KR102624907B1 - Method and apparatus for detecting landmark from three dimensional volume image - Google Patents

Abstract

According to an embodiment of the present disclosure, there is provided a method for updating a 33-dimensional map, performed by a computing device, comprising: receiving a plurality of query images from a client device, the method comprising: receiving a plurality of query images from the plurality of query images; Detecting an object and a variable object, estimating a camera pose indicating the position and direction of a camera on a three-dimensional map based on the extracted non-variable object, and the step corresponding to the estimated camera pose. and updating the 3D map based on variable objects in a reference image of the 3D map and variable objects extracted from the plurality of query images.

Description

Method and apparatus for updating a three-dimensional map {METHOD AND APPARATUS FOR DETECTING LANDMARK FROM THREE DIMENSIONAL VOLUME IMAGE}

This disclosure relates to a method and apparatus for updating a 3D map.

In general, augmented reality (AR) refers to a technology that fuses and complements virtual objects and information created with computer technology in the real world. With the recent advancement of technology, various services using augmented reality are provided, such as 3D map guidance service, car navigation route guidance service, tourist information provision service, furniture arrangement provision service in indoor space, clothing wearing service, etc. there is.

In particular, in the case of the 3D map guidance service, a glass-type wearable device that can be worn on the human body is worn on the user's head, and visual information about the 3D map is provided through the display on the device, providing the user with a 3D map service in real time. can be provided. In order to provide this service, the user's location and camera pose are estimated using the sensing information of the wearable device (i.e., sensing information acquired by a sensing device such as Lidar and/or a camera), and the estimated location and A 3D map creation process based on VPS (visual positioning system), which creates a 3D map using poses, is necessary.

However, the user's environment can change in real time, and the VPS-based 3D map is created using instantaneous sensing information acquired through a sensing device, so the 3D map at the moment the user requests the provision of a 3D map. Since the appearance of the actual space may not exactly match, the accuracy of the 3D map is low, which reduces the sense of immersion in the augmented reality content.

Therefore, a method for updating a 3D map in real time is required to increase the accuracy and immersion of the 3D map.

Korean Patent Publication No. 10-2022-0001274

The present disclosure was made in response to the above-described background technology, and seeks to provide a method and device for updating a 3D map.

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 an embodiment of the present disclosure for solving the above-described problem, a method for updating a 3D map performed by a computing device includes receiving a plurality of query images from one or two or more client devices. Receiving, detecting a non-variable object and a variable object from the plurality of query images, a camera pose indicating the position and direction of the camera on a three-dimensional map based on the extracted non-variable object. Estimating and updating the 3D map based on a variable object in a reference image of the 3D map corresponding to the estimated camera pose and a variable object extracted from the plurality of query images. It can be included.

In addition, the plurality of query images refers to a sequence of query images in which an overlapping area exists, received from one client, or a query image in which the overlapping area exists, received from a plurality of client devices at the same time. It can mean things.

In addition, the step of detecting the non-variable object and the variable object from the plurality of query images includes using a detection model learned to detect the non-variable object and the variable object from the plurality of query images. -This may be a step in detecting variable objects.

In addition, detecting the non-variable object and the variable object using the detection model includes inputting the plurality of query images into the detection model and detecting the non-variable object from the query image using the detection model. It may include detecting an object corresponding to a factor as the non-variable object and detecting an object corresponding to a variable factor as the variable object.

Additionally, the method includes generating the three-dimensional map and storing the generated three-dimensional map and spatial data for the three-dimensional map used to update the three-dimensional map in a database associated with the computing device. Additional steps may be included.

Additionally, the 3D map may be generated using Lidar scan, Structure from motion (SFM) algorithm, or Simultaneous Localization and Mapping (SLAM) algorithm.

In addition, the spatial data for the 3D map includes a plurality of reference images related to the 3D map, first feature point data for at least one object extracted from each of the plurality of reference images, and each of the plurality of reference images. Correspondingly, it may include second feature point data for at least one object extracted from the 3D map, GPS data corresponding to each of the plurality of reference images, and camera pose data corresponding to each of the plurality of reference images.

In addition, the step of estimating the camera pose may include extracting feature point data for the detected non-variable object, feature point data extracted for the non-variable object among feature point data previously stored for at least one object. It may include determining feature point data that matches and estimating the camera pose using pre-stored camera pose data corresponding to the determined feature point data.

Additionally, the feature point data may include two-dimensional coordinates and three-dimensional coordinates representing each feature point.

In addition, the step of updating the 3D map includes extracting feature point data for the detected variable object, feature point data for the variable object stored in advance corresponding to a reference image corresponding to the estimated camera pose, and the It may include determining whether to update the 3D map based on feature point data extracted for the variable object.

In addition, the step of determining whether to update the 3D map includes a difference value ( calculating a reprojection error; and determining whether the calculated difference value is greater than or equal to a preset threshold. If the calculated difference value is greater than or equal to the preset threshold value, the feature point data extracted for the variable object is used to calculate the difference value. The step of updating the 3D map may be included.

In addition, the step of updating the 3D map using feature point data extracted for the variable object includes, if the calculated difference value is greater than a preset threshold, the variable object in the 3D map corresponding to the reference image. It may include determining that at least one of the position or shape of has changed and changing at least one of the position or shape of the variable object in the 3D map using feature point data extracted for the variable object.

In addition, the step of changing at least one of the location or shape of the variable object in the 3D map includes converting at least some of the feature point coordinate values for the variable object in the 3D map into feature point coordinate values extracted for the variable object. It may be a stage of updating at least part of the process.

According to an embodiment of the present disclosure for solving the above-described problem, there is a computer program stored in a computer-readable storage medium, wherein the computer program, when executed on one or more processors, performs the following operations for updating a three-dimensional map. to be performed, and the operations include receiving a plurality of query images from one or more client devices, detecting a non-variable object and a variable object from the plurality of query images, and An operation of estimating a camera pose indicating the position and direction of a camera on a 3D map based on a variable object in a reference image of the 3D map corresponding to the estimated camera pose and a variable object extracted from the plurality of query images It may include an operation of updating the 3D map based on .

According to an embodiment of the present disclosure for solving the above-described problem, there is provided a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computing device, causes the computing device to update a three-dimensional map. To perform a method for: receiving a plurality of query images from one or more client devices, detecting a non-variable object and a variable object from the plurality of query images, the extracted - Estimating a camera pose indicating the position and direction of a camera on a 3D map based on a variable object, and from the variable object in the reference image of the 3D map corresponding to the estimated camera pose and the plurality of query images It may include updating the 3D map based on the extracted variable object.

According to an embodiment of the present disclosure for solving the above-described problem, a computing device for updating a 3D map includes at least one processor and a memory, wherein the at least one processor includes one or more clients. A camera pose that receives a plurality of query images from a device, detects non-variable objects and variable objects from the plurality of query images, and indicates the position and direction of the camera on a three-dimensional map based on the extracted non-variable objects. It may be configured to estimate and update the 3D map based on a variable object in a reference image of the 3D map corresponding to the estimated camera pose and a variable object extracted from the plurality of query images.

The technical solutions obtainable from this disclosure are not limited to the solutions mentioned above, and other solutions not mentioned above will be clearly apparent to those skilled in the art from the description below. It will be understandable.

According to some embodiments of the present disclosure, by updating the 3D map in real time, a highly accurate 3D map can be provided to the user and highly immersive augmented reality content can be provided.

Additionally, the time and resources used to update the 3D map can be minimized.

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 is a configuration diagram of an example system for updating a 3D map according to an embodiment of the present disclosure.
Figure 2 is a block diagram of a server for updating a 3D map according to an embodiment of the present disclosure.
Figure 3 is a schematic diagram showing a network function according to an embodiment of the present disclosure.
4 is a flowchart illustrating an example of a method for updating a 3D map according to an embodiment of the present disclosure.
Figure 5 is a schematic illustration for explaining a detection model learned to detect non-variable objects and variable objects according to an embodiment of the present disclosure.
FIG. 6 is a flowchart illustrating a method for estimating a camera pose based on a non-variable object according to an embodiment of the present disclosure.
Figure 7 is an example diagram for explaining a method of generating a 3D map according to an embodiment of the present disclosure.
Figure 8 is an example diagram for explaining a method of storing spatial data related to a 3D map according to an embodiment of the present disclosure.
FIG. 9 is a flowchart illustrating a method of updating a 3D map based on a variable object according to an embodiment of the present disclosure.
FIG. 10 is a flowchart illustrating a method of updating a 3D map using feature point data for a variable object according to an embodiment of the present disclosure.
11 is 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 configuration diagram of an example system for updating a 3D map according to an embodiment of the present disclosure.

Referring to FIG. 1, a system for updating a 3D map may include a client device 10 that requests an update to the 3D map and a server 100 that updates the 3D map according to the request. The components shown in FIG. 1 are exemplary, and additional components may exist or some of the components may be omitted.

According to some embodiments of the present disclosure, the client device 10 and the server 100 may mutually transmit and receive data for updating a 3D map according to some embodiments of the present disclosure through a communication network.

The client device 10 is a device for providing a plurality of query images for updating the 3D map, and is equipped with a camera, such as smart glasses for experiencing augmented reality or virtual reality (VR), or a camera. It may include a wearable device that can be connected to, a terminal, and/or any electronic device having network connectivity.

Specifically, the client device 10 may transmit a plurality of query images to the server 100 to request an update to the 3D map. Here, the client device 10 may be one client device (ie, a single client device) or two or more client devices. For example, if the client device 10 is a single client device, a plurality of query images may mean a sequence of query images with overlapping areas received from a single client device, and the client device 10 ) If there are two or more client devices, the plurality of query images may mean query images that are received from two or more client devices at the same time and have overlapping areas. Here, the query image may be a two-dimensional or three-dimensional image acquired through the camera of the client device 10, but is not limited thereto. In various embodiments, the client device 10 may transmit a query image to the server 100 according to a preset time period for 3D map update, or may transmit the query image at the request of the server 100, Also, it is not limited.

According to some embodiments of the present disclosure, the client device 10 may be any entity capable of processing, storing, and outputting any data, including a processor, a storage unit (memory and persistent storage media), and a display unit. there is.

The processor in the present disclosure may consist of one or more cores, including a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit of the client device 10. It may include any type of processor to request a 3D map or update a 3D map by executing instructions stored in memory, such as (TPU: tensor processing unit), and to display an output screen for the 3D map. You can. The processor may read a computer program stored in a memory and perform landmark detection according to an embodiment of the present disclosure.

The memory in the present disclosure may store a program for the operation of a processor, and may temporarily or permanently store input/output data. Memory is a flash memory type, hard disk type, multimedia card micro type, card type memory (e.g. SD or XD memory, etc.), and RAM (Random Access). Memory, RAM), 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, optical disk It may include at least one type of storage medium. These memories can be operated under processor control. Additionally, memory and storage may be used interchangeably with each other in the present disclosure.

Server 100 is a device for updating a three-dimensional map and may include any type of computer system or computer device, such as, for example, a computer, digital processor, portable device, and device controller.

Specifically, the server 100 receives a plurality of query images from the client device 10, estimates a camera pose indicating the location and direction of the camera of the client device 10 based on the plurality of query images, and then estimates the camera pose. The 3D map can be updated based on the reference image of the 3D map corresponding to the camera pose and a plurality of query images.

According to some embodiments of the present disclosure, the server 100 may be any entity capable of processing and storing any data, including a processor and a storage unit (memory and persistent storage media).

A processor in the present disclosure may consist of one or more cores, including a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), a tensor processing unit (TPU), a graphics processing unit (GPU), and neural processing of a computing device. It may include any type of processor for updating a 3D map by executing instructions stored in memory, such as a Neural Processing Unit (NPU). The processor may read the computer program stored in the memory and perform a 3D map update according to an embodiment of the present disclosure.

The memory in the present disclosure may store a program for the operation of a processor, and may temporarily or permanently store input/output data. Memory includes flash memory type, hard disk type, multimedia card micro type, card type memory (e.g. SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, magnetic memory, magnetic memory. It may include at least one type of storage medium among disks and optical disks. These memories can be operated under processor control. Additionally, memory and storage may be used interchangeably with each other in the present disclosure.

The storage unit according to the present disclosure may be implemented as a database. According to various embodiments, the system of the present disclosure may be equipped with a separate database for storing various data related to a 3D map. These databases can store 3D maps and spatial data related to 3D maps. Here, the 3D map is a point cloud obtained from RGB and/or depth map images captured through cameras at various locations, camera pose data at each location, GPS data from the camera, and RGB and/or depth map images. It refers to a 3D model reconstructed into a 3D mesh based on data, etc.

Spatial data related to a 3D map may include, but is not limited to, a reference image at each location of the 3D map, camera pose data, and feature point data for each of various objects.

Figure 2 is a block diagram of a server for updating a 3D map according to an embodiment of the present disclosure. The configuration of the server 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the server 100 may include different configurations for performing the computing environment of the server 100, and only some of the disclosed configurations may configure the server 100.

The server 100 may include a communication unit 110, a memory 120, and a processor 130. However, the above-described components are not essential for implementing the server 100, so the server 100 may have more or less components than the components listed above. Here, each component may be composed of a separate chip, module, or device, or may be included in one device.

The communication unit 110 according to an embodiment of the present disclosure may include any type of wired/wireless Internet module for network connection. Additionally, the communication unit 110 may include a short range communication module. Short-distance communication technologies include Bluetooth, Radio Frequency Identification (RFID), infrared data association (IrDA), Ultra-Wideband (UWB), and ZigBee.

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

According to some embodiments of the present disclosure, the communication unit 110 connects the server 100 to enable communication with an external device. The communication unit 110 may be connected to the client device 10 using wired/wireless communication and receive a plurality of query images.

According to an embodiment of the present disclosure, the storage unit 120 may store any type of information generated or determined by the processor 130 and any type of information received by the communication unit 110. According to some embodiments of the present disclosure, the storage unit 120 may store various data for updating a 3D map.

Storage unit 120 may include memory and/or persistent storage media. The storage unit 120 includes flash memory type, hard disk type, multimedia card micro type, card type memory (e.g. SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, It may include at least one type of storage medium among magnetic memory, magnetic disk, and optical disk. The server 100 may operate in relation to web storage that performs the storage function of the storage unit 120 on the Internet. The description of the storage unit described above is merely an example, and the present disclosure is not limited thereto.

The processor 130 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) and NPU (Neural Processing Unit) may include processors for data analysis and deep learning.

The processor 130 may read a computer program stored in the memory 130 and perform data processing to update a 3D map according to an embodiment of the present disclosure.

Specifically, to update the 3D map, the processor 130 detects non-variable objects and variable objects from a plurality of received query images, and estimates the camera pose of the client device 10 based on the non-variable objects. can do. Here, a non-variable object generally refers to a fixed object whose position or shape is considered difficult to change, and may include, for example, buildings, traffic lights, subway turnstiles, subway station entrances, bridges, overpasses, etc. It is not limited.

Subsequently, the processor 130 may update the 3D map based on the variable object detected from the plurality of query images and the variable object in the reference image of the 3D map corresponding to the estimated camera pose. Here, a variable object generally refers to an object whose position or shape is considered to be easily changeable, for example, people, animals, cars, bicycles, kickboards, motorcycles, mechanical equipment, chairs, computer monitors, books on a desk. , office supplies, flags, plant leaves, banners, tents, electric wires, cushions, liquid substances, etc., but are not limited to these.

In this way, to detect a non-variable or variable object, the processor 130 may use each artificial intelligence-based model learned to detect a non-variable object or a variable object from an input image. In other words, the processor 130 may detect non-variable and variable objects by performing at least one of object detection, classification, or segmentation from the query image using an artificial intelligence-based model. Hereinafter, a method for detecting a non-variable object or a variable object using an artificial intelligence-based model will be described in detail with reference to FIG. 5.

According to various embodiments of the present disclosure, the processor 130 may perform operations for learning a neural network. The processor 130 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, TPU, and NPU of the processor 130 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 an 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 the server 100 according to an embodiment of the present disclosure may be a CPU, GPGPU TPU, or NPU executable program.

Figure 3 is a schematic diagram showing a network function according to an embodiment of the present disclosure.

Throughout this specification, 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. In one embodiment, the detection model and/or extraction model herein may include the neural network described above.

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 networks (CNN), recurrent neural networks (RNN), auto encoders, generative adversarial networks (GAN), and restricted Boltzmann machines (RBM). machine), 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.

In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network to output output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be placed between input and output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically and reduced from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform nonlinear dimensionality reduction. The number of input layers and output layers can be corresponded to the dimension after preprocessing of the input data. In an auto-encoder structure, the number of nodes in the hidden layer included in the encoder may have a structure that decreases as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, not enough information may be conveyed, so if it is higher than a certain number (e.g., more than half of the input layers, etc.) ) may be maintained.

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 training data, regularization, dropout to disable some of the network nodes during the learning process, and use of a batch normalization layer are used. It can be applied.

Hereinafter, a method for updating a 3D map will be described with reference to FIGS. 4 to 10.

4 is a flowchart illustrating an example of a method for updating a 3D map according to an embodiment of the present disclosure. In the presented embodiment, the operations of FIG. 4 may be performed by the processor 130 of the server 100.

Referring to FIG. 4, the processor 130 receives a plurality of query images from one or more client devices (S400) and extracts non-variable objects and variable objects from the plurality of query images (S410). Here, the plurality of query images may mean a sequence of query images taken through a camera provided or connected to a single client device, or query images taken through cameras provided or connected to each of a plurality of client devices and received at the same time. However, it is not limited to this.

To extract non-variable objects and variable objects, the processor 130 may use an artificial intelligence-based detection model learned to detect non-variable objects and variable objects from a plurality of input images. A detailed description of the detection model will be provided below with reference to FIG. 5.

Figure 5 is a schematic illustration for explaining a detection model learned to detect non-variable objects and variable objects according to an embodiment of the present disclosure.

Referring to FIG. 5, the detection model 500 is an artificial intelligence-based model learned to detect a non-variable object 520 and a variable object 530 from input data 510 corresponding to a plurality of query images. Examples For example, it may be a deep learning model that can detect and segment objects of a predefined class, such as Mask RCNN, but is not limited to this. Here, the predefined class may include non-variable factors and variable factors.

Specifically, the detection model 500 may include an algorithm for object detection and an algorithm for segmentation, and can detect objects corresponding to non-variable factors and variable factors from the query image using the object detection algorithm and segmentation algorithm. Can be trained to recognize and classify.

The processor 130 according to the present disclosure inputs input data 510 corresponding to a plurality of query images into the detection model 500, uses the detection model 500 to distinguish the class of each object in the query image, Objects can be classified according to their distinct classes. In other words, the processor 130 can use the detection model 500 including an object detection algorithm to distinguish whether each object in the query image corresponds to a non-variable factor or a variable factor. Subsequently, the processor 130 classifies the non-variable object 520 corresponding to the non-variable factor and the variable object 530 corresponding to the variable factor using the detection model 500 including a segmentation algorithm, thereby classifying the non-variable object 520 corresponding to the variable factor. -The variable object 520 and the variable object 530 can be detected.

Referring again to FIG. 4, the processor 130 estimates a camera pose indicating the direction the camera is facing on the 3D map based on the detected non-variable object (S420).

To estimate the camera pose, the processor 130 may use feature point data for a non-variable object. A detailed explanation for camera pose estimation will be provided below with reference to FIG. 6.

FIG. 6 is a flowchart illustrating a method for estimating a camera pose based on a non-variable object according to an embodiment of the present disclosure.

Referring to FIG. 6, the processor 130 extracts feature point data for the detected non-variable object (S600). In order to extract feature point data like this, the processor 130 uses various functions such as SIFT (Scale Invariant Feature Transform), SURF (Speeded Up Robust Features), FAST, BRISK (Binary Robust Invariant Scalable Keypoints), and ORB (Oriented FAST and Rotated BRIEF). A feature point extraction algorithm or a deep learning model for feature point extraction may be used, but the method is not limited thereto, and various methods for feature point extraction may be used. In various embodiments, the processor 130 may extract feature point data using the SLAM algorithm. Here, the feature point data may include two-dimensional coordinates and three-dimensional coordinates representing each feature point. In various embodiments, the processor 130 may further extract a descriptor for distinguishing whether the feature point data is 2-dimensional coordinates or 3-dimensional coordinates along with the feature point data, but is not limited to this.

In order to estimate a camera pose based on feature point data for a non-variable object, when generating a 3D map, the processor 130 includes a reference image related to the 3D map, camera pose data at a location corresponding to each reference image, Spatial data including feature point data for at least one object extracted from each reference image and feature point data for at least one object in the 3D map may be stored in advance. Such spatial data may be pre-stored in the above-described storage unit 120 or a separate database related to the server 100. This will be described in detail below with reference to FIGS. 7 and 8.

FIG. 7 is an example diagram for explaining a method for generating a 3D map according to an embodiment of the present disclosure, and FIG. 8 is an example diagram for explaining a method for storing spatial data related to a 3D map according to an embodiment of the present disclosure. This is an example diagram.

Referring to FIG. 7 , the processor 130 may obtain RGB images, point cloud data, and camera data 710 acquired at each location from the camera 700. Here, the camera 700 may be an RGB-D camera capable of acquiring RGB images and point cloud data, but is not limited thereto, and various sensing devices capable of acquiring RGB images and point cloud data may be used. For example, a Lidar sensor and/or an Inertial Measurement Unit (IMU) sensor may be used, or sensors that perform similar functions may be used.

Additionally, camera data may include, but is not limited to, camera pose data, GPS data, or IMU data.

The processor 130 may generate a 3D map 720 consisting of a 3D mesh using the acquired RGB image, point cloud data, and camera data 710. To generate the 3D map 720, the processor 130 may use a Lidar scan, a Structure from motion (SFM) algorithm, or a Simultaneous Localization and Mapping (SLAM) algorithm, but is not limited thereto.

Subsequently, the processor 130 may detect each non-variable object and the variable object from the RGB image, and extract each feature point for the detected non-variable object and the variable object. As described above, object detection and feature point detection may use an algorithm or deep learning model for object detection and feature point extraction, but the method is not limited thereto, and various methods may be used for this purpose. In various embodiments, the processor 130 may use a plurality of algorithms or a plurality of deep learning models detected to perform object detection and feature point extraction, respectively, or may use an algorithm or deep learning model that simultaneously performs object detection and feature point extraction. there is.

The processor 130 provides a reference image (i.e., an RGB image) related to the 3-dimensional map together with the generated 3-dimensional map, and at least one object (i.e., a non-variable object and/or a variable object) extracted from each reference image. Includes first feature point data for, second feature point data for at least one object extracted from a 3D map corresponding to each reference image, GPS data corresponding to each reference image, and camera pose data corresponding to each reference image. Spatial data can be stored in the storage unit 120 or a separate database. Spatial data stored in this way can be illustratively shown in FIG. 8.

Referring to FIG. 8, spatial data includes a reference image, first feature point data for each object in the reference image, second feature point data for each object in a 3D map corresponding to the reference image, and each feature point is 2-dimensional or 3-dimensional. It may include a descriptor for distinguishing between coordinates, GPS data, camera pose data, the type of detected object, and the class of the detected object. Here, the first feature point data may include a set of two-dimensional feature point coordinates of a non-variable and/or variable object extracted from a reference image corresponding to the two-dimensional image. Additionally, the second feature point data may include a set of 3D feature point coordinates of a non-variable and/or variable object extracted from a 3D image of a 3D map corresponding to a reference image.

Referring again to FIG. 6, the processor 130 selects a feature point that matches feature point data extracted for a non-variable object among feature point data previously stored for at least one object (i.e., a non-variable and/or variable object). Determine data (S610). Specifically, the processor 130 may determine feature point data that matches feature point data of a non-variable object extracted from a plurality of query images among feature point data of each object pre-stored in the database, as shown in FIG. 8 . For example, the processor 130 may extract feature point data that matches feature point data of the extracted non-variable object from among the first feature point data or the second feature point data of each object stored as shown in FIG. 8 . For example, the processor 130 matches feature point data whose difference value with the feature point data of the extracted non-variable object is less than or equal to a preset threshold difference value among the feature point data of each object with the feature point data of the extracted non-variable object. It can be determined using feature point data.

Next, the processor 130 estimates the camera pose using pre-stored camera pose data corresponding to the determined feature point data (S620). Specifically, the processor 130 may determine camera pose data pre-stored in a database in response to the determined feature point data, and estimate the camera pose of the client device 10 using the determined camera pose data. For example, referring to Figure 8, the feature point data of the non-variable object extracted from a plurality of query images matches the first feature point data of the non-variable object 'traffic light' stored in advance corresponding to the reference image '0001'. If so, the processor 130 converts the pre-stored camera pose data 'R1 = [...] T1 = [...]' corresponding to the reference image '0001' into the camera pose data of the camera related to the client device 10. By determining as , the camera pose for the client device 10 can be estimated.

Referring again to FIG. 4, the processor 130 updates the 3D map based on the variable object in the reference image of the 3D map corresponding to the estimated camera pose and the variable object extracted from the plurality of query images (S430 ). In order to update the 3D map based on variable objects like this, the processor 130 can use feature point data for the variable objects. A detailed explanation for updating the 3D map will be described below with reference to FIG. 9.

FIG. 9 is a flowchart illustrating a method of updating a 3D map based on a variable object according to an embodiment of the present disclosure.

Referring to FIG. 9, the processor 130 extracts feature point data for the detected variable object (S900). In order to extract feature point data in this way, the processor 130 may use an algorithm or a deep learning model for feature point extraction as described above, but the method is not limited thereto, and various methods for feature point extraction may be used. In various embodiments, the processor 130 may extract a greater number of feature points for a variable object than feature points for a non-variable object.

The processor 130 determines whether to update the 3D map based on feature point data for the variable object stored in advance in response to the reference image corresponding to the estimated camera pose and feature point data extracted for the variable object (S910 ). Specifically, the processor 130 compares the feature point data for the variable object stored in advance in response to the reference image corresponding to the estimated camera pose and the feature point data extracted for the variable object to determine at least one of the position or shape of the variable object. You can determine whether has changed. When at least one of the location or shape of the variable object changes, the processor 130 may update the 3D map using feature point data extracted for the variable object. In order to determine whether to update the 3D map, this will be described in detail below with reference to FIG. 10.

FIG. 10 is a flowchart illustrating a method of updating a 3D map using feature point data for a variable object according to an embodiment of the present disclosure.

Referring to FIG. 10, the processor 130 calculates a difference value between at least a portion of the feature point data for the variable object stored in advance corresponding to the determined reference image and at least a portion of the feature point data extracted for the variable object (S1000). . For example, the processor 130 may calculate a difference value between at least some of the feature point coordinate values for the variable object stored in advance corresponding to the determined reference image and at least some of the feature point coordinate values extracted for the variable object. Here, the difference value may mean a reprojection error indicating an error between feature point coordinates.

The processor 130 determines whether the calculated difference value is more than a preset threshold (S1010), and if the calculated difference value is more than the preset threshold, a 3D map is created using feature point data extracted for the variable object. Update (S1020). Specifically, the processor 130 may determine that at least one of the position or shape of the variable object has changed if the number of feature points for which the calculated difference value is greater than or equal to a preset threshold is greater than or equal to the first threshold. Subsequently, the processor 130 may update the 3D map by correcting (or updating) the feature point data of the variable object in the 3D map using the feature point data extracted for the variable object. For example, the processor 130 changes the coordinate values of at least some of the feature point coordinate values of the variable object in the 3D map to the coordinate values of at least some of the feature point coordinate values extracted for the variable object, 3 The feature point data of the corresponding variable object in the dimensional map can be corrected (or updated).

If the calculated difference value is less than a preset threshold, the processor 130 ends the operation to update the 3D map.

Through this, the present invention can provide a highly accurate 3D map by updating the 3D map in real time.

In various embodiments, the processor 130 may update the 3D map by detecting objects with a high likelihood of being variable among variable objects and determining whether the location and/or shape of the detected object has changed. Specifically, the processor 130 may be driven by a first variable object, such as a person or an animal, corresponding to a living organism that can move objects corresponding to variable factors in the reference image with its own consciousness when generating a 3D map. Second variable objects such as cars, bicycles, kickboards, motorcycles, mechanical equipment, etc., third variable objects such as chairs, computer monitors, books on a desk, office supplies, etc. whose positions can be easily changed by people on a daily basis, natural phenomena Third variable objects such as flags, plant leaves, banners, tents, electric wires, etc. whose positions or shapes can be changed and fourth variable objects whose shapes can be easily changed such as cushions, liquid substances, flags, tent cloth, etc. You can create and store spatial data by dividing them into .

In this case, the processor 130 determines a variable object with a high possibility of change among the first to fourth variable objects, determines whether a change has been made to the location and/or shape of the determined variable object, and updates the 3D map. can do. For example, the processor 130 may determine that a first variable object is more likely to be variable than a third variable object whose location can change due to natural phenomena. In various embodiments, the variable possibilities may be set by the user. The processor 130 detects the first variable object from the acquired query image, compares the feature point data of the detected first variable object with the feature point data of the first variable object in the reference image corresponding to the estimated camera pose, and 1 After determining whether the location and/or shape of the variable object changes, it is possible to decide whether to update the 3D map.

In various embodiments, the processor 130 determines the variable object that is judged to have the greatest collision between the 3D map and real space when variable among the first to fourth variable objects, and determines the location and/or location of the determined variable object. Alternatively, the 3D map can be updated by determining whether changes have been made to the shape. For example, the processor 130 may determine that the collision between the 3D map and real space is greater when the second variable object is variable than the first variable object. In this case, the processor 130 detects the second variable object from the acquired query image, and compares the feature point data of the detected second variable object with the feature point data of the second variable object in the reference image corresponding to the estimated camera pose. After determining whether to change the location and/or shape of the second variable object, it is possible to determine whether to update the 3D map.

In various embodiments, the processor 130 may not perform a 3D map update even if at least one of the location or shape of the variable object changes if the conflict between the 3D map and real space is not significant. For example, if the shape of a circular cushion is distorted by a user, the processor 130 uses the feature point coordinate values for the variable object stored in advance in response to the reference image and the feature point coordinate values extracted for the variable object. By comparison, if the number of matching feature points is greater than or equal to the second critical number, it can be determined that the conflict between the 3D map and real space is not significant.

Through this, the present invention can minimize the amount of computation and resources consumed when updating a 3D map.

In the presented embodiment, the deep learning model is described as detecting an object and extracting feature point data for the extracted object using a feature point extraction algorithm, but it is not limited to this, and the processor 130 performs object detection and feature point extraction. You can also use deep learning models that are trained to perform simultaneously. In various embodiments, the processor 130 may perform feature point extraction for an object using the SLAM algorithm.

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 can 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, a data structure including weights of a neural network may include weights that change during the neural network learning process and/or weights that have completed neural network learning. Therefore, the above-described 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.

11 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 combination with 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). -, 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, such as the like, 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 via 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 base station. 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, the Internet, and 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 (16)

1. A method for updating a three-dimensional map, performed by a computing device, comprising:
Receiving a plurality of query images from one or more client devices;
Detecting non-variable objects and variable objects from the plurality of query images;
estimating a camera pose indicating the location and direction of a camera on a three-dimensional map based on the detected non-variable object; and
Comprising a step of updating the 3D map based on a variable object in a reference image of the 3D map corresponding to the estimated camera pose and a variable object extracted from the plurality of query images,
The steps for updating the 3D map are:
When there are a plurality of variable objects, classifying the plurality of variable objects into a plurality of groups based on predetermined unique characteristics of the objects;
determining a first group based on a different predetermined collision probability for each of the plurality of groups; and
Based on the comparison result of comparing the feature point data of the first variable object corresponding to the first group and the feature point data of the reference variable object corresponding to the first variable object in the reference image corresponding to the estimated camera pose, 3 Comprising updating the dimensional map,
How to update a 3D map.
The method of claim 1, wherein the plurality of query images are:
Refers to a sequence of query images in which overlapping areas exist, received from one client, or query images in which overlapping areas exist, received from multiple client devices at the same time.
How to update a 3D map.
The method of claim 1, wherein detecting the non-variable object and the variable object from the plurality of query images comprises:
A step of detecting the non-variable object using the non-variable object and a detection model learned to detect the variable object from the plurality of query images,
How to update a 3D map.
The method of claim 3, wherein detecting the non-variable object and the variable object using the detection model comprises:
Inputting the plurality of query images into the detection model; and
Comprising the steps of detecting an object corresponding to a non-variable factor as the non-variable object from the query image using the detection model, and detecting an object corresponding to a variable factor as the variable object,
How to update a 3D map.
According to paragraph 1,
generating the 3D map; and
Further comprising storing the generated 3D map and spatial data for the 3D map used to update the 3D map in a database associated with the computing device,
How to update a 3D map.
The method of claim 5, wherein the three-dimensional map is:
Generated using Lidar scan, SFM (Structure from motion) algorithm, or SLAM (Simultaneous Localization and Mapping) algorithm,
How to update a 3D map.
The method of claim 5, wherein the spatial data for the 3D map is:
A plurality of reference images related to the 3D map, first feature point data for at least one object extracted from each of the plurality of reference images, and at least one feature extracted from the 3D map corresponding to each of the plurality of reference images Containing second feature point data for the object, GPS data corresponding to each of the plurality of reference images, and camera pose data corresponding to each of the plurality of reference images,
How to update a 3D map.
The method of claim 4, wherein estimating the camera pose comprises:
extracting feature point data for the detected non-variable object;
determining feature point data that matches feature point data extracted for the non-variable object among feature point data previously stored for at least one object; and
Comprising the step of estimating the camera pose using camera pose data stored in advance in response to the determined feature point data,
How to update a 3D map.
The method of claim 7, wherein the feature point data is:
Containing two-dimensional coordinates and three-dimensional coordinates representing each feature point,
How to update a 3D map.
The method of claim 4, wherein updating the 3D map comprises:
extracting feature point data for the detected variable object; and
Comprising the step of determining whether to update the 3D map based on feature point data for the variable object stored in advance in response to the reference image corresponding to the estimated camera pose and feature point data extracted for the variable object. ,
How to update a 3D map.
The method of claim 10, wherein the step of determining whether to update the 3D map includes:
calculating a difference value (reprojection error) between at least a portion of feature point data for a variable object stored in advance corresponding to the reference image and at least a portion of feature point data extracted for the variable object; and
determining whether the calculated difference value is greater than or equal to a preset threshold, and if the calculated difference value is greater than or equal to the preset threshold, updating the 3D map using feature point data extracted for the variable object. containing,
How to update a 3D map.
The method of claim 11, wherein updating the 3D map using feature point data extracted for the variable object comprises:
determining that at least one of the location or shape of a variable object in the 3D map corresponding to the reference image has changed if the calculated difference value is greater than or equal to a preset threshold; and
Comprising the step of changing at least one of the position or shape of the variable object in the 3D map using feature point data extracted for the variable object,
How to update a 3D map.
The method of claim 12, wherein changing at least one of the location or shape of the variable object in the 3D map comprises:
A step of updating at least some of the feature point coordinate values for the variable object in the 3D map with at least some of the feature point coordinate values extracted for the variable object,
How to update a 3D map.
A computer program stored on a computer-readable storage medium, wherein the computer program, when executed on one or more processors, causes the following operations to be performed to update a three-dimensional map, the operations comprising:
Receiving a plurality of query images from one or more client devices;
detecting non-variable objects and variable objects from the plurality of query images;
Estimating a camera pose indicating the location and direction of a camera on a three-dimensional map based on the detected non-variable object; and
Comprising the operation of updating the 3D map based on a variable object in a reference image of the 3D map corresponding to the estimated camera pose and a variable object extracted from the plurality of query images,
The operation of updating the 3D map is:
When there are a plurality of variable objects, classifying the plurality of variable objects into a plurality of groups based on predetermined unique characteristics of the objects;
determining a first group based on a different predetermined collision probability for each of the plurality of groups; and
Based on the comparison result of comparing the feature point data of the first variable object corresponding to the first group and the feature point data of the reference variable object corresponding to the first variable object in the reference image corresponding to the estimated camera pose, 3 Including an operation of updating the dimensional map,
A computer program stored on a computer-readable storage medium.
A computer-readable storage medium storing a computer program, the computer program, when executed by a computing device, causing the computing device to perform a method for updating a three-dimensional map, the method comprising:
Receiving a plurality of query images from one or more client devices;
Detecting non-variable objects and variable objects from the plurality of query images;
estimating a camera pose indicating the location and direction of a camera on a three-dimensional map based on the detected non-variable object; and
Comprising a step of updating the 3D map based on a variable object in a reference image of the 3D map corresponding to the estimated camera pose and a variable object extracted from the plurality of query images,
The steps for updating the 3D map are:
When there are a plurality of variable objects, classifying the plurality of variable objects into a plurality of groups based on predetermined unique characteristics of the objects;
determining a first group based on a different predetermined collision probability for each of the plurality of groups; and
Based on the comparison result of comparing the feature point data of the first variable object corresponding to the first group and the feature point data of the reference variable object corresponding to the first variable object in the reference image corresponding to the estimated camera pose, 3 Comprising updating the dimensional map,
Computer readable storage medium.
A computing device for updating a three-dimensional map, comprising:
at least one processor; and
Contains memory,
The at least one processor:
Receive a plurality of query images from one or more client devices,
Detect non-variable objects and variable objects from the plurality of query images,
Estimating a camera pose indicating the location and direction of the camera on a 3D map based on the detected non-variable object,
configured to update the 3D map based on a variable object in a reference image of the 3D map corresponding to the estimated camera pose and a variable object extracted from the plurality of query images,
When updating the 3D map,
When there are a plurality of variable objects, classifying the plurality of variable objects into a plurality of groups based on unique characteristics predetermined for the objects,
determine a first group based on a different predetermined collision probability for each of the plurality of groups, and
Based on the comparison result of comparing the feature point data of the first variable object corresponding to the first group and the feature point data of the reference variable object corresponding to the first variable object in the reference image corresponding to the estimated camera pose, 3 Comprising updating the dimensional map,
Computing device.

Images