KR102635768B1 - Method for generating data set - Google Patents

Abstract

A method for generating a dataset performed by a computing device according to some embodiments of the present disclosure, comprising: generating a 3D model; Obtaining first viewpoint information including a first image, first camera information, and first point cloud information at a first viewpoint for the first area of the 3D model; Obtaining second viewpoint information including a second image from a second viewpoint for the first area, information on a second camera, and second point cloud information; And generating a dataset of a model for visual localization based on the first viewpoint information and the second viewpoint information, where the first viewpoint and the second viewpoint are different viewpoints. You can have

Description

Method for generating a dataset {METHOD FOR GENERATING DATA SET}

This disclosure relates to artificial intelligence technology, and more specifically, to a method for generating a dataset for an artificial intelligence-based model.

In recent years, machine-learning technology, including deep-learning, has received attention by showing results that exceed the performance of existing methods in analyzing various types of data such as video, voice, and text. In addition, machine learning technology is being introduced and utilized in various fields due to the scalability and flexibility inherent in the technology itself.

Among the various fields where machine learning technology can be applied, the image-related field is one of the fields that is most actively introducing machine learning technology in various detailed fields such as object recognition and object classification.

Visual localization refers to a technology that identifies the surrounding environment through a camera and determines where the camera user is currently located based on this. This visual positioning can estimate in real time the location of the user who took the image and the direction the camera is looking (camera pose) from the image. Such visual localization can, for example, analyze an image captured by a camera by obtaining feature points from the image using a model for visual localization.

As described above, in order to obtain accurate feature points from an image using a model for visual localization, it is necessary to preemptively secure a dataset for learning and verifying the model for visual localization.

Republic of Korea Patent Publication No. 10-2008-0128066 (published on June 24, 2010)

This disclosure was created in response to the above-described background technology, and seeks to provide a method for generating a dataset for a model for artificial intelligence-based visual localization.

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, there is provided a method for generating a dataset performed by a computing device including a processor, comprising: generating a 3D model; Obtaining first viewpoint information including a first image, first camera information, and first point cloud information at a first viewpoint for the first area of the 3D model; Obtaining second viewpoint information including a second image from a second viewpoint for the first area, information on a second camera, and second point cloud information; And generating a dataset of a model for visual localization based on the first viewpoint information and the second viewpoint information, where the first viewpoint and the second viewpoint are different viewpoints. You can have

Alternatively, generating the 3D model may include obtaining spatial information about an arbitrary space scanned or photographed using an imaging device; generating point cloud information for the arbitrary space, including color data based on the spatial information; and generating the 3D model based on point cloud information for the arbitrary space.

Alternatively, the spatial information may include information about objects existing in the arbitrary space.

Alternatively, the color data may include data related to the color of an object existing in the arbitrary space.

Alternatively, the point cloud information for the arbitrary space may further include location data related to the location of an object existing in the arbitrary space.

Alternatively, the information about the first camera may include location information and direction information of the first camera determined based on a predetermined reference point.

Alternatively, the method may further include training a model for visual localization using the dataset to output feature points corresponding to the first viewpoint information and the second viewpoint information.

Alternatively, using the dataset, feature points corresponding to the first viewpoint information and the second viewpoint information are output and descriptors of the corresponding feature points are the same for the visual positioning. A step of training the model may be further included.

Alternatively, a computer program stored on a computer-readable storage medium, the computer program comprising instructions for causing a processor of a computing device to generate a dataset to perform the following steps, said steps comprising: creating a 3D model; generating step; Obtaining first viewpoint information including a first image, first camera information, and first point cloud information at a first viewpoint for the first area of the 3D model; Obtaining second viewpoint information including a second image from a second viewpoint for the first area, information on a second camera, and second point cloud information; And generating a dataset of a model for visual localization based on the first viewpoint information and the second viewpoint information, where the first viewpoint and the second viewpoint are different viewpoints. You can have

Alternatively, a computing device for generating a dataset comprising: a processor comprising at least one core; a memory storing a computer program executable by the processor; and a network unit, wherein the processor generates a 3D model, and includes a first image at a first viewpoint for a first area of the 3D model, information on a first camera, and a first point group. acquire first viewpoint information including cloud) information, obtain second viewpoint information including a second image at a second viewpoint for the first area, information of a second camera, and second point cloud information, and A dataset of a model for visual localization is created based on the first viewpoint information and the second viewpoint information, where the first viewpoint and the second viewpoint may have different viewpoints.

The present disclosure can generate a dataset for a model for artificial intelligence-based visual localization.

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 examples below, 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 is a block diagram of a computing device for generating a dataset for a model for artificial intelligence-based visual localization according to some embodiments of the present disclosure.
Figure 2 is a schematic diagram showing network functions according to some embodiments of the present disclosure.
3 to 5 are diagrams for explaining a model for visual localization of a computing device according to some embodiments of the present disclosure.
FIG. 6 is a diagram illustrating a method for generating a dataset performed on a computing device according to some embodiments of the present disclosure.
7 depicts 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 “a case containing only A,” “a case containing only B,” and “a case of combining 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 this disclosure, network function, artificial neural network, and neural network may be used interchangeably.

1 is a block diagram of a computing device for generating a dataset for a model for artificial intelligence-based visual localization according to some embodiments of the present disclosure.

The image plane in the present disclosure may correspond to the screen of a photographing device (eg, camera, etc.) disposed to capture an image.

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 may include a processor 110, a memory 130, and a network unit 150.

The processor 110 may be composed of one or more cores, and may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit) may include a processor for data analysis and deep learning. The processor 110 may read a computer program stored in the memory 130 and perform data processing for machine learning 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, the processors of a plurality of computing devices can be used together to process learning of network functions and data classification using network functions. 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.

According to an 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 network unit 150.

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, hard disk type, multimedia card micro type, or card type memory (e.g. (e.g. SD or -Only Memory), and may include at least one type of storage medium among 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 merely an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure may include any wired or wireless communication network capable of transmitting and receiving arbitrary types of data and signals, etc., as expressed in the present disclosure.

The techniques described herein can be used in the networks mentioned above, as well as other networks.

The computing device 100 according to some embodiments of the present disclosure may generate a dataset for learning a neural network. For example, the computing device 100 may generate a dataset for learning or verifying a model for visual localization (eg, feature point acquisition model, etc.).

Visual positioning may refer to a technology that estimates the current location using images and depth maps (or point cloud information) indoors or outdoors.

Images in the present disclosure may include various images (eg, 2D images, black-and-white images, color images, etc.) excluding depth maps.

In the present disclosure, the depth map may be an image or information that shows the three-dimensional value corresponding to each pixel existing in the image and the relative distance from the image plane corresponding to the image.

The model for visual localization may be a neural network built through deep learning or machine learning. A model for visual localization can obtain feature point information from images included in input data. Feature point information may be information related to features obtained from the input image and depth map (or point cloud information). For example, feature point information may include at least one feature point and/or descriptor. At least one feature point may be a coordinate for each feature part of the image and depth map (or point cloud information). At least one descriptor may include information for describing each of at least one feature point. For example, at least one descriptor may include information about the directionality and size of each of the at least one feature point and/or the relationship between pixels surrounding each of the at least one feature point.

Additionally, a model for visual localization can be learned using a dataset. For example, when images of corresponding areas from different viewpoints are input to a model for visual localization, feature points obtained from each of the images may be learned to correspond to each other. A detailed description of the neural network will be described later with reference to FIG. 2.

A dataset may refer to a set of data for performing learning and verification of a neural network. The dataset may include a training dataset and/or a validation dataset. A learning dataset may be a set of data used in the learning process of a neural network. For example, a learning dataset may be a set of data used for learning in the learning process of a model for visual localization. A validation dataset may be a set of data used to evaluate a neural network. For example, a validation dataset may be a set of data used to evaluate a model for visual localization.

The processor 110 of the computing device 100 may generate a 3D model. Specifically, the processor 110 may acquire spatial information about any space scanned or photographed using an imaging device.

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

Spatial information may refer to information about the interior of a specific space. For example, spatial information may mean information about any type of object existing in any space. For example, spatial information may include at least one of distance, direction, and/or speed from an imaging device to an object existing in a certain space. Additionally, the spatial information may include at least one of the characteristics of the object's color, temperature, material distribution, and/or concentration. An object may refer to a software module that includes state data representing a state and operation (eg, procedure, method, function, etc.) data related to the state data. For example, the object may include at least one of a basic object, a moving object, and/or a specific predetermined object.

The processor 110 may generate point cloud information for an arbitrary space, including color data and/or location data, based on spatial information.

Point cloud information (e.g., first point cloud information, second point cloud information, point cloud information for an arbitrary space, etc.) is a three-dimensional space (e.g., an arbitrary space scanned or photographed using an imaging device, a 3D model) It may refer to information representing a set of points on the image (such as a specific area on the image). Point cloud information may refer to location information of measurement points related to the color and/or location of a basic object existing in an arbitrary space. The basic object may be an object related to a feature point obtained from a model for visual localization. The basic object may be an object excluding a moving object and a predetermined specific object. Accordingly, the point cloud information may be information from which information related to at least one of lighting, a moving object, and/or a predetermined specific object has been removed. Lighting information may be information related to light. A mobile object may be an object that is not permanently fixed but can move at a specific point in time or in a specific situation. For example, a moving object is an object that can move (eg, a car, a bicycle, etc.), and may not be obtained as a feature point in a model for visual localization. In other words, the moving object may not be related to the feature points obtained from the model for visual localization. The predetermined specific object is a floating object (for example, a plant) rather than a moving object, and may not be obtained as a feature point in a model for visual localization. That is, a specific predetermined object may not be related to a feature point obtained from a model for visual localization. According to one embodiment, the predetermined specific object may be an object set by the user. For example, a specific predetermined object may be an object that the user has set to not be included in the default object.

Additionally, point cloud information may include color data and/or location data. Color data may include data related to the color of an object existing in an arbitrary space. For example, color data may include vertex color values that include RGB color values of objects existing in arbitrary space. However, color data is not limited to this and may include various values representing colors.

Location data may include data related to the location of an object existing in arbitrary space. For example, location data may include the x, y, and z location coordinates of an object existing in arbitrary space. However, the meaning of location data is not limited to the above-described example, and may include various values indicating the location or depth of an object.

The processor 110 may generate a 3D model based on point cloud information.

A 3D model is a model created in three dimensions to correspond to an arbitrary space based on point cloud information, and may include point cloud information. For example, the processor 110 may change the point cloud included in the point cloud information in mesh units to generate a 3D model formed in three dimensions corresponding to an arbitrary space. Accordingly, the processor 110 may generate a 3D model by changing the point cloud included in the point cloud information into various other units. For another example, the processor 110 may generate a 3D model formed from a point cloud included in point cloud information. Accordingly, the processor 110 can generate a 3D model by using the point cloud included in the point cloud information without changing it. Here, any space may be a space scanned or photographed using an imaging device.

The processor 110 includes a first image at a first viewpoint for a first area of the 3D model, information of a first camera, and a first depth map (or first point cloud information). First viewpoint information can be obtained.

The first area may be a predetermined area within the 3D model. For example, the processor 110 may receive input from the user regarding a first area among a plurality of areas in the 3D model. Additionally, the processor 110 may receive the first area among a plurality of areas in the 3D model through a device (eg, a user's device, an administrator's device, etc.). For another example, the processor 110 may determine a first region among a plurality of regions in the 3D model in a random or predetermined order.

The first image may be an image taken of the first area by a first camera corresponding to a first viewpoint of the first area. For example, the first image may be any one of various images (eg, 2D image, black and white image, color image, etc.) excluding the depth map.

The information about the first camera may include location information and direction information of the first camera determined based on a predetermined reference point. The predetermined reference point may be the origin or a point corresponding to the location of the reference object. For example, the predetermined reference point may be a point corresponding to the position of the first camera. If the predetermined reference point is a point corresponding to the location of the first camera, the location information of the first camera may be (0, 0, 0). The location information of the first camera may include coordinates where the first camera exists. The direction information of the first camera may include at least one of the direction and/or angle from which the first camera is looking.

The first depth map may be an image or information representing the relative distance from the first image plane corresponding to the first image to the three-dimensional value corresponding to each pixel included in the first image.

For example, the processor 110 may draw a straight line (e.g., a 3D model) from each pixel of a first image plane corresponding to the screen of a first camera placed in virtual space (e.g., a 3D model) toward an object in virtual space. For example, light rays, etc.) can be generated. When each straight line collides with an object in virtual space, the processor 110 may determine the relative distance (e.g., depth value, etc.) by calculating the vertical distance between the collision point and the first image plane. . The processor 110 may determine the relative distance of the first pixel to be 0 when a straight line generated from the first pixel of each pixel of the first image plane toward the object in the virtual space does not collide with the object in the virtual space. there is.

The three-dimensional value may be a three-dimensional value corresponding to each pixel in an image (eg, a first image, a second image, etc.). For example, the three-dimensional value may include coordinate values (e.g., (1, 1, 1), (1, 2, 1), etc.) corresponding to each pixel present in the first image on the 3D model. there is.

The first image plane may correspond to the screen of the first camera positioned to capture the first image. For example, the first image plane may be a plane image displayed on the screen of the first camera.

The first point cloud information may be point cloud information from a first viewpoint for the first area. For example, first point cloud information may mean information representing a set of points for a first area at a first viewpoint. The first point cloud information may mean location information of measurement points related to the color and/or location of the basic object existing in the first area at the first viewpoint.

Meanwhile, the first depth map according to some embodiments of the present disclosure is the relative distance from the first camera (e.g., from the center of the first camera) to the three-dimensional value corresponding to each of the pixels included in the first image. It may be an image or information displayed separately.

For example, the processor 110 may generate a straight line (eg, a ray, etc.) from a first camera disposed in a virtual space (eg, a 3D model) toward an object in the virtual space. When each straight line collides with an object in virtual space, the processor 110 may determine a relative distance (for example, a depth value, etc.) by calculating the distance between the collision point and the first camera.

The processor 110 may obtain second view information including a second image from a second view of the first area, information about a second camera, and a second depth map (or second point cloud information).

The first viewpoint and the second viewpoint may have different viewpoints. For example, the first viewpoint and the second viewpoint may differ from each other in the location and/or viewing direction of the photographing device (eg, camera, etc.) that photographs the first area.

The second image may be an image taken of the first area by a second camera corresponding to a second viewpoint of the first area. For example, the second image may be any one of various images (eg, 2D image, black and white image, color image, etc.) excluding the depth map.

The information about the second camera may include location information and direction information of the second camera determined based on a predetermined reference point. The predetermined reference point may be the origin or a point corresponding to the location of the reference object. For example, the predetermined reference point may be a point corresponding to the position of the second camera. If the predetermined reference point is a point corresponding to the location of the second camera, the location information of the second camera may be (0, 0, 0). The location information of the second camera may include coordinates where the second camera exists. The direction information of the second camera may include at least one of the direction and/or angle from which the second camera is looking.

The second depth map may be an image or information representing a three-dimensional value corresponding to each pixel in the second image and a relative distance from the second image plane corresponding to the second image.

For example, the processor 110 may create a straight line (e.g., a 3D model) from each pixel of a second image plane corresponding to the screen of a second camera positioned in virtual space (e.g., a 3D model) toward an object in virtual space. For example, light rays, etc.) can be generated. When each straight line collides with an object in virtual space, the processor 110 may determine the relative distance (e.g., depth value, etc.) by calculating the vertical distance between the collision point and the second image plane. . The processor 110 may determine the relative distance of the first pixel to be 0 when a straight line generated from the first pixel of each pixel of the second image plane toward the object in virtual space does not collide with the object in virtual space. there is.

The second point cloud information may be point cloud information from a second viewpoint for the first area. For example, second point group information may mean information representing a set of points for the first area from a second viewpoint. The second point cloud information may mean location information of measurement points related to the color and/or location of the basic object existing in the first area from the second viewpoint.

Meanwhile, the second depth map according to some embodiments of the present disclosure is the relative distance from the second camera (for example, from the center of the second camera) to the three-dimensional value corresponding to each of the pixels included in the second image. It may be an image or information displayed separately.

For example, the processor 110 may generate a straight line (eg, a ray, etc.) from a second camera disposed in a virtual space (eg, a 3D model) toward an object in the virtual space. When each straight line collides with an object in virtual space, the processor 110 may determine a relative distance (eg, depth value, etc.) by calculating the distance between the collision point and the second camera.

The processor 110 may generate a model dataset for visual localization based on the first viewpoint information and the second viewpoint information.

The processor 110 may configure the first image, first camera information, and first depth map (or first point cloud information) included in the first viewpoint information into one set. Additionally, the processor 110 may configure the second image, second camera information, and second depth map (or second point cloud information) included in the second viewpoint information into one set.

The dataset of the model for visual localization may refer to a set of data for performing learning and verification of the model for visual localization. The dataset of the model for visual localization may include a training dataset and/or a validation dataset. A learning dataset may be a set of data used for learning in the learning process of a model for visual localization. A validation dataset may be a set of data used to evaluate a model for visual localization.

The processor 110 may use the dataset to learn a model for visual localization so that feature points corresponding to the first viewpoint information and the second viewpoint information are output. In addition, the processor 110 uses the dataset to output feature points corresponding to the first viewpoint information and the second viewpoint information, and to create a model for visual positioning in a direction in which the descriptors of the corresponding feature points are the same. It can be learned. A detailed description of this will be provided later with reference to FIGS. 3 to 5.

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

Throughout this specification, model for visual localization, computational model, neural network, network function, and neural network may be used with the same meaning. 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 for each learning data is used (i.e., labeled learning data), while 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 supervised learning on data classification, the training data may be data in which each training 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 that disables some of the network nodes during the learning process, and use of a batch normalization layer can be applied. there is.

According to an embodiment of the present disclosure, a computer-readable medium storing a data structure 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.

3 to 5 are diagrams for explaining a model for visual location of a computing device according to some embodiments of the present disclosure.

The processor 110 may obtain feature information including feature point information by inputting the image, depth map (or point cloud information), and camera information included in the input data into a model for visual localization. For example, the processor 110 uses a dataset to generate a first feature point and a first descriptor obtained from the first image and the first depth map (or first point cloud information) included in the first viewpoint information, and the second A model for visual localization may be trained so that the second feature point and the second descriptor obtained from the second image and the second depth map (or second point cloud information) included in the viewpoint information correspond to each other. Here, the first image and the second image may be images of the first area acquired at different viewpoints. Accordingly, when information about corresponding areas (e.g., images, depth maps, point cloud information, etc.) is input to the model for visual positioning, the processor 110 provides visual positioning so that feature point information obtained from the information corresponds to each other. A model for positioning can be trained.

Referring to FIG. 3 , the processor 110 may obtain first feature point information 30 by inputting the first viewpoint information 10 into the model 20 for visual localization. The first viewpoint information 10 may include the first depth map (or first point cloud information) 11, the first image 12, and information about the first camera. The first feature point information 30 may include a first feature point 31 and a first descriptor 32. The first feature point 31 may be the coordinates of the first part that is a feature in the first image. The first descriptor 32 may include information for describing the first feature point.

Referring to FIG. 4 , the processor 110 may obtain second feature point information 50 by inputting the second viewpoint information 40 into the model 20 for visual localization. The second viewpoint information 20 may include a second depth map (or second point cloud information) 41, a second image 42, and information about a second camera. The second feature point information 50 may include a second feature point 51 and a second descriptor 52. The second feature point 51 may be the coordinates of the first part that is a feature in the second image. The second descriptor 52 may include information for describing the second feature point.

Referring to FIG. 5, the processor 110 and/or the model 20 for visual positioning generates a first feature point 31 and a second feature point 51 based on the information of the first camera and the information of the second camera. You can compare whether these correspond to each other.

For example, the processor 110 and/or the model 20 for visual positioning may calculate a relative camera pose using information about the first camera and information about the second camera. The processor 110 and/or the model 20 for visual localization may compare whether the first feature point 31 and the second feature point 51 correspond to each other based on the relative camera pose.

In addition, the processor 110 and/or the model 20 for visual positioning determines whether the first descriptor 32 and the second descriptor 52 correspond to each other based on the information of the first camera and the information of the second camera. You can compare.

For example, the processor 110 and/or the model 20 for visual positioning may calculate a relative camera pose using information about the first camera and information about the second camera. The processor 110 and/or the model 20 for visual localization may compare whether the first descriptor 32 and the second descriptor 52 correspond to each other based on the relative camera pose.

3 to 5, the first depth map (or first point cloud information) 11 and the second depth map (or second point cloud information) 41 represent areas corresponding to each other at different viewpoints. It may be a captured depth map (or point cloud information obtained by photographing corresponding areas from different viewpoints). Additionally, the first image 12 and the second image 42 may be images taken of corresponding areas from different viewpoints.

The processor 110 and/or the model 20 for visual positioning may align the depth map (or point cloud information) and/or the image based on information from the camera and compare whether the feature points correspond to each other.

For example, the processor 110 and/or the model for visual localization 20 creates a first depth map (or first point cloud information) 11 based on the information of the first camera and the information of the second camera. And the second depth map (or second point cloud information) 41 may be aligned to compare whether the first feature point 31 and the second feature point 51 correspond to each other. Specifically, the processor 110 and/or the model 20 for visual localization uses the relative camera pose between the first camera and the second camera obtained through information of the first camera and information of the second camera to determine the first The depth map (or first point group information) 11 and the second depth map (or second point group information) 41 may be aligned. And, the first feature point 31 and the second feature point 51 are formed using the aligned first depth map (or first point group information) 11 and the second depth map (or second point group information) 41. ) can be compared to see if they correspond to each other.

For another example, the processor 110 and/or the model 20 for visual localization may display the first image 12 and the second image 42 based on the information of the first camera and the information of the second camera. By aligning, it is possible to compare whether the first feature point 31 and the second feature point 51 correspond to each other. Specifically, the processor 110 and/or the model 20 for visual localization uses the relative camera pose between the first camera and the second camera obtained through information of the first camera and information of the second camera to determine the first The image 12 and the second image 42 may be aligned. Also, it is possible to compare whether the first feature point 31 and the second feature point 51 correspond to each other using the aligned first image 12 and the second image 42.

As another example, the processor 110 and/or the model 20 for visual localization may generate a first depth map (or first point cloud information) based on the information of the first camera and the information of the second camera. 11) and the second depth map (or second point cloud information) 41 can be aligned to compare whether the first descriptor 32 and the second descriptor 52 correspond to each other. Specifically, the processor 110 and/or the model 20 for visual localization uses the relative camera pose between the first camera and the second camera obtained through information of the first camera and information of the second camera to determine the first The depth map (or first point group information) 11 and the second depth map (or second point group information) 41 may be aligned. And, the first descriptor 32 and the second descriptor 52 are generated using the aligned first depth map (or first point cloud information) 11 and the second depth map (or second point cloud information) 41. ) can be compared to see if they correspond to each other.

As another example, the processor 110 and/or the model 20 for visual localization may generate a first image 12 and a second image 42 based on information from the first camera and information from the second camera. It is possible to align and compare whether the first descriptor 32 and the second descriptor 52 correspond to each other. Specifically, the processor 110 and/or the model 20 for visual localization uses the relative camera pose between the first camera and the second camera obtained through information of the first camera and information of the second camera to determine the first The image 12 and the second image 42 may be aligned. Also, it is possible to compare whether the first descriptor 32 and the second descriptor 52 correspond to each other using the aligned first image 12 and the second image 42.

Accordingly, the processor 110 can use the dataset to learn a model for visual positioning so that feature points corresponding to the first viewpoint information 10 and the second viewpoint information 40 are output.

FIG. 6 is a diagram illustrating a method for generating a dataset performed on a computing device according to some embodiments of the present disclosure.

Referring to FIG. 6, the processor 110 of the computing device 100 may generate a 3D model (S110).

The processor 110 may acquire spatial information about any space scanned or photographed using an imaging device. Spatial information may include information about objects existing in arbitrary space.

The processor 110 may generate point cloud information including color data based on spatial information. Color data may include data related to the color of an object existing in an arbitrary space.

The processor 110 may generate a 3D model based on point cloud information. Point cloud information may further include location data related to the location of an object existing in arbitrary space.

The processor 110 acquires first viewpoint information including a first image from a first viewpoint for a first area of the 3D model, information of a first camera, and a first depth map (or first point cloud information). (S120).

The first depth map may be an image or information representing the relative distance from the first image plane corresponding to the first image to the three-dimensional value corresponding to each pixel included in the first image.

The first depth map may be an image or information indicating the relative distance from the first camera to the three-dimensional value corresponding to each pixel included in the first image.

The first image plane may correspond to the screen of the first camera positioned to capture the first image.

The information about the first camera may include location information and direction information of the first camera determined based on a predetermined reference point.

The processor 110 may acquire second viewpoint information including a second image from a second viewpoint for the first area, information on the second camera, and a second depth map (or second point cloud information) ( S130).

The processor 110 may generate a dataset of a model for visual positioning based on the first viewpoint information and the second viewpoint information (S140).

The processor 110 may use the dataset to learn a model for visual localization so that feature points corresponding to the first viewpoint information and the second viewpoint information are output.

The processor 110 uses the dataset to output feature points corresponding to the first viewpoint information and the second viewpoint information, and to learn a model for visual positioning in a direction in which the descriptors of the corresponding feature points are the same. You can.

As described above with reference to FIG. 6, the processor 110 creates a model for visual positioning using a dataset generated based on first viewpoint information and second viewpoint information obtained by photographing corresponding areas from different viewpoints. can be learned. When the viewpoint information at which the corresponding area was photographed at different viewpoints is input to the model for visual positioning, the processor 110 learns the model for visual positioning so that the feature points and descriptors obtained from each viewpoint information correspond to each other. You can do it. The processor 110 can train a model for visual localization using a dataset created using images acquired at different viewpoints. Accordingly, the processor 110 can consistently obtain feature points even when the viewpoint changes by using a model for visual localization. In addition, the processor 110 according to some embodiments of the present disclosure can not only consistently acquire feature points even when the viewpoint changes by using a visual positioning model, but also the values of the descriptors may not change significantly depending on the viewpoint change. . Accordingly, the processor 110 can more accurately perform matching between feature points in the visual localization process using the visual localization model.

The steps shown in FIG. 6 are exemplary steps. Accordingly, it will also be apparent to those skilled in the art that some of the steps in FIG. 6 may be omitted or additional steps may be present without departing from the scope of the present disclosure. Additionally, detailed information regarding the configurations depicted in FIG. 6 (eg, configuration of the computing device 100, etc.) may be replaced with the content previously described with reference to FIGS. 1 to 5.

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

Although the present disclosure has generally been described above as being capable of being implemented by a computing device, those skilled in the art will understand that the present disclosure can be implemented in combination with computer-executable instructions and/or other program modules that can be executed on one or more computers and/or in hardware and software. It will be well known that it can be implemented as a combination.

Typically, program modules include routines, programs, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Additionally, those skilled in the art will understand that the methods of the present disclosure are applicable to single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. It will be appreciated that each of these may be implemented in other computer system configurations, including those capable of operating in conjunction with one or more associated devices.

The described embodiments of the 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.

Computers 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 1100 is shown that implements various aspects of the present disclosure, including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to system memory 1106, to processing unit 1104. Processing unit 1104 may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be used as processing unit 1104.

System bus 1108 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 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112. The basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, and EEPROM, and is a basic input/output system that helps transfer information between components within the computer 1102, such as during startup. Contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

Computer 1102 may also include an internal hard disk drive (HDD) 1114 (e.g., EIDE, SATA)—the internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes - a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from or writing to a removable diskette 1118), and an optical disk drive 1120 (e.g., a CD-ROM for reading the disk 1122 or reading from or writing to other high-capacity optical media such as DVDs). Hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to system bus 1108 by hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to. The interface 1124 for implementing an external drive includes 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 computer 1102, drive and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to removable optical media such as HDDs, removable magnetic disks, and CDs or DVDs, those skilled in the art will also recognize removable optical media such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other types of computer-readable media may also be used in the example operating environment, and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in drives and RAM 1112, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or portions of the operating system, applications, modules and/or data may also be cached in RAM 1112. It will be appreciated that the present disclosure may be implemented on various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into computer 1102 through one or more wired/wireless input devices, such as a keyboard 1138 and a pointing device such as mouse 1140. 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 1104 through an input device interface 1142, which is often connected to the system bus 1108, 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 1144 or other type of display device is also connected to system bus 1108 through an interface, such as a video adapter 1146. In addition to monitor 1144, computers typically include other peripheral output devices (not shown) such as speakers, printers, etc.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148, via wired and/or wireless communications. Remote computer(s) 1148 may be a workstation, computing device computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and is generally connected to computer 1102. For simplicity, only memory storage device 1150 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) 1152 and/or a larger network, such as a wide area network (WAN) 1154. 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 1102 is connected to local network 1152 through wired and/or wireless communication network interfaces or adapters 1156. Adapter 1156 may facilitate wired or wireless communication to LAN 1152, which also includes a wireless access point installed thereon for communicating with wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158 or be connected to a communicating computing device on the WAN 1154 or to establish communications over the WAN 1154, such as over the Internet. Have other means. Modem 1158, which may be internal or external and a wired or wireless device, is coupled to system bus 1108 via serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored in remote memory/storage device 1150. 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 1102 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.

Wi-Fi (Wireless Fidelity) allows connection to the Internet, etc. without wires. Wi-Fi is a wireless technology, like cell phones, that allows these devices, such as computers, to send and receive data indoors and outdoors, anywhere within the coverage area of a cell tower. Wi-Fi networks use wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz wireless bands, for example, at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band). .

Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols and chips that may be referenced in the above description include voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields. It can be expressed by particles or particles, or any combination thereof.

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein may be used in electronic hardware, (for convenience) It will be understood that it may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interoperability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been described above generally with respect to their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and design constraints imposed on the overall system. A person skilled in the art of this disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this disclosure.

The various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash. Includes, but is not limited to, memory devices (e.g., EEPROM, cards, sticks, key drives, etc.). Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

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 appended method claims present elements of the various steps in a sample order but are not meant to be limited to the particular order or hierarchy presented.

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

Claims (10)

A method for generating a dataset performed by a computing device including a processor, comprising:
creating a 3D model;
Obtaining first viewpoint information including a first image taken from a first viewpoint for a first area of the 3D model, information on a first camera, and first point cloud information;
Obtaining second viewpoint information including a second image taken from a second viewpoint of the first area, information on a second camera, and second point cloud information;
generating a dataset of a model for visual localization based on the first viewpoint information and the second viewpoint information obtained by photographing the corresponding first areas from different viewpoints; and
Using the data set, training a model for visual localization to output feature points corresponding to the first viewpoint information and the second viewpoint information;
Including,
Here, the first viewpoint and the second viewpoint have different viewpoints,
method.
According to claim 1,
The step of creating the 3D model is,
Obtaining spatial information about an arbitrary space scanned or photographed using an imaging device;
generating point cloud information for the arbitrary space, including color data based on the spatial information; and
generating the 3D model based on point cloud information for the arbitrary space;
Including,
method.
According to claim 2,
The spatial information is,
Containing information about objects existing in the random space,
method.
According to claim 2,
The color data is,
Containing data related to the color of an object existing in the random space,
method.
According to claim 2,
The point cloud information for the arbitrary space is,
Further comprising location data related to the location of an object existing in the arbitrary space,
method.
According to claim 1,
The information of the first camera is,
Containing location information and direction information of the first camera determined based on a predetermined reference point,
method.
According to claim 1,
Using the data set, training a model for visual localization to output feature points corresponding to the first viewpoint information and the second viewpoint information;
Containing more,
method.
delete A computer program stored on a computer-readable storage medium, the computer program comprising instructions for causing a processor of a computing device to generate a dataset to perform the following steps, said steps being:
creating a 3D model;
Obtaining first viewpoint information including a first image taken from a first viewpoint for a first area of the 3D model, information on a first camera, and first point cloud information;
Obtaining second viewpoint information including a second image taken from a second viewpoint of the first area, information on a second camera, and second point cloud information;
generating a dataset of a model for visual localization based on the first viewpoint information and the second viewpoint information obtained by photographing the corresponding first areas from different viewpoints; and
Using the data set, training a model for visual localization to output feature points corresponding to the first viewpoint information and the second viewpoint information;
Including,
Here, the first viewpoint and the second viewpoint have different viewpoints,
A computer program stored on a computer-readable storage medium.
In a computing device for generating a dataset,
A processor including at least one core;
a memory storing a computer program executable by the processor; and
network department;
Including,
The processor,
create a 3D model,
Acquire first viewpoint information including a first image taken from a first viewpoint for the first area of the 3D model, information on a first camera, and first point cloud information,
Obtaining second viewpoint information including a second image taken from a second viewpoint for the first area, information on a second camera, and second point cloud information,
Generating a model dataset for visual localization based on the first viewpoint information and the second viewpoint information obtained by photographing the corresponding first areas from different viewpoints, and
Using the dataset, a model for visual positioning is trained so that feature points corresponding to the first viewpoint information and the second viewpoint information are output,
Here, the first viewpoint and the second viewpoint have different viewpoints,
Computing device.

Images