KR102272650B1 - System for providing virtual reality based interior service using three-dimentional space reconstruction - Google Patents

Abstract

The present invention relates to a system for providing an interior service using three-dimensional space reconstruction based on a virtual reality, which comprises: a user terminal for selecting, arranging, and outputting at least one interior object in a three-dimensional space in which a target space is converted into digital data after photographing an actual measurement drawing of the target space or receiving an actual measurement numerical value of the target space; and an interior service providing server including a storage unit for collecting the interior object, and databasing the same, a generation unit for generating the three-dimensional space using the actual measurement drawing or actual measurement numerical value photographed or input by the user terminal, and a synthesis unit for synthesizing the interior object selected and arranged on the three-dimensional space, and then outputting the same to the user terminal when the interior object is selected and arranged in the user terminal. Accordingly, direct construction can be assisted by being in contact with each technician.

Description

SYSTEM FOR PROVIDING VIRTUAL REALITY BASED INTERIOR SERVICE USING THREE-DIMENTIONAL SPACE RECONSTRUCTION

The present invention relates to a system for providing interior services using virtual reality-based three-dimensional space reconstruction. After configuring a target space in a three-dimensional space, when arranging and synthesizing an interior object, a platform that can add a sense of reality by considering illumination and sunlight to provide.

Recently, Microsoft, along with consulting firm The Future Laboratory, published a job outlook report according to new technologies and industry changes in the Internet of Things (IoT), virtual reality (VR), and artificial intelligence. This report presents the jobs that are expected to appear, and among them, Virtual Habitat Designer is included as a new job. This prediction is based on the fact that virtual reality headsets are sold and the infrastructure is built, and new companies are emerging in the industry, such as 3D modeling and digital compositing. The most basic type of work required in this future job group is a system that allows users to arrange and communicate as desired in a virtual space without restrictions due to the actual geographic location of users, such as furniture, which are essential to human living. It will be carried out on a technical basis.

At this time, a method of providing an interior service based on VR has been researched and developed. In this regard, in Korea Patent Publication No. 2020-0031312 (published on March 24, 2020), which is a prior art, the user directly In order to design and experience the optimal 3D design space in advance in advance, and at the same time to receive the estimate calculated according to the interior design, register material and construction information for each interior object, and use the user terminal to register the material and construction information. When an image of the space-time is acquired, dimensional information is calculated based on the acquired image, a two-dimensional plan is produced, and the height is applied to convert it into a three-dimensional view, and when the material and object selected in the user terminal are selected A configuration is disclosed in which VR information to which interior information is applied is expressed on a three-dimensional three-dimensional view, and a standard construction price and estimate are calculated and transmitted to a user terminal.

However, due to the recent increase in interest in self-interiors, the domestic market for home furnishings, which are products that decorate houses such as interior accessories and furniture, has also rapidly increased. occupies a significant portion, and furniture arrangement for efficient space utilization is not always simple, and it is often necessary to seek advice from experts or people around you. When faced with such difficulties, most people are choosing to share information, opinions, and advice through personal SNS, or to call experts from interior specialist companies for advice. However, if a space is represented by a 2D medium such as a photo or video, it is difficult to share accurate and detailed advice about the space because the actual feeling and situation of the space do not appear. In addition, when seeking advice from an expert, both the time and physical inconvenience of having to visit the space by the expert exist. Therefore, research and development of a platform that can give a sense of reality while trying to construct a house in three dimensions before decorating a house or interior is required.

In one embodiment of the present invention, a three-dimensional space is created using an actual measurement drawing or measurement value of a target space, and the result obtained by selecting and arranging at least one interior object in the three-dimensional space is provided as virtual reality. Even before construction, it is not a simple 2D or virtual reality that does not consider the direction or influence of illuminance or light, but reflects the direction of light, sunlight, and occlusion in 3D space to synthesize interior objects to create a sense of reality and realism. By applying a theme that can be expressed close to and recommended by concept or that can imitate the interior of a broadcast or drama, it can form a space and help decision-making, and by providing an estimate in a reverse auction method to enable self-construction, each technician It is possible to provide a method of providing an interior service using virtual reality-based 3D space reconstruction, which helps them to directly construct by contacting the company. However, the technical task to be achieved by the present embodiment is not limited to the technical task as described above, and other technical tasks may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention provides a three-dimensional space in which the target space is converted into digital data after taking an actual measurement drawing of the target space or receiving actual measurement values of the target space. Using a user terminal that selects and arranges at least one type of interior object and outputs it, a storage unit that collects at least one type of interior object and turns it into a database, and a measured drawing or measured value captured or input from the user terminal 3 a generating unit for generating a dimensional space, and a synthesizing unit for synthesizing at least one interior object selected and arranged in a three-dimensional space and outputting it from the user terminal when at least one interior object is selected and placed in the user terminal and an interior service providing server.

According to any one of the above-described problem solving means of the present invention, a three-dimensional space is created using an actual measurement drawing or measurement value of the target space, and the result obtained by selecting and arranging at least one interior object in the three-dimensional space is synthesized. Even before interior construction by providing virtual reality, it is not a simple 2D or virtual reality that does not take into account the direction or influence of illuminance or light, but to synthesize interior objects by reflecting the direction of light, amount of sunlight and occlusion in 3D space. Therefore, it is possible to express a sense of reality and reality close to reality, and by applying a theme that can be recommended by concept or that can imitate the interior of a broadcast or drama, it can form a space and help decision-making. By providing a quote, you can contact each technician and help them to do the construction directly.

1 is a view for explaining an interior service providing system using virtual reality-based 3D space reconstruction according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating an interior service providing server included in the system of FIG. 1 .
3 and 4 are diagrams for explaining an embodiment in which an interior service using virtual reality-based 3D space reconstruction is implemented according to an embodiment of the present invention.
5 is an operation flowchart illustrating a method of providing an interior service using virtual reality-based 3D space reconstruction according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . Also, when a part "includes" a component, it means that other components may be further included, rather than excluding other components, unless otherwise stated, and one or more other features However, it is to be understood that the existence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded in advance.

The terms "about", "substantially", etc. to the extent used throughout the specification are used in a sense at or close to the numerical value when the manufacturing and material tolerances inherent in the stated meaning are presented, and serve to enhance the understanding of the invention. To help, precise or absolute figures are used to prevent unfair use by unscrupulous infringers of the stated disclosure. As used throughout the specification of the present invention, the term “step for (to)” or “step for” does not mean “step for”.

In this specification, a "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware. Meanwhile, '~ unit' is not limited to software or hardware, and '~ unit' may be configured to be in an addressable storage medium or may be configured to reproduce one or more processors. Thus, as an example, '~' refers to components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. The functions provided in the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

In this specification, some of the operations or functions described as being performed by the terminal, apparatus, or device may be performed instead of in a server connected to the terminal, apparatus, or device. Similarly, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the terminal's unique number or personal identification information, which is the identification data of the terminal. can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining an interior service providing system using virtual reality-based 3D space reconstruction according to an embodiment of the present invention. Referring to FIG. 1 , an interior service providing system 1 using virtual reality-based 3D space reconstruction includes at least one user terminal 100 , an interior service providing server 300 , and at least one affiliated store terminal 400 . may include However, since the interior service providing system 1 using the virtual reality-based 3D space reconstruction of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1 .

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1 , at least one user terminal 100 may be connected to the interior service providing server 300 through the network 200 . In addition, the interior service providing server 300 may be connected to at least one user terminal 100 and at least one affiliate store terminal 400 through the network 200 . In addition, the at least one affiliated store terminal 400 may be connected to the interior service providing server 300 through the network 200 .

Here, the network refers to a connection structure in which information exchange is possible between each node, such as a plurality of terminals and servers, and an example of such a network includes a local area network (LAN), a wide area network (WAN: Wide Area Network), the Internet (WWW: World Wide Web), wired and wireless data communication networks, telephone networks, wired and wireless television networks, and the like. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi (Wi-Fi) , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC ( Near-Field Communication) networks, satellite broadcast networks, analog broadcast networks, Digital Multimedia Broadcasting (DMB) networks, and the like are included, but are not limited thereto.

In the following, the term at least one is defined as a term including the singular and the plural, and even if at least one term does not exist, each element may exist in the singular or plural, and may mean the singular or plural. it will be self-evident In addition, that each component is provided in singular or plural may be changed according to embodiments.

At least one user terminal 100 is a three-dimensional space by photographing an actual measurement drawing of the target space using a web page, an app page, a program, or an application related to an interior service using a virtual reality-based 3-dimensional space reconstruction, or by inputting an actual measurement value. It may be a terminal that generates In addition, the user terminal 100 may be a terminal that outputs a three-dimensional space reflecting insolation and illuminance using the separation distance and altitude from the surrounding buildings by inputting an address, and the altitude of the sun according to the season. Also, the user terminal 100 may be a terminal that selects at least one type of interior object and then arranges it in a three-dimensional space. In addition, the user terminal 100 may be a terminal that receives an interior object recommendation from the interior service providing server 300 according to a concept or an input size, and when clicking purchase after placing it, at least one affiliated store terminal ( 400 ), or it may be a terminal that purchases and pays on the interior service providing server 300 to proceed to the affiliated store terminal 400 via the interior service providing server 300 .

Here, the at least one user terminal 100 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation device, a laptop computer equipped with a web browser, a desktop computer, and a laptop computer. In this case, the at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100, for example, as a wireless communication device that guarantees portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smart phone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

The interior service providing server 300 may be a server that provides an interior service web page, an app page, a program, or an application using virtual reality-based 3D space reconstruction. And, the interior service providing server 300 receives at least one interior object detailed specification information, virtual reality content, augmented reality content, price information, affiliate store (seller) information, etc. from at least one affiliate store terminal 400, or It may be a server that collects with a web crawler and stores it in conjunction with it. Also, the interior service providing server 300 may be a server that collects changes in the altitude and azimuth of the sun through a public API by using an address as a query. At this time, the public API can be obtained through the KASI Korea Astronomy and Space Science Institute's Astronomy and Space Knowledge Information (https://astro.kasi.re.kr/life/pageView/10), but is not limited thereto. In addition, the interior service providing server 300 may be a server that arranges at least one interior object through augmented reality as well as virtual reality. In addition, the interior service providing server 300 may be a server capable of mapping and storing concept tags to each interior object for each concept, and recommending interior objects for each concept when a concept is designated by the user terminal 100 . In addition, the interior service providing server 300, in order to proceed with construction with the interior object selected and arranged in the user terminal 100, the estimate from at least one affiliated store terminal 400 in a reverse auction method to the user terminal 100 It may be a server that allows sending. In addition, the interior service providing server 300 may be a server for sharing a review on at least one affiliated store terminal 400 and uploading a review or rating.

Here, the interior service providing server 300 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, a navigation device, a laptop computer equipped with a web browser, a desktop computer, and a laptop computer.

The at least one affiliated store terminal 400 may be a doctor's terminal using a web page, an app page, a program, or an application related to an interior service using virtual reality-based 3D space reconstruction. In addition, the at least one affiliated store terminal 400 may be a terminal that transmits data on at least one interior object to be sold or constructed by the interior service providing server 300 to the interior service providing server 300 . In addition, the affiliated store terminal 400 sends a quotation when a quotation request is received from the user terminal 100 via the interior service provision server 300 , and a construction request or order is received from the interior service provision server 300 . In this case, it may be a terminal that proceeds the process to implement it.

Here, the at least one affiliated store terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a navigation device, a laptop computer equipped with a web browser, a desktop computer, and a laptop computer. In this case, the at least one affiliated store terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. The at least one affiliated store terminal 400 is, for example, a wireless communication device that guarantees portability and mobility, including navigation, Personal Communication System (PCS), Global System for Mobile communications (GSM), Personal Digital Cellular (PDC), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smart phone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

2 is a block diagram for explaining an interior service providing server included in the system of FIG. 1, and FIGS. 3 and 4 are interior services using virtual reality-based 3D space reconstruction according to an embodiment of the present invention. It is a diagram for explaining an embodiment.

Referring to FIG. 2 , the interior service providing server 300 includes a storage unit 310 , a generation unit 311 , a synthesis unit 313 , an illuminance management unit 320 , a drawing collection unit 330 , and a layout change unit ( 340 ), a comparison unit 350 , a recommendation unit 360 , a follow-up unit 370 , an estimate providing unit 380 , and a review management unit 390 .

The interior service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one user terminal 100 and at least one affiliated store terminal 400 is a virtual reality-based 3D When transmitting an interior service application, a program, an app page, a web page, etc. using space reconstruction, at least one user terminal 100 and at least one affiliated store terminal 400, the interior using virtual reality-based 3D space reconstruction You can install or open service applications, programs, app pages, web pages, etc. In addition, a service program may be driven in at least one user terminal 100 and at least one affiliate store terminal 400 by using a script executed in a web browser. Here, the web browser is a program that enables the use of a web (WWW: World Wide Web) service, and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, and the like. In addition, the application means an application on the terminal, for example, includes an app (App) executed in a mobile terminal (smartphone).

Referring to FIG. 2 , the storage unit 310 may collect at least one type of interior object and form it into a database. In this case, the at least one affiliated store terminal 400 may upload product data including at least one type of interior object, a purchase site, a price, a size, a product identification code, a color, and an option. If the affiliated stores are not sufficiently gathered or the platform is initially started, a database can be built by collecting interior objects uploaded to various brands or portal sites using a web crawler and turning them into VR or AR content. When a product identification code is assigned to each interior object, it can be used as it is, or a product identification code can be assigned by creating its own barcode or QR code system. In this case, the VR or AR content must be reflected as an attribute value to reflect the actual size, so that even if the user terminal 100 is driven in virtual reality or augmented reality afterward, it can be expressed according to the accumulation. Accordingly, it is possible to build a database to reflect the measured values when generating each content.

At this time, it is not difficult to synthesize the interior object, which is a virtual object, because VR already knows information about the three-dimensional space, but AR is another problem. Also, in the case of VR, no matter how realistically it is decorated, human perception of a virtual space exists, and since it is actually a virtual space, a gap may occur with reality. This may cause a sense of disparity due to the absence of shadows or contrast, which will be described later. In the case of home furnishing and interior work, effective simulation can be performed only when various props such as wallpaper, molding, and furniture used in the real living space are applied and compared. Augmented reality (AR) may be more suitable.

However, in the case of simulation systems using augmented reality, information for object expression according to the user's point of view, such as depth information on real space in a two-dimensional image, is not taken into consideration, so when a virtual 3D object is augmented, the mismatch of the real space occurs. In some cases, simulation for accurate home furnishings and interiors is difficult. Therefore, in an embodiment of the present invention, a virtual object for performing home furnishing is augmented to perform simulation by deriving feature points for the boundary region of an indoor space from a two-dimensional image and determining an object to be recognized. do.

Object recognition technology in augmented reality is a technology for tracking and detecting an object of interest in a two-dimensional camera image. To this end, an object tracking technology that detects changes in the motion and state of the object of interest by tracking the object using various information such as the color, size, edge, and feature point of the object in a two-dimensional image is required. A marker-based detection method, a texture-based method, an edge-based method, and a template-based method are classified according to the shape of a feature point for detecting an object. Since the marker-based method detects an object based on a marker composed of black and white, it is used because it enables efficient object tracking even with simple image processing, but it is not used in the field of providing realistic content due to the problem of the visual immersion of the marker. is not Accordingly, based on the reference texture, using natural feature points such as edges, the 3D model is projected on the current frame using the camera pose (R, t), and the change of the pose estimated in the previous frame is tracked through Equation 1 below. Thus, it is possible to use techniques to augment objects.

The edge-based detection technique performs an efficient inspection because it estimates the linearity strength of the edge and the vector change in the case of a target target where it is difficult to extract a texture. However, since it is necessary to estimate the posture of the edge, it detects the object and creates a virtual There is a problem that the processing time calculated for matching objects becomes long. In order to reduce the calculation processing time, a template-based method of tracing a feature point in the same manner as in Equation 2 below according to the degree of pixel change using a Gaussian differential value in an input image may be used.

In an embodiment of the present invention, an object may be augmented by tracking feature points in real space and calculating a camera pose of a tracking target based on real spatial information. Therefore, it is possible to use a method of augmenting an object by estimating a depth perspective of an indoor space in a camera image through an edge-based object tracking technology and modifying the geometry information of a recognition target.

<Histogram smoothing and image binarization>

When the brightness of the light is changed, the brightness value in the RGB image has a large difference in the same color. If the change in brightness is large, the threshold value is modulated. If the image is binarized, noise in the image is generated, which affects the detection of the object. Therefore, the distribution of the histogram is reconstructed through Equation 3 below by dispersing the unbiased histogram by performing a histogram equalization technique.

When the histogram is uniformly distributed through Equation 3, it is distributed as beekeeping based on a specific random value to form a population group. In this bimodally distributed histogram, the pixel integral is calculated through Equation 4 below, the calculated pixel integral is applied to the image, and the average value for the region with a high threshold distribution is derived, and the threshold is set through Equation 5. can

<Extracting spatial coordinates>

In real space, since there is a lighting area and a space where the reflection of lighting occurs, noise that is modulated in the binarized image is generated, causing a problem in that the correct spatial coordinate points are removed. Therefore, by applying the Contours method for tracking the outer boundary line, the outline of the area higher than the threshold is detected to determine the noise level of the outer area. When a region higher than the threshold is detected by applying the contours method, it is determined that the area where the feature point is extracted is up to the space where the noise is generated. Therefore, in order to remove only the generated spatial noise when noise occurs, only two histogram regions with high deviations from the block regions Tl and Tb of the histogram derived through the adaptive threshold are extracted and the median value is calculated.

Through the calculated intermediate value, the input image is converted to an arbitrary gray level T, and the histogram is divided into two clusters C1 and C2 based on T. The image is re-binarized by generating a threshold by applying the segmented C1 and C2. If the black-and-white area is separately extracted from the re-binarized image, a noise-free area is extracted. The outline region is detected by applying the Laplacian algorithm to the denoised binarized image. The Rafflesian technique does not connect the outline area with a single line, but connects multiple outline areas according to the pixel value of the object to show the difference in shading. Feature coordinates for the indoor space are derived using the CAMShift algorithm that extracts feature points by finding locations that change according to Hue value distribution in the detected outline area. At this time, feature points with strong corner precision are derived by excluding the feature degree for the noise region.

<Object candidate area setting>

In order to detect a real object, pattern analysis is performed by comparing feature points based on reference data. However, when pattern analysis is performed on the feature points for the entire image, erroneous detection occurs due to the feature points having the same vector direction. Accordingly, straight segments are extracted by applying an edge tracing algorithm from the edge detection image detected through the Laplacian algorithm. By connecting the extracted segments to create a region, the labeling technique that matches the same number (Label) of adjacent pixels in the region is applied to group each region in the image.

When grouping is performed for each region, a plurality of feature candidate regions are extracted. Since the object to be recognized can be classified according to the edge features forming the outline, a candidate area having a similar outline pattern among the feature candidate areas extracted by applying the template matching technique is set as the object candidate area. When the object candidate area is set, in order to detect the pattern of the object, four lines with high linear strength are extracted based on the information of the edge pixels to extract the edge area.

One point P1 is selected among the four extracted edge points and the edge point P2 located farthest from that point is extracted according to the three square theorem (Pythagorean Theorem). Then, from the extracted point P2, the farthest edge point P1 is searched for, and the two extracted points P1, P2? Extract the farthest edge point P3. When the three points P1, P2, and P3 are extracted, a point P4 having the maximum area of the rectangle is extracted using Equation 6 below.

<Feature vector extraction and object augmentation>

A vector according to the edge intensity is extracted for each pixel region group from the detected object candidate region, and vector information on the detected C edge classes is sorted and listed.

A vector matrix is generated for the removed vectors, and a feature vector group having eigenvalues is generated by linearly transforming the generated vector matrix to extract a feature point for an object target candidate region.

When the feature point of the object is detected, pattern recognition is performed on the feature area, and the corner point area is extracted from the feature points where the performed pattern exists. When the corner point area is extracted, the center of gravity coordinates are created by connecting the two points with the maximum distance between the two points. Camera Calibration is performed on the generated coordinates, as shown in Equation 9 below.

In the above equation, t is the movement vector of the camera, r is each column vector of the rotation matrix R of the camera, and the variable K is the projection transformation matrix, which is defined as the following equation. Here, the positions Cx and Cy of the principal point are calculated through Equations 10 to 12 below.

Based on the projection-transformed coordinates, it is applied to the warping matrix on the virtual object in the virtual space and synthesized in the output image.

The generator 311 may generate a three-dimensional space by using an actual measurement drawing or measurement values captured or input by the user terminal 100 . In the case of an actual measurement drawing, the size of each room, living room, kitchen, or bathroom is displayed horizontally and vertically, providing a basis for composing a two-dimensional plane. Here, if only H, ie, height, is provided, a three-dimensional plane can be simply configured. Of course, when H is a different space, it is necessary to provide all of them and designate the location, but since most residential spaces have flat ceilings, this will be described as a reference. In the case of most apartments, all floor plans are publicly available, so when building the initial database, all of them can be collected with a web crawler. When all are collected, if the user inputs only the area, apartment name, number, etc., the floor plan corresponding to the corresponding building, floor plan or type, as well as a 3D space can be provided directly.

When at least one interior object is selected and arranged in the user terminal 100 , the synthesis unit 313 synthesizes at least one interior object selected and arranged in a three-dimensional space and then outputs it from the user terminal 100 . let it do The user terminal 100, after photographing an actual measurement drawing of the target space or receiving actual measurement values of the target space, selects and arranges at least one type of interior object in a three-dimensional space in which the target space is converted into digital data. can be printed out.

In the case of arranging augmented reality content, it is possible to measure the exact number of placement space through the proportional expression between the height of a real person and the height on the camera screen, and link the site by using web crawling. In addition, it is possible to provide a purchasing method that reduces the time and hassle at the same time while recommending furniture through a numerical value measured in a proportional manner. Simply, after the user enters their key, point the camera towards the space where you want to place the furniture. After entering the key, the user matches the human-shaped sample floating on the camera and takes a picture in the space where the furniture will be placed. The user selects both endpoints of the space where the user wants to place the furniture on the photo. When two points are taken, the proportional expression between the height of the user who first entered it and the height of the person captured by the camera is obtained. The width and height of the layout space are obtained through the distance between the two points, and the actual width and height of the layout space can be obtained through the proportional expression between the actual user's height and the user's height on the screen. When the actual number is measured, the user can select a furniture item to purchase and use web crawling to be connected to a furniture purchase site that matches the measured value.

In order to calculate the proportional expression between the actual size and the size on the screen, the width and height of the furniture on the screen are obtained through the endpoint (x1,y1) and the other endpoint (x2,y2) on the picture taken with the camera. The width of the furniture on the screen is x2-x1, and the height of the furniture on the screen is y2-y1. In order to find the actual width and height of the furniture, you need to use the proportional expression between the height entered by the first user and the height on the screen. For example, if the user's height is input as 160cm and the height on the screen is 1000px, the ratio between the actual size and the size on the screen is 4cm : 25px. Therefore, the actual width of the furniture can be obtained through the proportional formula '4cm : 25px = (Actual furniture width)cm : (x2-x1)px', and the actual height of the furniture is '4cm :25px = (Actual furniture height)cm : (y2-) y1)px' can be obtained through the proportional expression.

Web crawling refers to the act of selecting and collecting only the necessary parts of the numerous data on the web page. Data collection is possible through HTML documents in web browsers such as Internet Explorer and Chrome. To parse a web page, you can use the Jsoup library, which is an HTML parser based on Java, to trace the DOM structure and extract data. DOM means Document Object Model, and jsoup receives web pages at once in the DOM method, puts them in memory, and processes them in a tree format. When the user selects a furniture item, a list of purchase sites for the searched item may be listed based on the value of the actual space obtained through the proportional expression between the actual user's height and the user's key on the screen. In addition, a list of recommended products of the selected furniture item may be displayed.

This is a .select() method that parses the document from the selected furniture purchase site URL, traces the DOM structure, finds tags with title, price, furniture image, and the actual purchase site URL information, and filters out only the found tags. was used to extract data. In this way, the title, price, and picture of the furniture are displayed to the user, and if the user clicks the URL of the site, the user can connect to the site and purchase the furniture. You can save time without having to go through multiple processes because it measures the number that fits the user's actual living space and connects you to the site that suits you. In addition, it is possible to increase the economic efficiency of users and improve their quality of life by reducing the risk of purchasing furniture that does not fit the figures.

The illuminance management unit 320, when the user terminal 100 inputs the direction of the target space to any one of east, west, north, and south, and inputs an address where the target space is located, consider the height of the surrounding buildings and the height of the target space for each time zone. It can be set to reflect the illuminance in the 3D space. Techniques for analyzing the amount of sunlight include the Waldram (solar trajectory) analysis technique and the Solar View analysis technique. Recently, the quantitative analysis of sunlight has become possible with the development of computer simulator technology. In particular, a program that can calculate the sunlight exposure area has been developed so that it can be quantitatively calculated during solar analysis using the Solar View analysis technique. By analyzing the sunlight by season and time of day, it is possible to analyze the sunlight according to the distance, height, and floor height of adjacent buildings in the downtown area. The amount of sunlight can be accurately simulated.

In addition, using LiDAR data and numerical maps, three-dimensional urban space can be accurately expressed through simulation, and the solar rights of each generation can be quantitatively analyzed by dividing the total amount of sunlight and continuous hours of sunlight by using the altitude and azimuth of the sun. . In addition, using photogrammetry and laser surveying techniques, 3D image models of topography and features can be constructed and used for solar field analysis. In addition, it is also possible to analyze and reflect changes in daylight hours due to terrain using a Hemispherical Viewshed (HV) algorithm.

At this time, it is true that the virtual reality or augmented reality interior objects have a reduced sense of presence because interaction with the real world is missing. Accordingly, a method of increasing the realism of a virtual object (interior object) by calculating the direction of the light source by estimating the position of the light source using the shadow and creating a shadow in a general space rather than within a defined object boundary may be further used. .

<Extraction of the bottom surface>

In order to track the light source in real time from the input image, the floor on which the shadow is to be generated is first separated. In one embodiment of the present invention, the location of the floor is separated by using the wall and the floor having different colors. The extracted floor surface is created as a plane with the same height as the marker through 3D Pose Estimation, and there is no need to separately create a ghost object.

<Shadow Separation>

To track the light source from the shadow, we can first separate the shadow. The input image is converted from the RGB region to the light-sensitive HSV region, and Penumbra and Umbra images can be obtained using the boundary value. By separating the generated shadows from the extracted shadows, it is possible to estimate the light source corresponding to each.

<Estimation of light source location>

The generated shadow separated from the shadow separation is created on the floor and the 3D position is estimated based on the uv value of the floor. The three-dimensional coordinates are estimated based on the information of the modeled cuboid, and the point of intersection of vectors connecting the corner of the shadow and the corner of the cuboid can be referred to as the position of the light source.

<Create virtual shadow>

The result of estimating the light source and using it to create a shadow can be reflected in the interior object. The shadow generation can use a GPU-based ray tracing method, which is a method of generating a physically-based realistic image. It is possible to estimate the position of the light source through the input image and to create a realistic shadow through the ray tracing method using simple light source information using GPU. can be raised further. In consideration of the above-described azimuth and altitude of the sun, and the number of layers in the target space of the user, the above-described method may be applied based on the direction in which sunlight enters with time and the position and size of the window. In this case, it is possible to see in the virtual space when an interior object is placed in a state where the light is not turned on, and in this case, the direction of the window is set as the direction of the light source.

The drawing collection unit 330 may collect drawings for each floor plan of at least one type of aggregate building, map the drawings to an area, a name of the aggregate structure, and a floor plan, and store it. The above-mentioned web crawler and DOM can also be used when collecting drawings.

The arrangement change unit 340, when changing the arrangement of the interior object already provided in the user terminal 100, identifies the interior object photographed in the user terminal 100 or input the product identification code, and then creates a list of holdings can do.

The comparison unit 350, when the user terminal 100 inputs the size or option of an interior object desired to be arranged, extracts at least one interior object satisfying the size or option and transmits it to the user terminal 100, It is possible to compare detailed specifications of at least one interior object through a comparison table for each preset item.

The recommendation unit 360 attaches and tags at least one kind of concept tag to at least one interior object, and when any one concept tag is selected in the user terminal 100 , at least one concept tag to which the selected concept tag is attached. It may be recommended to check the interior object in the user terminal 100 .

The following unit 370 extracts product meta information from metadata of at least one type of content in order to collect information on at least one interior accessory included in at least one type of content, and a user When any one frame is selected from at least one frame constituting the content in the terminal 100 , product meta information synchronized with the selected frame may be extracted and transmitted to the user terminal 100 . Recently, by adding product meta information to metadata, the number of content service providers that service IPTV or VOD has increased, making it easier to use the information. When collecting this product meta information, frame numbers are synchronized and mapped together. By extracting this, it is easy to know what props or materials were used in the scene. However, since the structure or size of the house in the TV drama cannot be the same as the structure or size of the user's house, through the above method, consider the structure, size, and floor height of the room or living room to find more products with a similar atmosphere or option. may give

When at least one type of interior object is selected in the user terminal 100, the quotation providing unit 380 collects a quotation in a reverse auction method based on spatial data of the three-dimensional space and the selected at least one interior object, and the user It can be transmitted to the terminal 100 .

The post management unit 390, after arranging at least one type of interior object in the three-dimensional space in the user terminal 100, when the interior proceeds, the user terminal 100 after the interior shooting data of the target space It can be collected and shared as before and after photos, and reviews and ratings for reviews of interior decoration can be collected and converted into a database. If the interior was done, it could be a case of purchasing accessories, or it could be a case of carrying out construction such as remodeling. To this end, the at least one affiliated store terminal 400 may start a transportation process when an order form is received from the user terminal 100 via the interior service providing server 300 .

At this time, even if the same furniture or interior accessories are arranged, the atmosphere of the house may be different depending on the type of finish and materials used. For example, if the atmosphere of the kitchen is a modern kitchen, a vintage kitchen, a neat kitchen, etc., it will take the role of a professional who arranges according to various concepts and atmospheres. If artificial intelligence replaces it, it will help people who do self-construction or interior make decisions and troubles. be able to Recently, the use of machine learning technology that solves the limitations of the rule-based method and enables a more intelligent approach is spreading. Artificial neural network-based machine learning technology, represented by deep learning, utilizes an inductive approach in which a computer learns how to solve a problem on its own through given data rather than a rule-based problem solving defined by an expert. This AI data learning and problem solving method can be applied to the interior as well, and new approaches to various problems such as computer design knowledge learning, requirements analysis, and alternative generation may be possible.

By using artificial intelligence technology for interior design, it is possible to use the intelligent interior design object modeling automation method that applies the spatial information learning model. A spatial information learning model that automatically infers spatial information required in the interior design object modeling process and an intelligent object modeling automation method to which it is applied will be described below.

In the interior design object modeling detailing stage, there are several determinants of object placement, and the designer determines the number and spacing of objects to be arranged by interpreting the information in the given space and performs the design. The information of the target space used for decision making can be classified into shape information of the space, basic attribute information (eg, space name, atmosphere, concept, user, etc.), and requirement-related attribute information defined in each specialized field. BIM manages various attribute information of buildings together with 3D geometric models and secures interoperability through IFC, a standardized data format. In order to understand the relationship between the attribute information provided by the actual BIM, the information required for object creation, and the determinants of object creation using this information, the classification and mapping relationship of information can be identified. Based on the IFC attribute classification system, which is the standard information system of BIM, it is possible to identify information that requires additional input for interior design object modeling. Among the information necessary for object creation, the specialized field requirements require individual management because the spatial classification system and required values applied to the design differ according to countries and projects, and additional input by experts may be required.

The purpose of machine learning-based spatial information inference is to infer spatial information that is necessary for object placement decision-making, but is not provided by the BIM model, among the information classified in the above step. The specialized field information required for modeling detailing is derived by analyzing the information given in various forms such as drawings and documents by a design expert. The process of an expert deriving detailed attribute information from basic information is a manual process that relies on the expert's knowledge, so it may take a lot of time to analyze information and create alternatives. The artificial neural network-based machine learning model is capable of classifying and inferring information at a level similar to that of a human based on learning a vast amount of data, which can also be used to infer information in specialized fields required for design. Since machine learning-based spatial information inference can aim to infer additional information using the basic property information of an object given in the BIM model, the information used as input is based on the geometric shape of the object defined when the spatial object is created and basically An input general attribute may be mainly used, and input data may be selected according to characteristics of information to be inferred.

If attributes, shapes, etc. are defined, and the use, atmosphere, and concept are word embeddings or tagging tasks are completed including manual work, each arrangement, atmosphere, use, spatial attribute, etc., using at least one type of artificial intelligence algorithm, etc. At least one artificial intelligence algorithm is modeled through the process of learning After modeling is complete, you can actually measure the accuracy by inputting a test dataset that already knows the layout, atmosphere, use, and properties of the space. When enough data is collected and learning is carried out, experts can produce results such as arranging props or furniture. The user only inputs his/her house structure, and if he/she inputs a desired concept or condition, he/she can obtain a result value selected and arranged through an artificial intelligence algorithm. If additional price attributes are added, training may be provided to recommend other products with a lower price while maintaining a similar design. Of course, in this case, price attribute information must be stored in each product in advance, and if the user cannot accurately express his or her taste in words, the words expressing each atmosphere and the words that actually create or become interiors in such an atmosphere It is also possible to understand the intention through the process of linking the photos.

Hereinafter, an operation process according to the configuration of the interior service providing server of FIG. 2 will be described in detail with reference to FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

An embodiment of the present invention can be implemented in the form of an interior application or homepage that can be decorated as you like by reconstructing a three-dimensional space. When designing interiors, I usually look at other houses in magazines or on the Internet to envision my house, but in reality, it is difficult to imagine and plan a concrete appearance as it often does not match the structure or characteristics of my house. Changing the arrangement of furniture in the house you are currently living in can be done after making a detailed plan and then proceeding with it, and it is even more difficult to conceive of the interior design before moving in. Since it is a house I have never lived in, I cannot consider the movement and it is difficult to get a sense of what kind of brightness of lighting is appropriate for the square footage. It can be very helpful to have a way to try and revisit and plan everything from material selection to furniture placement.

<Spatial Recognition and Composition>

As shown in Fig. 3 (a), before decorating or changing a house, it is possible to configure it three-dimensionally on the Internet in advance, so that when a house drawing is taken with a camera, the drawing is read and applied to reconstruct it into a three-dimensional space, and there is no drawing. If you put the actual length, you can make the space three-dimensional. In addition, depending on the direction of the house (southwest/southeast, etc.), the floor, or whether it is covered by the building on the opposite side, it is possible to estimate the level of light by time period, taking into account the time of sunlight, etc., and the floor plan of each apartment complex It can also include a function that allows you to automatically upload a drawing and configure it into a three-dimensional space by entering the area/apartment name/flat by securing If you enter the building and floor of the apartment, the illuminance for each hour is automatically applied.

<Interior>

As shown in (b) of FIG. 3 , a wallpaper color may be selected. By linking each brand of paper for each color, it can be compared, and it can be included in the comparison box, and even the same color can be implemented so that the degree of darkness can be compared. In addition, if you want to proceed without changing the wallpaper that has already been attached, you can make it applied immediately by entering the brand name of the wallpaper. If you just want to arrange new furniture, in the case of brand furniture, enter the product name/color of the existing furniture and the furniture will be applied. In this case, the actual photos of the existing furniture can be prepared by securing the front/side so that the actual photos of the furniture can be uploaded. Accordingly, furniture arrangement can be output on the screen as desired, and if a size range is set in consideration of new furniture, various pieces of furniture can be selected. In addition, it is possible to compare furniture selected as candidates by putting it in a comparison box, and items such as material/weight/color are automatically applied so that it is possible to compare not only with photos but also with tables, which adds convenience. At this time, brand furniture is linked by a link so that it can be purchased. If you want to customize it, you can choose the desired size, material, number of shelves, door color, opening or sliding door, etc., and request a quote by selecting this. After putting it in a box and uploading it, furniture installers can compare and select by making an estimate.

The same can be applied to home appliances, and lighting can be tried in various ways. At this time, the color of the wallpaper/space can be changed according to the brightness level, and you can try different colors such as daylight white/daylight color/bulb color. Various bathroom appliances (faucet, shower booth, shower head, etc.) can be linked in various ways by brand.

The information required for lighting arrangement includes the appropriate illuminance value according to the facility and space use, the size of the space, the reflectivity of interior finishing materials, and whether or not furniture is used on the wall. Spatial area, floor height, reflectivity of interior finishing materials, and whether or not walls are used can be automatically collected by using the spatial object property values of BIM. In contrast, the appropriate illuminance range for each spatial use is information that is not managed in the BIM model, and additional analysis and input are required according to the purpose of the spatial object. The KS standard illuminance standard table used in Korea stipulates the appropriate illuminance range according to the activity type of occupants, and suggests activity types and illuminance standards according to the use of space in each facility. An expert can perform the task of inferring the use of a space and appropriate illuminance through given information using architectural knowledge, but in the case of a computer program, the mapping relationship between the input use value and the use classification defined in the illuminance standard is clearly defined. Otherwise, it is impossible to infer the appropriate illuminance according to the use.

Therefore, it is possible to infer the use of a space using the name of a spatial object input from the BIM model through rule-based mapping, but it is possible to infer the use of a space using various names that refer to the same space, such as the name of a new space not defined in advance or an abbreviation used for each project. Defining all mapping relationships for expressions is limited. To solve these problems in an intelligent way, a machine learning model that infers spatial usage and appropriate illuminance can be used.

As the information on the lighting equipment to be placed, information on the size and performance of the lighting equipment for placement is required. The size of a lighting fixture is basic information that determines the maximum number of lights that can enter a space. The performance information required to calculate the number of lighting fixtures required to satisfy the proper illuminance of a space includes the luminous flux of lighting, the compensation rate of light loss, and the illumination rate. As for the information of lighting equipment, performance information such as shape information and basic luminous flux and required power can be managed in the BIM model, but additional input is required for detailed information such as light sensitivity compensation rate and illumination rate. The required illuminance value for each space use that requires additional input is inferred through a machine learning model, and a pre-built DB can be used for the light compensation rate and illumination rate of the lighting object.

The object attribute values used at this time are: name, use, facility classification, floor height, area, wall use or not, interior finishing material reflectance (floor, wall, ceiling), lighting object name, luminous flux, power required, lighting fixture size, required illuminance by use The value may include, but is not limited to, a light compensation rate, an illumination rate, and the like. The spatial usage inference model can utilize the previously studied spatial usage inference model. The implemented model uses 4 spatial object attribute values as input values: 1) space name, 2) area, 3) height, and 4) number of doors installed in the space among the information that can be extracted from spatial objects in the BIM authoring tool. Since the indoor space in a modern building has a shape similar to a certain area, it is difficult to classify the use of the space only with the corresponding information, and the accuracy can be improved by using the number of additional doors and the name of the space. The use of the space output through learning can be classified according to the KS standard illuminance standard table, and appropriate illuminance can be inferred.

Among the properties used for inference of usage, the name of the space expressed in text can use the word embedding learning model to numerically express the meaning of the word. In the learning process of expressing the meaning of a word as a multidimensional vector, the size of the dimension is a parameter that can be specified by the user. As the size increases, the learning accuracy may increase, but it affects the learning speed. In consideration of the accuracy and speed of spatial usage inference learning, the meaning of the vocabulary is transformed into an N-dimensional vector, and the above-mentioned attribute values along with the transformed values are used as input values for the usage inference model. The spatial use classification learning may be performed for various residential target buildings, but is not limited thereto.

When placing a lighting object, data input is automatically performed using the spatial object and attribute values of the lighting object selected by the user. When a spatial object and a lighting object are selected in the BIM authoring tool, the property values that can be automatically calculated in the BIM model are stored in each variable according to the classification of information required for lighting arrangement. Additionally, the spatial properties required for the spatial usage inference model are transmitted to the inference model to infer the use of the space. The inferred use of the space is mapped according to the appropriate illuminance range defined in the KS illuminance standard, and then used in the calculation module. As with spatial objects, in the case of lighting objects, the values that can be automatically retrieved from the BIM model are automatically stored in each variable. The light compensation rate and illumination rate that require additional input are determined according to predefined rules.

The photosensitivity compensation rate is a value for adjusting the expected luminous flux in consideration of the decrease in illuminance of the lighting equipment. Since it is difficult to infer an exact value at the design stage, it can be set as a fixed value and used for illuminance calculation. Illumination factor is the ratio of the incident light flux reaching the working surface, and is determined by the type of luminaire, the actual number, and the reflectivity of the wall and ceiling finishes. As for the illumination rate according to the relevant determinant, data already organized in a table for each type of lighting equipment has been established, and the illuminance can be calculated using the values presented in the table. Depending on the type of some lighting fixtures to be implemented, the lighting rate table may be created as a DB table so that the lighting rate value can be called according to the input information. The actual index required to call the illumination rate and the reflectivity of interior finishing materials can be calculated using the spatial object attribute information of the BIM model presented in the table.

After calculating the lighting arrangement interval for lighting arrangement that meets the illuminance standard of the space, calculate the number of required lighting fixtures. The required number of lighting fixtures can be derived through the previously studied formula using the luminous flux method, and the number of lighting objects is calculated based on the assumption that the lighting intervals are equally spaced to ensure uniform illuminance of the space. do. The suitability of the selected lighting equipment for use in the target space is judged by comparing the calculated number of required lighting fixtures and the number of lighting fixtures that can be installed in the space. It is derived using the spacing and the size of the luminaire. The minimum distance between the wall and the lighting and the minimum spacing between the lights are determined by the height of the space and the size of the lighting equipment, and the maximum number of lighting equipment that can be installed can be set when the minimum distance is installed. If the number of lighting fixtures calculated by the luminous flux method is within the applicable range based on the maximum number of lights that can be installed in the space and the minimum number of lights required for uniform distribution of lighting, the lighting fixtures are placed in the space. If the calculated number of lighting fixtures is out of the corresponding range, it returns to the step of selecting a lighting object.

When outputting the results of automatic lighting arrangement, related property values of spatial objects and lighting objects obtained through input, the number of lighting fixtures to be placed in the automatically generated lighting plan alternative, expected indoor illuminance according to the arrangement, the installation interval between placed lights, etc. Batch results may be provided to the user. Quantitative figures presented as a result of lighting object creation enable an objective comparison between alternative lighting plans and can contribute to the selection of an accurate plan. In addition, through automation based on BIM objects, it is possible to additionally utilize object information such as visualization and quantity calculation that can be used in BIM software.

<Recommended function>

When a concept such as a living room such as a study room/bedroom/study is inserted as shown in FIG. 3(c), a recommended furniture arrangement/lighting/property suggestion function that reflects the concept according to the drawing may be included. At this time, you can choose a concept for each atmosphere. At this time, you can compare the items you see and put them in your shopping cart, and you can also link to each furniture brand link.

<Following function>

As shown in Figure 3 (d), it is possible to separately create items for viewing lighting/furniture/props/home appliances, etc. appearing in magazines, dramas, advertisement movies, etc., so that they can be referenced and included in the comparison box, and can also be linked as a purchase link.

<Self-construction help function>

As shown in (a) of FIG. 4 , it is possible to obtain an idea of the interior by using the above items and to consult with a company, but it is also possible to construct by yourself if you plan carefully to specific parts. If you want a self-interior, you can create a function that helps. If you request a quote by uploading the materials/drawings you want, you can connect with wallpaper companies/flooring and flooring companies, get comparative consultations, and select and proceed. Furniture/home appliances/accessories can be purchased and installed more easily.

<Review sharing and award>

As shown in (b) of FIG. 4 , it is possible to post a review of planning and progressing the interior by using a homepage or an application, and a reward for this can be paid. People who read reviews can touch and check details such as interior materials/furniture that have been built. In that way, referring to vivid reviews can help interior ideas/plans, etc. It is also possible to upload reviews for each item such as furniture, home appliances, and accessories, so that actual user reviews can be posted, and by allowing users to post reviews on painting/flooring, etc., it will help the next user to choose a company. It is expected that it will be more useful if you create a function that allows you to view reviews by selecting by area/apartment.

What has not been described with respect to the method of providing an interior service using the virtual reality-based 3D space reconstruction of FIGS. 2 to 4 is described above with respect to the method of providing an interior service using the virtual reality-based 3D space reconstruction through FIG. 1 . Since it is the same as the content or can be easily inferred from the described content, the following description will be omitted.

5 is a diagram illustrating a process in which data is transmitted/received between components included in the interior service providing system using the virtual reality-based 3D space reconstruction of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process in which data is transmitted and received between each component will be described with reference to FIG. 5, but the present application is not limited to such an embodiment, and the example shown in FIG. 5 according to the various embodiments described above will be described. It is apparent to those skilled in the art that the data transmission/reception process may be changed.

Referring to FIG. 5 , the interior service providing server collects at least one type of interior object and forms it into a database ( S5100 ).

In addition, the interior service providing server generates a three-dimensional space using a measured drawing or measured values captured or input from the user terminal (S5200), and when selecting and arranging at least one interior object in the user terminal, three-dimensional After synthesizing at least one interior object selected and arranged on the space, it is synthesized to be output from the user terminal (S5300).

The order between the above-described steps (S5100 to S5300) is only an example, and is not limited thereto. That is, the order between the above-described steps ( S5100 to S5300 ) may be mutually changed, and some of these steps may be simultaneously executed or deleted.

Matters that have not been described with respect to the method of providing an interior service using the virtual reality-based 3D space reconstruction of FIG. 5 are described above with respect to the method of providing an interior service using the virtual reality-based 3D space reconstruction through FIGS. 1 to 4 . Since it is the same as the content or can be easily inferred from the described content, the following description will be omitted.

The interior service providing method using virtual reality-based 3D space reconstruction according to an embodiment described with reference to FIG. 5 is in the form of a recording medium including instructions executable by a computer, such as an application or program module executed by a computer. can also be implemented. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer-readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The interior service providing method using virtual reality-based 3D space reconstruction according to an embodiment of the present invention described above may include an application basically installed in a terminal (which may include a program included in a platform or an operating system basically installed in the terminal, etc.) ), and may be executed by an application (ie, a program) installed directly in the master terminal through an application providing server such as an application store server, an application, or a web server related to a corresponding service by the user. In this sense, the above-described interior service providing method using virtual reality-based 3D space reconstruction according to an embodiment of the present invention is implemented as an application (that is, a program) installed basically in a terminal or directly installed by a user and installed in the terminal. It may be recorded on a computer-readable recording medium, such as.

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims (10)

a user terminal for photographing an actual measurement drawing of a target space or receiving an actual measurement value of the target space, and then selecting, arranging, and outputting at least one type of interior object in a three-dimensional space in which the target space is converted into digital data; and
A storage unit that collects at least one type of interior object and converts it into a database, a generation unit that generates a three-dimensional space using actual measurements taken or inputted from the user terminal or measured values, and the at least one interior in the user terminal In the case of selecting and arranging an object, a synthesizing unit for synthesizing at least one interior object selected and arranged in the three-dimensional space and then outputting it from the user terminal, the direction of the target space in the user terminal is selected among east, west, north and south When inputting any one and inputting the address where the target space is located, an illuminance management unit configured to reflect the illuminance for each time period in the three-dimensional space in consideration of the height of surrounding buildings and the height at which the target space is located, at least one type A drawing collection unit that collects drawings by floor plan for a collective building of the area, the name of the collective building and maps and stores the map, and when changing the arrangement of an interior object already provided in the user terminal, shooting or product from the user terminal A layout change unit that identifies the interior object for which an identification code has been input and creates a holding list after identifying the interior object, and when inputting the size or option of the interior object desired for placement in the user terminal, at least one item that satisfies the size or option An interior service providing server including a comparison unit that extracts an interior object and transmits it to the user terminal, and compares the detailed specifications of the at least one interior object through a comparison table for each preset item;
The user terminal is
When placing augmented reality content, after the user enters his/her key, points the camera toward the space where the furniture is to be placed, takes a photo, selects both endpoints of the space where the furniture is to be placed on the photo, and two points When the picture is taken, the actual width and height of the layout space is obtained through the proportional expression between the height of the user who entered the first input and the height of the user captured by the camera, and the furniture item to be purchased according to the user's selection is selected, and the number measured using web crawling You are connected to a furniture purchase site that suits you and purchase furniture,
The interior service providing server,
The spatial information required in the interior design object modeling process is automatically inferred by performing machine learning by a spatial information learning model using the house structure, desired concept, and condition input by the user of the user terminal as input values, and the inferred spatial information is applied to the interior design object modeling process to provide the result of selection and arrangement of props or furniture in the space,
Interior service using virtual reality-based 3D space reconstruction, characterized in that it provides recommended furniture arrangement, recommended lighting, and recommended props suggestion functions reflecting the concept of any one of study room, bedroom, and study input by the user of the user terminal system.
delete delete delete delete The method of claim 1,
The interior service providing system using the virtual reality-based three-dimensional space reconstruction,
When product data including the at least one kind of interior object, purchase site, price, size, product identification code, color and option are uploaded, and an order form is received from the user terminal via the interior service providing server at least one merchant terminal initiating the transport process;
Interior service providing system using virtual reality-based three-dimensional space reconstruction, characterized in that it further comprises.
The method of claim 1,
The interior service providing server,
At least one type of concept tag is attached and tagged to the at least one interior object, and when any one concept tag is selected in the user terminal, at least one interior object to which the selected concept tag is attached is added to the user terminal Recommendations to check;
Interior service providing system using virtual reality-based three-dimensional space reconstruction, characterized in that it further comprises.
The method of claim 1,
The interior service providing server,
In order to collect information on at least one interior accessory included in at least one type of content, product meta information is extracted from metadata of the at least one type of content, and at least one of the contents constituting the content in the user terminal is extracted. a following unit for extracting product meta information synchronized with the selected frame and transmitting it to the user terminal when any one frame is selected from one frame;
Interior service providing system using virtual reality-based three-dimensional space reconstruction, characterized in that it further comprises.
The method of claim 1,
The interior service providing server,
When the user terminal selects the at least one type of interior object, a quote system for collecting an estimate in a reverse auction method based on the spatial data of the three-dimensional space and the selected at least one interior object, and transmitting it to the user terminal study;
Interior service providing system using virtual reality-based three-dimensional space reconstruction, characterized in that it further comprises.
The method of claim 1,
The interior service providing server,
After disposing the at least one kind of interior object in the three-dimensional space in the user terminal, when the interior is performed, photographing data of the target space after the interior is collected from the user terminal and shared as before and after photos, a review management unit that collects reviews and ratings for reviews of the interiors and turns them into a database;
Interior service providing system using virtual reality-based three-dimensional space reconstruction, characterized in that it further comprises.

Images