 820 being held by the user 810, a line of sight for the firearm 820 in virtual reality space ( 830), three-dimensional coordinates corresponding to each of the starting and ending points may be determined. Based on the determined three-dimensional coordinates, the aiming line 830 in virtual reality space can be created.

In one embodiment, the aiming line 830 displayed in the virtual reality space may be displayed differently based on material information of the object in the virtual reality space. For example, in the case of the first object 840, it may be mapped as having a material through which a bullet of a specific first speed or first force can pass, and in the case of the second object 850, it may be mapped as having a material that can pass through a bullet of a specific first speed or force. 2 It can be mapped as having a material that a bullet of force can pass through. Accordingly, the aiming line 830 is displayed as passing through a specific object based on predefined characteristic information of the firearm 820, bullet information, location information of the

objects

840 and 850, and location information of the firearm 820. It can be decided whether it will happen or not. In the example shown in FIG. 8, the aiming line 830 may be displayed as passing through the first object 840 but not passing through the second object 850, and accordingly, the first object 840 and the second object ( An aiming line 860 passing through the first object 840 may be displayed between the

lines

850 and 850 .

In additional embodiments of the present disclosure, material information for

objects

840 and 850 may vary based on weather or climate information, for example. Changes in material information mapped to each of these

objects

840 and 850 may occur based on weather and climate information. As such, the technique according to an embodiment of the present disclosure allows the aiming line 830, which is generated according to the direction and position estimation of the firearm 820, to interact with the

objects

840 and 850, making it more efficient in the process of tactical training. Accurate information can be represented as augmented reality objects or virtual reality objects.

In a further embodiment of the present disclosure, the computing device 100 classifies objects included in query data using a pre-trained artificial intelligence-based image classification model or image segmentation model and pre-stores objects corresponding to the classified objects. Attribute information about an object including object material information and object recognition information can be obtained. Using this artificial intelligence-based classification or segmentation model, material information about an object may be automatically reflected in the virtual reality space without manually mapping the material information about the object.

In a further embodiment of the present disclosure, computing device 100 may include predefined characteristic information of firearm 820, bullet information, location information of

objects

840 and 850, and material information of

objects

840 and 850. , based on the spatial information of the path between the firearm 820 and the

objects

840 and 850 and the location information of the firearm 820, the expected arrival path of the bullet fired from the muzzle may be determined. The bullet's expected arrival path may be variably determined based on information (eg, terrain information) assigned to objects in the virtual reality space and climate or weather information in the virtual reality space.

The technique according to an embodiment of the present disclosure can efficiently implement tactical training in which multiple users participate through virtual reality or augmented reality technology by implementing gun pose estimation through linkage between VPS and UWB.

FIG. 9 exemplarily shows a method for reflecting information about an object in a virtual reality space according to an embodiment of the present disclosure. At least some of the steps shown in FIG. 9 may be performed, for example, by a first computing device. Depending on the implementation aspect, some of the steps shown in FIG. 9 may be omitted or additional steps may be added.

Referring to FIG. 9, the first computing device may obtain first query data related to a space including an object scanned or photographed by the imaging device (910).

The first computing device may include a processor, memory, and communication unit. In one embodiment of the present disclosure, the first computing device may include different configurations for performing a computing environment of the first computing device, and only some of the disclosed configurations may configure the first computing device.

The first computing device in the present disclosure may refer to any type of node constituting a system for implementing embodiments of the present disclosure. The first computing device may refer to any type of user terminal or any type of server. The components of the first computing device described above are exemplary and some may be excluded or additional components may be included. For example, when the above-described first computing device includes a user terminal, an output unit (not shown) and an input unit (not shown) may be included within the scope of the first computing device.

In one embodiment, the processor of the first computing device may consist of at least one core, and may include a central processing unit (CPU) and a general purpose graphics processing unit (GPGPU) of the first computing device. ), and may include a processor for data analysis and/or processing, such as a tensor processing unit (TPU).

The processor of the first computing device may read a computer program stored in the memory of the first computing device to perform methods for supporting visual localization and/or tactical training according to an embodiment of the present disclosure. Additionally, the processor of the first computing device may read a computer program stored in the memory of the first computing device to perform methods for supporting visual localization and/or tactical training according to an embodiment of the present disclosure. there is.

According to an embodiment of the present disclosure, the processor of the first computing device may perform an operation for learning a neural network. The processor of the first computing device processes input data for learning in deep learning (DL), extracts features from input data, calculates errors, and learns neural networks such as updating the weights of the neural network using backpropagation. You can perform calculations for . At least one of the CPU, GPGPU, and TPU of the processor of the first computing device may process learning of the network function. For example, CPU and GPGPU can work together to process learning of network functions and data classification using network functions. Additionally, in one embodiment of the present disclosure, processors of a plurality of computing devices may be used together to process learning of a network function and data classification using a network function. Additionally, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program. Operations on a neural network according to an embodiment of the present disclosure may be replaced with the content described above with respect to FIG. 2.

Additionally, a processor of the first computing device may typically handle overall operations of the first computing device. For example, the processor of the first computing device processes data, information, or signals input or output through components included in the first computing device or runs an application program stored in the storage to provide appropriate information to the user. Alternatively, functions may be provided or processed.

According to one embodiment of the present disclosure, the memory of the first computing device may store any type of information generated or determined by the processor of the first computing device and any type of information received by the first computing device. According to an embodiment of the present disclosure, the memory of the first computing device may be a storage medium that stores computer software that allows the processor of the first computing device to perform operations according to embodiments of the present disclosure. Accordingly, the memory of the first computing device may refer to computer readable media for storing software codes required to perform embodiments of the present disclosure, data to be executed by the codes, and execution results of the codes.

According to one embodiment of the present disclosure, the memory of the first computing device may refer to any type of storage medium. For example, the memory of the first computing device may be a flash memory type or a hard disk type. (hard disk type), multimedia card micro type, card type memory (e.g. SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM It may include at least one type of storage medium among Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), magnetic memory, magnetic disk, and optical disk. The first computing device may operate in relation to web storage that performs a storage function of the memory of the first computing device on the Internet. The description of the memory described above is merely an example, and the memory of the first computing device used in the present disclosure is not limited to the examples described above.

The communication unit (not shown) of the first computing device in the present disclosure may be configured regardless of the communication mode, such as wired or wireless, and may be used in a personal area network (PAN) or a wide area network (WAN). ), etc. can be composed of various communication networks. In addition, the communication unit may operate based on the known World Wide Web (WWW), and may also use wireless transmission technology used for short-distance communication, such as Infrared Data Association (IrDA) or Bluetooth. there is.

A first computing device in the present disclosure may include any type of user terminal and/or any type of server. Accordingly, embodiments of the present disclosure may be performed by a server and/or a user device.

An imaging device may refer to any type of equipment for detecting optical images, converting them into electrical signals, and transmitting them to the computing device 100. For example, the imaging device may include at least one of a camera, scanner, Lidar, and/or vision sensor. The computing device 100 may include a device or may be linked to an external device wirelessly or wired.

The first query data may include a first query image and first metadata acquired by the imaging device. For example, the first query image may include at least one red-green-blue (RGB) image and/or at least one grayscale image. The first metadata may include hardware-related information of the imaging device, such as focal length, principal point, resolution, etc.

In one embodiment of the present disclosure, the first metadata may further include camera information of the imaging device, and an example of such camera information may include intrinsic parameters of the camera.

The first computing device may receive first query data and receive information about the object, including pre-stored material information of the object and recognition information of the object, from a second computing device that performs classification on the first query data. There is (920).

The second computing device may include a processor, memory, and communication unit. In one embodiment of the present disclosure, the second computing device may include different configurations for performing a computing environment of the second computing device, and only some of the disclosed configurations may configure the second computing device.

The second computing device in the present disclosure may refer to any type of node constituting a system for implementing embodiments of the present disclosure. The second computing device may refer to any type of user terminal or any type of server. The components of the second computing device described above are exemplary and some may be excluded or additional components may be included. For example, when the above-described second computing device includes a user terminal, an output unit (not shown) and an input unit (not shown) may be included within the scope of the second computing device.

In one embodiment, the processor of the second computing device may consist of at least one core, and may include a central processing unit (CPU) and a general purpose graphics processing unit (GPGPU) of the second computing device. ), and may include a processor for data analysis and/or processing, such as a tensor processing unit (TPU).

The processor of the second computing device may read a computer program stored in the memory of the second computing device to perform methodologies for visual localization and/or methodologies for supporting tactical training according to an embodiment of the present disclosure. Additionally, the processor of the second computing device may read a computer program stored in the memory of the second computing device to perform methodologies for visual localization and/or methodologies for supporting tactical training according to an embodiment of the present disclosure. there is.

According to an embodiment of the present disclosure, the processor of the second computing device may perform an operation for learning a neural network. The processor of the second computing device processes input data for learning in deep learning (DL), extracts features from input data, calculates errors, and learns neural networks such as updating the weights of the neural network using backpropagation. You can perform calculations for . At least one of the CPU, GPGPU, and TPU of the processor of the second computing device may process learning of the network function. For example, CPU and GPGPU can work together to process learning of network functions and data classification using network functions. Additionally, in one embodiment of the present disclosure, processors of a plurality of computing devices may be used together to process learning of a network function and data classification using a network function. Additionally, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program. Operations on a neural network according to an embodiment of the present disclosure may be replaced with the content described above with respect to FIG. 2.

Additionally, a processor of the second computing device may typically handle the overall operation of the second computing device. For example, the processor of the second computing device processes data, information, or signals input or output through components included in the second computing device or runs an application stored in the storage to provide appropriate information to the user. Alternatively, functions may be provided or processed.

According to one embodiment of the present disclosure, the memory of the second computing device may store any type of information generated or determined by the processor of the second computing device and any type of information received by the second computing device. According to an embodiment of the present disclosure, the memory of the second computing device may be a storage medium that stores computer software that allows the processor of the second computing device to perform operations according to embodiments of the present disclosure. Accordingly, the memory of the second computing device may refer to computer readable media for storing software codes required to perform embodiments of the present disclosure, data to be executed by the codes, and execution results of the codes.

According to one embodiment of the present disclosure, the memory of the second computing device may mean any type of storage medium. For example, the memory of the second computing device may be a flash memory type or a hard disk type. (hard disk type), multimedia card micro type, card type memory (e.g. SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM It may include at least one type of storage medium among Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), magnetic memory, magnetic disk, and optical disk. The second computing device may operate in connection with web storage that performs a storage function of the memory of the second computing device on the Internet. The description of the memory described above is merely an example, and the memory of the second computing device used in the present disclosure is not limited to the examples described above.

The communication unit of the second computing device in the present disclosure may be configured regardless of communication mode, such as wired or wireless, and may be configured through various communication networks such as a personal area network (PAN) and a wide area network (WAN). It can be composed of . In addition, the communication unit may operate based on the known World Wide Web (WWW), and may also use wireless transmission technology used for short-distance communication, such as Infrared Data Association (IrDA) or Bluetooth. there is.

The second computing device in this disclosure may include any type of user terminal and/or any type of server. Accordingly, embodiments of the present disclosure may be performed by a server and/or a user device.

The second computing device may classify objects included in the first query data using a pre-trained classification model. The pre-trained classification model may include an object detection algorithm, a segmentation algorithm (for example, the PointNet algorithm that segments a 3D point cloud by point of the point cloud, etc.), etc. Accordingly, the second computing device can classify the object of the input two-dimensional image or three-dimensional point cloud using a pre-learned classification model. For example, when the second computing device acquires a two-dimensional image, it can distinguish the type (class) of the object in the two-dimensional image using a pre-trained classification model. For another example, when a 3-dimensional point cloud is acquired, the second computing device determines the type of object for each point through point-wise segmentation of the 3-dimensional point cloud using a pre-learned classification model. You can. For another example, when a 3D point cloud is acquired, the second computing device changes the 3D point cloud into mesh units and sets the boundary of the meshed object using a pre-learned classification model. The type of object can be determined on a mesh basis.

The second computing device may obtain information about the object including material information and object recognition information of a pre-stored object corresponding to the classified object.

The material information of an object may include information about the physical elements of the object. For example, the material information of the object may include at least one of temperature, viscosity, absorption rate, reflectance, transmittance, scattering rate, attenuation rate, evaporation rate, elastic coefficient, and/or friction coefficient at the volume or surface of the object. The volume of an object may be a three-dimensional area excluding the surface of the object. For example, if the object is in the form of a gas, the volume of the object may refer to the area occupied by the gas.

The material information of an object may include information about non-physical elements of the object. For example, the material information of the object may include at least one of information about whether the object is blocking, blocking channel information, information about whether a trigger exists, information about a trigger channel, and/or tag information for programming.

Object recognition information is information required to recognize an object and may include at least one of the type of object and/or the location of the object.

When the first computing device creates a virtual reality space based on the first query data, the first computing device may reflect the material information of the object in the virtual reality space (930).

The first computing device may map information about the object to an area corresponding to the recognition information of the object in the virtual reality space. For example, the first computing device may map information about the tree to an area corresponding to the tree in the virtual reality space.

The first computing device may obtain first real location information corresponding to the first query data based on the first query data.

The first computing device may receive first spatial information corresponding to the first real location information from a third computing device that stores spatial information corresponding to the real location.

The third computing device may include a processor, memory, and communication unit. In one embodiment of the present disclosure, the third computing device may include different configurations for performing the computing environment of the third computing device, and only some of the disclosed configurations may configure the third computing device.

A third computing device in the present disclosure may refer to any type of node constituting a system for implementing embodiments of the present disclosure. The third computing device may refer to any type of user terminal or any type of server. The components of the third computing device described above are exemplary and some may be excluded or additional components may be included. For example, when the above-described third computing device includes a user terminal, an output unit (not shown) and an input unit (not shown) may be included within the scope of the third computing device.

In one embodiment, the processor of the third computing device may consist of at least one core, and may include a central processing unit (CPU) and a general purpose graphics processing unit (GPGPU) of the third computing device. ), and may include a processor for data analysis and/or processing, such as a tensor processing unit (TPU).

Additionally, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program. Operations on a neural network according to an embodiment of the present disclosure may be replaced with the content described above with respect to FIG. 2.

Additionally, a processor of the third computing device may typically handle the overall operation of the third computing device. For example, the processor of the third computing device processes data, information, or signals input or output through components included in the third computing device or runs an application stored in the storage to provide appropriate information to the user. Alternatively, functions may be provided or processed.

According to one embodiment of the present disclosure, the memory of the third computing device may store any type of information generated or determined by the processor of the third computing device and any type of information received by the third computing device. According to an embodiment of the present disclosure, the memory of the third computing device may be a storage medium that stores computer software that allows the processor of the third computing device to perform operations according to embodiments of the present disclosure. Accordingly, the memory of the third computing device may refer to computer readable media for storing software codes required to perform embodiments of the present disclosure, data to be executed by the codes, and execution results of the codes. The memory of the third computing device may store spatial information corresponding to the actual location. For example, the memory of the third computing device may store spatial information including weather information corresponding to the actual location.

According to one embodiment of the present disclosure, the memory of the third computing device may mean any type of storage medium. For example, the memory of the third computing device may be a flash memory type or a hard disk type. (hard disk type), multimedia card micro type, card type memory (e.g. SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM It may include at least one type of storage medium among Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), magnetic memory, magnetic disk, and optical disk. The third computing device may operate in relation to web storage that performs a storage function of the memory of the third computing device on the Internet. The description of the memory described above is merely an example, and the memory of the third computing device used in the present disclosure is not limited to the examples described above.

The communication unit (not shown) of the third computing device in the present disclosure may be configured regardless of the communication mode, such as wired or wireless, and may be used in a personal area network (PAN) or a wide area network (WAN). ), etc. can be composed of various communication networks. In addition, the communication unit may operate based on the known World Wide Web (WWW), and may also use wireless transmission technology used for short-distance communication, such as Infrared Data Association (IrDA) or Bluetooth. there is.

A third computing device in this disclosure may include any type of user terminal and/or any type of server. Accordingly, embodiments of the present disclosure may be performed by a server and/or a user device.

The first computing device may reflect the first spatial information on the virtual reality space based on the first spatial information. The first spatial information may include first weather information corresponding to the first actual location information. For example, if the first actual location information is Seoul, the first spatial information may include weather information corresponding to Seoul.

The first space information may include information about physical elements of the first space. For example, the first spatial information includes the gravitational field, magnetic field, electric field, Coriolis force, wind direction, wind speed, temperature, humidity, air resistance, altitude above sea level, air density, viscosity, and scattering rate within the space (e.g., first space). , it may include at least one of atmospheric pressure, elastic coefficient, friction coefficient, vector field, and/or tensor field.

A vector field may be a set of vector values assigned to each point in space. A vector value may refer to a physical quantity with size and direction, such as position, speed, force, etc. For example, the vector value may include the strength of the gravitational field, the strength of the magnetic field, etc. However, the above-mentioned vector values are only examples and may include various values.

A tensor field may be a set of tensor values assigned to each point in space. The tensor value may be a value representing the moment of inertia or deformation of an object.

The first space information may include information about non-physical elements of the first space. For example, the first space information may include at least one of information about whether there is blocking in the first space, blocking channel information, information about whether there is a trigger, information about the trigger channel, and/or tag information for programming. there is.

The first computing device may change the material information of the object reflected in the virtual reality space based on the first spatial information. For example, the first computing device may change the evaporation rate, which is one of the material information of the water in the water cup reflected in the virtual reality space, according to the temperature included in the first spatial information.

Material information and spatial information of objects reflected on the virtual reality space may change with time based on preset rules on the virtual reality space.

Preset laws may include physical laws, mechanical laws, etc. For example, preset laws may include Newton's law of gravity, Einstein's general theory of relativity, etc. For example, the preset law is the first law in which the strength of attraction is inversely proportional to the cube of the distance, the second law in which the gravitational constant G is greater than the actual value, etc., are arbitrary laws that do not exist previously set by the environment or the user. may include. However, the preset rule is not limited to this and may be determined depending on the environment.

Newton's law of gravity and Einstein's general theory of relativity explain how objects with mass interact with objects with different masses, but even if the assumptions are the same, the results may differ depending on the theory. Therefore, the material information and spatial information of the object reflected on the virtual reality space affect each other (e.g., between the material information of the first object and the material information of the second object, the material information of the first object and the first object) influence between spatial information, influence between first spatial information and second spatial information of a second space different from the first space, etc.), may change with time based on preset laws in the virtual reality space.

When placing a virtual object in a virtual reality space, the first computing device may determine material information of the virtual object in a preset manner. The preset method may include a method of arbitrarily determining among a plurality of material information, a method of setting the material information of a real object corresponding to a virtual object, etc.

The first computing device may receive second query data from a user device worn by the user.

The first computing device may determine a pose, including a location and orientation related to the user, based on the second query data. For example, the first computing device may perform visual localization based on second query data obtained from the user device to determine a pose including a location and orientation related to the user device. The first computing device may provide an augmented reality and/or virtual reality platform. The first computing device may allow the client to enjoy activities on the augmented reality and/or virtual reality platform by obtaining captured data from the client's device, thereby estimating the current location and orientation of the client device.

In one embodiment, the user device may include an HMD device, AR glasses, and/or VR glasses used by one user of a plurality of users participating in tactical training. The second query data may include a query image and metadata obtained by the user device.

In one embodiment, the second query image may include a two-dimensional RGB image or a grayscale image. In one embodiment, the second query image may include a two-dimensional RGB image or gray scale image and a depth map. Metadata may include location information of the user device. Location information is, for example, geodetic datum or geodetic system (or geodetic reference datum, geodetic reference system, or geodetic reference frame), spatial reference system (SRS) or coordinate reference system (CRS) used in a specific region or country. , or may include coordinate values and/or direction values for a geographic coordinate system (GCS), etc. Other examples of location information may include GPS.

In one embodiment of the present disclosure, metadata may further include camera information of the user device, and an example of such camera information may include intrinsic parameters of the camera. The first computing device may determine a pose estimation algorithm used to perform visual localization among a plurality of pose estimation algorithms, based on camera information of the user device. For example, pose estimation for a user device (eg, camera) may estimate 6DoF in a direction that minimizes reprojection error.

In one embodiment, a pose, including a position and orientation relative to the user device, may be determined based on second query data obtained by the user device, for example, via a VPS. These poses may include information about where the user device is currently located and where it is pointing. In one embodiment, the pose may include the position and orientation of the helmet worn by the user. That is, the pose may include the position and orientation of equipment (eg, helmet, hat, etc.) located proximally to the user device.

The first computing device may determine the relative pose of a firearm linked to the user device based on the pose.

In one embodiment, the first set of tags may be located on equipment (eg, a helmet) located proximally to the user device. The second set of tags may be located on equipment (eg, a firearm) located distal to the user device. By way of example and not limitation, the first set of tags may include three tags and the second set of tags may include two tags. A measurement value including at least one of Time Difference Of Arrival (TDOA) or Round Trip Time (RTT) between the tags may be determined through communication between the first set of tags and the second set of tags. Based on these measurements, the first computing device can determine the relative pose of the firearm based on the pose. In a further embodiment, the user device or another user terminal connected to the user device may determine the relative pose of the firearm using measurements obtained through communication between tags.

For example, the first computing device (or user device) may provide a first measurement comprising at least one of TDOA or RTT between a first tag of the first set of tags and a second tag of the second set of tags, and Based on a second measurement value including at least one of TDOA or RTT between a third tag of the first set of tags and a fourth tag of the second set of tags, the position of the firearm based on the determined pose is determined. The relative pose, including relative direction and relative position, may be determined.

The first computing device may calculate an expected path of a bullet fired through the muzzle of a firearm in virtual reality space based on the pose and the relative pose. For example, the first computing device may determine the muzzle of the gun as the starting point of the bullet in virtual reality space based on the pose and the relative pose. And, the first computing device fires from the muzzle based on predefined characteristic information of the firearm, bullet information, location information of objects, material information of the objects, spatial information of the path between the firearm and the objects, and location information of the firearm. The end point of the bullet can be determined. Additionally, the first computing device may determine the path connecting the starting and ending points of the bullet with a line as the expected path of the bullet. The bullet's expected arrival path may be variably determined based on information (eg, terrain information) assigned to objects in the virtual reality space and climate or weather information in the virtual reality space.

In the technique according to an embodiment of the present disclosure, the accuracy of the bullet's expected path can be improved by reflecting the material information and spatial information of the object in the virtual reality space created through VPS.

According to one embodiment, at least one of the first computing device, the second computing device, and/or the third computing device may be included in the computing device 100. Accordingly, the description of at least one of the first computing device, the second computing device, and/or the third computing device may be replaced with the description of the computing device 100 described above. In addition, the first computing device, the second computing device, and the third computing device are included in one computing device 100 and share configuration with each other within one computing device 100, and provide information about objects in the virtual reality space. A method to reflect can be performed.

According to another embodiment, the first computing device, the second computing device, and the third computing device may each exist as separate entities.

A component, module, or unit in the present disclosure includes routines, procedures, programs, components, data structures, etc. that perform a specific task or implement a specific abstract data type. Additionally, one of ordinary skill in the art will understand that the methods presented in this disclosure can be used in uni-processor or multiprocessor computing devices, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. ( It will be fully appreciated that each of these may be implemented with other computer system configurations, including those capable of operating in conjunction with one or more associated devices.

Embodiments described in this disclosure can also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computing devices typically include a variety of computer-readable media. Computer-readable media can be any medium that can be accessed by a computer, and such computer-readable media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media.

Computer-readable storage media refers to volatile and non-volatile media, transient and non-transitory media, removable and non-removable, implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Includes media. Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage. This includes, but is not limited to, a device, or any other medium that can be accessed by a computer and used to store desired information.

A computer-readable transmission medium typically implements computer-readable instructions, data structures, program modules, or other data on a modulated data signal, such as a carrier wave or other transport mechanism. Includes all information delivery media. The term modulated data signal refers to a signal in which one or more of the characteristics of the signal have been set or changed to encode information within the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An example environment 2000 is shown that implements various aspects of the invention, including a computer 2002, which includes a processing unit 2004, a system memory 2006, and a system bus 2008. do. Computer 200 herein may be used interchangeably with computing device. System bus 2008 couples system components, including but not limited to system memory 2006, to processing unit 2004. Processing unit 2004 may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be used as processing units 2004.

System bus 2008 may be any of several types of bus structures that may further be interconnected to a memory bus, peripheral bus, and local bus using any of a variety of commercial bus architectures. System memory 2006 includes read only memory (ROM) 2010 and random access memory (RAM) 2012. The basic input/output system (BIOS) is stored in non-volatile memory (2010), such as ROM, EPROM, and EEPROM, and is a basic input/output system (BIOS) that helps transfer information between components within the computer (2002), such as during startup. Contains routines. RAM 2012 may also include high-speed RAM, such as static RAM for caching data.

Computer 2002 may also read from or use an internal hard disk drive (HDD) 2014 (e.g., EIDE, SATA), magnetic floppy disk drive (FDD) 2016 (e.g., removable diskette 2018). (for writing to), SSDs, and optical disk drives (2020) (e.g., for reading CD-ROM disks (2022) or for reading from or writing to other high-capacity optical media, such as DVDs). Includes. The hard disk drive 2014, magnetic disk drive 2016, and optical disk drive 2020 are connected to a system bus 2008 by a hard disk drive interface 2024, magnetic disk drive interface 2026, and optical drive interface 2028, respectively. ) can be connected to. The interface 2024 for implementing an external drive includes, for example, at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. For the computer 2002, drive and media correspond to storing any data in a suitable digital format. Although the description of computer-readable storage media above refers to removable optical media such as HDDs, removable magnetic disks, and CDs or DVDs, those skilled in the art will also understand removable optical media such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other types of computer-readable storage media may also be used in the exemplary operating environment and that any such media may contain computer-executable instructions for performing the methods of the invention. .

A number of program modules may be stored in the drive and RAM 2012, including an operating system 2030, one or more application programs 2032, other program modules 2034, and program data 2036. All or portions of the operating system, applications, modules and/or data may also be cached in RAM 2012. It will be appreciated that the invention may be implemented on various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 2002 through one or more wired/wireless input devices, such as a pointing device such as a keyboard 2038 and a mouse 2040. Other input devices (not shown) may include microphones, IR remote controls, joysticks, game pads, stylus pens, touch screens, etc. These and other input devices are connected to the processing unit 2004 through an input device interface 2042, which is often connected to the system bus 2008, but may also include a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, It can be connected by other interfaces, etc.

A monitor 2044 or other type of display device is also connected to system bus 2008 through an interface, such as a video adapter 2046. In addition to the monitor 2044, computers typically include other peripheral output devices (not shown) such as speakers, printers, etc.

Computer 2002 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 2048, via wired and/or wireless communications. Remote computer(s) 2048 may be a workstation, server computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and generally refers to computer 2002. For simplicity, only memory storage device 2050 is shown, although it includes many or all of the components described. The logical connections depicted include wired/wireless connections to a local area network (LAN) 2052 and/or a larger network, such as a wide area network (WAN) 2054. These LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, such as the Internet.

When used in a LAN networking environment, computer 2002 is connected to local network 2052 through wired and/or wireless communications network interfaces or adapters 2056. Adapter 2056 may facilitate wired or wireless communication to LAN 2052, which also includes a wireless access point installed thereon for communicating with wireless adapter 2056. When used in a WAN networking environment, the computer 2002 may include a modem 2058, connected to a communication server on the WAN 2054, or other means of establishing communication over the WAN 2054, such as via the Internet. has Modem 2058, which may be internal or external and a wired or wireless device, is coupled to system bus 2008 via serial port interface 2042. In a networked environment, program modules described for computer 2002, or portions thereof, may be stored in remote memory/storage device 2050. It will be appreciated that the network connections shown are exemplary and that other means of establishing a communications link between computers may be used.

Computer 2002 may be associated with any wireless device or object deployed and operating in wireless communications, such as a printer, scanner, desktop and/or portable computer, portable data assistant (PDA), communications satellite, wirelessly detectable tag. Performs actions to communicate with any device or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, communication may be a predefined structure as in a conventional network or may simply be ad hoc communication between at least two devices.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of illustrative approaches. It is to be understood that the specific order or hierarchy of steps in processes may be rearranged within the scope of the present disclosure, based on design priorities. The method claims of this disclosure provide elements of the various steps in a sample order but are not meant to be limited to the specific order or hierarchy presented.

This disclosure was made as part of a government-supported project described below.

Assignment identification number: 1711160547

Task number: 2022-0-00137-001

Ministry name: Ministry of Science and ICT

Name of project management (professional) organization: Information and Communications Planning and Evaluation Institute

Research project name: Realistic content core technology development

Research project name: XR user interaction evaluation and application technology development

Contribution rate: 1/1

Name of project carrying out organization: Electronics and Telecommunications Research Institute

Research period: 2022.04.01 ~ 2025.12.31

As described above, the relevant content has been described in the best form for carrying out the invention.

It can be used in computing devices, systems, etc. to support tactical training using visual localization.

Claims

1. A method for reflecting information about an object in a virtual reality space, performed by a first computing device, comprising:

Obtaining first query data related to a space containing an object scanned or photographed by an imaging device;

Receiving information about an object including pre-stored object material information and object recognition information from a second computing device that receives the first query data and performs classification on the first query data; and

When creating a virtual reality space based on the first query data, reflecting material information of the object in the virtual reality space;

Including,

method.
According to claim 1,

The material information of the object is,

Containing at least one of temperature, viscosity, absorption rate, reflectance, transmittance, scattering rate, attenuation rate, elastic coefficient, or friction coefficient at the volume or surface of the object,

method.
According to claim 1,

The material information of the object is,

Containing at least one of information about whether the object is blocking, blocking channel information, information about whether a trigger is present, information about a trigger channel, or tag information for programming,

method.
According to claim 1,

The step of reflecting the material information of the object is,

mapping information about the object to an area corresponding to recognition information of the object in the virtual reality space;

Including,

method.
According to claim 1,

Obtaining first real location information corresponding to the first query data based on the first query data;

Receiving first spatial information corresponding to the first real location information from a third computing device storing spatial information corresponding to the real location; and

Based on the first spatial information, reflecting the first spatial information on the virtual reality space;

Containing more,

method.
According to claim 5,

The first spatial information is,

Containing first weather information corresponding to the first real location information,

method.
According to claim 5,

The first spatial information is,

Gravity field, magnetic field, electric field, Coriolis force, wind direction, wind speed, temperature, humidity, air resistance, altitude above sea level, air density, viscosity, scattering rate, atmospheric pressure, elastic coefficient, friction coefficient, vector field or tensor field in space. Containing at least one of (tensor fields),

method.
According to claim 5,

The first spatial information is,

Containing at least one of information about whether there is blocking in the first space, blocking channel information, information about whether there is a trigger, information about the trigger channel, or tag information for programming,

method.
According to claim 5,

The step of reflecting the first spatial information on the virtual reality space includes:

changing material information of the object reflected on the virtual reality space based on the first space information;

Including,

method.
According to claim 1,

The material information and spatial information of the object reflected on the virtual reality space change with time based on rules preset in the virtual reality space,

method.
According to claim 1,

The second computing device,

Classify the object included in the first query data using a pre-trained classification model, and

Obtaining information about the object, including material information of the pre-stored object corresponding to the classified object and recognition information of the object,

method.
According to claim 1,

When placing a virtual object in the virtual reality space, determining material information of the virtual object in a preset manner;

Containing more,

method.
According to claim 1,

Receiving second query data from a user device worn by the user;

Based on the second query data, determining a pose including a location and orientation related to the user;

determining a relative pose of a firearm linked to the user device based on the pose; and

calculating an expected path of a bullet fired through the muzzle of the firearm in the virtual reality space based on the pose and the relative pose;

Including,

method.
A computer program stored in a computer-readable storage medium, the computer program comprising instructions for causing a processor of a first computing device to perform the following steps for reflecting information about an object in a virtual reality space, the steps comprising: :

Obtaining first query data related to a space containing an object scanned or photographed by an imaging device;

Receiving information about an object including pre-stored object material information and object recognition information from a second computing device that receives the first query data and performs classification on the first query data; and

When creating a virtual reality space based on the first query data, reflecting material information of the object in the virtual reality space;

Including,

A computer program stored on a computer-readable storage medium.
In a first computing device for reflecting information about an object in a virtual reality space,

processor;

Memory; and

network department;

Including,

The processor,

Obtaining first query data related to a space containing an object scanned or photographed by the imaging device,

Receiving information about the object, including pre-stored object material information and object recognition information, from a second computing device that receives the first query data and performs classification on the first query data, and

When creating a virtual reality space based on the first query data, reflecting material information of the object in the virtual reality space,

First computing device.