WO2024071733A1 - Method and apparatus for identifier recognition-based location determination - Google Patents

Abstract

The present disclosure relates to a method for identifier recognition-based location determination, which is executed by at least one processor of a computing apparatus. The method for identifier recognition-based location determination comprises the steps of: receiving an image in which an identifier arranged in a space has been captured; detecting the identifier from the received image; determining a first pose of the identifier from the received image; and determining the location of the computing apparatus within the space from the determined first pose.

Description

Identifier recognition based location determination method and device

The present disclosure relates to a method and device for determining location based on identifier recognition, and specifically to a method and device for determining the location of a computing device in space by detecting an identifier disposed in space.

Recently, various technologies have been widely used to measure the location of terminals such as smartphones and robots. In particular, the use of indoor robots capable of autonomous driving is increasing, and there is a need to determine the location of the device in space for autonomous driving of indoor robots.

However, the conventional LIDAR (Light Detection and Ranging)-based location measurement method is capable of relatively sophisticated measurements, but is difficult to use because it requires a lot of cost and high skill level, and location measurement methods using WIFI, beacons, magnetic fields, etc. are sensitive to changes in surrounding conditions. However, there is a problem in providing accurate location information because it is difficult to have an accuracy of less than 1m. In addition, in the case of GPS-based location measurement, it is difficult to use between high-rise buildings, indoors, or underground, and it is difficult to achieve accuracy of less than 1 meter.

The present disclosure provides a location determination method based on identifier recognition, a computer program stored in a recording medium, and a system (device) to solve the above problems.

The present disclosure may be implemented in various ways, including a method, system (device), or computer-readable non-transitory recording medium recording instructions.

An identifier recognition-based location determination method, executed by at least one processor of a computing device, comprising: receiving an image having an identifier disposed in space; detecting an identifier from the received image; Determining a first pose of the identifier and determining a position of the computing device in space from the determined first pose.

According to an embodiment of the present disclosure, a computer-readable non-transitory recording medium recording instructions for executing the above-described method on a computer is provided.

In the computing device according to an embodiment of the present disclosure, it includes a communication module, a memory, and at least one processor connected to the memory and configured to execute at least one computer-readable program included in the memory, and at least one program Receives an image in which an identifier disposed in space is captured, detects the identifier from the received image, determines a first pose of the identifier from the received image, and determines a position in space from the determined first pose. Contains instructions for determining the location of the computing device.

In various embodiments of the present disclosure, the location of a computing device within an indoor space can be determined with high accuracy.

In various embodiments of the present disclosure, identifiers and their poses can be learned without generating an image for each pose of every identifier by generating template image data.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be explained by those skilled in the art in the technical field to which this disclosure pertains from the description of the claims (hereinafter referred to as 'the person skilled in the art'). can be clearly understood.

Embodiments of the present disclosure will be described with reference to the accompanying drawings described below, in which like reference numerals indicate like elements, but are not limited thereto.

1 is a diagram illustrating an example of a space and an identifier arranged in the space according to an embodiment of the present disclosure.

Figure 2 is a schematic diagram showing a configuration in which an information processing system is connected to communicate with a plurality of user terminals in order to provide an identifier recognition-based location determination service according to an embodiment of the present disclosure.

Figure 3 is a block diagram showing the internal configuration of a user terminal and an information processing system according to an embodiment of the present disclosure.

Figure 4 is a block diagram showing the internal configuration of a processor of an information processing system according to an embodiment of the present disclosure.

FIG. 5 is a diagram illustrating template image data, an identifier pose, and markers arranged in space to generate an identifier pose according to an embodiment of the present disclosure.

FIG. 6 is a diagram illustrating an example of an identifier area and template image data according to an embodiment of the present disclosure.

FIG. 7 is a diagram illustrating an example in which feature data of a detected identifier is converted according to an embodiment of the present disclosure.

FIG. 8 is a diagram illustrating an example in which the first pose of an identifier is corrected and the second pose is determined according to an embodiment of the present disclosure.

Figure 9 is an exemplary diagram showing an artificial neural network model according to an embodiment of the present disclosure.

Figure 10 is a schematic diagram showing the process of learning an artificial neural network model.

Figure 11 is a flowchart showing a method for generating template image data according to an embodiment of the present disclosure.

Figure 12 is a flowchart showing a location determination method based on identifier recognition according to an embodiment of the present disclosure.

Hereinafter, specific details for implementing the present disclosure will be described in detail with reference to the attached drawings. However, in the following description, detailed descriptions of well-known functions or configurations will be omitted if there is a risk of unnecessarily obscuring the gist of the present disclosure.

In the accompanying drawings, identical or corresponding components are given the same reference numerals. Additionally, in the description of the following embodiments, overlapping descriptions of identical or corresponding components may be omitted. However, even if descriptions of components are omitted, it is not intended that such components are not included in any embodiment.

Advantages and features of the disclosed embodiments and methods for achieving them will become clear by referring to the embodiments described below in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the present disclosure is complete and that the present disclosure does not convey the scope of the invention to those skilled in the art. It is provided only for complete information.

Terms used in this specification will be briefly described, and the disclosed embodiments will be described in detail. The terms used in this specification are general terms that are currently widely used as much as possible while considering the function in the present disclosure, but this may vary depending on the intention or precedent of a technician working in the related field, the emergence of new technology, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the relevant invention. Accordingly, the terms used in this disclosure should be defined based on the meaning of the term and the overall content of the present disclosure, rather than simply the name of the term.

In this specification, singular expressions include plural expressions, unless the context clearly specifies the singular. Additionally, plural expressions include singular expressions, unless the context clearly specifies plural expressions. When it is said that a certain part includes a certain element throughout the specification, this does not mean excluding other elements, but may further include other elements, unless specifically stated to the contrary.

Additionally, the term 'module' or 'unit' used in the specification refers to a software or hardware component, and the 'module' or 'unit' performs certain roles. However, 'module' or 'unit' is not limited to software or hardware. A 'module' or 'unit' may be configured to reside on an addressable storage medium and may be configured to run on one or more processors. Thus, as an example, a 'module' or 'part' refers to components such as software components, object-oriented software components, class components and task components, processes, functions and properties. , procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. Components and 'modules' or 'parts' may be combined into smaller components and 'modules' or 'parts' or further components and 'modules' or 'parts'. Could be further separated.

According to an embodiment of the present disclosure, a 'module' or 'unit' may be implemented with a processor and memory. 'Processor' should be interpreted broadly to include general-purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, etc. In some contexts, 'processor' may refer to an application-specific integrated circuit (ASIC), programmable logic device (PLD), field programmable gate array (FPGA), etc. 'Processor' refers to a combination of processing devices, for example, a combination of a DSP and a microprocessor, a combination of a plurality of microprocessors, a combination of one or more microprocessors in combination with a DSP core, or any other such combination of configurations. You may. Additionally, 'memory' should be interpreted broadly to include any electronic component capable of storing electronic information. 'Memory' refers to random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable-programmable read-only memory (EPROM), May also refer to various types of processor-readable media, such as electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage, registers, etc. A memory is said to be in electronic communication with a processor if the processor can read information from and/or write information to the memory. The memory integrated into the processor is in electronic communication with the processor.

In the present disclosure, 'pose' may refer to the orientation and/or position of a specific object located or arranged in any three-dimensional space (including real space and virtual space). 'Pose' may refer to the orientation and/or position of an object based on a specific fixed point in three-dimensional space, and the relative orientation and/or position of the object based on a change point (e.g., the position of the user terminal). /Or it may refer to a location.

In this disclosure, 'computing device' may refer to a user terminal (including a robot) and/or an information processing system. For example, an identifier recognition based location determination method executed by at least one processor of a computing device may be executed by a user terminal, may be executed by an information processing system, may have some steps performed by the user terminal, and other steps may be executed by information processing system. Can be executed by a processing system.

FIG. 1 is a diagram illustrating an example of a space 100 and an identifier 130 arranged in the space according to an embodiment of the present disclosure. An identifier 130 may be placed on the space 100 to determine the location of the user terminal 120 within the space 100. Specifically, the user 110 may capture the identifier 130 placed in the space 100 through the image sensor of the user terminal 120, and the location of the user terminal 120 may be determined based on the captured image. there is. In Figure 1, the user 110 is shown as capturing the identifier 130 through the user terminal 120, but the identifier 130 is not limited to this, and the identifier 130 may be captured by a robot (or a terminal provided in the robot). there is. For example, the robot may be an autonomous robot and may be configured to image random identifiers placed in space at predetermined time periods or distances.

Identifiers 130 may be arranged in the space 100 at predetermined intervals. In one embodiment, the identifiers 130 may be placed at intervals (e.g., 4 m) such that the next identifier can be detected in succession as soon as the previously detected identifier disappears from the image while the user 110 is moving. .

The identifier 130 may include a unique mark for each identifier so that each identifier can be distinguished. The identifier 130 may include a unique ID in text form, but is not limited thereto, and may include any form of identification mark such as an image. In one embodiment, the identifier 130 may include special characters so that the front and back sides of the identifier can be distinguished. For example, the identifier may be displayed in the form of 'A^001', 'Z^999', etc. The identifier 130 may be configured according to a predetermined standard length, format, and/or shape so that rule-based filtering can be applied.

Figure 2 shows a configuration in which the information processing system 230 is connected to enable communication with a plurality of user terminals 210_1, 210_2, 210_3, and 210_4 in order to provide an identifier recognition-based location determination service according to an embodiment of the present disclosure. This is an outline diagram. Information processing system 230 may include system(s) capable of providing identifier recognition-based location determination services. In one embodiment, information processing system 230 includes one or more server devices and/or capable of storing, providing, and executing computer-executable programs (e.g., downloadable applications) and data related to identifier recognition-based location determination services. It may include a database, or one or more distributed computing devices and/or distributed databases based on cloud computing services. For example, the information processing system 230 may include separate systems (eg, servers) for identifier recognition-based location determination services.

Identifier recognition-based location determination services provided by the information processing system 230 may be provided to users through applications installed on each of the plurality of user terminals 210_1, 210_2, 210_3, and 210_4.

A plurality of user terminals 210_1, 210_2, 210_3, and 210_4 may communicate with the information processing system 230 through the network 220. The network 220 may be configured to enable communication between a plurality of user terminals 210_1, 210_2, 210_3, and 210_4 and the information processing system 230. Depending on the installation environment, the network 220 may be, for example, a wired network such as Ethernet, a wired home network (Power Line Communication), a telephone line communication device, and RS-serial communication, a mobile communication network, a wireless LAN (WLAN), It may consist of wireless networks such as Wi-Fi, Bluetooth, and ZigBee, or a combination thereof. The communication method is not limited, and includes communication methods that utilize communication networks that the network 220 may include (e.g., mobile communication networks, wired Internet, wireless Internet, broadcasting networks, satellite networks, etc.), as well as user terminals (210_1, 210_2, 210_3) , 210_4), short-range wireless communication may also be included.

In FIG. 2, a mobile phone terminal 210_1, a tablet terminal 210_2, a PC terminal 210_3, and a robot 210_4 are shown as examples of user terminals, but the user terminal is not limited thereto. The user terminals 210_1, 210_2, 210_3, and 210_4 may be any computing device capable of wired and/or wireless communication and capable of installing and executing an identifier recognition-based location determination application. For example, user terminals include smartphones, mobile phones, navigation devices, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, game consoles, and wearable devices ( It may include wearable devices, IoT (internet of things) devices, VR (virtual reality) devices, AR (augmented reality) devices, etc. In one embodiment, robot 210_4 may be a computing device designed to move within a specific space or a device including such a computing device. For example, the robot 210_4 may be a computing device configured to enable autonomous driving by determining its position in space and a path to move.

In addition, in Figure 2, three user terminals (210_1, 210_2, 210_3, 210_4) are shown communicating with the information processing system 230 through the network 220, but this is not limited to this, and a different number of user terminals It may also be configured to communicate with information processing system 230 via network 220 .

Figure 3 is a block diagram showing the internal configuration of the user terminal 210 and the information processing system 230 according to an embodiment of the present disclosure. The user terminal 210 may refer to any computing device capable of executing an identifier recognition-based location determination application and capable of wired/wireless communication, for example, the mobile phone terminal 210_1 and tablet terminal 210_2 of FIG. 2 ), PC terminal (210_3), etc. As shown, the user terminal 210 may include a memory 312, a processor 314, a communication module 316, and an input/output interface 318. Similarly, information processing system 230 may include memory 332, processor 334, communication module 336, and input/output interface 338. As shown in FIG. 3, the user terminal 210 and the information processing system 230 are configured to communicate information and/or data through the network 220 using respective communication modules 316 and 336. It can be. Additionally, the input/output device 320 may be configured to input information and/or data to the user terminal 210 through the input/output interface 318 or to output information and/or data generated from the user terminal 210.

Memories 312 and 332 may include any non-transitory computer-readable recording medium. According to one embodiment, the memories 312 and 332 are non-permanent mass storage devices such as read only memory (ROM), disk drive, solid state drive (SSD), flash memory, etc. It can be included. As another example, non-perishable mass storage devices such as ROM, SSD, flash memory, disk drive, etc. may be included in the user terminal 210 or the information processing system 230 as a separate persistent storage device that is distinct from memory. Additionally, the memories 312 and 332 may store an operating system and at least one program code (eg, code for an application related to an identifier recognition-based location determination service, etc.).

These software components may be loaded from a computer-readable recording medium separate from the memories 312 and 332. This separate computer-readable recording medium may include a recording medium directly connectable to the user terminal 210 and the information processing system 230, for example, a floppy drive, disk, tape, DVD/CD- It may include computer-readable recording media such as ROM drives and memory cards. As another example, software components may be loaded into the memories 312 and 332 through the communication modules 316 and 336 rather than computer-readable recording media. For example, at least one program is a computer program (e.g., an identifier recognition-based location determination service) that is installed by files provided through the network 220 by developers or a file distribution system that distributes installation files for applications. It may be loaded into the memories 312 and 332 based on the application associated with it, etc.).

The processors 314 and 334 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to the processors 314 and 334 by memories 312 and 332 or communication modules 316 and 336. For example, the processors 314 and 334 may be configured to execute instructions received according to program codes stored in a recording device such as the memory 312 and 332.

The communication modules 316 and 336 may provide a configuration or function for the user terminal 210 and the information processing system 230 to communicate with each other through the network 220, and may provide a configuration or function for the user terminal 210 and/or information processing. The system 230 may provide a configuration or function for communicating with other user terminals or other systems (for example, a separate cloud system, etc.). For example, a request or data generated by the processor 314 of the user terminal 210 according to a program code stored in a recording device such as the memory 312 is transmitted through the network 220 under the control of the communication module 316. It may be delivered to processing system 230. Conversely, a control signal or command provided under the control of the processor 334 of the information processing system 230 is transmitted through the communication module 316 of the user terminal 210 through the communication module 336 and the network 220. It may be received by the user terminal 210.

The input/output interface 318 may be a means for interfacing with the input/output device 320. As an example, input devices may include devices such as cameras, keyboards, microphones, mice, etc., including audio sensors and/or image sensors, and output devices may include devices such as displays, speakers, haptic feedback devices, etc. You can. As another example, the input/output interface 318 may be a means for interfacing with a device that has components or functions for performing input and output, such as a touch screen, integrated into one. In FIG. 3 , the input/output device 320 is shown not to be included in the user terminal 210, but the present invention is not limited to this and may be configured as a single device with the user terminal 210. Additionally, the input/output interface 338 of the information processing system 230 may be connected to the information processing system 230 or means for interfacing with a device (not shown) for input or output that the information processing system 230 may include. It can be. In FIG. 3, the input/ output interfaces 318 and 338 are shown as elements configured separately from the processors 314 and 334, but the present invention is not limited thereto, and the input/ output interfaces 318 and 338 may be configured to be included in the processors 314 and 334. there is.

The user terminal 210 and information processing system 230 may include more components than those in FIG. 3 . However, there is no need to clearly show most prior art components. In one embodiment, the user terminal 210 may be implemented to include at least some of the input/output devices 320 described above. Additionally, the user terminal 210 may further include other components such as a transceiver, a global positioning system (GPS) module, a camera, various sensors, and a database. For example, if the user terminal 210 is a smartphone, it may include components generally included in a smartphone, such as an acceleration sensor, a gyro sensor, a microphone module, a camera module, and various physical devices. Various components such as buttons, buttons using a touch panel, input/output ports, and vibrators for vibration may be implemented to be further included in the user terminal 210.

According to one embodiment, the processor 314 of the user terminal 210 may be configured to operate an application or a web browser application that provides an identifier recognition-based location determination service. At this time, the program code associated with the application may be loaded into the memory 312 of the user terminal 210. While the application is operating, the processor 314 of the user terminal 210 receives information and/or data provided from the input/output device 320 through the input/output interface 318 or the information processing system ( Information and/or data may be received from 230), and the received information and/or data may be processed and stored in the memory 312. Additionally, such information and/or data may be provided to information processing system 230 via communication module 316.

While the application is running, the processor 314 inputs or selects voice data, text, and images through input devices such as a touch screen, keyboard, camera including an audio sensor and/or an image sensor, and a microphone connected to the input/output interface 318. , video, etc. can be received, and the received voice data, text, image and/or video, etc. are stored in the memory 312 or provided to the information processing system 230 through the communication module 316 and the network 220. can do. In one embodiment, processor 314 receives user input that selects a graphical object displayed on a display, entered through an input device, and sends data/requests corresponding to the received user input to network 220 and a communication module. It can be provided to the information processing system 230 through (316).

The processor 314 of the user terminal 210 may transmit information and/or data to the input/output device 320 through the input/output interface 318 and output the information. For example, the processor 314 of the user terminal 210 processes information through the output device 320, such as a display output capable device (e.g., touch screen, display, etc.), an audio output capable device (e.g., speaker), etc. and/or data may be output.

The processor 334 of the information processing system 230 may be configured to manage, process, and/or store information and/or data received from a plurality of user terminals 210 and/or a plurality of external systems. Information and/or data processed by processor 334 may be provided to user terminal 210 through communication module 336 and network 220.

Figure 4 is a block diagram showing the internal configuration of the processor 334 of the information processing system according to an embodiment of the present disclosure. As shown, the processor 334 may include an identifier detection unit 410, a pose determination unit 420, a position determination unit 430, etc.

The identifier detector 410 may receive an image containing an identifier placed in space and detect the identifier therefrom. Specifically, the identifier detection unit 410 may detect an identifier using a machine learning model learned to detect an identifier from a given image. This will be described in detail later in FIGS. 9 and 10.

The pose determination unit 420 may receive an image in which an identifier arranged in space is captured and determine the first pose of the identifier therefrom. Specifically, the pose determination unit 420 determines feature data of the identifier detected from the image in which the identifier is captured, and feature data (e.g., letters constituting the text or From a plurality of frame sets containing (feature points in numbers), a key frame containing feature data with the highest similarity to the feature data of the determined identifier may be selected. Then, the pose determination unit 420 may determine the first pose of the identifier by converting the feature data of the key frame to correspond to the feature data of the detected identifier. In one embodiment, the pose determination unit 420 may select a key frame by applying homography transformation to the feature data of the determined identifier.

In one embodiment, the pose determination unit 420 may determine the second pose of the identifier by correcting the determined first pose based on pattern direction information in space. This will be described in detail later in FIG. 8. In another embodiment, the pose determination unit 420 may determine the second pose by correcting the first pose based on the gravity value measured by the gravity sensor. For example, the pose determination unit 420 may correct the x-axis rotation and z-axis rotation values of the first pose based on the direction in which the identifier is arranged based on the direction of gravity and direction information measured by the gravity sensor.

The position determination unit 430 may determine the position of the computing device in space from the pose determined by the pose determination unit 420. Specifically, if the pose of the identifier determined by the pose determination unit 420 is a pose calculated centered on an image sensor such as a user terminal, the position determination unit 430 determines the inverse matrix of the pose matrix and the pose within the space of the identifier. The pose matrix of the image sensor in space can be calculated through matrix multiplication with the matrix. Thereafter, the position determination unit 430 may calculate at which location the image with the identifier was captured based on the calculated pose matrix of the image sensor.

The internal configuration of the processor 334 shown in FIG. 4 is only an example, and in some embodiments, it may include additional configurations other than the internal configuration shown, and some configurations may be omitted. For example, when some of the above internal configurations are omitted, the processor 314 of the user terminal may be configured to perform the functions of some of the omitted internal configurations. In addition, although the internal configuration of the processor 334 is described in FIG. 4 by dividing it by function, this does not necessarily mean that it is physically divided. The identifier detection unit 410, pose determination unit 420, and position determination unit 430 are described separately, but this is for the purpose of facilitating understanding of the invention and is not limited thereto.

In addition, in Figure 4, the identifier detection unit 410, pose determination unit 420, and position determination unit 430 are shown to be implemented by the processor 334 of the information processing system 230, but the identifier is not limited thereto. At least a portion of the detection unit 410, pose determination unit 420, and position determination unit 430 may be implemented by the processor 314 of the user terminal 210.

FIG. 5 is a diagram illustrating template image data 532, an identifier pose 534, and markers 510 and 520 arranged in space to generate the identifier pose 534 according to an embodiment of the present disclosure. FIG. 6 is a diagram illustrating an example of an identifier area 530 and template image data 532 according to an embodiment of the present disclosure.

Before the identifier is placed in space, one or more markers 510, 520 are placed in advance at a specific location in the space where the identifier is to be placed, and then template image data 532 and/or identifier pose 534 are created using this. can be created. The generated template image data 532 and/or identifier pose 534 can be used to train a machine learning model or artificial neural network model learned to detect the identifier.

The template image data 532 may include identifier text information, information associated with the size, location, and/or area in which the identifier is displayed, etc. Template image data 532 may be created by applying the font of the identifier to be actually attached to the space. Specifically, the template image data 532 may be generated by projecting and synthesizing an identifier onto a predetermined identifier area 530 in real space. In one embodiment, the identifier text image may be synthesized through image processing or rendering.

Identifier pose 534 may refer to a pose within the space of an identifier. The identifier pose 534 may be determined based on the poses of the markers 510 and 520 and the poses of the identifiers based on the markers 510 and 520 .

Specifically, the identifier pose 534 can be determined by Equation 1 below, and the identifier pose 534 can be the basis for determining the location of the computing device along with the pose of the identifier determined from the image in which the identifier is captured. .

(P_s: identifier pose (534), R_sm: relative pose of identifier and marker (510, 520), P_m: pose of marker (510, 520))

The marker may include one or more markers, and as more markers are used, the accuracy or reliability of the identifier pose 534 determined based on them may increase. For example, the marker may include a main marker 510 and an auxiliary marker 520, where the size of the auxiliary marker 520 may be larger than the size of the main marker 510. In one embodiment, template image data 532 and/or identifier pose 534 may be generated based on at least one of primary marker 510 or secondary marker 520 . In another embodiment, the template image data 532 and/or the identifier pose 534 are generated based on the auxiliary marker 520 or the primary marker when the reliability of the primary marker 510 is calculated below a predetermined value. It may be generated based on 510 and auxiliary marker 520. For example, when the main marker 510 moves away from the camera, the reliability of the main marker 510 may be lowered due to pixel error, and the template image data 532 and/or identifier pose 534 may be used by the secondary marker 520. It can be created based on .

FIG. 7 is a diagram illustrating an example in which feature data of a detected identifier is converted according to an embodiment of the present disclosure. After the identifier is detected from the image 710 in which the identifier arranged in space is captured, characteristic data of the identifier may be determined. Characteristic data of an identifier may refer to data associated with specific points of the identifier. For example, data associated with both end points of the number '1' constituting the identifier and the middle protruding point below both end points of '3' may form part of the characteristic data of the identifier.

Thereafter, from a plurality of frame sets containing feature data in each of a plurality of poses of the detected identifier, a key frame 720 containing feature data with the highest similarity to the feature data of the determined identifier will be selected. You can. In one embodiment, a key frame 720 may be selected by applying homography transformation to the feature data of the determined identifier. That is, by projecting the image in 3D space into 2D space and converting the images from two different viewpoints in 3D space, the key frame 720 containing the feature data with the highest similarity to the feature data of the determined identifier is selected. It can be.

Then, the pose of the identifier can be determined by converting the feature data of the key frame to correspond to the feature data of the detected identifier. At this time, the pose of the identifier can be determined through the Perspective-n-Point (PnP) algorithm.

FIG. 8 is a diagram illustrating an example in which the first pose 814 of an identifier is corrected and the second pose 826 is determined according to an embodiment of the present disclosure. A second pose 826 with improved accuracy may be determined by using pattern direction information 822 around the identifiers 812 and 824. In one embodiment, the pattern direction information 822 may be determined by detecting straight lines around the identifiers 812 and 824 that are parallel to the identifiers 812 and 814 in the horizontal or vertical direction using a line segmentation method. Through this configuration, the problem that pose error occurs due to pixel error can be solved as the positions of the identifiers 812 and 824 recognized by the camera become distant.

FIG. 9 is an exemplary diagram showing an artificial neural network model 900 according to an embodiment of the present disclosure, and FIG. 10 is a schematic diagram showing a process in which the artificial neural network model 900 is learned. The artificial neural network model 900 is an example of a machine learning model, and in machine learning technology and cognitive science, it is a statistical learning algorithm implemented based on the structure of a biological neural network or a structure for executing the algorithm.

According to one embodiment, the artificial neural network model 900 has nodes, which are artificial neurons that form a network through the combination of synapses, as in a biological neural network, repeatedly adjusting the weights of synapses to determine the correct input corresponding to a specific input. By learning to reduce the error between the output and the inferred output, a machine learning model with problem-solving capabilities can be represented. For example, the artificial neural network model 900 may include a random probability model, a neural network model, etc. used in artificial intelligence learning methods such as machine learning and deep learning.

According to one embodiment, the above-described identifier detection model may be created in the form of an artificial neural network model 900. For example, the artificial neural network model 900 may receive template image data 1030 associated with an identifier and detect the identifier. At this time, the template image data 1030 may include identifier text information, information related to the size, location, or area where the identifier is displayed, etc.

The artificial neural network model 900 is implemented as a multilayer perceptron (MLP) consisting of multiple layers of nodes and connections between them. The artificial neural network model 900 according to this embodiment can be implemented using one of various artificial neural network model structures including MLP. As shown in FIG. 4, the artificial neural network model 900 includes an input layer 920 that receives an input signal or data 910 from the outside, and an output layer that outputs an output signal or data 950 corresponding to the input data. (940), located between the input layer 920 and the output layer 940, receives a signal from the input layer 920, extracts the characteristics, and transmits it to the output layer 940. n (where n is a positive integer) It consists of hidden layers (930_1 to 930_n). Here, the output layer 940 receives signals from the hidden layers 930_1 to 930_n and outputs them to the outside.

The learning method of the artificial neural network model 900 includes a supervised learning method that learns to optimize problem solving by inputting a teacher signal (correct answer), and an unsupervised learning method that does not require a teacher signal. ) There is a way. According to one embodiment, the computing device may learn the artificial neural network model 900 using template image data 1030.

According to one embodiment, the computing device may directly generate learning data for training the artificial neural network model 900. For example, the computing device can generate a training data set that includes template image data 1030. Then, the computing device can train an artificial neural network model 900 to detect the identifier based on the generated training data set.

According to one embodiment, input variables of the artificial neural network model 900 may include template image data 1030. In this way, when the above-described input variables are input through the input layer 920, the output variables output from the output layer 940 of the artificial neural network model 900 are information associated with the identifier of the template image data 1030 (e.g. , identifier text, location, etc.).

In this way, a plurality of input variables and a plurality of output variables corresponding to the input layer 920 and the output layer 940 of the artificial neural network model 900 are matched, respectively, and the input layer 920, the hidden layers 930_1 to 930_n, and By adjusting the synapse values between nodes included in the output layer 940, learning can be performed so that the correct output corresponding to a specific input can be extracted. Through this learning process, the characteristics hidden in the input variables of the artificial neural network model 900 can be identified, and the nodes of the artificial neural network model 900 can be connected to reduce the error between the output variable calculated based on the input variable and the target output. You can adjust the synapse values (or weights) between them. In addition, the computing device learns an algorithm that receives the template image data 1030 as input, and can learn in a way to minimize the loss of information (i.e., annotation information) associated with the identifier of the template image data 1030. there is.

Using the artificial neural network model 900 learned in this way, information associated with the identifier of each template image data 1030 can be extracted.

Template image data 1030 may be generated based on one or more markers arranged in space as described above with reference to FIG. 5 , and the one or more markers may include a main marker 1010 and an auxiliary marker 1020. In one embodiment, the template image data 532 is generated based on the auxiliary marker 1020 when the reliability of the main marker 1010 is calculated below a predetermined value, or the template image data 532 is generated based on the main marker 1010 and the auxiliary marker 1020. ) can be created based on.

FIG. 11 is a flowchart illustrating a method 1100 for generating template image data according to an embodiment of the present disclosure. The method 1100 may be initiated by a computing device (or at least one processor of the computing device) receiving an image displaying a primary marker and a secondary marker (S1110). Afterwards, the computing device may determine whether the reliability of the main marker is less than or equal to a predetermined value (S1120). In one embodiment, the reliability of the main marker may be calculated based on the distance between the main marker and the location where the image displaying the main marker and the auxiliary marker was captured.

If the reliability of the main marker is greater than a predetermined value, template image data may be generated based on the main marker or based on the main marker and the auxiliary marker (S1130). On the other hand, if the reliability of the main marker is below a predetermined value, a template image may be generated based on the auxiliary marker (S1140).

FIG. 12 is a flowchart illustrating a location determination method 1200 based on identifier recognition according to an embodiment of the present disclosure. In one embodiment, the identifier recognition based location determination method 1200 may be performed by a processor (e.g., at least one processor of a computing device). The identifier recognition-based location determination method 1200 may be initiated by a processor receiving an image containing an identifier arranged in space (S1210).

Afterwards, the processor may detect an identifier from the received image (S1220). In one embodiment, the processor may detect identifiers using a machine learning model trained to detect identifiers from a given image. At this time, the machine learning model may be learned based on template image data associated with the identifier and area information associated with the identifier in the space, and the template image data may be generated based on one or more markers placed in the space. . One or more markers include a main marker and an auxiliary marker whose size is larger than the main marker, and template image data may be generated based on the auxiliary marker when the reliability of the main marker is calculated to be less than a predetermined value.

Afterwards, the processor may determine the first pose of the identifier from the received image (S1230). In one embodiment, the processor determines feature data of the detected identifier, and, among a plurality of frame sets including feature data in each of a plurality of poses of the detected identifier, the feature that has the highest similarity to the feature data of the determined identifier. You can select key frames containing data. Then, the processor may determine the first pose of the identifier by converting the feature data of the key frame to correspond to the feature data of the detected identifier. In this case, the processor can select a key frame by applying homography transformation to the feature data of the determined identifier.

Thereafter, the processor may determine the position of the computing device in space from the determined first pose (S1240). The processor may determine a location of the computing device based on the pose within the space of the determined first pose and identifier. In this case, the pose in the space of the identifier may be calculated based on the third pose of the identifier based on one or more markers arranged in the space and the fourth pose of the one or more markers.

The processor may calibrate the first pose to determine a second pose of the identifier and determine a location of the computing device in space from the second pose of the identifier. In one embodiment, the processor may determine the second pose of the identifier by correcting the first pose based on pattern direction information in space. In another embodiment, the processor may determine the second pose by correcting the first pose based on the gravity value measured by the gravity sensor.

The above-described method may be provided as a computer program stored in a computer-readable recording medium for execution on a computer. The medium may continuously store a computer-executable program, or may temporarily store it for execution or download. In addition, the medium may be a variety of recording or storage means in the form of a single or several pieces of hardware combined. It is not limited to a medium directly connected to a computer system and may be distributed over a network. Examples of media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, And there may be something configured to store program instructions, including ROM, RAM, flash memory, etc. Additionally, examples of other media include recording or storage media managed by app stores that distribute applications, sites or servers that supply or distribute various other software, etc.

The methods, operations, or techniques of this disclosure may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will understand that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented in electronic hardware, computer software, or combinations of both. To clearly illustrate this interchange of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and design requirements imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementations should not be interpreted as causing a departure from the scope of the present disclosure.

In a hardware implementation, the processing units used to perform the techniques may include one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs). ), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, and other electronic units designed to perform the functions described in this disclosure. , a computer, or a combination thereof.

Accordingly, the various illustrative logical blocks, modules, and circuits described in connection with this disclosure may be general-purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or It may be implemented or performed as any combination of those designed to perform the functions described in. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other configuration.

For firmware and/or software implementations, techniques include random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), and PROM ( on computer-readable media such as programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage devices, etc. It can also be implemented with stored instructions. Instructions may be executable by one or more processors and may cause the processor(s) to perform certain aspects of the functionality described in this disclosure.

Although the above-described embodiments have been described as utilizing aspects of the presently disclosed subject matter in one or more standalone computer systems, the disclosure is not limited thereto and may also be implemented in conjunction with any computing environment, such as a network or distributed computing environment. . Furthermore, aspects of the subject matter of this disclosure may be implemented in multiple processing chips or devices, and storage may be similarly effected across the multiple devices. These devices may include PCs, network servers, and portable devices.

Although the present disclosure has been described in relation to some embodiments in this specification, various modifications and changes may be made without departing from the scope of the present disclosure as can be understood by a person skilled in the art to which the invention pertains. Additionally, such modifications and changes should be considered to fall within the scope of the claims appended hereto.

Claims (20)

1. An identifier recognition-based location determination method executed by at least one processor of a computing device, comprising:

   Receiving an image with an identifier arranged in space;

   detecting the identifier from the received image;

   determining a first pose of the identifier from the received image; and

   determining a position of the computing device in space from the determined first pose.

   Including, an identifier recognition based location determination method.
2. According to paragraph 1,

   Determining the location of the computing device includes:

   determining a second pose of the identifier by correcting the first pose; and

   determining a location of the computing device in space from a second pose of the identifier,

   Identifier recognition based location determination method.
3. According to paragraph 2,

   The step of determining the second pose of the identifier by correcting the first pose includes:

   Determining a second pose of the identifier by correcting the first pose based on pattern direction information in the space,

   Identifier recognition based location determination method.
4. According to paragraph 2,

   The step of determining the second pose of the identifier by correcting the first pose includes:

   Determining the second pose by correcting the first pose based on a gravity value measured by a gravity sensor,

   Identifier recognition based location determination method.
5. According to paragraph 1,

   The step of detecting the identifier is,

   Detecting the identifier using a machine learning model trained to detect the identifier from a given image,

   Identifier recognition based location determination method.
6. According to clause 5,

   The machine learning model is,

   A location determination method based on identifier recognition, wherein the method is learned based on template image data associated with the identifier.
7. According to clause 6,

   The template image data is generated based on one or more markers arranged in the space.
8. In clause 7,

   The one or more markers are:

   Comprising a main marker and a secondary marker larger in size than the main marker,

   The template image data is generated based on the auxiliary marker when the reliability of the main marker is calculated below a predetermined value.
9. According to paragraph 1,

   The step of determining the first pose of the identifier is:

   determining characteristic data of the detected identifier;

   selecting a key frame containing feature data with the highest degree of similarity to feature data of the determined identifier from a plurality of frame sets including feature data in each of a plurality of poses of the detected identifier; and

   A method for determining a position based on identifier recognition, comprising determining a first pose of the identifier by converting the feature data of the key frame to correspond to feature data of the detected identifier.
10. According to clause 9,

    The step of selecting the key frame is,

    A method for determining position based on identifier recognition, comprising the step of selecting the key frame by applying homography transformation to feature data of the determined identifier.
11. According to paragraph 1,

    Determining the location of the computing device includes:

    Determining a position of the computing device based on the determined first pose and the pose in the space of the identifier.
12. According to clause 11,

    The pose of the identifier within the space is:

    A positioning method based on identifier recognition, calculated based on a third pose of the identifier based on one or more markers arranged in the space and a fourth pose of the one or more markers.
13. A computer-readable non-transitory recording medium recording instructions for executing the method according to claim 1 on a computer.
14. In a computing device,

    communication module;

    Memory; and

    At least one processor connected to the memory and configured to execute at least one computer-readable program included in the memory

    Including,

    The at least one program is,

    Receives an image with an identifier placed in space,

    detecting the identifier from the received image,

    Determine a first pose of the identifier from the received image,

    and instructions for determining a position of the computing device in space from the determined first pose.
15. According to clause 14,

    Determining the location of the computing device includes:

    Computing device comprising calibrating the first pose to determine a second pose of the identifier and determining a location of the computing device in space from the second pose of the identifier.
16. According to clause 14,

    Detecting the identifier is:

    A computing device comprising detecting the identifier using a machine learning model trained to detect the identifier from a given image.
17. According to clause 14,

    Determining the first pose of the identifier includes:

    Determining feature data of the detected identifier, including feature data having the highest degree of similarity with feature data of the determined identifier among a plurality of frame sets including feature data in each of a plurality of poses of the detected identifier. Computing device comprising determining a first pose of the identifier by selecting a key frame and transforming feature data of the key frame to correspond to feature data of the detected identifier.
18. According to clause 17,

    Selecting the key frame involves:

    Computing device further comprising selecting the key frame by applying homography transformation to feature data of the determined identifier.
19. According to clause 14,

    Determining the location of the computing device includes:

    Computing device comprising calculating a location of the computing device based on the determined first pose and the pose in the space of the identifier.
20. According to clause 19,

    The pose of the identifier within the space is:

    Computing device calculated based on a third pose of the identifier based on one or more markers disposed in the space and a fourth pose of the one or more markers.

Images